{"Event":"SparkListenerLogStart","Spark Version":"3.5.1"}
{"Event":"SparkListenerResourceProfileAdded","Resource Profile Id":0,"Executor Resource Requests":{"memory":{"Resource Name":"memory","Amount":1024,"Discovery Script":"","Vendor":""},"offHeap":{"Resource Name":"offHeap","Amount":0,"Discovery Script":"","Vendor":""}},"Task Resource Requests":{"cpus":{"Resource Name":"cpus","Amount":1.0}}}
{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"driver","Host":"73850a3d530b","Port":41293},"Maximum Memory":455501414,"Timestamp":1784106873550,"Maximum Onheap Memory":455501414,"Maximum Offheap Memory":0}
{"Event":"SparkListenerEnvironmentUpdate","JVM Information":{"Java Home":"/usr/lib/jvm/java-17-openjdk-amd64","Java Version":"17.0.19 (Debian)","Scala Version":"version 2.12.18"},"Spark Properties":{"spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.driver.host":"73850a3d530b","spark.serializer.objectStreamReset":"100","spark.eventLog.enabled":"true","spark.driver.port":"34401","spark.rdd.compress":"True","spark.hadoop.fs.s3a.path.style.access":"true","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.scheduler.mode":"FIFO","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.pyFiles":"","spark.app.submitTime":"1784106871422","spark.app.startTime":"1784106872542","spark.executor.id":"driver","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.submit.deployMode":"client","spark.master":"spark://spark-master:7077","spark.eventLog.dir":"file:/opt/spark-events","spark.eventLog.compress":"true","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.id":"app-20260715131433-0082"},"Hadoop Properties":{"hadoop.service.shutdown.timeout":"30s","yarn.resourcemanager.amlauncher.thread-count":"50","yarn.sharedcache.enabled":"false","fs.s3a.connection.maximum":"96","yarn.nodemanager.numa-awareness.numactl.cmd":"/usr/bin/numactl","fs.viewfs.overload.scheme.target.o3fs.impl":"org.apache.hadoop.fs.ozone.OzoneFileSystem","fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","yarn.app.mapreduce.am.scheduler.heartbeat.interval-ms":"1000","yarn.timeline-service.timeline-client.number-of-async-entities-to-merge":"10","hadoop.security.kms.client.timeout":"60","hadoop.http.authentication.kerberos.principal":"HTTP/_HOST@LOCALHOST","mapreduce.jobhistory.loadedjob.tasks.max":"-1","yarn.resourcemanager.application-tag-based-placement.enable":"false","mapreduce.framework.name":"local","yarn.sharedcache.uploader.server.thread-count":"50","yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds.min":"3600","yarn.nodemanager.linux-container-executor.nonsecure-mode.user-pattern":"^[_.A-Za-z0-9][-@_.A-Za-z0-9]{0,255}?[$]?$","tfile.fs.output.buffer.size":"262144","yarn.app.mapreduce.am.job.task.listener.thread-count":"30","yarn.nodemanager.node-attributes.resync-interval-ms":"120000","fs.s3a.secret.key":"*********(redacted)","yarn.nodemanager.container-log-monitor.interval-ms":"60000","hadoop.security.groups.cache.background.reload.threads":"3","yarn.resourcemanager.webapp.cross-origin.enabled":"false","fs.AbstractFileSystem.ftp.impl":"org.apache.hadoop.fs.ftp.FtpFs","fs.viewfs.overload.scheme.target.gs.impl":"com.google.cloud.hadoop.fs.gcs.GoogleHadoopFS","hadoop.registry.secure":"false","hadoop.shell.safely.delete.limit.num.files":"100","mapreduce.job.acl-view-job":" ","fs.s3a.s3guard.ddb.background.sleep":"25ms","fs.s3a.retry.limit":"7","mapreduce.jobhistory.loadedjobs.cache.size":"5","fs.s3a.s3guard.ddb.table.create":"false","fs.viewfs.overload.scheme.target.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","yarn.nodemanager.amrmproxy.enabled":"false","yarn.timeline-service.entity-group-fs-store.with-user-dir":"false","mapreduce.shuffle.pathcache.expire-after-access-minutes":"5","mapreduce.input.fileinputformat.split.minsize":"0","yarn.resourcemanager.container.liveness-monitor.interval-ms":"600000","yarn.resourcemanager.client.thread-count":"50","io.seqfile.compress.blocksize":"1000000","yarn.nodemanager.runtime.linux.docker.allowed-container-runtimes":"runc","fs.viewfs.overload.scheme.target.http.impl":"org.apache.hadoop.fs.http.HttpFileSystem","yarn.resourcemanager.nodemanagers.heartbeat-interval-slowdown-factor":"1.0","yarn.sharedcache.checksum.algo.impl":"org.apache.hadoop.yarn.sharedcache.ChecksumSHA256Impl","yarn.nodemanager.amrmproxy.interceptor-class.pipeline":"org.apache.hadoop.yarn.server.nodemanager.amrmproxy.DefaultRequestInterceptor","yarn.timeline-service.entity-group-fs-store.leveldb-cache-read-cache-size":"10485760","mapreduce.reduce.shuffle.fetch.retry.interval-ms":"1000","mapreduce.task.profile.maps":"0-2","yarn.scheduler.include-port-in-node-name":"false","yarn.nodemanager.admin-env":"MALLOC_ARENA_MAX=$MALLOC_ARENA_MAX","yarn.resourcemanager.node-removal-untracked.timeout-ms":"60000","mapreduce.am.max-attempts":"2","hadoop.security.kms.client.failover.sleep.base.millis":"100","mapreduce.jobhistory.webapp.https.address":"0.0.0.0:19890","yarn.node-labels.fs-store.impl.class":"org.apache.hadoop.yarn.nodelabels.FileSystemNodeLabelsStore","yarn.nodemanager.collector-service.address":"${yarn.nodemanager.hostname}:8048","fs.trash.checkpoint.interval":"0","mapreduce.job.map.output.collector.class":"org.apache.hadoop.mapred.MapTask$MapOutputBuffer","yarn.resourcemanager.node-ip-cache.expiry-interval-secs":"-1","hadoop.http.authentication.signature.secret.file":"*********(redacted)","hadoop.jetty.logs.serve.aliases":"true","yarn.resourcemanager.placement-constraints.handler":"disabled","yarn.timeline-service.handler-thread-count":"10","yarn.resourcemanager.max-completed-applications":"1000","yarn.nodemanager.aux-services.manifest.enabled":"false","yarn.resourcemanager.system-metrics-publisher.enabled":"false","yarn.resourcemanager.placement-constraints.algorithm.class":"org.apache.hadoop.yarn.server.resourcemanager.scheduler.constraint.algorithm.DefaultPlacementAlgorithm","yarn.sharedcache.webapp.address":"0.0.0.0:8788","fs.s3a.select.input.csv.quote.escape.character":"\\\\","yarn.resourcemanager.delegation.token.renew-interval":"*********(redacted)","yarn.sharedcache.nm.uploader.replication.factor":"10","hadoop.security.groups.negative-cache.secs":"30","yarn.app.mapreduce.task.container.log.backups":"0","mapreduce.reduce.skip.proc-count.auto-incr":"true","fs.viewfs.overload.scheme.target.swift.impl":"org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem","hadoop.security.group.mapping.ldap.posix.attr.gid.name":"gidNumber","ipc.client.fallback-to-simple-auth-allowed":"false","yarn.nodemanager.resource.memory.enforced":"true","yarn.resourcemanager.system-metrics-publisher.timeline-server-v1.enable-batch":"false","yarn.client.failover-proxy-provider":"org.apache.hadoop.yarn.client.ConfiguredRMFailoverProxyProvider","yarn.timeline-service.http-authentication.simple.anonymous.allowed":"true","ha.health-monitor.check-interval.ms":"1000","yarn.nodemanager.runtime.linux.runc.host-pid-namespace.allowed":"false","hadoop.metrics.jvm.use-thread-mxbean":"false","ipc.[port_number].faircallqueue.multiplexer.weights":"8,4,2,1","yarn.acl.reservation-enable":"false","yarn.resourcemanager.store.class":"org.apache.hadoop.yarn.server.resourcemanager.recovery.FileSystemRMStateStore","yarn.app.mapreduce.am.hard-kill-timeout-ms":"10000","fs.s3a.etag.checksum.enabled":"false","yarn.nodemanager.container-metrics.enable":"true","ha.health-monitor.rpc.connect.max.retries":"1","yarn.timeline-service.client.fd-clean-interval-secs":"60","yarn.resourcemanager.nodemanagers.heartbeat-interval-scaling-enable":"false","yarn.resourcemanager.nodemanagers.heartbeat-interval-ms":"1000","hadoop.common.configuration.version":"3.0.0","fs.s3a.s3guard.ddb.table.capacity.read":"0","yarn.nodemanager.remote-app-log-dir-suffix":"logs","yarn.nodemanager.container-log-monitor.dir-size-limit-bytes":"1000000000","yarn.nodemanager.windows-container.cpu-limit.enabled":"false","yarn.nodemanager.runtime.linux.docker.privileged-containers.allowed":"false","file.blocksize":"67108864","hadoop.http.idle_timeout.ms":"60000","hadoop.registry.zk.retry.ceiling.ms":"60000","yarn.scheduler.configuration.leveldb-store.path":"${hadoop.tmp.dir}/yarn/system/confstore","yarn.sharedcache.store.in-memory.initial-delay-mins":"10","mapreduce.jobhistory.principal":"jhs/_HOST@REALM.TLD","mapreduce.map.skip.proc-count.auto-incr":"true","fs.s3a.committer.name":"file","mapreduce.task.profile.reduces":"0-2","hadoop.zk.num-retries":"1000","yarn.webapp.xfs-filter.enabled":"true","fs.viewfs.overload.scheme.target.hdfs.impl":"org.apache.hadoop.hdfs.DistributedFileSystem","seq.io.sort.mb":"100","yarn.scheduler.configuration.max.version":"100","yarn.timeline-service.webapp.https.address":"${yarn.timeline-service.hostname}:8190","yarn.resourcemanager.scheduler.address":"${yarn.resourcemanager.hostname}:8030","yarn.node-labels.enabled":"false","yarn.resourcemanager.webapp.ui-actions.enabled":"true","mapreduce.task.timeout":"600000","yarn.sharedcache.client-server.thread-count":"50","hadoop.security.groups.shell.command.timeout":"0s","hadoop.security.crypto.cipher.suite":"AES/CTR/NoPadding","yarn.nodemanager.elastic-memory-control.oom-handler":"org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.resources.DefaultOOMHandler","yarn.resourcemanager.connect.max-wait.ms":"900000","fs.defaultFS":"file:///","yarn.minicluster.use-rpc":"false","ipc.[port_number].decay-scheduler.decay-factor":"0.5","fs.har.impl.disable.cache":"true","yarn.webapp.ui2.enable":"false","io.compression.codec.bzip2.library":"system-native","yarn.webapp.filter-invalid-xml-chars":"false","yarn.nodemanager.runtime.linux.runc.layer-mounts-interval-secs":"600","fs.s3a.select.input.csv.record.delimiter":"\\n","fs.s3a.change.detection.source":"etag","ipc.[port_number].backoff.enable":"false","yarn.nodemanager.distributed-scheduling.enabled":"false","mapreduce.shuffle.connection-keep-alive.timeout":"5","yarn.resourcemanager.webapp.https.address":"${yarn.resourcemanager.hostname}:8090","yarn.webapp.enable-rest-app-submissions":"true","mapreduce.jobhistory.address":"0.0.0.0:10020","yarn.resourcemanager.nm-tokens.master-key-rolling-interval-secs":"*********(redacted)","yarn.is.minicluster":"false","yarn.nodemanager.address":"${yarn.nodemanager.hostname}:0","fs.abfss.impl":"org.apache.hadoop.fs.azurebfs.SecureAzureBlobFileSystem","fs.AbstractFileSystem.s3a.impl":"org.apache.hadoop.fs.s3a.S3A","mapreduce.task.combine.progress.records":"10000","yarn.resourcemanager.epoch.range":"0","yarn.resourcemanager.am.max-attempts":"2","yarn.nodemanager.runtime.linux.runc.image-toplevel-dir":"/runc-root","yarn.nodemanager.linux-container-executor.cgroups.hierarchy":"/hadoop-yarn","fs.AbstractFileSystem.wasbs.impl":"org.apache.hadoop.fs.azure.Wasbs","yarn.timeline-service.entity-group-fs-store.cache-store-class":"org.apache.hadoop.yarn.server.timeline.MemoryTimelineStore","yarn.nodemanager.runtime.linux.runc.allowed-container-networks":"host,none,bridge","fs.ftp.transfer.mode":"BLOCK_TRANSFER_MODE","ipc.server.log.slow.rpc":"false","ipc.server.reuseaddr":"true","fs.ftp.timeout":"0","yarn.resourcemanager.node-labels.provider.fetch-interval-ms":"1800000","yarn.router.webapp.https.address":"0.0.0.0:8091","yarn.nodemanager.webapp.cross-origin.enabled":"false","fs.wasb.impl":"org.apache.hadoop.fs.azure.NativeAzureFileSystem","yarn.resourcemanager.auto-update.containers":"false","yarn.app.mapreduce.am.job.committer.cancel-timeout":"60000","yarn.scheduler.configuration.zk-store.parent-path":"/confstore","yarn.nodemanager.default-container-executor.log-dirs.permissions":"710","yarn.app.attempt.diagnostics.limit.kc":"64","fs.viewfs.overload.scheme.target.swebhdfs.impl":"org.apache.hadoop.hdfs.web.SWebHdfsFileSystem","yarn.client.failover-no-ha-proxy-provider":"org.apache.hadoop.yarn.client.DefaultNoHARMFailoverProxyProvider","fs.s3a.change.detection.mode":"server","ftp.bytes-per-checksum":"512","yarn.nodemanager.resource.memory-mb":"-1","fs.AbstractFileSystem.abfs.impl":"org.apache.hadoop.fs.azurebfs.Abfs","yarn.timeline-service.writer.flush-interval-seconds":"60","fs.s3a.fast.upload.active.blocks":"4","yarn.resourcemanager.submission-preprocessor.enabled":"false","hadoop.security.credential.clear-text-fallback":"true","yarn.nodemanager.collector-service.thread-count":"5","ipc.[port_number].scheduler.impl":"org.apache.hadoop.ipc.DefaultRpcScheduler","fs.azure.secure.mode":"false","mapreduce.jobhistory.joblist.cache.size":"20000","fs.ftp.host":"0.0.0.0","yarn.timeline-service.writer.async.queue.capacity":"100","yarn.resourcemanager.fs.state-store.num-retries":"0","yarn.resourcemanager.nodemanager-connect-retries":"10","yarn.nodemanager.log-aggregation.num-log-files-per-app":"30","hadoop.security.kms.client.encrypted.key.cache.low-watermark":"0.3f","fs.s3a.committer.magic.enabled":"true","yarn.timeline-service.client.max-retries":"30","dfs.ha.fencing.ssh.connect-timeout":"30000","yarn.log-aggregation-enable":"false","yarn.system-metrics-publisher.enabled":"false","mapreduce.reduce.markreset.buffer.percent":"0.0","fs.AbstractFileSystem.viewfs.impl":"org.apache.hadoop.fs.viewfs.ViewFs","yarn.resourcemanager.nodemanagers.heartbeat-interval-speedup-factor":"1.0","mapreduce.task.io.sort.factor":"10","yarn.nodemanager.amrmproxy.client.thread-count":"25","ha.failover-controller.new-active.rpc-timeout.ms":"60000","yarn.nodemanager.container-localizer.java.opts":"-Xmx256m","mapreduce.jobhistory.datestring.cache.size":"200000","mapreduce.job.acl-modify-job":" ","yarn.nodemanager.windows-container.memory-limit.enabled":"false","yarn.timeline-service.webapp.address":"${yarn.timeline-service.hostname}:8188","yarn.app.mapreduce.am.job.committer.commit-window":"10000","yarn.nodemanager.container-manager.thread-count":"20","yarn.minicluster.fixed.ports":"false","hadoop.tags.system":"YARN,HDFS,NAMENODE,DATANODE,REQUIRED,SECURITY,KERBEROS,PERFORMANCE,CLIENT\n      ,SERVER,DEBUG,DEPRECATED,COMMON,OPTIONAL","yarn.cluster.max-application-priority":"0","yarn.timeline-service.ttl-enable":"true","mapreduce.jobhistory.recovery.store.fs.uri":"${hadoop.tmp.dir}/mapred/history/recoverystore","hadoop.caller.context.signature.max.size":"40","ipc.[port_number].decay-scheduler.backoff.responsetime.enable":"false","yarn.client.load.resource-types.from-server":"false","ha.zookeeper.session-timeout.ms":"10000","ipc.[port_number].decay-scheduler.metrics.top.user.count":"10","tfile.io.chunk.size":"1048576","fs.s3a.s3guard.ddb.table.capacity.write":"0","yarn.dispatcher.print-events-info.threshold":"5000","mapreduce.job.speculative.slowtaskthreshold":"1.0","io.serializations":"org.apache.hadoop.io.serializer.WritableSerialization, org.apache.hadoop.io.serializer.avro.AvroSpecificSerialization, org.apache.hadoop.io.serializer.avro.AvroReflectSerialization","hadoop.security.kms.client.failover.sleep.max.millis":"2000","hadoop.security.group.mapping.ldap.directory.search.timeout":"10000","yarn.scheduler.configuration.store.max-logs":"1000","yarn.nodemanager.node-attributes.provider.fetch-interval-ms":"600000","fs.swift.impl":"org.apache.hadoop.fs.swift.snative.SwiftNativeFileSystem","yarn.nodemanager.local-cache.max-files-per-directory":"8192","hadoop.http.cross-origin.enabled":"false","hadoop.zk.acl":"world:anyone:rwcda","yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.num-manifests-to-cache":"10","mapreduce.map.sort.spill.percent":"0.80","yarn.timeline-service.entity-group-fs-store.scan-interval-seconds":"60","yarn.node-attribute.fs-store.impl.class":"org.apache.hadoop.yarn.server.resourcemanager.nodelabels.FileSystemNodeAttributeStore","fs.s3a.retry.interval":"500ms","yarn.timeline-service.client.best-effort":"false","yarn.resourcemanager.webapp.delegation-token-auth-filter.enabled":"*********(redacted)","hadoop.security.group.mapping.ldap.posix.attr.uid.name":"uidNumber","fs.AbstractFileSystem.swebhdfs.impl":"org.apache.hadoop.fs.SWebHdfs","yarn.nodemanager.elastic-memory-control.timeout-sec":"5","fs.s3a.select.enabled":"true","mapreduce.ifile.readahead":"true","yarn.timeline-service.leveldb-timeline-store.ttl-interval-ms":"300000","yarn.timeline-service.reader.webapp.address":"${yarn.timeline-service.webapp.address}","yarn.resourcemanager.placement-constraints.algorithm.pool-size":"1","yarn.timeline-service.hbase.coprocessor.jar.hdfs.location":"/hbase/coprocessor/hadoop-yarn-server-timelineservice.jar","hadoop.security.kms.client.encrypted.key.cache.num.refill.threads":"2","yarn.resourcemanager.scheduler.class":"org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler","yarn.app.mapreduce.am.command-opts":"-Xmx1024m","fs.s3a.metadatastore.fail.on.write.error":"true","hadoop.http.sni.host.check.enabled":"false","mapreduce.cluster.local.dir":"${hadoop.tmp.dir}/mapred/local","io.mapfile.bloom.error.rate":"0.005","fs.client.resolve.topology.enabled":"false","yarn.nodemanager.runtime.linux.allowed-runtimes":"default","yarn.sharedcache.store.class":"org.apache.hadoop.yarn.server.sharedcachemanager.store.InMemorySCMStore","ha.failover-controller.graceful-fence.rpc-timeout.ms":"5000","ftp.replication":"3","fs.getspaceused.jitterMillis":"60000","hadoop.security.uid.cache.secs":"14400","mapreduce.job.maxtaskfailures.per.tracker":"3","fs.s3a.metadatastore.impl":"org.apache.hadoop.fs.s3a.s3guard.NullMetadataStore","io.skip.checksum.errors":"false","yarn.app.mapreduce.client-am.ipc.max-retries-on-timeouts":"3","yarn.timeline-service.webapp.xfs-filter.xframe-options":"SAMEORIGIN","fs.s3a.connection.timeout":"200000","yarn.app.mapreduce.am.webapp.https.enabled":"false","mapreduce.job.max.split.locations":"15","yarn.resourcemanager.nm-container-queuing.max-queue-length":"15","yarn.resourcemanager.delegation-token.always-cancel":"*********(redacted)","hadoop.registry.zk.session.timeout.ms":"60000","yarn.federation.cache-ttl.secs":"300","mapreduce.jvm.system-properties-to-log":"os.name,os.version,java.home,java.runtime.version,java.vendor,java.version,java.vm.name,java.class.path,java.io.tmpdir,user.dir,user.name","yarn.resourcemanager.opportunistic-container-allocation.nodes-used":"10","yarn.timeline-service.entity-group-fs-store.active-dir":"/tmp/entity-file-history/active","mapreduce.shuffle.transfer.buffer.size":"131072","yarn.timeline-service.client.retry-interval-ms":"1000","yarn.timeline-service.flowname.max-size":"0","yarn.http.policy":"HTTP_ONLY","fs.s3a.socket.send.buffer":"8192","fs.AbstractFileSystem.abfss.impl":"org.apache.hadoop.fs.azurebfs.Abfss","yarn.sharedcache.uploader.server.address":"0.0.0.0:8046","yarn.resourcemanager.delegation-token.max-conf-size-bytes":"*********(redacted)","hadoop.http.authentication.token.validity":"*********(redacted)","mapreduce.shuffle.max.connections":"0","yarn.minicluster.yarn.nodemanager.resource.memory-mb":"4096","mapreduce.job.emit-timeline-data":"false","yarn.nodemanager.resource.system-reserved-memory-mb":"-1","hadoop.kerberos.min.seconds.before.relogin":"60","mapreduce.jobhistory.move.thread-count":"3","yarn.resourcemanager.admin.client.thread-count":"1","yarn.dispatcher.drain-events.timeout":"300000","ipc.[port_number].decay-scheduler.backoff.responsetime.thresholds":"10s,20s,30s,40s","fs.s3a.buffer.dir":"${hadoop.tmp.dir}/s3a","hadoop.ssl.enabled.protocols":"TLSv1.2","mapreduce.jobhistory.admin.address":"0.0.0.0:10033","yarn.log-aggregation-status.time-out.ms":"600000","fs.s3a.accesspoint.required":"false","mapreduce.shuffle.port":"13562","yarn.resourcemanager.max-log-aggregation-diagnostics-in-memory":"10","yarn.nodemanager.health-checker.interval-ms":"600000","yarn.resourcemanager.proxy.connection.timeout":"60000","yarn.router.clientrm.interceptor-class.pipeline":"org.apache.hadoop.yarn.server.router.clientrm.DefaultClientRequestInterceptor","yarn.resourcemanager.zk-appid-node.split-index":"0","ftp.blocksize":"67108864","yarn.nodemanager.runtime.linux.sandbox-mode.local-dirs.permissions":"read","yarn.router.rmadmin.interceptor-class.pipeline":"org.apache.hadoop.yarn.server.router.rmadmin.DefaultRMAdminRequestInterceptor","yarn.nodemanager.log-container-debug-info.enabled":"true","yarn.resourcemanager.activities-manager.app-activities.max-queue-length":"100","yarn.resourcemanager.application-https.policy":"NONE","yarn.client.max-cached-nodemanagers-proxies":"0","yarn.nodemanager.linux-container-executor.cgroups.delete-delay-ms":"20","yarn.nodemanager.delete.debug-delay-sec":"0","yarn.nodemanager.pmem-check-enabled":"true","yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage":"90.0","mapreduce.app-submission.cross-platform":"false","yarn.resourcemanager.work-preserving-recovery.scheduling-wait-ms":"10000","yarn.nodemanager.container-retry-minimum-interval-ms":"1000","hadoop.security.groups.cache.secs":"300","yarn.federation.enabled":"false","yarn.workflow-id.tag-prefix":"workflowid:","fs.azure.local.sas.key.mode":"false","ipc.maximum.data.length":"134217728","fs.s3a.endpoint":"http://minio:9000","mapreduce.shuffle.max.threads":"0","yarn.router.pipeline.cache-max-size":"25","yarn.resourcemanager.nm-container-queuing.load-comparator":"QUEUE_LENGTH","yarn.resourcemanager.resource-tracker.nm.ip-hostname-check":"false","hadoop.security.authorization":"false","mapreduce.job.complete.cancel.delegation.tokens":"*********(redacted)","fs.s3a.paging.maximum":"5000","nfs.exports.allowed.hosts":"* rw","yarn.nodemanager.amrmproxy.ha.enable":"false","fs.AbstractFileSystem.gs.impl":"com.google.cloud.hadoop.fs.gcs.GoogleHadoopFS","mapreduce.jobhistory.http.policy":"HTTP_ONLY","yarn.sharedcache.store.in-memory.check-period-mins":"720","hadoop.security.group.mapping.ldap.ssl":"false","fs.s3a.downgrade.syncable.exceptions":"true","yarn.client.application-client-protocol.poll-interval-ms":"200","yarn.scheduler.configuration.leveldb-store.compaction-interval-secs":"86400","yarn.timeline-service.writer.class":"org.apache.hadoop.yarn.server.timelineservice.storage.HBaseTimelineWriterImpl","ha.zookeeper.parent-znode":"/hadoop-ha","yarn.resourcemanager.submission-preprocessor.file-refresh-interval-ms":"60000","yarn.nodemanager.log-aggregation.policy.class":"org.apache.hadoop.yarn.server.nodemanager.containermanager.logaggregation.AllContainerLogAggregationPolicy","mapreduce.reduce.shuffle.merge.percent":"0.66","hadoop.security.group.mapping.ldap.search.filter.group":"(objectClass=group)","yarn.resourcemanager.placement-constraints.scheduler.pool-size":"1","yarn.resourcemanager.activities-manager.cleanup-interval-ms":"5000","yarn.nodemanager.resourcemanager.minimum.version":"NONE","mapreduce.job.speculative.speculative-cap-running-tasks":"0.1","yarn.admin.acl":"*","ipc.[port_number].identity-provider.impl":"org.apache.hadoop.ipc.UserIdentityProvider","yarn.nodemanager.recovery.supervised":"false","yarn.sharedcache.admin.thread-count":"1","yarn.resourcemanager.ha.automatic-failover.enabled":"true","yarn.nodemanager.container-log-monitor.total-size-limit-bytes":"10000000000","mapreduce.reduce.skip.maxgroups":"0","mapreduce.reduce.shuffle.connect.timeout":"180000","yarn.nodemanager.health-checker.scripts":"script","yarn.resourcemanager.address":"${yarn.resourcemanager.hostname}:8032","ipc.client.ping":"true","mapreduce.task.local-fs.write-limit.bytes":"-1","fs.adl.oauth2.access.token.provider.type":"*********(redacted)","mapreduce.shuffle.ssl.file.buffer.size":"65536","yarn.resourcemanager.ha.automatic-failover.embedded":"true","yarn.nodemanager.resource-plugins.gpu.docker-plugin":"nvidia-docker-v1","fs.s3a.s3guard.consistency.retry.interval":"2s","fs.s3a.multipart.purge":"false","yarn.scheduler.configuration.store.class":"file","yarn.resourcemanager.nm-container-queuing.queue-limit-stdev":"1.0f","mapreduce.job.end-notification.max.attempts":"5","mapreduce.output.fileoutputformat.compress.codec":"org.apache.hadoop.io.compress.DefaultCodec","yarn.nodemanager.container-monitor.procfs-tree.smaps-based-rss.enabled":"false","ipc.client.bind.wildcard.addr":"false","yarn.resourcemanager.webapp.rest-csrf.enabled":"false","ha.health-monitor.connect-retry-interval.ms":"1000","yarn.nodemanager.keytab":"/etc/krb5.keytab","mapreduce.jobhistory.keytab":"/etc/security/keytab/jhs.service.keytab","fs.s3a.threads.max":"64","yarn.nodemanager.runtime.linux.docker.image-update":"false","mapreduce.reduce.shuffle.input.buffer.percent":"0.70","fs.viewfs.overload.scheme.target.abfss.impl":"org.apache.hadoop.fs.azurebfs.SecureAzureBlobFileSystem","yarn.dispatcher.cpu-monitor.samples-per-min":"60","hadoop.security.token.service.use_ip":"*********(redacted)","yarn.nodemanager.runtime.linux.docker.allowed-container-networks":"host,none,bridge","yarn.nodemanager.node-labels.resync-interval-ms":"120000","hadoop.tmp.dir":"/tmp/hadoop-${user.name}","mapreduce.job.maps":"2","mapreduce.jobhistory.webapp.rest-csrf.custom-header":"X-XSRF-Header","mapreduce.job.end-notification.max.retry.interval":"5000","yarn.log-aggregation.retain-check-interval-seconds":"-1","yarn.resourcemanager.resource-tracker.client.thread-count":"50","yarn.nodemanager.containers-launcher.class":"org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainersLauncher","yarn.rm.system-metrics-publisher.emit-container-events":"false","yarn.timeline-service.leveldb-timeline-store.start-time-read-cache-size":"10000","yarn.resourcemanager.ha.automatic-failover.zk-base-path":"/yarn-leader-election","io.seqfile.local.dir":"${hadoop.tmp.dir}/io/local","fs.s3a.s3guard.ddb.throttle.retry.interval":"100ms","fs.AbstractFileSystem.wasb.impl":"org.apache.hadoop.fs.azure.Wasb","mapreduce.client.submit.file.replication":"10","mapreduce.jobhistory.minicluster.fixed.ports":"false","fs.s3a.multipart.threshold":"128M","yarn.resourcemanager.webapp.xfs-filter.xframe-options":"SAMEORIGIN","mapreduce.jobhistory.done-dir":"${yarn.app.mapreduce.am.staging-dir}/history/done","ipc.server.purge.interval":"15","ipc.client.idlethreshold":"4000","yarn.nodemanager.linux-container-executor.cgroups.strict-resource-usage":"false","mapreduce.reduce.input.buffer.percent":"0.0","yarn.nodemanager.runtime.linux.docker.userremapping-gid-threshold":"1","yarn.nodemanager.webapp.rest-csrf.enabled":"false","fs.ftp.host.port":"21","ipc.ping.interval":"60000","yarn.resourcemanager.history-writer.multi-threaded-dispatcher.pool-size":"10","yarn.resourcemanager.admin.address":"${yarn.resourcemanager.hostname}:8033","file.client-write-packet-size":"65536","ipc.client.kill.max":"10","mapreduce.reduce.speculative":"true","hadoop.security.key.default.bitlength":"128","mapreduce.job.reducer.unconditional-preempt.delay.sec":"300","yarn.nodemanager.disk-health-checker.interval-ms":"120000","yarn.nodemanager.log.deletion-threads-count":"4","fs.s3a.committer.abort.pending.uploads":"true","yarn.webapp.filter-entity-list-by-user":"false","yarn.resourcemanager.activities-manager.app-activities.ttl-ms":"600000","ipc.client.connection.maxidletime":"10000","mapreduce.task.io.sort.mb":"100","yarn.nodemanager.localizer.client.thread-count":"5","io.erasurecode.codec.rs.rawcoders":"rs_native,rs_java","io.erasurecode.codec.rs-legacy.rawcoders":"rs-legacy_java","yarn.sharedcache.admin.address":"0.0.0.0:8047","yarn.resourcemanager.placement-constraints.algorithm.iterator":"SERIAL","yarn.nodemanager.localizer.cache.cleanup.interval-ms":"600000","hadoop.security.crypto.codec.classes.aes.ctr.nopadding":"org.apache.hadoop.crypto.OpensslAesCtrCryptoCodec, org.apache.hadoop.crypto.JceAesCtrCryptoCodec","mapreduce.job.cache.limit.max-resources-mb":"0","fs.s3a.connection.ssl.enabled":"false","yarn.nodemanager.process-kill-wait.ms":"5000","mapreduce.job.hdfs-servers":"${fs.defaultFS}","yarn.app.mapreduce.am.webapp.https.client.auth":"false","hadoop.workaround.non.threadsafe.getpwuid":"true","fs.df.interval":"60000","ipc.[port_number].decay-scheduler.thresholds":"13,25,50","fs.s3a.multiobjectdelete.enable":"true","yarn.sharedcache.cleaner.resource-sleep-ms":"0","yarn.nodemanager.disk-health-checker.min-healthy-disks":"0.25","hadoop.shell.missing.defaultFs.warning":"false","io.file.buffer.size":"65536","fs.viewfs.overload.scheme.target.wasb.impl":"org.apache.hadoop.fs.azure.NativeAzureFileSystem","hadoop.security.group.mapping.ldap.search.attr.member":"member","hadoop.security.random.device.file.path":"/dev/urandom","hadoop.security.sensitive-config-keys":"*********(redacted)","fs.s3a.s3guard.ddb.max.retries":"9","fs.viewfs.overload.scheme.target.file.impl":"org.apache.hadoop.fs.LocalFileSystem","hadoop.rpc.socket.factory.class.default":"org.apache.hadoop.net.StandardSocketFactory","yarn.intermediate-data-encryption.enable":"false","yarn.resourcemanager.connect.retry-interval.ms":"30000","yarn.nodemanager.container.stderr.pattern":"{*stderr*,*STDERR*}","yarn.scheduler.minimum-allocation-mb":"1024","yarn.app.mapreduce.am.staging-dir":"/tmp/hadoop-yarn/staging","mapreduce.reduce.shuffle.read.timeout":"180000","hadoop.http.cross-origin.max-age":"1800","io.erasurecode.codec.xor.rawcoders":"xor_native,xor_java","fs.s3a.s3guard.consistency.retry.limit":"7","fs.s3a.connection.establish.timeout":"5000","mapreduce.job.running.map.limit":"0","yarn.minicluster.control-resource-monitoring":"false","hadoop.ssl.require.client.cert":"false","hadoop.kerberos.kinit.command":"kinit","yarn.federation.state-store.class":"org.apache.hadoop.yarn.server.federation.store.impl.MemoryFederationStateStore","mapreduce.reduce.log.level":"INFO","hadoop.security.dns.log-slow-lookups.threshold.ms":"1000","mapreduce.job.ubertask.enable":"false","adl.http.timeout":"-1","yarn.resourcemanager.placement-constraints.retry-attempts":"3","hadoop.caller.context.enabled":"false","hadoop.security.group.mapping.ldap.num.attempts":"3","yarn.nodemanager.vmem-pmem-ratio":"2.1","hadoop.rpc.protection":"authentication","ha.health-monitor.rpc-timeout.ms":"45000","yarn.nodemanager.remote-app-log-dir":"/tmp/logs","hadoop.zk.timeout-ms":"10000","fs.s3a.s3guard.cli.prune.age":"86400000","yarn.nodemanager.resource.pcores-vcores-multiplier":"1.0","yarn.nodemanager.runtime.linux.sandbox-mode":"disabled","yarn.app.mapreduce.am.containerlauncher.threadpool-initial-size":"10","fs.viewfs.overload.scheme.target.webhdfs.impl":"org.apache.hadoop.hdfs.web.WebHdfsFileSystem","fs.s3a.committer.threads":"8","hadoop.zk.retry-interval-ms":"1000","hadoop.security.crypto.buffer.size":"8192","yarn.nodemanager.node-labels.provider.fetch-interval-ms":"600000","mapreduce.jobhistory.recovery.store.leveldb.path":"${hadoop.tmp.dir}/mapred/history/recoverystore","yarn.client.failover-retries-on-socket-timeouts":"0","fs.s3a.ssl.channel.mode":"default_jsse","yarn.nodemanager.resource.memory.enabled":"false","fs.azure.authorization.caching.enable":"true","fs.s3a.access.key":"*********(redacted)","hadoop.security.instrumentation.requires.admin":"false","yarn.nodemanager.delete.thread-count":"4","mapreduce.job.finish-when-all-reducers-done":"true","hadoop.registry.jaas.context":"Client","yarn.timeline-service.leveldb-timeline-store.path":"${hadoop.tmp.dir}/yarn/timeline","io.map.index.interval":"128","yarn.resourcemanager.nm-container-queuing.max-queue-wait-time-ms":"100","fs.abfs.impl":"org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem","mapreduce.job.counters.max":"120","mapreduce.jobhistory.webapp.rest-csrf.enabled":"false","yarn.timeline-service.store-class":"org.apache.hadoop.yarn.server.timeline.LeveldbTimelineStore","mapreduce.jobhistory.move.interval-ms":"180000","fs.s3a.change.detection.version.required":"true","yarn.nodemanager.localizer.fetch.thread-count":"4","yarn.resourcemanager.scheduler.client.thread-count":"50","hadoop.ssl.hostname.verifier":"DEFAULT","yarn.timeline-service.leveldb-state-store.path":"${hadoop.tmp.dir}/yarn/timeline","mapreduce.job.classloader":"false","mapreduce.task.profile.map.params":"${mapreduce.task.profile.params}","ipc.client.connect.timeout":"20000","hadoop.security.auth_to_local.mechanism":"hadoop","yarn.timeline-service.app-collector.linger-period.ms":"60000","yarn.nm.liveness-monitor.expiry-interval-ms":"600000","yarn.resourcemanager.reservation-system.planfollower.time-step":"1000","yarn.resourcemanager.proxy.timeout.enabled":"true","yarn.resourcemanager.activities-manager.scheduler-activities.ttl-ms":"600000","yarn.nodemanager.runtime.linux.docker.enable-userremapping.allowed":"true","yarn.webapp.api-service.enable":"false","yarn.nodemanager.recovery.enabled":"false","mapreduce.job.end-notification.retry.interval":"1000","fs.du.interval":"600000","fs.ftp.impl":"org.apache.hadoop.fs.ftp.FTPFileSystem","yarn.nodemanager.container.stderr.tail.bytes":"4096","yarn.nodemanager.disk-health-checker.disk-free-space-threshold.enabled":"true","hadoop.security.group.mapping.ldap.read.timeout.ms":"60000","hadoop.security.groups.cache.warn.after.ms":"5000","file.bytes-per-checksum":"512","mapreduce.outputcommitter.factory.scheme.s3a":"org.apache.hadoop.fs.s3a.commit.S3ACommitterFactory","hadoop.security.groups.cache.background.reload":"false","yarn.nodemanager.container-monitor.enabled":"true","yarn.nodemanager.elastic-memory-control.enabled":"false","net.topology.script.number.args":"100","mapreduce.task.merge.progress.records":"10000","yarn.nodemanager.localizer.address":"${yarn.nodemanager.hostname}:8040","yarn.timeline-service.keytab":"/etc/krb5.keytab","mapreduce.reduce.shuffle.fetch.retry.timeout-ms":"30000","yarn.resourcemanager.rm.container-allocation.expiry-interval-ms":"600000","yarn.nodemanager.container-executor.exit-code-file.timeout-ms":"2000","mapreduce.fileoutputcommitter.algorithm.version":"1","yarn.resourcemanager.work-preserving-recovery.enabled":"true","mapreduce.map.skip.maxrecords":"0","yarn.sharedcache.root-dir":"/sharedcache","fs.s3a.retry.throttle.limit":"20","hadoop.http.authentication.type":"simple","fs.viewfs.overload.scheme.target.oss.impl":"org.apache.hadoop.fs.aliyun.oss.AliyunOSSFileSystem","mapreduce.job.cache.limit.max-resources":"0","mapreduce.task.userlog.limit.kb":"0","ipc.[port_number].weighted-cost.handler":"1","yarn.resourcemanager.scheduler.monitor.enable":"false","ipc.client.connect.max.retries":"10","hadoop.registry.zk.retry.times":"5","yarn.nodemanager.resource-monitor.interval-ms":"3000","yarn.nodemanager.resource-plugins.gpu.allowed-gpu-devices":"auto","mapreduce.job.sharedcache.mode":"disabled","yarn.nodemanager.webapp.rest-csrf.custom-header":"X-XSRF-Header","mapreduce.shuffle.listen.queue.size":"128","yarn.scheduler.configuration.mutation.acl-policy.class":"org.apache.hadoop.yarn.server.resourcemanager.scheduler.DefaultConfigurationMutationACLPolicy","mapreduce.map.cpu.vcores":"1","yarn.log-aggregation.file-formats":"TFile","yarn.timeline-service.client.fd-retain-secs":"300","fs.s3a.select.output.csv.field.delimiter":",","yarn.nodemanager.health-checker.timeout-ms":"1200000","hadoop.user.group.static.mapping.overrides":"dr.who=;","fs.azure.sas.expiry.period":"90d","fs.s3a.select.output.csv.record.delimiter":"\\n","mapreduce.jobhistory.recovery.store.class":"org.apache.hadoop.mapreduce.v2.hs.HistoryServerFileSystemStateStoreService","fs.viewfs.overload.scheme.target.https.impl":"org.apache.hadoop.fs.http.HttpsFileSystem","fs.s3a.s3guard.ddb.table.sse.enabled":"false","yarn.resourcemanager.fail-fast":"${yarn.fail-fast}","yarn.resourcemanager.proxy-user-privileges.enabled":"false","yarn.router.webapp.interceptor-class.pipeline":"org.apache.hadoop.yarn.server.router.webapp.DefaultRequestInterceptorREST","yarn.nodemanager.resource.memory.cgroups.soft-limit-percentage":"90.0","mapreduce.job.reducer.preempt.delay.sec":"0","hadoop.util.hash.type":"murmur","yarn.nodemanager.disk-validator":"basic","yarn.app.mapreduce.client.job.max-retries":"3","fs.viewfs.overload.scheme.target.ftp.impl":"org.apache.hadoop.fs.ftp.FTPFileSystem","mapreduce.reduce.shuffle.retry-delay.max.ms":"60000","hadoop.security.group.mapping.ldap.connection.timeout.ms":"60000","mapreduce.task.profile.params":"-agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s","yarn.app.mapreduce.shuffle.log.backups":"0","yarn.nodemanager.container-diagnostics-maximum-size":"10000","hadoop.registry.zk.retry.interval.ms":"1000","yarn.nodemanager.linux-container-executor.cgroups.delete-timeout-ms":"1000","fs.AbstractFileSystem.file.impl":"org.apache.hadoop.fs.local.LocalFs","yarn.nodemanager.log-aggregation.roll-monitoring-interval-seconds":"-1","mapreduce.jobhistory.cleaner.interval-ms":"86400000","hadoop.registry.zk.quorum":"localhost:2181","yarn.nodemanager.runtime.linux.runc.allowed-container-runtimes":"runc","mapreduce.output.fileoutputformat.compress":"false","yarn.resourcemanager.am-rm-tokens.master-key-rolling-interval-secs":"*********(redacted)","fs.s3a.assumed.role.session.duration":"30m","hadoop.security.group.mapping.ldap.conversion.rule":"none","hadoop.ssl.server.conf":"ssl-server.xml","fs.s3a.retry.throttle.interval":"100ms","seq.io.sort.factor":"100","fs.viewfs.overload.scheme.target.ofs.impl":"org.apache.hadoop.fs.ozone.RootedOzoneFileSystem","yarn.sharedcache.cleaner.initial-delay-mins":"10","mapreduce.client.completion.pollinterval":"5000","hadoop.ssl.keystores.factory.class":"org.apache.hadoop.security.ssl.FileBasedKeyStoresFactory","yarn.app.mapreduce.am.resource.cpu-vcores":"1","yarn.timeline-service.enabled":"false","yarn.nodemanager.runtime.linux.docker.capabilities":"CHOWN,DAC_OVERRIDE,FSETID,FOWNER,MKNOD,NET_RAW,SETGID,SETUID,SETFCAP,SETPCAP,NET_BIND_SERVICE,SYS_CHROOT,KILL,AUDIT_WRITE","yarn.acl.enable":"false","yarn.timeline-service.entity-group-fs-store.done-dir":"/tmp/entity-file-history/done/","hadoop.security.group.mapping.ldap.num.attempts.before.failover":"3","mapreduce.task.profile":"false","hadoop.prometheus.endpoint.enabled":"false","yarn.resourcemanager.fs.state-store.uri":"${hadoop.tmp.dir}/yarn/system/rmstore","mapreduce.jobhistory.always-scan-user-dir":"false","fs.s3a.metadatastore.metadata.ttl":"15m","yarn.nodemanager.opportunistic-containers-use-pause-for-preemption":"false","yarn.nodemanager.linux-container-executor.nonsecure-mode.local-user":"nobody","yarn.timeline-service.reader.class":"org.apache.hadoop.yarn.server.timelineservice.storage.HBaseTimelineReaderImpl","yarn.resourcemanager.configuration.provider-class":"org.apache.hadoop.yarn.LocalConfigurationProvider","yarn.nodemanager.runtime.linux.docker.userremapping-uid-threshold":"1","yarn.resourcemanager.configuration.file-system-based-store":"/yarn/conf","mapreduce.job.cache.limit.max-single-resource-mb":"0","yarn.nodemanager.runtime.linux.docker.stop.grace-period":"10","yarn.resourcemanager.resource-profiles.source-file":"resource-profiles.json","mapreduce.job.dfs.storage.capacity.kill-limit-exceed":"false","yarn.nodemanager.resource.percentage-physical-cpu-limit":"100","mapreduce.jobhistory.client.thread-count":"10","tfile.fs.input.buffer.size":"262144","mapreduce.client.progressmonitor.pollinterval":"1000","yarn.nodemanager.log-dirs":"${yarn.log.dir}/userlogs","yarn.resourcemanager.opportunistic.max.container-allocation.per.am.heartbeat":"-1","fs.automatic.close":"true","yarn.resourcemanager.delegation-token-renewer.thread-retry-interval":"*********(redacted)","fs.s3a.select.input.csv.quote.character":"\"","yarn.nodemanager.hostname":"0.0.0.0","ipc.[port_number].cost-provider.impl":"org.apache.hadoop.ipc.DefaultCostProvider","yarn.nodemanager.runtime.linux.runc.manifest-to-resources-plugin":"org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.runtime.runc.HdfsManifestToResourcesPlugin","yarn.nodemanager.remote-app-log-dir-include-older":"true","yarn.nodemanager.resource.memory.cgroups.swappiness":"0","ftp.stream-buffer-size":"4096","yarn.fail-fast":"false","yarn.nodemanager.runtime.linux.runc.layer-mounts-to-keep":"100","yarn.timeline-service.app-aggregation-interval-secs":"15","hadoop.security.group.mapping.ldap.search.filter.user":"(&(objectClass=user)(sAMAccountName={0}))","ipc.[port_number].weighted-cost.lockshared":"10","yarn.nodemanager.container-localizer.log.level":"INFO","yarn.timeline-service.address":"${yarn.timeline-service.hostname}:10200","mapreduce.job.ubertask.maxmaps":"9","fs.s3a.threads.keepalivetime":"60","mapreduce.jobhistory.webapp.rest-csrf.methods-to-ignore":"GET,OPTIONS,HEAD","mapreduce.task.files.preserve.failedtasks":"false","yarn.app.mapreduce.client.job.retry-interval":"2000","ha.failover-controller.graceful-fence.connection.retries":"1","fs.s3a.select.output.csv.quote.escape.character":"\\\\","yarn.resourcemanager.delegation.token.max-lifetime":"*********(redacted)","hadoop.kerberos.keytab.login.autorenewal.enabled":"false","yarn.timeline-service.client.drain-entities.timeout.ms":"2000","yarn.nodemanager.resource-plugins.fpga.vendor-plugin.class":"org.apache.hadoop.yarn.server.nodemanager.containermanager.resourceplugin.fpga.IntelFpgaOpenclPlugin","yarn.resourcemanager.nodemanagers.heartbeat-interval-min-ms":"1000","yarn.timeline-service.entity-group-fs-store.summary-store":"org.apache.hadoop.yarn.server.timeline.LeveldbTimelineStore","mapreduce.reduce.cpu.vcores":"1","mapreduce.job.encrypted-intermediate-data.buffer.kb":"128","fs.client.resolve.remote.symlinks":"true","yarn.nodemanager.webapp.https.address":"0.0.0.0:8044","hadoop.http.cross-origin.allowed-origins":"*","mapreduce.job.encrypted-intermediate-data":"false","yarn.nodemanager.disk-health-checker.disk-utilization-threshold.enabled":"true","fs.s3a.executor.capacity":"16","yarn.timeline-service.entity-group-fs-store.retain-seconds":"604800","yarn.resourcemanager.metrics.runtime.buckets":"60,300,1440","yarn.timeline-service.generic-application-history.max-applications":"10000","yarn.nodemanager.local-dirs":"${hadoop.tmp.dir}/nm-local-dir","mapreduce.shuffle.connection-keep-alive.enable":"false","yarn.node-labels.configuration-type":"centralized","fs.s3a.path.style.access":"true","yarn.nodemanager.aux-services.mapreduce_shuffle.class":"org.apache.hadoop.mapred.ShuffleHandler","yarn.sharedcache.store.in-memory.staleness-period-mins":"10080","fs.adl.impl":"org.apache.hadoop.fs.adl.AdlFileSystem","yarn.resourcemanager.application.max-tags":"10","hadoop.domainname.resolver.impl":"org.apache.hadoop.net.DNSDomainNameResolver","yarn.resourcemanager.nodemanager.minimum.version":"NONE","mapreduce.jobhistory.webapp.xfs-filter.xframe-options":"SAMEORIGIN","yarn.app.mapreduce.am.staging-dir.erasurecoding.enabled":"false","net.topology.impl":"org.apache.hadoop.net.NetworkTopology","io.map.index.skip":"0","yarn.timeline-service.reader.webapp.https.address":"${yarn.timeline-service.webapp.https.address}","fs.ftp.data.connection.mode":"ACTIVE_LOCAL_DATA_CONNECTION_MODE","mapreduce.job.local-fs.single-disk-limit.check.kill-limit-exceed":"true","fs.azure.buffer.dir":"${hadoop.tmp.dir}/abfs","yarn.scheduler.maximum-allocation-vcores":"4","hadoop.http.cross-origin.allowed-headers":"X-Requested-With,Content-Type,Accept,Origin","yarn.nodemanager.log-aggregation.compression-type":"none","yarn.timeline-service.version":"1.0f","yarn.ipc.rpc.class":"org.apache.hadoop.yarn.ipc.HadoopYarnProtoRPC","mapreduce.reduce.maxattempts":"4","yarn.resourcemanager.system-metrics-publisher.timeline-server-v1.batch-size":"1000","hadoop.security.dns.log-slow-lookups.enabled":"false","mapreduce.job.committer.setup.cleanup.needed":"true","hadoop.security.secure.random.impl":"org.apache.hadoop.crypto.random.OpensslSecureRandom","mapreduce.job.running.reduce.limit":"0","fs.s3a.select.errors.include.sql":"false","fs.s3a.connection.request.timeout":"0","ipc.maximum.response.length":"134217728","yarn.resourcemanager.webapp.rest-csrf.methods-to-ignore":"GET,OPTIONS,HEAD","mapreduce.job.token.tracking.ids.enabled":"*********(redacted)","hadoop.caller.context.max.size":"128","yarn.nodemanager.runtime.linux.docker.host-pid-namespace.allowed":"false","yarn.nodemanager.runtime.linux.docker.delayed-removal.allowed":"false","hadoop.registry.system.acls":"sasl:yarn@, sasl:mapred@, sasl:hdfs@","yarn.nodemanager.recovery.dir":"${hadoop.tmp.dir}/yarn-nm-recovery","fs.s3a.fast.upload.buffer":"disk","mapreduce.jobhistory.intermediate-done-dir":"${yarn.app.mapreduce.am.staging-dir}/history/done_intermediate","yarn.app.mapreduce.shuffle.log.separate":"true","yarn.log-aggregation.debug.filesize":"104857600","fs.s3a.max.total.tasks":"32","fs.s3a.readahead.range":"64K","hadoop.http.authentication.simple.anonymous.allowed":"true","fs.s3a.attempts.maximum":"20","hadoop.registry.zk.connection.timeout.ms":"15000","yarn.resourcemanager.delegation-token-renewer.thread-count":"*********(redacted)","yarn.resourcemanager.delegation-token-renewer.thread-timeout":"*********(redacted)","yarn.timeline-service.leveldb-timeline-store.start-time-write-cache-size":"10000","yarn.nodemanager.aux-services.manifest.reload-ms":"0","yarn.nodemanager.emit-container-events":"true","yarn.resourcemanager.resource-profiles.enabled":"false","yarn.timeline-service.hbase-schema.prefix":"prod.","fs.azure.authorization":"false","mapreduce.map.log.level":"INFO","ha.failover-controller.active-standby-elector.zk.op.retries":"3","yarn.resourcemanager.decommissioning-nodes-watcher.poll-interval-secs":"20","mapreduce.output.fileoutputformat.compress.type":"RECORD","yarn.resourcemanager.leveldb-state-store.path":"${hadoop.tmp.dir}/yarn/system/rmstore","yarn.timeline-service.webapp.rest-csrf.custom-header":"X-XSRF-Header","mapreduce.ifile.readahead.bytes":"4194304","yarn.sharedcache.app-checker.class":"org.apache.hadoop.yarn.server.sharedcachemanager.RemoteAppChecker","yarn.nodemanager.linux-container-executor.nonsecure-mode.limit-users":"true","yarn.nodemanager.resource.detect-hardware-capabilities":"false","mapreduce.cluster.acls.enabled":"false","mapreduce.job.speculative.retry-after-no-speculate":"1000","fs.viewfs.overload.scheme.target.abfs.impl":"org.apache.hadoop.fs.azurebfs.AzureBlobFileSystem","hadoop.security.group.mapping.ldap.search.group.hierarchy.levels":"0","yarn.resourcemanager.fs.state-store.retry-interval-ms":"1000","file.stream-buffer-size":"4096","yarn.resourcemanager.application-timeouts.monitor.interval-ms":"3000","mapreduce.map.output.compress.codec":"org.apache.hadoop.io.compress.DefaultCodec","mapreduce.map.speculative":"true","yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.hdfs-hash-file":"/runc-root/image-tag-to-hash","mapreduce.job.speculative.retry-after-speculate":"15000","yarn.nodemanager.linux-container-executor.cgroups.mount":"false","yarn.app.mapreduce.am.container.log.backups":"0","yarn.app.mapreduce.am.log.level":"INFO","yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin":"org.apache.hadoop.yarn.server.nodemanager.containermanager.linux.runtime.runc.ImageTagToManifestPlugin","io.bytes.per.checksum":"512","mapreduce.job.reduce.slowstart.completedmaps":"0.05","yarn.timeline-service.http-authentication.type":"simple","hadoop.security.group.mapping.ldap.search.attr.group.name":"cn","yarn.nodemanager.resource-plugins.fpga.allowed-fpga-devices":"auto","yarn.timeline-service.client.internal-timers-ttl-secs":"420","fs.s3a.select.output.csv.quote.character":"\"","hadoop.http.logs.enabled":"true","fs.s3a.block.size":"32M","yarn.sharedcache.client-server.address":"0.0.0.0:8045","yarn.nodemanager.logaggregation.threadpool-size-max":"100","yarn.resourcemanager.hostname":"0.0.0.0","yarn.resourcemanager.delegation.key.update-interval":"86400000","mapreduce.reduce.shuffle.fetch.retry.enabled":"${yarn.nodemanager.recovery.enabled}","mapreduce.map.memory.mb":"-1","mapreduce.task.skip.start.attempts":"2","fs.AbstractFileSystem.hdfs.impl":"org.apache.hadoop.fs.Hdfs","yarn.nodemanager.disk-health-checker.enable":"true","fs.s3a.select.output.csv.quote.fields":"always","ipc.client.tcpnodelay":"true","ipc.client.rpc-timeout.ms":"0","yarn.nodemanager.webapp.rest-csrf.methods-to-ignore":"GET,OPTIONS,HEAD","yarn.resourcemanager.delegation-token-renewer.thread-retry-max-attempts":"*********(redacted)","ipc.client.low-latency":"false","mapreduce.input.lineinputformat.linespermap":"1","yarn.router.interceptor.user.threadpool-size":"5","ipc.client.connect.max.retries.on.timeouts":"45","yarn.timeline-service.leveldb-timeline-store.read-cache-size":"104857600","fs.AbstractFileSystem.har.impl":"org.apache.hadoop.fs.HarFs","mapreduce.job.split.metainfo.maxsize":"10000000","yarn.am.liveness-monitor.expiry-interval-ms":"600000","yarn.resourcemanager.container-tokens.master-key-rolling-interval-secs":"*********(redacted)","yarn.timeline-service.entity-group-fs-store.app-cache-size":"10","yarn.nodemanager.runtime.linux.runc.hdfs-manifest-to-resources-plugin.stat-cache-timeout-interval-secs":"360","fs.s3a.socket.recv.buffer":"8192","rpc.metrics.timeunit":"MILLISECONDS","yarn.resourcemanager.resource-tracker.address":"${yarn.resourcemanager.hostname}:8031","yarn.nodemanager.node-labels.provider.fetch-timeout-ms":"1200000","mapreduce.job.heap.memory-mb.ratio":"0.8","yarn.resourcemanager.leveldb-state-store.compaction-interval-secs":"3600","yarn.resourcemanager.webapp.rest-csrf.custom-header":"X-XSRF-Header","yarn.nodemanager.pluggable-device-framework.enabled":"false","yarn.scheduler.configuration.fs.path":"file://${hadoop.tmp.dir}/yarn/system/schedconf","mapreduce.client.output.filter":"FAILED","hadoop.http.filter.initializers":"org.apache.hadoop.http.lib.StaticUserWebFilter","mapreduce.reduce.memory.mb":"-1","yarn.timeline-service.hostname":"0.0.0.0","file.replication":"1","yarn.nodemanager.container-metrics.unregister-delay-ms":"10000","yarn.nodemanager.container-metrics.period-ms":"-1","mapreduce.fileoutputcommitter.task.cleanup.enabled":"false","yarn.nodemanager.log.retain-seconds":"10800","yarn.timeline-service.entity-group-fs-store.cleaner-interval-seconds":"3600","ipc.[port_number].callqueue.impl":"java.util.concurrent.LinkedBlockingQueue","yarn.resourcemanager.keytab":"/etc/krb5.keytab","hadoop.security.group.mapping.providers.combined":"true","mapreduce.reduce.merge.inmem.threshold":"1000","yarn.timeline-service.recovery.enabled":"false","fs.azure.saskey.usecontainersaskeyforallaccess":"true","yarn.sharedcache.nm.uploader.thread-count":"20","yarn.resourcemanager.nodemanager-graceful-decommission-timeout-secs":"3600","ipc.[port_number].weighted-cost.lockfree":"1","mapreduce.shuffle.ssl.enabled":"false","yarn.timeline-service.hbase.coprocessor.app-final-value-retention-milliseconds":"259200000","yarn.nodemanager.opportunistic-containers-max-queue-length":"0","yarn.resourcemanager.state-store.max-completed-applications":"${yarn.resourcemanager.max-completed-applications}","mapreduce.job.speculative.minimum-allowed-tasks":"10","fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","yarn.log-aggregation.retain-seconds":"-1","yarn.nodemanager.disk-health-checker.min-free-space-per-disk-mb":"0","mapreduce.jobhistory.max-age-ms":"604800000","hadoop.http.cross-origin.allowed-methods":"GET,POST,HEAD","yarn.resourcemanager.opportunistic-container-allocation.enabled":"false","mapreduce.jobhistory.webapp.address":"0.0.0.0:19888","hadoop.system.tags":"YARN,HDFS,NAMENODE,DATANODE,REQUIRED,SECURITY,KERBEROS,PERFORMANCE,CLIENT\n      ,SERVER,DEBUG,DEPRECATED,COMMON,OPTIONAL","yarn.log-aggregation.file-controller.TFile.class":"org.apache.hadoop.yarn.logaggregation.filecontroller.tfile.LogAggregationTFileController","yarn.client.nodemanager-connect.max-wait-ms":"180000","yarn.resourcemanager.webapp.address":"${yarn.resourcemanager.hostname}:8088","mapreduce.jobhistory.recovery.enable":"false","mapreduce.reduce.shuffle.parallelcopies":"5","fs.AbstractFileSystem.webhdfs.impl":"org.apache.hadoop.fs.WebHdfs","fs.trash.interval":"0","yarn.app.mapreduce.client.max-retries":"3","hadoop.security.authentication":"simple","mapreduce.task.profile.reduce.params":"${mapreduce.task.profile.params}","yarn.app.mapreduce.am.resource.mb":"1536","mapreduce.input.fileinputformat.list-status.num-threads":"1","yarn.nodemanager.container-executor.class":"org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor","io.mapfile.bloom.size":"1048576","yarn.timeline-service.ttl-ms":"604800000","yarn.resourcemanager.nm-container-queuing.min-queue-length":"5","yarn.nodemanager.resource.cpu-vcores":"-1","mapreduce.job.reduces":"1","fs.s3a.multipart.size":"64M","fs.s3a.select.input.csv.comment.marker":"#","yarn.scheduler.minimum-allocation-vcores":"1","mapreduce.job.speculative.speculative-cap-total-tasks":"0.01","hadoop.ssl.client.conf":"ssl-client.xml","mapreduce.job.queuename":"default","mapreduce.job.encrypted-intermediate-data-key-size-bits":"128","fs.s3a.metadatastore.authoritative":"false","ipc.[port_number].weighted-cost.response":"1","yarn.nodemanager.webapp.xfs-filter.xframe-options":"SAMEORIGIN","ha.health-monitor.sleep-after-disconnect.ms":"1000","yarn.app.mapreduce.shuffle.log.limit.kb":"0","hadoop.security.group.mapping":"org.apache.hadoop.security.JniBasedUnixGroupsMappingWithFallback","yarn.client.application-client-protocol.poll-timeout-ms":"-1","mapreduce.jobhistory.jhist.format":"binary","mapreduce.task.stuck.timeout-ms":"600000","yarn.resourcemanager.application.max-tag.length":"100","yarn.resourcemanager.ha.enabled":"false","dfs.client.ignore.namenode.default.kms.uri":"false","hadoop.http.staticuser.user":"dr.who","mapreduce.task.exit.timeout.check-interval-ms":"20000","mapreduce.jobhistory.intermediate-user-done-dir.permissions":"770","mapreduce.task.exit.timeout":"60000","yarn.nodemanager.linux-container-executor.resources-handler.class":"org.apache.hadoop.yarn.server.nodemanager.util.DefaultLCEResourcesHandler","mapreduce.reduce.shuffle.memory.limit.percent":"0.25","yarn.resourcemanager.reservation-system.enable":"false","mapreduce.map.output.compress":"false","ha.zookeeper.acl":"world:anyone:rwcda","ipc.server.max.connections":"0","yarn.nodemanager.runtime.linux.docker.default-container-network":"host","yarn.router.webapp.address":"0.0.0.0:8089","yarn.scheduler.maximum-allocation-mb":"8192","yarn.resourcemanager.scheduler.monitor.policies":"org.apache.hadoop.yarn.server.resourcemanager.monitor.capacity.ProportionalCapacityPreemptionPolicy","yarn.sharedcache.cleaner.period-mins":"1440","yarn.nodemanager.resource-plugins.gpu.docker-plugin.nvidia-docker-v1.endpoint":"http://localhost:3476/v1.0/docker/cli","yarn.app.mapreduce.am.container.log.limit.kb":"0","ipc.client.connect.retry.interval":"1000","yarn.timeline-service.http-cross-origin.enabled":"false","fs.wasbs.impl":"org.apache.hadoop.fs.azure.NativeAzureFileSystem$Secure","yarn.resourcemanager.nodemanagers.heartbeat-interval-max-ms":"1000","yarn.federation.subcluster-resolver.class":"org.apache.hadoop.yarn.server.federation.resolver.DefaultSubClusterResolverImpl","yarn.resourcemanager.zk-state-store.parent-path":"/rmstore","fs.s3a.select.input.csv.field.delimiter":",","mapreduce.jobhistory.cleaner.enable":"true","yarn.timeline-service.client.fd-flush-interval-secs":"10","hadoop.security.kms.client.encrypted.key.cache.expiry":"43200000","yarn.client.nodemanager-client-async.thread-pool-max-size":"500","mapreduce.map.maxattempts":"4","yarn.resourcemanager.nm-container-queuing.sorting-nodes-interval-ms":"1000","fs.s3a.committer.staging.tmp.path":"tmp/staging","yarn.nodemanager.sleep-delay-before-sigkill.ms":"250","yarn.resourcemanager.nm-container-queuing.min-queue-wait-time-ms":"10","mapreduce.job.end-notification.retry.attempts":"0","yarn.nodemanager.resource.count-logical-processors-as-cores":"false","hadoop.registry.zk.root":"/registry","adl.feature.ownerandgroup.enableupn":"false","yarn.resourcemanager.zk-max-znode-size.bytes":"1048576","mapreduce.job.reduce.shuffle.consumer.plugin.class":"org.apache.hadoop.mapreduce.task.reduce.Shuffle","yarn.resourcemanager.delayed.delegation-token.removal-interval-ms":"*********(redacted)","yarn.nodemanager.localizer.cache.target-size-mb":"10240","fs.s3a.committer.staging.conflict-mode":"append","mapreduce.client.libjars.wildcard":"true","fs.s3a.committer.staging.unique-filenames":"true","yarn.nodemanager.node-attributes.provider.fetch-timeout-ms":"1200000","fs.s3a.list.version":"2","ftp.client-write-packet-size":"65536","ipc.[port_number].weighted-cost.lockexclusive":"100","fs.AbstractFileSystem.adl.impl":"org.apache.hadoop.fs.adl.Adl","yarn.nodemanager.container-log-monitor.enable":"false","hadoop.security.key.default.cipher":"AES/CTR/NoPadding","yarn.client.failover-retries":"0","fs.s3a.multipart.purge.age":"86400","mapreduce.job.local-fs.single-disk-limit.check.interval-ms":"5000","net.topology.node.switch.mapping.impl":"org.apache.hadoop.net.ScriptBasedMapping","yarn.nodemanager.amrmproxy.address":"0.0.0.0:8049","ipc.server.listen.queue.size":"256","ipc.[port_number].decay-scheduler.period-ms":"5000","yarn.nodemanager.runtime.linux.runc.image-tag-to-manifest-plugin.cache-refresh-interval-secs":"60","map.sort.class":"org.apache.hadoop.util.QuickSort","fs.viewfs.rename.strategy":"SAME_MOUNTPOINT","hadoop.security.kms.client.authentication.retry-count":"1","fs.permissions.umask-mode":"022","fs.s3a.assumed.role.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","yarn.nodemanager.runtime.linux.runc.privileged-containers.allowed":"false","yarn.nodemanager.vmem-check-enabled":"true","yarn.nodemanager.numa-awareness.enabled":"false","yarn.nodemanager.recovery.compaction-interval-secs":"3600","yarn.app.mapreduce.client-am.ipc.max-retries":"3","yarn.resourcemanager.system-metrics-publisher.timeline-server-v1.interval-seconds":"60","yarn.federation.registry.base-dir":"yarnfederation/","yarn.nodemanager.health-checker.run-before-startup":"false","mapreduce.job.max.map":"-1","mapreduce.job.local-fs.single-disk-limit.bytes":"-1","mapreduce.shuffle.pathcache.concurrency-level":"16","mapreduce.job.ubertask.maxreduces":"1","mapreduce.shuffle.pathcache.max-weight":"10485760","hadoop.security.kms.client.encrypted.key.cache.size":"500","hadoop.security.java.secure.random.algorithm":"SHA1PRNG","ha.failover-controller.cli-check.rpc-timeout.ms":"20000","mapreduce.jobhistory.jobname.limit":"50","fs.s3a.select.input.compression":"none","yarn.client.nodemanager-connect.retry-interval-ms":"10000","ipc.[port_number].scheduler.priority.levels":"4","yarn.timeline-service.state-store-class":"org.apache.hadoop.yarn.server.timeline.recovery.LeveldbTimelineStateStore","yarn.nodemanager.env-whitelist":"JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_HOME,PATH,LANG,TZ","yarn.sharedcache.nested-level":"3","yarn.timeline-service.webapp.rest-csrf.methods-to-ignore":"GET,OPTIONS,HEAD","fs.azure.user.agent.prefix":"unknown","yarn.resourcemanager.zk-delegation-token-node.split-index":"*********(redacted)","yarn.nodemanager.numa-awareness.read-topology":"false","yarn.nodemanager.webapp.address":"${yarn.nodemanager.hostname}:8042","rpc.metrics.quantile.enable":"false","yarn.registry.class":"org.apache.hadoop.registry.client.impl.FSRegistryOperationsService","mapreduce.jobhistory.admin.acl":"*","yarn.resourcemanager.system-metrics-publisher.dispatcher.pool-size":"10","yarn.scheduler.queue-placement-rules":"user-group","hadoop.http.authentication.kerberos.keytab":"${user.home}/hadoop.keytab","yarn.resourcemanager.recovery.enabled":"false","fs.s3a.select.input.csv.header":"none","yarn.nodemanager.runtime.linux.runc.hdfs-manifest-to-resources-plugin.stat-cache-size":"500","yarn.timeline-service.webapp.rest-csrf.enabled":"false","yarn.nodemanager.disk-health-checker.min-free-space-per-disk-watermark-high-mb":"0"},"System Properties":{"java.io.tmpdir":"/tmp","line.separator":"\n","path.separator":":","sun.management.compiler":"HotSpot 64-Bit Tiered Compilers","SPARK_SUBMIT":"true","sun.cpu.endian":"little","java.specification.maintenance.version":"1","java.specification.version":"17","java.vm.specification.name":"Java Virtual Machine Specification","java.vendor":"Debian","java.vm.specification.version":"17","user.home":"/home/airflow","sun.arch.data.model":"64","sun.boot.library.path":"/usr/lib/jvm/java-17-openjdk-amd64/lib","user.dir":"/opt/airflow","java.library.path":"/usr/local/lib:/usr/java/packages/lib:/usr/lib/x86_64-linux-gnu/jni:/lib/x86_64-linux-gnu:/usr/lib/x86_64-linux-gnu:/usr/lib/jni:/lib:/usr/lib","os.arch":"amd64","java.vm.version":"17.0.19+10-1-deb12u2-Debian","jetty.git.hash":"abdcda73818a1a2c705da276edb0bf6581e7997e","java.runtime.version":"17.0.19+10-1-deb12u2-Debian","java.vm.info":"mixed mode, sharing","java.runtime.name":"OpenJDK Runtime Environment","java.version.date":"2026-04-21","file.separator":"/","java.class.version":"61.0","java.specification.name":"Java Platform API Specification","file.encoding":"UTF-8","jdk.reflect.useDirectMethodHandle":"false","user.timezone":"Europe/Samara","java.specification.vendor":"Oracle Corporation","sun.java.launcher":"SUN_STANDARD","java.vm.compressedOopsMode":"32-bit","os.version":"6.12.48+deb13-amd64","native.encoding":"UTF-8","java.vm.specification.vendor":"Oracle Corporation","sun.jnu.encoding":"UTF-8","user.language":"en","java.vendor.url":"https://tracker.debian.org/openjdk-17","os.name":"Linux","java.vm.vendor":"Debian","jdk.debug":"release","java.vendor.url.bug":"https://bugs.debian.org/openjdk-17","user.name":"airflow","java.vm.name":"OpenJDK 64-Bit Server VM","sun.java.command":"*********(redacted)","java.home":"/usr/lib/jvm/java-17-openjdk-amd64","java.version":"17.0.19","sun.io.unicode.encoding":"UnicodeLittle"},"Metrics Properties":{"*.sink.servlet.class":"org.apache.spark.metrics.sink.MetricsServlet","*.sink.servlet.path":"/metrics/json","applications.sink.servlet.path":"/metrics/applications/json","master.sink.servlet.path":"/metrics/master/json"},"Classpath Entries":{"/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/avro-1.11.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jcl-over-slf4j-2.0.7.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/snappy-java-1.1.10.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/JLargeArrays-1.5.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-common-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jakarta.annotation-api-1.3.5.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-logging-1.1.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/scala-parser-combinators_2.12-2.3.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/super-csv-2.2.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/zjsonpatch-0.3.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/metrics-jvm-4.2.19.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-compiler-3.1.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-scheduling-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-sketch_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-node-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/parquet-common-1.13.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/arrow-format-12.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/xz-1.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/dropwizard-metrics-hadoop-metrics2-reporter-0.1.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-apps-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-launcher_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-codec-socks-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/scala-collection-compat_2.12-2.7.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hadoop-aws-3.3.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/zookeeper-jute-3.6.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/json-1.8.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jakarta.servlet-api-4.0.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/chill-java-0.10.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jersey-server-2.40.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/tink-1.9.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-core_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/snakeyaml-2.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/scala-library-2.12.18.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-buffer-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/metrics-graphite-4.2.19.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-coordination-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-metastore-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/lz4-java-1.8.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/leveldbjni-all-1.8.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-shims-0.23-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-autoscaling-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/conf":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-tags_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-hive-thriftserver_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/derby-10.14.2.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jersey-container-servlet-2.40.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-sql-api_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/zstd-jni-1.5.5-4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/gson-2.2.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jakarta.validation-api-2.0.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/activation-1.1.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-classes-epoll-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/antlr-runtime-3.5.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jta-1.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-httpclient-okhttp-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-shims-scheduler-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-metrics-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-storageclass-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/antlr4-runtime-4.9.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/orc-mapreduce-1.9.2-shaded-protobuf.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/json4s-core_2.12-3.7.0-M11.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/parquet-jackson-1.13.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/httpclient-4.5.14.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/chill_2.12-0.10.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jdo-api-3.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-math3-3.6.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-pool2-2.11.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/json4s-ast_2.12-3.7.0-M11.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/oro-2.0.8.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-common-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/flatbuffers-java-1.12.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-cli-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/datanucleus-core-4.1.17.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-exec-2.3.9-core.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/metrics-core-4.2.19.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-annotations-2.15.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-jdbc-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-lang3-3.12.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-collections4-4.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/postgresql-42.7.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-kubernetes_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/parquet-hadoop-1.13.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jul-to-slf4j-2.0.7.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/RoaringBitmap-0.9.45.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-events-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-token-provider-kafka-0-10_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-pool-1.5.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-core-asl-1.9.13.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/parquet-column-1.13.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jsr305-3.0.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-client-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/metrics-json-4.2.19.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/aopalliance-repackaged-2.6.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-crypto-1.1.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/json4s-scalap_2.12-3.7.0-M11.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/mesos-1.4.3-shaded-protobuf.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/threeten-extra-1.7.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-sql_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-rbac-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-native-unix-common-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/javolution-5.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/arrow-memory-core-12.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/json4s-jackson_2.12-3.7.0-M11.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/shims-0.9.45.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/snakeyaml-engine-2.6.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-collections-3.2.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-client-api-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-shims-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/datanucleus-rdbms-4.1.19.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-mllib_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-handler-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/parquet-format-structures-1.13.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-mapper-asl-1.9.13.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hadoop-yarn-server-web-proxy-3.3.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-native-kqueue-4.1.96.Final-osx-aarch_64.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/logging-interceptor-3.12.12.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jpam-1.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-network-shuffle_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/javax.jdo-3.2.0-m3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/slf4j-api-2.0.7.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/cats-kernel_2.12-2.1.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/libthrift-0.12.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/log4j-api-2.20.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jakarta.inject-2.6.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jakarta.ws.rs-api-2.1.6.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-repl_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/scala-compiler-2.12.18.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-dataformat-yaml-2.15.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/minlog-1.3.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/univocity-parsers-2.9.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/paranamer-2.8.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/curator-client-2.13.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-admissionregistration-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spire-platform_2.12-0.17.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/arrow-vector-12.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-batch-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/log4j-1.2-api-2.20.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/log4j-core-2.20.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/aircompressor-0.26.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/guava-14.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/JTransforms-3.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/breeze-macros_2.12-2.1.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/zookeeper-3.6.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/py4j-0.10.9.7.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-native-kqueue-4.1.96.Final-osx-x86_64.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/arpack-3.0.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/pickle-1.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/opencsv-2.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-databind-2.15.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-datatype-jsr310-2.15.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/HikariCP-2.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/ST4-4.0.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-core-2.15.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jaxb-runtime-2.3.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-dbcp-1.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jersey-client-2.40.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/httpcore-4.4.16.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/joda-time-2.12.5.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hk2-utils-2.6.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/scala-xml_2.12-2.1.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/objenesis-3.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-extensions-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-yarn_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kryo-shaded-4.0.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-beeline-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-catalyst_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-mllib-local_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-codec-http-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/annotations-17.0.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/arrow-memory-netty-12.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/aws-java-sdk-bundle-1.12.262.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/javassist-3.29.2-GA.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-common-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hadoop-shaded-guava-1.1.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-text-1.10.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-resolver-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-discovery-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/compress-lzf-1.1.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-core-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/arpack_combined_all-0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spire_2.12-0.17.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/avro-ipc-1.11.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-io-2.13.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-hive_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/ivy-2.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/bonecp-0.8.0.RELEASE.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/osgi-resource-locator-1.0.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-streaming_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/rocksdbjni-8.3.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/okhttp-3.12.12.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/avro-mapred-1.11.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jersey-common-2.40.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-cli-1.5.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-sql-kafka-0-10_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/clickhouse-jdbc-0.6.0-all.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/libfb303-0.9.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-codec-http2-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-llap-common-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-shims-common-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/stream-2.9.6.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/scala-reflect-2.12.18.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-classes-kqueue-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-gatewayapi-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/istack-commons-runtime-3.0.8.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-lang-2.6.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hk2-api-2.6.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/datasketches-java-3.3.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/okio-1.15.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/curator-recipes-2.13.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hadoop-client-api-3.3.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-codec-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-network-common_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/datanucleus-api-jdo-4.2.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kafka-clients-3.7.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-common-utils_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/lapack-3.0.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/orc-core-1.9.2-shaded-protobuf.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/janino-3.1.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/blas-3.0.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-flowcontrol-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-handler-proxy-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-graphx_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-native-epoll-4.1.96.Final-linux-x86_64.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/parquet-encoding-1.13.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jodd-core-3.5.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-mesos_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spire-macros_2.12-0.17.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-transport-native-epoll-4.1.96.Final-linux-aarch_64.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hadoop-client-runtime-3.3.4.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-certificates-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jersey-hk2-2.40.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spire-util_2.12-0.17.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-compress-1.23.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-storage-api-2.8.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-apiextensions-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/algebra_2.12-2.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/metrics-jmx-4.2.19.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/breeze_2.12-2.1.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/xbean-asm9-shaded-4.23.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/stax-api-1.0.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-serde-2.3.9.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/netty-all-4.1.96.Final.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/orc-shims-1.9.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/audience-annotations-0.5.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/curator-framework-2.13.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hk2-locator-2.6.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-resource-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/hive-service-rpc-3.1.3.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-kvstore_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jakarta.xml.bind-api-2.3.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-networking-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jersey-container-servlet-core-2.40.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/commons-codec-1.16.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/datasketches-memory-2.1.0.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jline-2.14.6.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/jackson-module-scala_2.12-2.15.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/spark-unsafe_2.12-3.5.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/kubernetes-model-policy-6.7.2.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/transaction-api-1.1.jar":"System Classpath","/home/airflow/.local/lib/python3.11/site-packages/pyspark/jars/log4j-slf4j2-impl-2.20.0.jar":"System Classpath"}}
{"Event":"SparkListenerApplicationStart","App Name":"dm_course_completion_rate","App ID":"app-20260715131433-0082","Timestamp":1784106872542,"User":"airflow"}
{"Event":"SparkListenerExecutorAdded","Timestamp":1784106876246,"Executor ID":"0","Executor Info":{"Host":"172.28.0.49","Total Cores":5,"Log Urls":{"stdout":"http://172.28.0.49:8081/logPage/?appId=app-20260715131433-0082&executorId=0&logType=stdout","stderr":"http://172.28.0.49:8081/logPage/?appId=app-20260715131433-0082&executorId=0&logType=stderr"},"Attributes":{},"Resources":{},"Resource Profile Id":0,"Registration Time":1784106876246}}
{"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"0","Host":"172.28.0.49","Port":39865},"Maximum Memory":455501414,"Timestamp":1784106876325,"Maximum Onheap Memory":455501414,"Maximum Offheap Memory":0}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionStart","executionId":0,"rootExecutionId":0,"description":"parquet at NativeMethodAccessorImpl.java:0","details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (37)\n+- Execute InsertIntoHadoopFsRelationCommand (36)\n   +- WriteFiles (35)\n      +- Sort (34)\n         +- Exchange (33)\n            +- Project (32)\n               +- Project (31)\n                  +- BroadcastHashJoin LeftOuter BuildRight (30)\n                     :- Project (20)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (19)\n                     :     :- Project (12)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (11)\n                     :     :     :- Project (7)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (6)\n                     :     :     :     :- Filter (2)\n                     :     :     :     :  +- Scan csv  (1)\n                     :     :     :     +- BroadcastExchange (5)\n                     :     :     :        +- Filter (4)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (10)\n                     :     :        +- Filter (9)\n                     :     :           +- Scan csv  (8)\n                     :     +- BroadcastExchange (18)\n                     :        +- HashAggregate (17)\n                     :           +- Exchange (16)\n                     :              +- HashAggregate (15)\n                     :                 +- Filter (14)\n                     :                    +- Scan csv  (13)\n                     +- BroadcastExchange (29)\n                        +- HashAggregate (28)\n                           +- Exchange (27)\n                              +- HashAggregate (26)\n                                 +- HashAggregate (25)\n                                    +- Exchange (24)\n                                       +- HashAggregate (23)\n                                          +- Filter (22)\n                                             +- Scan csv  (21)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(6) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(7) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(8) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(9) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(10) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(11) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(12) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(13) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(14) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(15) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(16) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(17) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(18) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(19) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(20) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(21) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(22) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(23) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(24) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(25) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(26) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(27) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(28) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(29) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(30) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(31) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(32) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(33) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(34) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(35) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(36) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(37) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=false\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=false","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":37,"metricType":"sum"},{"name":"number of files read","accumulatorId":38,"metricType":"sum"},{"name":"metadata time","accumulatorId":39,"metricType":"timing"},{"name":"size of files read","accumulatorId":40,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":36,"metricType":"sum"}]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":46,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":45,"metricType":"timing"},{"name":"time to build","accumulatorId":44,"metricType":"timing"},{"name":"time to collect","accumulatorId":43,"metricType":"timing"},{"name":"number of output rows","accumulatorId":42,"metricType":"sum"},{"name":"data size","accumulatorId":41,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":35,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":56,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":55,"metricType":"timing"},{"name":"time to build","accumulatorId":54,"metricType":"timing"},{"name":"time to collect","accumulatorId":53,"metricType":"timing"},{"name":"number of output rows","accumulatorId":52,"metricType":"sum"},{"name":"data size","accumulatorId":51,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":34,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":100,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":96,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":97,"metricType":"timing"},{"name":"peak memory","accumulatorId":95,"metricType":"size"},{"name":"number of output rows","accumulatorId":94,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":99,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":98,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":92,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":86,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":93,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":87,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":84,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":81,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":90,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":83,"metricType":"sum"},{"name":"records read","accumulatorId":80,"metricType":"sum"},{"name":"local bytes read","accumulatorId":78,"metricType":"size"},{"name":"fetch wait time","accumulatorId":79,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":76,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":82,"metricType":"sum"},{"name":"local blocks read","accumulatorId":75,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":85,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":74,"metricType":"sum"},{"name":"data size","accumulatorId":72,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":88,"metricType":"size"},{"name":"number of partitions","accumulatorId":73,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":89,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":77,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":91,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":68,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":69,"metricType":"timing"},{"name":"peak memory","accumulatorId":67,"metricType":"size"},{"name":"number of output rows","accumulatorId":66,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":71,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":70,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":65,"metricType":"timing"},{"name":"time to build","accumulatorId":64,"metricType":"timing"},{"name":"time to collect","accumulatorId":63,"metricType":"timing"},{"name":"number of output rows","accumulatorId":62,"metricType":"sum"},{"name":"data size","accumulatorId":61,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":33,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":178,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":174,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":175,"metricType":"timing"},{"name":"peak memory","accumulatorId":173,"metricType":"size"},{"name":"number of output rows","accumulatorId":172,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":177,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":176,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":170,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":164,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":171,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":165,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":162,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":159,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":168,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":161,"metricType":"sum"},{"name":"records read","accumulatorId":158,"metricType":"sum"},{"name":"local bytes read","accumulatorId":156,"metricType":"size"},{"name":"fetch wait time","accumulatorId":157,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":154,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":160,"metricType":"sum"},{"name":"local blocks read","accumulatorId":153,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":163,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":152,"metricType":"sum"},{"name":"data size","accumulatorId":150,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":166,"metricType":"size"},{"name":"number of partitions","accumulatorId":151,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":167,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":155,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":169,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":146,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":147,"metricType":"timing"},{"name":"peak memory","accumulatorId":145,"metricType":"size"},{"name":"number of output rows","accumulatorId":144,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":149,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":148,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":140,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":141,"metricType":"timing"},{"name":"peak memory","accumulatorId":139,"metricType":"size"},{"name":"number of output rows","accumulatorId":138,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":143,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":142,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":136,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":130,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":137,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":131,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":128,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":125,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":134,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":127,"metricType":"sum"},{"name":"records read","accumulatorId":124,"metricType":"sum"},{"name":"local bytes read","accumulatorId":122,"metricType":"size"},{"name":"fetch wait time","accumulatorId":123,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":120,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":126,"metricType":"sum"},{"name":"local blocks read","accumulatorId":119,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":129,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":118,"metricType":"sum"},{"name":"data size","accumulatorId":116,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":132,"metricType":"size"},{"name":"number of partitions","accumulatorId":117,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":133,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":121,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":135,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":112,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":113,"metricType":"timing"},{"name":"peak memory","accumulatorId":111,"metricType":"size"},{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":115,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":114,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":109,"metricType":"timing"},{"name":"time to build","accumulatorId":108,"metricType":"timing"},{"name":"time to collect","accumulatorId":107,"metricType":"timing"},{"name":"number of output rows","accumulatorId":106,"metricType":"sum"},{"name":"data size","accumulatorId":105,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":32,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":30,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":24,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":31,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":25,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":22,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":19,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":28,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":21,"metricType":"sum"},{"name":"records read","accumulatorId":18,"metricType":"sum"},{"name":"local bytes read","accumulatorId":16,"metricType":"size"},{"name":"fetch wait time","accumulatorId":17,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":14,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":20,"metricType":"sum"},{"name":"local blocks read","accumulatorId":13,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":23,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":12,"metricType":"sum"},{"name":"data size","accumulatorId":10,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":26,"metricType":"size"},{"name":"number of partitions","accumulatorId":11,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":27,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":15,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":29,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":7,"metricType":"timing"},{"name":"peak memory","accumulatorId":8,"metricType":"size"},{"name":"spill size","accumulatorId":9,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":5,"metricType":"timing"},{"name":"number of written files","accumulatorId":1,"metricType":"sum"},{"name":"job commit time","accumulatorId":6,"metricType":"timing"},{"name":"number of output rows","accumulatorId":3,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":4,"metricType":"sum"},{"name":"written output","accumulatorId":2,"metricType":"size"}]}],"metadata":{},"metrics":[]},"time":1784106878002,"modifiedConfigs":{},"jobTags":[]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (71)\n+- == Current Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (40)\n   +- WriteFiles (39)\n      +- Sort (38)\n         +- Exchange (37)\n            +- Project (36)\n               +- Project (35)\n                  +- BroadcastHashJoin LeftOuter BuildRight (34)\n                     :- Project (23)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (22)\n                     :     :- Project (14)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (13)\n                     :     :     :- Project (8)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (7)\n                     :     :     :     :- Filter (2)\n                     :     :     :     :  +- Scan csv  (1)\n                     :     :     :     +- BroadcastQueryStage (6)\n                     :     :     :        +- BroadcastExchange (5)\n                     :     :     :           +- * Filter (4)\n                     :     :     :              +- Scan csv  (3)\n                     :     :     +- BroadcastQueryStage (12)\n                     :     :        +- BroadcastExchange (11)\n                     :     :           +- * Filter (10)\n                     :     :              +- Scan csv  (9)\n                     :     +- BroadcastExchange (21)\n                     :        +- HashAggregate (20)\n                     :           +- ShuffleQueryStage (19)\n                     :              +- Exchange (18)\n                     :                 +- * HashAggregate (17)\n                     :                    +- * Filter (16)\n                     :                       +- Scan csv  (15)\n                     +- BroadcastExchange (33)\n                        +- HashAggregate (32)\n                           +- Exchange (31)\n                              +- HashAggregate (30)\n                                 +- HashAggregate (29)\n                                    +- ShuffleQueryStage (28)\n                                       +- Exchange (27)\n                                          +- * HashAggregate (26)\n                                             +- * Filter (25)\n                                                +- Scan csv  (24)\n+- == Initial Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (70)\n   +- WriteFiles (69)\n      +- Sort (68)\n         +- Exchange (67)\n            +- Project (66)\n               +- Project (65)\n                  +- BroadcastHashJoin LeftOuter BuildRight (64)\n                     :- Project (55)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (54)\n                     :     :- Project (48)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (47)\n                     :     :     :- Project (44)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (43)\n                     :     :     :     :- Filter (2)\n                     :     :     :     :  +- Scan csv  (1)\n                     :     :     :     +- BroadcastExchange (42)\n                     :     :     :        +- Filter (41)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (46)\n                     :     :        +- Filter (45)\n                     :     :           +- Scan csv  (9)\n                     :     +- BroadcastExchange (53)\n                     :        +- HashAggregate (52)\n                     :           +- Exchange (51)\n                     :              +- HashAggregate (50)\n                     :                 +- Filter (49)\n                     :                    +- Scan csv  (15)\n                     +- BroadcastExchange (63)\n                        +- HashAggregate (62)\n                           +- Exchange (61)\n                              +- HashAggregate (60)\n                                 +- HashAggregate (59)\n                                    +- Exchange (58)\n                                       +- HashAggregate (57)\n                                          +- Filter (56)\n                                             +- Scan csv  (24)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter [codegen id : 1]\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]\n\n(6) BroadcastQueryStage\nOutput [2]: [user_id#26, name#27]\nArguments: 0\n\n(7) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(8) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(9) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(10) Filter [codegen id : 2]\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(11) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]\n\n(12) BroadcastQueryStage\nOutput [2]: [course_id#18, title#19]\nArguments: 1\n\n(13) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(14) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(15) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(16) Filter [codegen id : 3]\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(17) HashAggregate [codegen id : 3]\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(18) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]\n\n(19) ShuffleQueryStage\nOutput [2]: [course_id#9, count#207L]\nArguments: 2\n\n(20) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(21) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=251]\n\n(22) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(23) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(24) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(25) Filter [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(26) HashAggregate [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(27) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]\n\n(28) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: 3\n\n(29) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(30) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(31) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=270]\n\n(32) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(33) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=272]\n\n(34) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(35) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(36) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(37) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=276]\n\n(38) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(39) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(40) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(41) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(42) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(43) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(44) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(45) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(46) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(47) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(48) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(49) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(50) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(51) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(52) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(53) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(54) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(55) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(56) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(57) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(58) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(59) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(60) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(61) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(62) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(63) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(64) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(65) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(66) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(67) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(68) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(69) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(70) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(71) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=false\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=false","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=276]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":37,"metricType":"sum"},{"name":"number of files read","accumulatorId":38,"metricType":"sum"},{"name":"metadata time","accumulatorId":39,"metricType":"timing"},{"name":"size of files read","accumulatorId":40,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":36,"metricType":"sum"}]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":218,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":217,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":216,"metricType":"timing"},{"name":"time to build","accumulatorId":215,"metricType":"timing"},{"name":"time to collect","accumulatorId":214,"metricType":"timing"},{"name":"number of output rows","accumulatorId":213,"metricType":"sum"},{"name":"data size","accumulatorId":212,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":211,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":225,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":224,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":223,"metricType":"timing"},{"name":"time to build","accumulatorId":222,"metricType":"timing"},{"name":"time to collect","accumulatorId":221,"metricType":"timing"},{"name":"number of output rows","accumulatorId":220,"metricType":"sum"},{"name":"data size","accumulatorId":219,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":210,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=251]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 2","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":266,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":262,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":263,"metricType":"timing"},{"name":"peak memory","accumulatorId":261,"metricType":"size"},{"name":"number of output rows","accumulatorId":260,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":265,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":264,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":259,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":257,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":251,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":258,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":252,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":249,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":246,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":255,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":248,"metricType":"sum"},{"name":"records read","accumulatorId":245,"metricType":"sum"},{"name":"local bytes read","accumulatorId":243,"metricType":"size"},{"name":"fetch wait time","accumulatorId":244,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":241,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":247,"metricType":"sum"},{"name":"local blocks read","accumulatorId":240,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":250,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":239,"metricType":"sum"},{"name":"data size","accumulatorId":237,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":253,"metricType":"size"},{"name":"number of partitions","accumulatorId":238,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":254,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":242,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":256,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":233,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":234,"metricType":"timing"},{"name":"peak memory","accumulatorId":232,"metricType":"size"},{"name":"number of output rows","accumulatorId":231,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":236,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":235,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":230,"metricType":"timing"},{"name":"time to build","accumulatorId":229,"metricType":"timing"},{"name":"time to collect","accumulatorId":228,"metricType":"timing"},{"name":"number of output rows","accumulatorId":227,"metricType":"sum"},{"name":"data size","accumulatorId":226,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":209,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=272]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=270]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":341,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":337,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":338,"metricType":"timing"},{"name":"peak memory","accumulatorId":336,"metricType":"size"},{"name":"number of output rows","accumulatorId":335,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":340,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":339,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":334,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":332,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":326,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":333,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":327,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":324,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":321,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":330,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":323,"metricType":"sum"},{"name":"records read","accumulatorId":320,"metricType":"sum"},{"name":"local bytes read","accumulatorId":318,"metricType":"size"},{"name":"fetch wait time","accumulatorId":319,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":316,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":322,"metricType":"sum"},{"name":"local blocks read","accumulatorId":315,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":325,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":314,"metricType":"sum"},{"name":"data size","accumulatorId":312,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":328,"metricType":"size"},{"name":"number of partitions","accumulatorId":313,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":329,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":317,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":331,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":308,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":309,"metricType":"timing"},{"name":"peak memory","accumulatorId":307,"metricType":"size"},{"name":"number of output rows","accumulatorId":306,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":311,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":310,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":302,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":303,"metricType":"timing"},{"name":"peak memory","accumulatorId":301,"metricType":"size"},{"name":"number of output rows","accumulatorId":300,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":305,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":304,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":298,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":292,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":299,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":293,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":290,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":287,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":296,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":289,"metricType":"sum"},{"name":"records read","accumulatorId":286,"metricType":"sum"},{"name":"local bytes read","accumulatorId":284,"metricType":"size"},{"name":"fetch wait time","accumulatorId":285,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":282,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":288,"metricType":"sum"},{"name":"local blocks read","accumulatorId":281,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":291,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":280,"metricType":"sum"},{"name":"data size","accumulatorId":278,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":294,"metricType":"size"},{"name":"number of partitions","accumulatorId":279,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":295,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":283,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":297,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":274,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":275,"metricType":"timing"},{"name":"peak memory","accumulatorId":273,"metricType":"size"},{"name":"number of output rows","accumulatorId":272,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":277,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":276,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":271,"metricType":"timing"},{"name":"time to build","accumulatorId":270,"metricType":"timing"},{"name":"time to collect","accumulatorId":269,"metricType":"timing"},{"name":"number of output rows","accumulatorId":268,"metricType":"sum"},{"name":"data size","accumulatorId":267,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":208,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":206,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":200,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":207,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":201,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":198,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":195,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":204,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":197,"metricType":"sum"},{"name":"records read","accumulatorId":194,"metricType":"sum"},{"name":"local bytes read","accumulatorId":192,"metricType":"size"},{"name":"fetch wait time","accumulatorId":193,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":190,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":196,"metricType":"sum"},{"name":"local blocks read","accumulatorId":189,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":199,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":188,"metricType":"sum"},{"name":"data size","accumulatorId":186,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":202,"metricType":"size"},{"name":"number of partitions","accumulatorId":187,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":203,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":191,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":205,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":183,"metricType":"timing"},{"name":"peak memory","accumulatorId":184,"metricType":"size"},{"name":"spill size","accumulatorId":185,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":5,"metricType":"timing"},{"name":"number of written files","accumulatorId":1,"metricType":"sum"},{"name":"job commit time","accumulatorId":6,"metricType":"timing"},{"name":"number of output rows","accumulatorId":3,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":4,"metricType":"sum"},{"name":"written output","accumulatorId":2,"metricType":"size"}]}],"metadata":{},"metrics":[]}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[102,1],[103,10],[104,1046]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[48,1],[49,12],[50,1037]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[58,1],[59,7],[60,378]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[238,200]]}
{"Event":"SparkListenerJobStart","Job ID":1,"Submission Time":1784106878830,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":9,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[8],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":8,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"3\",\"name\":\"WholeStageCodegen (1)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[5],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":0,"Name":"FileScanRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":5,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[0],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[0],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId e6669e75-9101-42f9-b090-408b61913c18)","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":9,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[8],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":8,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"3\",\"name\":\"WholeStageCodegen (1)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[5],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":0,"Name":"FileScanRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":5,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[0],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106878857,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId e6669e75-9101-42f9-b090-408b61913c18)","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerJobStart","Job ID":0,"Submission Time":1784106878915,"Stage Infos":[{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":7,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[6],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":2,"Name":"FileScanRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":6,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"7\",\"name\":\"WholeStageCodegen (2)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[4],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":4,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[2],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[1],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId fd149ed9-481e-4f66-b440-ddebaf18c35b)","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":7,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[6],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":2,"Name":"FileScanRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":6,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"7\",\"name\":\"WholeStageCodegen (2)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[4],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":4,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[2],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106878918,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId fd149ed9-481e-4f66-b440-ddebaf18c35b)","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[180,1],[181,0],[182,1808]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[313,200]]}
{"Event":"SparkListenerJobStart","Job ID":2,"Submission Time":1784106879043,"Stage Infos":[{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[10],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[2],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"2\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[10],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106879055,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"2\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerJobStart","Job ID":3,"Submission Time":1784106879102,"Stage Infos":[{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[14],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":13,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[12],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"17\",\"name\":\"WholeStageCodegen (4)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[13],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[3],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[14],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":13,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[12],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"17\",\"name\":\"WholeStageCodegen (4)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[13],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106879117,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":0,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106878923,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":1,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106879031,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskStart","Stage ID":2,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106879097,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskStart","Stage ID":3,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106879131,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskEnd","Stage ID":0,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106878923,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106881740,"Failed":false,"Killed":false,"Accumulables":[{"ID":47,"Name":"number of output rows","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":217,"Name":"duration","Update":"1372","Value":"1372","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":218,"Name":"number of output rows","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":342,"Name":"internal.metrics.executorDeserializeTime","Update":805,"Value":805,"Internal":true,"Count Failed Values":true},{"ID":343,"Name":"internal.metrics.executorDeserializeCpuTime","Update":216554430,"Value":216554430,"Internal":true,"Count Failed Values":true},{"ID":344,"Name":"internal.metrics.executorRunTime","Update":1834,"Value":1834,"Internal":true,"Count Failed Values":true},{"ID":345,"Name":"internal.metrics.executorCpuTime","Update":382926329,"Value":382926329,"Internal":true,"Count Failed Values":true},{"ID":346,"Name":"internal.metrics.resultSize","Update":2030,"Value":2030,"Internal":true,"Count Failed Values":true},{"ID":347,"Name":"internal.metrics.jvmGCTime","Update":37,"Value":37,"Internal":true,"Count Failed Values":true},{"ID":348,"Name":"internal.metrics.resultSerializationTime","Update":3,"Value":3,"Internal":true,"Count Failed Values":true},{"ID":373,"Name":"internal.metrics.input.bytesRead","Update":1037,"Value":1037,"Internal":true,"Count Failed Values":true},{"ID":374,"Name":"internal.metrics.input.recordsRead","Update":20,"Value":20,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":805,"Executor Deserialize CPU Time":216554430,"Executor Run Time":1834,"Executor CPU Time":382926329,"Peak Execution Memory":0,"Result Size":2030,"JVM GC Time":37,"Result Serialization Time":3,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":0,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":0,"Total Records Read":0,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":1037,"Records Read":20},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":9,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[8],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":8,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"3\",\"name\":\"WholeStageCodegen (1)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[5],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":0,"Name":"FileScanRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":5,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[0],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106878857,"Completion Time":1784106881748,"Accumulables":[{"ID":47,"Name":"number of output rows","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":217,"Name":"duration","Value":"1372","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":218,"Name":"number of output rows","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":342,"Name":"internal.metrics.executorDeserializeTime","Value":805,"Internal":true,"Count Failed Values":true},{"ID":343,"Name":"internal.metrics.executorDeserializeCpuTime","Value":216554430,"Internal":true,"Count Failed Values":true},{"ID":344,"Name":"internal.metrics.executorRunTime","Value":1834,"Internal":true,"Count Failed Values":true},{"ID":345,"Name":"internal.metrics.executorCpuTime","Value":382926329,"Internal":true,"Count Failed Values":true},{"ID":346,"Name":"internal.metrics.resultSize","Value":2030,"Internal":true,"Count Failed Values":true},{"ID":347,"Name":"internal.metrics.jvmGCTime","Value":37,"Internal":true,"Count Failed Values":true},{"ID":348,"Name":"internal.metrics.resultSerializationTime","Value":3,"Internal":true,"Count Failed Values":true},{"ID":373,"Name":"internal.metrics.input.bytesRead","Value":1037,"Internal":true,"Count Failed Values":true},{"ID":374,"Name":"internal.metrics.input.recordsRead","Value":20,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":1,"Completion Time":1784106881760,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"SparkListenerTaskEnd","Stage ID":1,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":1,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106879031,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106881743,"Failed":false,"Killed":false,"Accumulables":[{"ID":57,"Name":"number of output rows","Update":"5","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":224,"Name":"duration","Update":"1372","Value":"1372","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":225,"Name":"number of output rows","Update":"5","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":377,"Name":"internal.metrics.executorDeserializeTime","Update":804,"Value":804,"Internal":true,"Count Failed Values":true},{"ID":378,"Name":"internal.metrics.executorDeserializeCpuTime","Update":167046308,"Value":167046308,"Internal":true,"Count Failed Values":true},{"ID":379,"Name":"internal.metrics.executorRunTime","Update":1834,"Value":1834,"Internal":true,"Count Failed Values":true},{"ID":380,"Name":"internal.metrics.executorCpuTime","Update":674271973,"Value":674271973,"Internal":true,"Count Failed Values":true},{"ID":381,"Name":"internal.metrics.resultSize","Update":1921,"Value":1921,"Internal":true,"Count Failed Values":true},{"ID":382,"Name":"internal.metrics.jvmGCTime","Update":37,"Value":37,"Internal":true,"Count Failed Values":true},{"ID":383,"Name":"internal.metrics.resultSerializationTime","Update":3,"Value":3,"Internal":true,"Count Failed Values":true},{"ID":408,"Name":"internal.metrics.input.bytesRead","Update":378,"Value":378,"Internal":true,"Count Failed Values":true},{"ID":409,"Name":"internal.metrics.input.recordsRead","Update":5,"Value":5,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":804,"Executor Deserialize CPU Time":167046308,"Executor Run Time":1834,"Executor CPU Time":674271973,"Peak Execution Memory":0,"Result Size":1921,"JVM GC Time":37,"Result Serialization Time":3,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":0,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":0,"Total Records Read":0,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":378,"Records Read":5},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":7,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[6],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":2,"Name":"FileScanRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":6,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"7\",\"name\":\"WholeStageCodegen (2)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[4],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":4,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[2],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106878918,"Completion Time":1784106881761,"Accumulables":[{"ID":57,"Name":"number of output rows","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":224,"Name":"duration","Value":"1372","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":225,"Name":"number of output rows","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":377,"Name":"internal.metrics.executorDeserializeTime","Value":804,"Internal":true,"Count Failed Values":true},{"ID":378,"Name":"internal.metrics.executorDeserializeCpuTime","Value":167046308,"Internal":true,"Count Failed Values":true},{"ID":379,"Name":"internal.metrics.executorRunTime","Value":1834,"Internal":true,"Count Failed Values":true},{"ID":380,"Name":"internal.metrics.executorCpuTime","Value":674271973,"Internal":true,"Count Failed Values":true},{"ID":381,"Name":"internal.metrics.resultSize","Value":1921,"Internal":true,"Count Failed Values":true},{"ID":382,"Name":"internal.metrics.jvmGCTime","Value":37,"Internal":true,"Count Failed Values":true},{"ID":383,"Name":"internal.metrics.resultSerializationTime","Value":3,"Internal":true,"Count Failed Values":true},{"ID":408,"Name":"internal.metrics.input.bytesRead","Value":378,"Internal":true,"Count Failed Values":true},{"ID":409,"Name":"internal.metrics.input.recordsRead","Value":5,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":0,"Completion Time":1784106881761,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"SparkListenerTaskEnd","Stage ID":2,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":2,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106879097,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106881762,"Failed":false,"Killed":false,"Accumulables":[{"ID":101,"Name":"number of output rows","Update":"18","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":237,"Name":"data size","Update":"120","Value":"120","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":256,"Name":"shuffle bytes written","Update":"312","Value":"312","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":257,"Name":"shuffle records written","Update":"5","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":258,"Name":"shuffle write time","Update":"21057760","Value":"21057760","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":259,"Name":"duration","Update":"1360","Value":"1360","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":260,"Name":"number of output rows","Update":"5","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":261,"Name":"peak memory","Update":"262144","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":263,"Name":"time in aggregation build","Update":"1176","Value":"1176","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":266,"Name":"number of output rows","Update":"18","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":412,"Name":"internal.metrics.executorDeserializeTime","Update":805,"Value":805,"Internal":true,"Count Failed Values":true},{"ID":413,"Name":"internal.metrics.executorDeserializeCpuTime","Update":199719235,"Value":199719235,"Internal":true,"Count Failed Values":true},{"ID":414,"Name":"internal.metrics.executorRunTime","Update":1825,"Value":1825,"Internal":true,"Count Failed Values":true},{"ID":415,"Name":"internal.metrics.executorCpuTime","Update":382414393,"Value":382414393,"Internal":true,"Count Failed Values":true},{"ID":416,"Name":"internal.metrics.resultSize","Update":2858,"Value":2858,"Internal":true,"Count Failed Values":true},{"ID":417,"Name":"internal.metrics.jvmGCTime","Update":37,"Value":37,"Internal":true,"Count Failed Values":true},{"ID":418,"Name":"internal.metrics.resultSerializationTime","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":421,"Name":"internal.metrics.peakExecutionMemory","Update":262144,"Value":262144,"Internal":true,"Count Failed Values":true},{"ID":440,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":312,"Value":312,"Internal":true,"Count Failed Values":true},{"ID":441,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":5,"Value":5,"Internal":true,"Count Failed Values":true},{"ID":442,"Name":"internal.metrics.shuffle.write.writeTime","Update":21057760,"Value":21057760,"Internal":true,"Count Failed Values":true},{"ID":443,"Name":"internal.metrics.input.bytesRead","Update":1046,"Value":1046,"Internal":true,"Count Failed Values":true},{"ID":444,"Name":"internal.metrics.input.recordsRead","Update":18,"Value":18,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":805,"Executor Deserialize CPU Time":199719235,"Executor Run Time":1825,"Executor CPU Time":382414393,"Peak Execution Memory":262144,"Result Size":2858,"JVM GC Time":37,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":0,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":0,"Total Records Read":0,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":312,"Shuffle Write Time":21057760,"Shuffle Records Written":5},"Input Metrics":{"Bytes Read":1046,"Records Read":18},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[10],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106879055,"Completion Time":1784106881765,"Accumulables":[{"ID":101,"Name":"number of output rows","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":237,"Name":"data size","Value":"120","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":256,"Name":"shuffle bytes written","Value":"312","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":257,"Name":"shuffle records written","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":258,"Name":"shuffle write time","Value":"21057760","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":259,"Name":"duration","Value":"1360","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":260,"Name":"number of output rows","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":261,"Name":"peak memory","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":263,"Name":"time in aggregation build","Value":"1176","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":266,"Name":"number of output rows","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":412,"Name":"internal.metrics.executorDeserializeTime","Value":805,"Internal":true,"Count Failed Values":true},{"ID":413,"Name":"internal.metrics.executorDeserializeCpuTime","Value":199719235,"Internal":true,"Count Failed Values":true},{"ID":414,"Name":"internal.metrics.executorRunTime","Value":1825,"Internal":true,"Count Failed Values":true},{"ID":415,"Name":"internal.metrics.executorCpuTime","Value":382414393,"Internal":true,"Count Failed Values":true},{"ID":416,"Name":"internal.metrics.resultSize","Value":2858,"Internal":true,"Count Failed Values":true},{"ID":417,"Name":"internal.metrics.jvmGCTime","Value":37,"Internal":true,"Count Failed Values":true},{"ID":418,"Name":"internal.metrics.resultSerializationTime","Value":1,"Internal":true,"Count Failed Values":true},{"ID":421,"Name":"internal.metrics.peakExecutionMemory","Value":262144,"Internal":true,"Count Failed Values":true},{"ID":440,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":312,"Internal":true,"Count Failed Values":true},{"ID":441,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":5,"Internal":true,"Count Failed Values":true},{"ID":442,"Name":"internal.metrics.shuffle.write.writeTime","Value":21057760,"Internal":true,"Count Failed Values":true},{"ID":443,"Name":"internal.metrics.input.bytesRead","Value":1046,"Internal":true,"Count Failed Values":true},{"ID":444,"Name":"internal.metrics.input.recordsRead","Value":18,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":2,"Completion Time":1784106881768,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"SparkListenerTaskEnd","Stage ID":3,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":3,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106879131,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106881764,"Failed":false,"Killed":false,"Accumulables":[{"ID":179,"Name":"number of output rows","Update":"58","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":312,"Name":"data size","Update":"1760","Value":"1760","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":331,"Name":"shuffle bytes written","Update":"3205","Value":"3205","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":332,"Name":"shuffle records written","Update":"55","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":333,"Name":"shuffle write time","Update":"21665852","Value":"21665852","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":334,"Name":"duration","Update":"1365","Value":"1365","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":335,"Name":"number of output rows","Update":"55","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":336,"Name":"peak memory","Update":"262144","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":338,"Name":"time in aggregation build","Update":"1191","Value":"1191","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":341,"Name":"number of output rows","Update":"58","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":447,"Name":"internal.metrics.executorDeserializeTime","Update":764,"Value":764,"Internal":true,"Count Failed Values":true},{"ID":448,"Name":"internal.metrics.executorDeserializeCpuTime","Update":164730942,"Value":164730942,"Internal":true,"Count Failed Values":true},{"ID":449,"Name":"internal.metrics.executorRunTime","Update":1830,"Value":1830,"Internal":true,"Count Failed Values":true},{"ID":450,"Name":"internal.metrics.executorCpuTime","Update":570319800,"Value":570319800,"Internal":true,"Count Failed Values":true},{"ID":451,"Name":"internal.metrics.resultSize","Update":2815,"Value":2815,"Internal":true,"Count Failed Values":true},{"ID":452,"Name":"internal.metrics.jvmGCTime","Update":37,"Value":37,"Internal":true,"Count Failed Values":true},{"ID":456,"Name":"internal.metrics.peakExecutionMemory","Update":262144,"Value":262144,"Internal":true,"Count Failed Values":true},{"ID":475,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":3205,"Value":3205,"Internal":true,"Count Failed Values":true},{"ID":476,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":55,"Value":55,"Internal":true,"Count Failed Values":true},{"ID":477,"Name":"internal.metrics.shuffle.write.writeTime","Update":21665852,"Value":21665852,"Internal":true,"Count Failed Values":true},{"ID":478,"Name":"internal.metrics.input.bytesRead","Update":1808,"Value":1808,"Internal":true,"Count Failed Values":true},{"ID":479,"Name":"internal.metrics.input.recordsRead","Update":58,"Value":58,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":764,"Executor Deserialize CPU Time":164730942,"Executor Run Time":1830,"Executor CPU Time":570319800,"Peak Execution Memory":262144,"Result Size":2815,"JVM GC Time":37,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":0,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":0,"Total Records Read":0,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":3205,"Shuffle Write Time":21665852,"Shuffle Records Written":55},"Input Metrics":{"Bytes Read":1808,"Records Read":58},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":3,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[14],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":13,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[12],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"17\",\"name\":\"WholeStageCodegen (4)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[13],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106879117,"Completion Time":1784106881771,"Accumulables":[{"ID":179,"Name":"number of output rows","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":312,"Name":"data size","Value":"1760","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":331,"Name":"shuffle bytes written","Value":"3205","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":332,"Name":"shuffle records written","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":333,"Name":"shuffle write time","Value":"21665852","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":334,"Name":"duration","Value":"1365","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":335,"Name":"number of output rows","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":336,"Name":"peak memory","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":338,"Name":"time in aggregation build","Value":"1191","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":341,"Name":"number of output rows","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":447,"Name":"internal.metrics.executorDeserializeTime","Value":764,"Internal":true,"Count Failed Values":true},{"ID":448,"Name":"internal.metrics.executorDeserializeCpuTime","Value":164730942,"Internal":true,"Count Failed Values":true},{"ID":449,"Name":"internal.metrics.executorRunTime","Value":1830,"Internal":true,"Count Failed Values":true},{"ID":450,"Name":"internal.metrics.executorCpuTime","Value":570319800,"Internal":true,"Count Failed Values":true},{"ID":451,"Name":"internal.metrics.resultSize","Value":2815,"Internal":true,"Count Failed Values":true},{"ID":452,"Name":"internal.metrics.jvmGCTime","Value":37,"Internal":true,"Count Failed Values":true},{"ID":456,"Name":"internal.metrics.peakExecutionMemory","Value":262144,"Internal":true,"Count Failed Values":true},{"ID":475,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":3205,"Internal":true,"Count Failed Values":true},{"ID":476,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":55,"Internal":true,"Count Failed Values":true},{"ID":477,"Name":"internal.metrics.shuffle.write.writeTime","Value":21665852,"Internal":true,"Count Failed Values":true},{"ID":478,"Name":"internal.metrics.input.bytesRead","Value":1808,"Internal":true,"Count Failed Values":true},{"ID":479,"Name":"internal.metrics.input.recordsRead","Value":58,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":3,"Completion Time":1784106881774,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[216,9],[215,21],[214,3575],[213,20],[212,1048736]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[223,9],[222,22],[221,3572],[220,5],[219,1048616]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (75)\n+- == Current Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (42)\n   +- WriteFiles (41)\n      +- Sort (40)\n         +- Exchange (39)\n            +- Project (38)\n               +- Project (37)\n                  +- BroadcastHashJoin LeftOuter BuildRight (36)\n                     :- Project (25)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (24)\n                     :     :- Project (14)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (13)\n                     :     :     :- Project (8)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (7)\n                     :     :     :     :- Filter (2)\n                     :     :     :     :  +- Scan csv  (1)\n                     :     :     :     +- BroadcastQueryStage (6)\n                     :     :     :        +- BroadcastExchange (5)\n                     :     :     :           +- * Filter (4)\n                     :     :     :              +- Scan csv  (3)\n                     :     :     +- BroadcastQueryStage (12)\n                     :     :        +- BroadcastExchange (11)\n                     :     :           +- * Filter (10)\n                     :     :              +- Scan csv  (9)\n                     :     +- BroadcastQueryStage (23)\n                     :        +- BroadcastExchange (22)\n                     :           +- * HashAggregate (21)\n                     :              +- AQEShuffleRead (20)\n                     :                 +- ShuffleQueryStage (19), Statistics(sizeInBytes=120.0 B, rowCount=5)\n                     :                    +- Exchange (18)\n                     :                       +- * HashAggregate (17)\n                     :                          +- * Filter (16)\n                     :                             +- Scan csv  (15)\n                     +- BroadcastExchange (35)\n                        +- HashAggregate (34)\n                           +- Exchange (33)\n                              +- HashAggregate (32)\n                                 +- HashAggregate (31)\n                                    +- ShuffleQueryStage (30)\n                                       +- Exchange (29)\n                                          +- * HashAggregate (28)\n                                             +- * Filter (27)\n                                                +- Scan csv  (26)\n+- == Initial Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (74)\n   +- WriteFiles (73)\n      +- Sort (72)\n         +- Exchange (71)\n            +- Project (70)\n               +- Project (69)\n                  +- BroadcastHashJoin LeftOuter BuildRight (68)\n                     :- Project (59)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (58)\n                     :     :- Project (52)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (51)\n                     :     :     :- Project (48)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (47)\n                     :     :     :     :- Filter (44)\n                     :     :     :     :  +- Scan csv  (43)\n                     :     :     :     +- BroadcastExchange (46)\n                     :     :     :        +- Filter (45)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (50)\n                     :     :        +- Filter (49)\n                     :     :           +- Scan csv  (9)\n                     :     +- BroadcastExchange (57)\n                     :        +- HashAggregate (56)\n                     :           +- Exchange (55)\n                     :              +- HashAggregate (54)\n                     :                 +- Filter (53)\n                     :                    +- Scan csv  (15)\n                     +- BroadcastExchange (67)\n                        +- HashAggregate (66)\n                           +- Exchange (65)\n                              +- HashAggregate (64)\n                                 +- HashAggregate (63)\n                                    +- Exchange (62)\n                                       +- HashAggregate (61)\n                                          +- Filter (60)\n                                             +- Scan csv  (26)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter [codegen id : 1]\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]\n\n(6) BroadcastQueryStage\nOutput [2]: [user_id#26, name#27]\nArguments: 0\n\n(7) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(8) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(9) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(10) Filter [codegen id : 2]\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(11) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]\n\n(12) BroadcastQueryStage\nOutput [2]: [course_id#18, title#19]\nArguments: 1\n\n(13) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(14) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(15) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(16) Filter [codegen id : 3]\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(17) HashAggregate [codegen id : 3]\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(18) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]\n\n(19) ShuffleQueryStage\nOutput [2]: [course_id#9, count#207L]\nArguments: 2\n\n(20) AQEShuffleRead\nInput [2]: [course_id#9, count#207L]\nArguments: coalesced\n\n(21) HashAggregate [codegen id : 5]\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(22) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]\n\n(23) BroadcastQueryStage\nOutput [2]: [course_id#9, lessons_in_course#50L]\nArguments: 4\n\n(24) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(25) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(26) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(27) Filter [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(28) HashAggregate [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(29) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]\n\n(30) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: 3\n\n(31) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(32) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(33) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=270]\n\n(34) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(35) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=344]\n\n(36) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(37) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(38) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(39) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=407]\n\n(40) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(41) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(42) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(43) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(44) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(45) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(46) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(47) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(48) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(49) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(50) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(51) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(52) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(53) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(54) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(55) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(56) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(57) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(58) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(59) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(60) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(61) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(62) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(63) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(64) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(65) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(66) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(67) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(68) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(69) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(70) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(71) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(72) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(73) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(74) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(75) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=false\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=false","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=407]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":518,"metricType":"sum"},{"name":"number of files read","accumulatorId":519,"metricType":"sum"},{"name":"metadata time","accumulatorId":520,"metricType":"timing"},{"name":"size of files read","accumulatorId":521,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":517,"metricType":"sum"}]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":218,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":217,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":216,"metricType":"timing"},{"name":"time to build","accumulatorId":215,"metricType":"timing"},{"name":"time to collect","accumulatorId":214,"metricType":"timing"},{"name":"number of output rows","accumulatorId":213,"metricType":"sum"},{"name":"data size","accumulatorId":212,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":516,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":225,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":224,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":223,"metricType":"timing"},{"name":"time to build","accumulatorId":222,"metricType":"timing"},{"name":"time to collect","accumulatorId":221,"metricType":"timing"},{"name":"number of output rows","accumulatorId":220,"metricType":"sum"},{"name":"data size","accumulatorId":219,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":515,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 4","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 2","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":266,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":262,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":263,"metricType":"timing"},{"name":"peak memory","accumulatorId":261,"metricType":"size"},{"name":"number of output rows","accumulatorId":260,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":265,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":264,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":259,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":257,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":251,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":258,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":252,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":249,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":246,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":255,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":248,"metricType":"sum"},{"name":"records read","accumulatorId":245,"metricType":"sum"},{"name":"local bytes read","accumulatorId":243,"metricType":"size"},{"name":"fetch wait time","accumulatorId":244,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":241,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":247,"metricType":"sum"},{"name":"local blocks read","accumulatorId":240,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":250,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":239,"metricType":"sum"},{"name":"data size","accumulatorId":237,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":253,"metricType":"size"},{"name":"number of partitions","accumulatorId":238,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":254,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":242,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":256,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":534,"metricType":"sum"},{"name":"partition data size","accumulatorId":535,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":536,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":530,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":531,"metricType":"timing"},{"name":"peak memory","accumulatorId":529,"metricType":"size"},{"name":"number of output rows","accumulatorId":528,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":533,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":532,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":527,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":526,"metricType":"timing"},{"name":"time to build","accumulatorId":525,"metricType":"timing"},{"name":"time to collect","accumulatorId":524,"metricType":"timing"},{"name":"number of output rows","accumulatorId":523,"metricType":"sum"},{"name":"data size","accumulatorId":522,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":514,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=344]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=270]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":341,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":337,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":338,"metricType":"timing"},{"name":"peak memory","accumulatorId":336,"metricType":"size"},{"name":"number of output rows","accumulatorId":335,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":340,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":339,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":334,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":332,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":326,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":333,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":327,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":324,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":321,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":330,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":323,"metricType":"sum"},{"name":"records read","accumulatorId":320,"metricType":"sum"},{"name":"local bytes read","accumulatorId":318,"metricType":"size"},{"name":"fetch wait time","accumulatorId":319,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":316,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":322,"metricType":"sum"},{"name":"local blocks read","accumulatorId":315,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":325,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":314,"metricType":"sum"},{"name":"data size","accumulatorId":312,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":328,"metricType":"size"},{"name":"number of partitions","accumulatorId":313,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":329,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":317,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":331,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":308,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":309,"metricType":"timing"},{"name":"peak memory","accumulatorId":307,"metricType":"size"},{"name":"number of output rows","accumulatorId":306,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":311,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":310,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":302,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":303,"metricType":"timing"},{"name":"peak memory","accumulatorId":301,"metricType":"size"},{"name":"number of output rows","accumulatorId":300,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":305,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":304,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":298,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":292,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":299,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":293,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":290,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":287,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":296,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":289,"metricType":"sum"},{"name":"records read","accumulatorId":286,"metricType":"sum"},{"name":"local bytes read","accumulatorId":284,"metricType":"size"},{"name":"fetch wait time","accumulatorId":285,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":282,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":288,"metricType":"sum"},{"name":"local blocks read","accumulatorId":281,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":291,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":280,"metricType":"sum"},{"name":"data size","accumulatorId":278,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":294,"metricType":"size"},{"name":"number of partitions","accumulatorId":279,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":295,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":283,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":297,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":274,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":275,"metricType":"timing"},{"name":"peak memory","accumulatorId":273,"metricType":"size"},{"name":"number of output rows","accumulatorId":272,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":277,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":276,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":541,"metricType":"timing"},{"name":"time to build","accumulatorId":540,"metricType":"timing"},{"name":"time to collect","accumulatorId":539,"metricType":"timing"},{"name":"number of output rows","accumulatorId":538,"metricType":"sum"},{"name":"data size","accumulatorId":537,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":513,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":511,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":505,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":512,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":506,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":503,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":500,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":509,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":502,"metricType":"sum"},{"name":"records read","accumulatorId":499,"metricType":"sum"},{"name":"local bytes read","accumulatorId":497,"metricType":"size"},{"name":"fetch wait time","accumulatorId":498,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":495,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":501,"metricType":"sum"},{"name":"local blocks read","accumulatorId":494,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":504,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":493,"metricType":"sum"},{"name":"data size","accumulatorId":491,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":507,"metricType":"size"},{"name":"number of partitions","accumulatorId":492,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":508,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":496,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":510,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":488,"metricType":"timing"},{"name":"peak memory","accumulatorId":489,"metricType":"size"},{"name":"spill size","accumulatorId":490,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":486,"metricType":"timing"},{"name":"number of written files","accumulatorId":482,"metricType":"sum"},{"name":"job commit time","accumulatorId":487,"metricType":"timing"},{"name":"number of output rows","accumulatorId":484,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":485,"metricType":"sum"},{"name":"written output","accumulatorId":483,"metricType":"size"}]}],"metadata":{},"metrics":[]}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[534,1],[536,1],[535,324]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (77)\n+- == Current Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (44)\n   +- WriteFiles (43)\n      +- Sort (42)\n         +- Exchange (41)\n            +- Project (40)\n               +- Project (39)\n                  +- BroadcastHashJoin LeftOuter BuildRight (38)\n                     :- Project (25)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (24)\n                     :     :- Project (14)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (13)\n                     :     :     :- Project (8)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (7)\n                     :     :     :     :- Filter (2)\n                     :     :     :     :  +- Scan csv  (1)\n                     :     :     :     +- BroadcastQueryStage (6), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n                     :     :     :        +- BroadcastExchange (5)\n                     :     :     :           +- * Filter (4)\n                     :     :     :              +- Scan csv  (3)\n                     :     :     +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                     :     :        +- BroadcastExchange (11)\n                     :     :           +- * Filter (10)\n                     :     :              +- Scan csv  (9)\n                     :     +- BroadcastQueryStage (23)\n                     :        +- BroadcastExchange (22)\n                     :           +- * HashAggregate (21)\n                     :              +- AQEShuffleRead (20)\n                     :                 +- ShuffleQueryStage (19), Statistics(sizeInBytes=120.0 B, rowCount=5)\n                     :                    +- Exchange (18)\n                     :                       +- * HashAggregate (17)\n                     :                          +- * Filter (16)\n                     :                             +- Scan csv  (15)\n                     +- BroadcastExchange (37)\n                        +- HashAggregate (36)\n                           +- ShuffleQueryStage (35)\n                              +- Exchange (34)\n                                 +- * HashAggregate (33)\n                                    +- * HashAggregate (32)\n                                       +- AQEShuffleRead (31)\n                                          +- ShuffleQueryStage (30), Statistics(sizeInBytes=1760.0 B, rowCount=55)\n                                             +- Exchange (29)\n                                                +- * HashAggregate (28)\n                                                   +- * Filter (27)\n                                                      +- Scan csv  (26)\n+- == Initial Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (76)\n   +- WriteFiles (75)\n      +- Sort (74)\n         +- Exchange (73)\n            +- Project (72)\n               +- Project (71)\n                  +- BroadcastHashJoin LeftOuter BuildRight (70)\n                     :- Project (61)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (60)\n                     :     :- Project (54)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (53)\n                     :     :     :- Project (50)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (49)\n                     :     :     :     :- Filter (46)\n                     :     :     :     :  +- Scan csv  (45)\n                     :     :     :     +- BroadcastExchange (48)\n                     :     :     :        +- Filter (47)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (52)\n                     :     :        +- Filter (51)\n                     :     :           +- Scan csv  (9)\n                     :     +- BroadcastExchange (59)\n                     :        +- HashAggregate (58)\n                     :           +- Exchange (57)\n                     :              +- HashAggregate (56)\n                     :                 +- Filter (55)\n                     :                    +- Scan csv  (15)\n                     +- BroadcastExchange (69)\n                        +- HashAggregate (68)\n                           +- Exchange (67)\n                              +- HashAggregate (66)\n                                 +- HashAggregate (65)\n                                    +- Exchange (64)\n                                       +- HashAggregate (63)\n                                          +- Filter (62)\n                                             +- Scan csv  (26)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter [codegen id : 1]\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]\n\n(6) BroadcastQueryStage\nOutput [2]: [user_id#26, name#27]\nArguments: 0\n\n(7) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(8) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(9) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(10) Filter [codegen id : 2]\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(11) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]\n\n(12) BroadcastQueryStage\nOutput [2]: [course_id#18, title#19]\nArguments: 1\n\n(13) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(14) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(15) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(16) Filter [codegen id : 3]\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(17) HashAggregate [codegen id : 3]\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(18) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]\n\n(19) ShuffleQueryStage\nOutput [2]: [course_id#9, count#207L]\nArguments: 2\n\n(20) AQEShuffleRead\nInput [2]: [course_id#9, count#207L]\nArguments: coalesced\n\n(21) HashAggregate [codegen id : 5]\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(22) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]\n\n(23) BroadcastQueryStage\nOutput [2]: [course_id#9, lessons_in_course#50L]\nArguments: 4\n\n(24) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(25) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(26) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(27) Filter [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(28) HashAggregate [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(29) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]\n\n(30) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: 3\n\n(31) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: coalesced\n\n(32) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(33) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(34) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]\n\n(35) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, count#210L]\nArguments: 5\n\n(36) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(37) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=524]\n\n(38) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(39) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(40) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(41) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=528]\n\n(42) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(43) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(44) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(45) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(46) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(47) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(48) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(49) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(50) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(51) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(52) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(53) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(54) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(55) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(56) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(57) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(58) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(59) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(60) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(61) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(62) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(63) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(64) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(65) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(66) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(67) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(68) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(69) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(70) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(71) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(72) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(73) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(74) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(75) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(76) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(77) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=false\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=false","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=528]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":578,"metricType":"sum"},{"name":"number of files read","accumulatorId":579,"metricType":"sum"},{"name":"metadata time","accumulatorId":580,"metricType":"timing"},{"name":"size of files read","accumulatorId":581,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":577,"metricType":"sum"}]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":218,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":217,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":216,"metricType":"timing"},{"name":"time to build","accumulatorId":215,"metricType":"timing"},{"name":"time to collect","accumulatorId":214,"metricType":"timing"},{"name":"number of output rows","accumulatorId":213,"metricType":"sum"},{"name":"data size","accumulatorId":212,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":576,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":225,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":224,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":223,"metricType":"timing"},{"name":"time to build","accumulatorId":222,"metricType":"timing"},{"name":"time to collect","accumulatorId":221,"metricType":"timing"},{"name":"number of output rows","accumulatorId":220,"metricType":"sum"},{"name":"data size","accumulatorId":219,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":575,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 4","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 2","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":266,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":262,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":263,"metricType":"timing"},{"name":"peak memory","accumulatorId":261,"metricType":"size"},{"name":"number of output rows","accumulatorId":260,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":265,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":264,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":259,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":257,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":251,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":258,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":252,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":249,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":246,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":255,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":248,"metricType":"sum"},{"name":"records read","accumulatorId":245,"metricType":"sum"},{"name":"local bytes read","accumulatorId":243,"metricType":"size"},{"name":"fetch wait time","accumulatorId":244,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":241,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":247,"metricType":"sum"},{"name":"local blocks read","accumulatorId":240,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":250,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":239,"metricType":"sum"},{"name":"data size","accumulatorId":237,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":253,"metricType":"size"},{"name":"number of partitions","accumulatorId":238,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":254,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":242,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":256,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":534,"metricType":"sum"},{"name":"partition data size","accumulatorId":535,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":536,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":530,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":531,"metricType":"timing"},{"name":"peak memory","accumulatorId":529,"metricType":"size"},{"name":"number of output rows","accumulatorId":528,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":533,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":532,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":527,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":526,"metricType":"timing"},{"name":"time to build","accumulatorId":525,"metricType":"timing"},{"name":"time to collect","accumulatorId":524,"metricType":"timing"},{"name":"number of output rows","accumulatorId":523,"metricType":"sum"},{"name":"data size","accumulatorId":522,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":574,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=524]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 5","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]","children":[{"nodeName":"WholeStageCodegen (6)","simpleString":"WholeStageCodegen (6)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":341,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":337,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":338,"metricType":"timing"},{"name":"peak memory","accumulatorId":336,"metricType":"size"},{"name":"number of output rows","accumulatorId":335,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":340,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":339,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":334,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":332,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":326,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":333,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":327,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":324,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":321,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":330,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":323,"metricType":"sum"},{"name":"records read","accumulatorId":320,"metricType":"sum"},{"name":"local bytes read","accumulatorId":318,"metricType":"size"},{"name":"fetch wait time","accumulatorId":319,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":316,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":322,"metricType":"sum"},{"name":"local blocks read","accumulatorId":315,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":325,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":314,"metricType":"sum"},{"name":"data size","accumulatorId":312,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":328,"metricType":"size"},{"name":"number of partitions","accumulatorId":313,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":329,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":317,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":331,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":628,"metricType":"sum"},{"name":"partition data size","accumulatorId":629,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":630,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":624,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":625,"metricType":"timing"},{"name":"peak memory","accumulatorId":623,"metricType":"size"},{"name":"number of output rows","accumulatorId":622,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":627,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":626,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":618,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":619,"metricType":"timing"},{"name":"peak memory","accumulatorId":617,"metricType":"size"},{"name":"number of output rows","accumulatorId":616,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":621,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":620,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":615,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":613,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":607,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":614,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":608,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":605,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":602,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":611,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":604,"metricType":"sum"},{"name":"records read","accumulatorId":601,"metricType":"sum"},{"name":"local bytes read","accumulatorId":599,"metricType":"size"},{"name":"fetch wait time","accumulatorId":600,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":597,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":603,"metricType":"sum"},{"name":"local blocks read","accumulatorId":596,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":606,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":595,"metricType":"sum"},{"name":"data size","accumulatorId":593,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":609,"metricType":"size"},{"name":"number of partitions","accumulatorId":594,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":610,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":598,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":612,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":589,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":590,"metricType":"timing"},{"name":"peak memory","accumulatorId":588,"metricType":"size"},{"name":"number of output rows","accumulatorId":587,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":592,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":591,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":586,"metricType":"timing"},{"name":"time to build","accumulatorId":585,"metricType":"timing"},{"name":"time to collect","accumulatorId":584,"metricType":"timing"},{"name":"number of output rows","accumulatorId":583,"metricType":"sum"},{"name":"data size","accumulatorId":582,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":573,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":571,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":565,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":572,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":566,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":563,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":560,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":569,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":562,"metricType":"sum"},{"name":"records read","accumulatorId":559,"metricType":"sum"},{"name":"local bytes read","accumulatorId":557,"metricType":"size"},{"name":"fetch wait time","accumulatorId":558,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":555,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":561,"metricType":"sum"},{"name":"local blocks read","accumulatorId":554,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":564,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":553,"metricType":"sum"},{"name":"data size","accumulatorId":551,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":567,"metricType":"size"},{"name":"number of partitions","accumulatorId":552,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":568,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":556,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":570,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":548,"metricType":"timing"},{"name":"peak memory","accumulatorId":549,"metricType":"size"},{"name":"spill size","accumulatorId":550,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":546,"metricType":"timing"},{"name":"number of written files","accumulatorId":542,"metricType":"sum"},{"name":"job commit time","accumulatorId":547,"metricType":"timing"},{"name":"number of output rows","accumulatorId":544,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":545,"metricType":"sum"},{"name":"written output","accumulatorId":543,"metricType":"size"}]}],"metadata":{},"metrics":[]}}
{"Event":"SparkListenerJobStart","Job ID":4,"Submission Time":1784106881882,"Stage Infos":[{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"30\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[17],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"31\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[16],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"34\",\"name\":\"AQEShuffleRead\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[11],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[4],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},{"Stage ID":4,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[10],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"15\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[5,4],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"30\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId 95eb2714-b78b-4d64-9d32-dbf4c973164f)","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"30\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[17],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"31\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[16],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"34\",\"name\":\"AQEShuffleRead\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[11],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[4],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106881889,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"30\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId 95eb2714-b78b-4d64-9d32-dbf4c973164f)","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":5,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106881898,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[628,1],[630,1],[629,3394]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[594,200]]}
{"Event":"SparkListenerJobStart","Job ID":5,"Submission Time":1784106881934,"Stage Infos":[{"Stage ID":6,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[14],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":13,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[12],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"17\",\"name\":\"WholeStageCodegen (4)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[13],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},{"Stage ID":7,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"35\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[20],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"40\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[15],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"36\",\"name\":\"WholeStageCodegen (6)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[19],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[6],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[6,7],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"35\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":7,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"35\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[20],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"40\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[15],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"36\",\"name\":\"WholeStageCodegen (6)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[19],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[6],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106881946,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"35\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":7,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106881967,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskEnd","Stage ID":5,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106881898,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106882134,"Failed":false,"Killed":false,"Accumulables":[{"ID":240,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":243,"Name":"local bytes read","Update":"312","Value":"312","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":244,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":245,"Name":"records read","Update":"5","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":527,"Name":"duration","Update":"15","Value":"15","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":528,"Name":"number of output rows","Update":"5","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":529,"Name":"peak memory","Update":"4456432","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":531,"Name":"time in aggregation build","Update":"8","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":532,"Name":"avg hash probes per key","Update":"10","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":631,"Name":"internal.metrics.executorDeserializeTime","Update":100,"Value":100,"Internal":true,"Count Failed Values":true},{"ID":632,"Name":"internal.metrics.executorDeserializeCpuTime","Update":32896031,"Value":32896031,"Internal":true,"Count Failed Values":true},{"ID":633,"Name":"internal.metrics.executorRunTime","Update":122,"Value":122,"Internal":true,"Count Failed Values":true},{"ID":634,"Name":"internal.metrics.executorCpuTime","Update":75306520,"Value":75306520,"Internal":true,"Count Failed Values":true},{"ID":635,"Name":"internal.metrics.resultSize","Update":5214,"Value":5214,"Internal":true,"Count Failed Values":true},{"ID":640,"Name":"internal.metrics.peakExecutionMemory","Update":4456432,"Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":642,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":643,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":644,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":645,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":646,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":312,"Value":312,"Internal":true,"Count Failed Values":true},{"ID":647,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":648,"Name":"internal.metrics.shuffle.read.recordsRead","Update":5,"Value":5,"Internal":true,"Count Failed Values":true},{"ID":649,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":650,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":651,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":652,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":653,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":654,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":655,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":656,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":657,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":658,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":100,"Executor Deserialize CPU Time":32896031,"Executor Run Time":122,"Executor CPU Time":75306520,"Peak Execution Memory":4456432,"Result Size":5214,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":1,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":312,"Total Records Read":5,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":0,"Records Read":0},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"30\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[17],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"31\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[16],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"34\",\"name\":\"AQEShuffleRead\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[11],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[4],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106881889,"Completion Time":1784106882139,"Accumulables":[{"ID":240,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":243,"Name":"local bytes read","Value":"312","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":244,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":245,"Name":"records read","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":527,"Name":"duration","Value":"15","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":528,"Name":"number of output rows","Value":"5","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":529,"Name":"peak memory","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":531,"Name":"time in aggregation build","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":532,"Name":"avg hash probes per key","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":631,"Name":"internal.metrics.executorDeserializeTime","Value":100,"Internal":true,"Count Failed Values":true},{"ID":632,"Name":"internal.metrics.executorDeserializeCpuTime","Value":32896031,"Internal":true,"Count Failed Values":true},{"ID":633,"Name":"internal.metrics.executorRunTime","Value":122,"Internal":true,"Count Failed Values":true},{"ID":634,"Name":"internal.metrics.executorCpuTime","Value":75306520,"Internal":true,"Count Failed Values":true},{"ID":635,"Name":"internal.metrics.resultSize","Value":5214,"Internal":true,"Count Failed Values":true},{"ID":640,"Name":"internal.metrics.peakExecutionMemory","Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":642,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":643,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":644,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":645,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":646,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":312,"Internal":true,"Count Failed Values":true},{"ID":647,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":648,"Name":"internal.metrics.shuffle.read.recordsRead","Value":5,"Internal":true,"Count Failed Values":true},{"ID":649,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":650,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":651,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":652,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":653,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":654,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":655,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":656,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":657,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":658,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":4,"Completion Time":1784106882140,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[526,4],[525,15],[524,303],[523,5],[522,1048616]]}
{"Event":"SparkListenerTaskEnd","Stage ID":7,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106881967,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106882205,"Failed":false,"Killed":false,"Accumulables":[{"ID":315,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":318,"Name":"local bytes read","Update":"3205","Value":"3205","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":319,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":320,"Name":"records read","Update":"55","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":593,"Name":"data size","Update":"800","Value":"800","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":612,"Name":"shuffle bytes written","Update":"1560","Value":"1560","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":613,"Name":"shuffle records written","Update":"25","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":614,"Name":"shuffle write time","Update":"5795562","Value":"5795562","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":615,"Name":"duration","Update":"53","Value":"53","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":616,"Name":"number of output rows","Update":"25","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":617,"Name":"peak memory","Update":"262144","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":619,"Name":"time in aggregation build","Update":"8","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":622,"Name":"number of output rows","Update":"55","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":623,"Name":"peak memory","Update":"262144","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":625,"Name":"time in aggregation build","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":666,"Name":"internal.metrics.executorDeserializeTime","Update":52,"Value":52,"Internal":true,"Count Failed Values":true},{"ID":667,"Name":"internal.metrics.executorDeserializeCpuTime","Update":29082133,"Value":29082133,"Internal":true,"Count Failed Values":true},{"ID":668,"Name":"internal.metrics.executorRunTime","Update":175,"Value":175,"Internal":true,"Count Failed Values":true},{"ID":669,"Name":"internal.metrics.executorCpuTime","Update":138541313,"Value":138541313,"Internal":true,"Count Failed Values":true},{"ID":670,"Name":"internal.metrics.resultSize","Update":5847,"Value":5847,"Internal":true,"Count Failed Values":true},{"ID":675,"Name":"internal.metrics.peakExecutionMemory","Update":524288,"Value":524288,"Internal":true,"Count Failed Values":true},{"ID":677,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":678,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":679,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":680,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":681,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":3205,"Value":3205,"Internal":true,"Count Failed Values":true},{"ID":682,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":683,"Name":"internal.metrics.shuffle.read.recordsRead","Update":55,"Value":55,"Internal":true,"Count Failed Values":true},{"ID":684,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":685,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":686,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":687,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":688,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":689,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":690,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":691,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":692,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":693,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":694,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":1560,"Value":1560,"Internal":true,"Count Failed Values":true},{"ID":695,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":25,"Value":25,"Internal":true,"Count Failed Values":true},{"ID":696,"Name":"internal.metrics.shuffle.write.writeTime","Update":5795562,"Value":5795562,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":52,"Executor Deserialize CPU Time":29082133,"Executor Run Time":175,"Executor CPU Time":138541313,"Peak Execution Memory":524288,"Result Size":5847,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":1,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":3205,"Total Records Read":55,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":1560,"Shuffle Write Time":5795562,"Shuffle Records Written":25},"Input Metrics":{"Bytes Read":0,"Records Read":0},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":7,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"35\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[20],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"40\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[15],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"36\",\"name\":\"WholeStageCodegen (6)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[19],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[6],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106881946,"Completion Time":1784106882207,"Accumulables":[{"ID":315,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":318,"Name":"local bytes read","Value":"3205","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":319,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":320,"Name":"records read","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":593,"Name":"data size","Value":"800","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":612,"Name":"shuffle bytes written","Value":"1560","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":613,"Name":"shuffle records written","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":614,"Name":"shuffle write time","Value":"5795562","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":615,"Name":"duration","Value":"53","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":616,"Name":"number of output rows","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":617,"Name":"peak memory","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":619,"Name":"time in aggregation build","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":622,"Name":"number of output rows","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":623,"Name":"peak memory","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":625,"Name":"time in aggregation build","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":666,"Name":"internal.metrics.executorDeserializeTime","Value":52,"Internal":true,"Count Failed Values":true},{"ID":667,"Name":"internal.metrics.executorDeserializeCpuTime","Value":29082133,"Internal":true,"Count Failed Values":true},{"ID":668,"Name":"internal.metrics.executorRunTime","Value":175,"Internal":true,"Count Failed Values":true},{"ID":669,"Name":"internal.metrics.executorCpuTime","Value":138541313,"Internal":true,"Count Failed Values":true},{"ID":670,"Name":"internal.metrics.resultSize","Value":5847,"Internal":true,"Count Failed Values":true},{"ID":675,"Name":"internal.metrics.peakExecutionMemory","Value":524288,"Internal":true,"Count Failed Values":true},{"ID":677,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":678,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":679,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":680,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":681,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":3205,"Internal":true,"Count Failed Values":true},{"ID":682,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":683,"Name":"internal.metrics.shuffle.read.recordsRead","Value":55,"Internal":true,"Count Failed Values":true},{"ID":684,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":685,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":686,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":687,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":688,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":689,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":690,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":691,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":692,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":693,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":694,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":1560,"Internal":true,"Count Failed Values":true},{"ID":695,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":25,"Internal":true,"Count Failed Values":true},{"ID":696,"Name":"internal.metrics.shuffle.write.writeTime","Value":5795562,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":5,"Completion Time":1784106882211,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (79)\n+- == Current Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (46)\n   +- WriteFiles (45)\n      +- Sort (44)\n         +- Exchange (43)\n            +- Project (42)\n               +- Project (41)\n                  +- BroadcastHashJoin LeftOuter BuildRight (40)\n                     :- Project (25)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (24)\n                     :     :- Project (14)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (13)\n                     :     :     :- Project (8)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (7)\n                     :     :     :     :- Filter (2)\n                     :     :     :     :  +- Scan csv  (1)\n                     :     :     :     +- BroadcastQueryStage (6), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n                     :     :     :        +- BroadcastExchange (5)\n                     :     :     :           +- * Filter (4)\n                     :     :     :              +- Scan csv  (3)\n                     :     :     +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                     :     :        +- BroadcastExchange (11)\n                     :     :           +- * Filter (10)\n                     :     :              +- Scan csv  (9)\n                     :     +- BroadcastQueryStage (23), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                     :        +- BroadcastExchange (22)\n                     :           +- * HashAggregate (21)\n                     :              +- AQEShuffleRead (20)\n                     :                 +- ShuffleQueryStage (19), Statistics(sizeInBytes=120.0 B, rowCount=5)\n                     :                    +- Exchange (18)\n                     :                       +- * HashAggregate (17)\n                     :                          +- * Filter (16)\n                     :                             +- Scan csv  (15)\n                     +- BroadcastQueryStage (39)\n                        +- BroadcastExchange (38)\n                           +- * HashAggregate (37)\n                              +- AQEShuffleRead (36)\n                                 +- ShuffleQueryStage (35), Statistics(sizeInBytes=800.0 B, rowCount=25)\n                                    +- Exchange (34)\n                                       +- * HashAggregate (33)\n                                          +- * HashAggregate (32)\n                                             +- AQEShuffleRead (31)\n                                                +- ShuffleQueryStage (30), Statistics(sizeInBytes=1760.0 B, rowCount=55)\n                                                   +- Exchange (29)\n                                                      +- * HashAggregate (28)\n                                                         +- * Filter (27)\n                                                            +- Scan csv  (26)\n+- == Initial Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (78)\n   +- WriteFiles (77)\n      +- Sort (76)\n         +- Exchange (75)\n            +- Project (74)\n               +- Project (73)\n                  +- BroadcastHashJoin LeftOuter BuildRight (72)\n                     :- Project (63)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (62)\n                     :     :- Project (56)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (55)\n                     :     :     :- Project (52)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (51)\n                     :     :     :     :- Filter (48)\n                     :     :     :     :  +- Scan csv  (47)\n                     :     :     :     +- BroadcastExchange (50)\n                     :     :     :        +- Filter (49)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (54)\n                     :     :        +- Filter (53)\n                     :     :           +- Scan csv  (9)\n                     :     +- BroadcastExchange (61)\n                     :        +- HashAggregate (60)\n                     :           +- Exchange (59)\n                     :              +- HashAggregate (58)\n                     :                 +- Filter (57)\n                     :                    +- Scan csv  (15)\n                     +- BroadcastExchange (71)\n                        +- HashAggregate (70)\n                           +- Exchange (69)\n                              +- HashAggregate (68)\n                                 +- HashAggregate (67)\n                                    +- Exchange (66)\n                                       +- HashAggregate (65)\n                                          +- Filter (64)\n                                             +- Scan csv  (26)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter [codegen id : 1]\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]\n\n(6) BroadcastQueryStage\nOutput [2]: [user_id#26, name#27]\nArguments: 0\n\n(7) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(8) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(9) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(10) Filter [codegen id : 2]\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(11) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]\n\n(12) BroadcastQueryStage\nOutput [2]: [course_id#18, title#19]\nArguments: 1\n\n(13) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(14) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(15) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(16) Filter [codegen id : 3]\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(17) HashAggregate [codegen id : 3]\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(18) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]\n\n(19) ShuffleQueryStage\nOutput [2]: [course_id#9, count#207L]\nArguments: 2\n\n(20) AQEShuffleRead\nInput [2]: [course_id#9, count#207L]\nArguments: coalesced\n\n(21) HashAggregate [codegen id : 5]\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(22) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]\n\n(23) BroadcastQueryStage\nOutput [2]: [course_id#9, lessons_in_course#50L]\nArguments: 4\n\n(24) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(25) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(26) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(27) Filter [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(28) HashAggregate [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(29) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]\n\n(30) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: 3\n\n(31) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: coalesced\n\n(32) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(33) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(34) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]\n\n(35) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, count#210L]\nArguments: 5\n\n(36) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: coalesced\n\n(37) HashAggregate [codegen id : 7]\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(38) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=702]\n\n(39) BroadcastQueryStage\nOutput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: 6\n\n(40) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(41) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(42) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(43) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=713]\n\n(44) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(45) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(46) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(47) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(48) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(49) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(50) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(51) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(52) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(53) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(54) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(55) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(56) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(57) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(58) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(59) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(60) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(61) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(62) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(63) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(64) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(65) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(66) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(67) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(68) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(69) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(70) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(71) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(72) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(73) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(74) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(75) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(76) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(77) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(78) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(79) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=false\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=false","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=713]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":737,"metricType":"sum"},{"name":"number of files read","accumulatorId":738,"metricType":"sum"},{"name":"metadata time","accumulatorId":739,"metricType":"timing"},{"name":"size of files read","accumulatorId":740,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":736,"metricType":"sum"}]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":218,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":217,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":216,"metricType":"timing"},{"name":"time to build","accumulatorId":215,"metricType":"timing"},{"name":"time to collect","accumulatorId":214,"metricType":"timing"},{"name":"number of output rows","accumulatorId":213,"metricType":"sum"},{"name":"data size","accumulatorId":212,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":735,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":225,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":224,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":223,"metricType":"timing"},{"name":"time to build","accumulatorId":222,"metricType":"timing"},{"name":"time to collect","accumulatorId":221,"metricType":"timing"},{"name":"number of output rows","accumulatorId":220,"metricType":"sum"},{"name":"data size","accumulatorId":219,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":734,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 4","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 2","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":266,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":262,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":263,"metricType":"timing"},{"name":"peak memory","accumulatorId":261,"metricType":"size"},{"name":"number of output rows","accumulatorId":260,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":265,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":264,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":259,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":257,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":251,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":258,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":252,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":249,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":246,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":255,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":248,"metricType":"sum"},{"name":"records read","accumulatorId":245,"metricType":"sum"},{"name":"local bytes read","accumulatorId":243,"metricType":"size"},{"name":"fetch wait time","accumulatorId":244,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":241,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":247,"metricType":"sum"},{"name":"local blocks read","accumulatorId":240,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":250,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":239,"metricType":"sum"},{"name":"data size","accumulatorId":237,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":253,"metricType":"size"},{"name":"number of partitions","accumulatorId":238,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":254,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":242,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":256,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":534,"metricType":"sum"},{"name":"partition data size","accumulatorId":535,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":536,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":530,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":531,"metricType":"timing"},{"name":"peak memory","accumulatorId":529,"metricType":"size"},{"name":"number of output rows","accumulatorId":528,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":533,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":532,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":527,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":526,"metricType":"timing"},{"name":"time to build","accumulatorId":525,"metricType":"timing"},{"name":"time to collect","accumulatorId":524,"metricType":"timing"},{"name":"number of output rows","accumulatorId":523,"metricType":"sum"},{"name":"data size","accumulatorId":522,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":733,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 6","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=702]","children":[{"nodeName":"WholeStageCodegen (7)","simpleString":"WholeStageCodegen (7)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 5","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]","children":[{"nodeName":"WholeStageCodegen (6)","simpleString":"WholeStageCodegen (6)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":341,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":337,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":338,"metricType":"timing"},{"name":"peak memory","accumulatorId":336,"metricType":"size"},{"name":"number of output rows","accumulatorId":335,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":340,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":339,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":334,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":332,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":326,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":333,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":327,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":324,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":321,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":330,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":323,"metricType":"sum"},{"name":"records read","accumulatorId":320,"metricType":"sum"},{"name":"local bytes read","accumulatorId":318,"metricType":"size"},{"name":"fetch wait time","accumulatorId":319,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":316,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":322,"metricType":"sum"},{"name":"local blocks read","accumulatorId":315,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":325,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":314,"metricType":"sum"},{"name":"data size","accumulatorId":312,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":328,"metricType":"size"},{"name":"number of partitions","accumulatorId":313,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":329,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":317,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":331,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":628,"metricType":"sum"},{"name":"partition data size","accumulatorId":629,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":630,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":624,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":625,"metricType":"timing"},{"name":"peak memory","accumulatorId":623,"metricType":"size"},{"name":"number of output rows","accumulatorId":622,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":627,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":626,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":618,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":619,"metricType":"timing"},{"name":"peak memory","accumulatorId":617,"metricType":"size"},{"name":"number of output rows","accumulatorId":616,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":621,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":620,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":615,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":613,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":607,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":614,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":608,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":605,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":602,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":611,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":604,"metricType":"sum"},{"name":"records read","accumulatorId":601,"metricType":"sum"},{"name":"local bytes read","accumulatorId":599,"metricType":"size"},{"name":"fetch wait time","accumulatorId":600,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":597,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":603,"metricType":"sum"},{"name":"local blocks read","accumulatorId":596,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":606,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":595,"metricType":"sum"},{"name":"data size","accumulatorId":593,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":609,"metricType":"size"},{"name":"number of partitions","accumulatorId":594,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":610,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":598,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":612,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":753,"metricType":"sum"},{"name":"partition data size","accumulatorId":754,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":755,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":749,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":750,"metricType":"timing"},{"name":"peak memory","accumulatorId":748,"metricType":"size"},{"name":"number of output rows","accumulatorId":747,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":752,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":751,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":746,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":745,"metricType":"timing"},{"name":"time to build","accumulatorId":744,"metricType":"timing"},{"name":"time to collect","accumulatorId":743,"metricType":"timing"},{"name":"number of output rows","accumulatorId":742,"metricType":"sum"},{"name":"data size","accumulatorId":741,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":732,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":730,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":724,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":731,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":725,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":722,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":719,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":728,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":721,"metricType":"sum"},{"name":"records read","accumulatorId":718,"metricType":"sum"},{"name":"local bytes read","accumulatorId":716,"metricType":"size"},{"name":"fetch wait time","accumulatorId":717,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":714,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":720,"metricType":"sum"},{"name":"local blocks read","accumulatorId":713,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":723,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":712,"metricType":"sum"},{"name":"data size","accumulatorId":710,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":726,"metricType":"size"},{"name":"number of partitions","accumulatorId":711,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":727,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":715,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":729,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":707,"metricType":"timing"},{"name":"peak memory","accumulatorId":708,"metricType":"size"},{"name":"spill size","accumulatorId":709,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":705,"metricType":"timing"},{"name":"number of written files","accumulatorId":701,"metricType":"sum"},{"name":"job commit time","accumulatorId":706,"metricType":"timing"},{"name":"number of output rows","accumulatorId":703,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":704,"metricType":"sum"},{"name":"written output","accumulatorId":702,"metricType":"size"}]}],"metadata":{},"metrics":[]}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[753,1],[755,1],[754,1652]]}
{"Event":"SparkListenerJobStart","Job ID":6,"Submission Time":1784106882260,"Stage Infos":[{"Stage ID":9,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"35\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[20],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"40\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[15],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"36\",\"name\":\"WholeStageCodegen (6)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[19],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[8],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},{"Stage ID":10,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"48\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[23],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":22,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"52\",\"name\":\"AQEShuffleRead\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[21],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":23,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"49\",\"name\":\"WholeStageCodegen (7)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[22],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[9],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},{"Stage ID":8,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"16\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[14],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":13,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"21\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[12],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"17\",\"name\":\"WholeStageCodegen (4)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[13],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[9,10,8],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"48\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.job.tags":"broadcast exchange (runId a1e329ea-4cf0-4146-9355-fe6aaf9d9de1)","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":10,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"48\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[23],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":22,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"52\",\"name\":\"AQEShuffleRead\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[21],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":23,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"49\",\"name\":\"WholeStageCodegen (7)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[22],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[9],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106882263,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"48\",\"name\":\"BroadcastExchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.job.interruptOnCancel":"true","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.job.tags":"broadcast exchange (runId a1e329ea-4cf0-4146-9355-fe6aaf9d9de1)","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":10,"Stage Attempt ID":0,"Task Info":{"Task ID":6,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106882268,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskEnd","Stage ID":10,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106882268,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106882332,"Failed":false,"Killed":false,"Accumulables":[{"ID":596,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":599,"Name":"local bytes read","Update":"1560","Value":"1560","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":600,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":601,"Name":"records read","Update":"25","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":746,"Name":"duration","Update":"8","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":747,"Name":"number of output rows","Update":"25","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":748,"Name":"peak memory","Update":"4456432","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":750,"Name":"time in aggregation build","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":751,"Name":"avg hash probes per key","Update":"10","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":756,"Name":"internal.metrics.executorDeserializeTime","Update":17,"Value":17,"Internal":true,"Count Failed Values":true},{"ID":757,"Name":"internal.metrics.executorDeserializeCpuTime","Update":11005152,"Value":11005152,"Internal":true,"Count Failed Values":true},{"ID":758,"Name":"internal.metrics.executorRunTime","Update":37,"Value":37,"Internal":true,"Count Failed Values":true},{"ID":759,"Name":"internal.metrics.executorCpuTime","Update":29769442,"Value":29769442,"Internal":true,"Count Failed Values":true},{"ID":760,"Name":"internal.metrics.resultSize","Update":7410,"Value":7410,"Internal":true,"Count Failed Values":true},{"ID":765,"Name":"internal.metrics.peakExecutionMemory","Update":4456432,"Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":767,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":768,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":769,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":770,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":771,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":1560,"Value":1560,"Internal":true,"Count Failed Values":true},{"ID":772,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":773,"Name":"internal.metrics.shuffle.read.recordsRead","Update":25,"Value":25,"Internal":true,"Count Failed Values":true},{"ID":774,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":775,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":776,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":777,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":778,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":779,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":780,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":781,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":782,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":783,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":17,"Executor Deserialize CPU Time":11005152,"Executor Run Time":37,"Executor CPU Time":29769442,"Peak Execution Memory":4456432,"Result Size":7410,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":1,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":1560,"Total Records Read":25,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":0,"Records Read":0},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":10,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"48\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[23],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":22,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"52\",\"name\":\"AQEShuffleRead\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[21],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":23,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"49\",\"name\":\"WholeStageCodegen (7)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[22],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[9],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:219)\njava.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)\njava.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136)\njava.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106882263,"Completion Time":1784106882333,"Accumulables":[{"ID":596,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":599,"Name":"local bytes read","Value":"1560","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":600,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":601,"Name":"records read","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":746,"Name":"duration","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":747,"Name":"number of output rows","Value":"25","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":748,"Name":"peak memory","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":750,"Name":"time in aggregation build","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":751,"Name":"avg hash probes per key","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":756,"Name":"internal.metrics.executorDeserializeTime","Value":17,"Internal":true,"Count Failed Values":true},{"ID":757,"Name":"internal.metrics.executorDeserializeCpuTime","Value":11005152,"Internal":true,"Count Failed Values":true},{"ID":758,"Name":"internal.metrics.executorRunTime","Value":37,"Internal":true,"Count Failed Values":true},{"ID":759,"Name":"internal.metrics.executorCpuTime","Value":29769442,"Internal":true,"Count Failed Values":true},{"ID":760,"Name":"internal.metrics.resultSize","Value":7410,"Internal":true,"Count Failed Values":true},{"ID":765,"Name":"internal.metrics.peakExecutionMemory","Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":767,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":768,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":769,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":770,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":771,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":1560,"Internal":true,"Count Failed Values":true},{"ID":772,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":773,"Name":"internal.metrics.shuffle.read.recordsRead","Value":25,"Internal":true,"Count Failed Values":true},{"ID":774,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":775,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":776,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":777,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":778,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":779,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":780,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":781,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":782,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":783,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":6,"Completion Time":1784106882334,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[745,2],[744,11],[743,103],[742,25],[741,1049600]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (80)\n+- == Current Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (47)\n   +- WriteFiles (46)\n      +- Sort (45)\n         +- ShuffleQueryStage (44)\n            +- Exchange (43)\n               +- * Project (42)\n                  +- * Project (41)\n                     +- * BroadcastHashJoin LeftOuter BuildRight (40)\n                        :- * Project (25)\n                        :  +- * BroadcastHashJoin LeftOuter BuildRight (24)\n                        :     :- * Project (14)\n                        :     :  +- * BroadcastHashJoin Inner BuildRight (13)\n                        :     :     :- * Project (8)\n                        :     :     :  +- * BroadcastHashJoin Inner BuildRight (7)\n                        :     :     :     :- * Filter (2)\n                        :     :     :     :  +- Scan csv  (1)\n                        :     :     :     +- BroadcastQueryStage (6), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n                        :     :     :        +- BroadcastExchange (5)\n                        :     :     :           +- * Filter (4)\n                        :     :     :              +- Scan csv  (3)\n                        :     :     +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                        :     :        +- BroadcastExchange (11)\n                        :     :           +- * Filter (10)\n                        :     :              +- Scan csv  (9)\n                        :     +- BroadcastQueryStage (23), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                        :        +- BroadcastExchange (22)\n                        :           +- * HashAggregate (21)\n                        :              +- AQEShuffleRead (20)\n                        :                 +- ShuffleQueryStage (19), Statistics(sizeInBytes=120.0 B, rowCount=5)\n                        :                    +- Exchange (18)\n                        :                       +- * HashAggregate (17)\n                        :                          +- * Filter (16)\n                        :                             +- Scan csv  (15)\n                        +- BroadcastQueryStage (39), Statistics(sizeInBytes=1025.0 KiB, rowCount=25)\n                           +- BroadcastExchange (38)\n                              +- * HashAggregate (37)\n                                 +- AQEShuffleRead (36)\n                                    +- ShuffleQueryStage (35), Statistics(sizeInBytes=800.0 B, rowCount=25)\n                                       +- Exchange (34)\n                                          +- * HashAggregate (33)\n                                             +- * HashAggregate (32)\n                                                +- AQEShuffleRead (31)\n                                                   +- ShuffleQueryStage (30), Statistics(sizeInBytes=1760.0 B, rowCount=55)\n                                                      +- Exchange (29)\n                                                         +- * HashAggregate (28)\n                                                            +- * Filter (27)\n                                                               +- Scan csv  (26)\n+- == Initial Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (79)\n   +- WriteFiles (78)\n      +- Sort (77)\n         +- Exchange (76)\n            +- Project (75)\n               +- Project (74)\n                  +- BroadcastHashJoin LeftOuter BuildRight (73)\n                     :- Project (64)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (63)\n                     :     :- Project (57)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (56)\n                     :     :     :- Project (53)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (52)\n                     :     :     :     :- Filter (49)\n                     :     :     :     :  +- Scan csv  (48)\n                     :     :     :     +- BroadcastExchange (51)\n                     :     :     :        +- Filter (50)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (55)\n                     :     :        +- Filter (54)\n                     :     :           +- Scan csv  (9)\n                     :     +- BroadcastExchange (62)\n                     :        +- HashAggregate (61)\n                     :           +- Exchange (60)\n                     :              +- HashAggregate (59)\n                     :                 +- Filter (58)\n                     :                    +- Scan csv  (15)\n                     +- BroadcastExchange (72)\n                        +- HashAggregate (71)\n                           +- Exchange (70)\n                              +- HashAggregate (69)\n                                 +- HashAggregate (68)\n                                    +- Exchange (67)\n                                       +- HashAggregate (66)\n                                          +- Filter (65)\n                                             +- Scan csv  (26)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter [codegen id : 8]\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter [codegen id : 1]\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]\n\n(6) BroadcastQueryStage\nOutput [2]: [user_id#26, name#27]\nArguments: 0\n\n(7) BroadcastHashJoin [codegen id : 8]\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(8) Project [codegen id : 8]\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(9) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(10) Filter [codegen id : 2]\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(11) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]\n\n(12) BroadcastQueryStage\nOutput [2]: [course_id#18, title#19]\nArguments: 1\n\n(13) BroadcastHashJoin [codegen id : 8]\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(14) Project [codegen id : 8]\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(15) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(16) Filter [codegen id : 3]\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(17) HashAggregate [codegen id : 3]\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(18) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]\n\n(19) ShuffleQueryStage\nOutput [2]: [course_id#9, count#207L]\nArguments: 2\n\n(20) AQEShuffleRead\nInput [2]: [course_id#9, count#207L]\nArguments: coalesced\n\n(21) HashAggregate [codegen id : 5]\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(22) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]\n\n(23) BroadcastQueryStage\nOutput [2]: [course_id#9, lessons_in_course#50L]\nArguments: 4\n\n(24) BroadcastHashJoin [codegen id : 8]\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(25) Project [codegen id : 8]\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(26) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(27) Filter [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(28) HashAggregate [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(29) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]\n\n(30) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: 3\n\n(31) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: coalesced\n\n(32) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(33) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(34) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]\n\n(35) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, count#210L]\nArguments: 5\n\n(36) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: coalesced\n\n(37) HashAggregate [codegen id : 7]\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(38) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=702]\n\n(39) BroadcastQueryStage\nOutput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: 6\n\n(40) BroadcastHashJoin [codegen id : 8]\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(41) Project [codegen id : 8]\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(42) Project [codegen id : 8]\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(43) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=820]\n\n(44) ShuffleQueryStage\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: 7\n\n(45) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(46) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(47) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(48) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(49) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(50) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(51) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(52) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(53) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(54) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(55) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(56) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(57) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(58) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(59) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(60) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(61) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(62) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(63) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(64) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(65) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(66) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(67) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(68) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(69) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(70) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(71) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(72) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(73) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(74) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(75) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(76) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(77) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(78) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(79) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(80) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=false\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=false","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 7","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=820]","children":[{"nodeName":"WholeStageCodegen (8)","simpleString":"WholeStageCodegen (8)","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":828,"metricType":"sum"},{"name":"number of files read","accumulatorId":829,"metricType":"sum"},{"name":"metadata time","accumulatorId":830,"metricType":"timing"},{"name":"size of files read","accumulatorId":831,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":827,"metricType":"sum"}]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":218,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":217,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":216,"metricType":"timing"},{"name":"time to build","accumulatorId":215,"metricType":"timing"},{"name":"time to collect","accumulatorId":214,"metricType":"timing"},{"name":"number of output rows","accumulatorId":213,"metricType":"sum"},{"name":"data size","accumulatorId":212,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":826,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":225,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":224,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":223,"metricType":"timing"},{"name":"time to build","accumulatorId":222,"metricType":"timing"},{"name":"time to collect","accumulatorId":221,"metricType":"timing"},{"name":"number of output rows","accumulatorId":220,"metricType":"sum"},{"name":"data size","accumulatorId":219,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":825,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 4","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 2","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":266,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":262,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":263,"metricType":"timing"},{"name":"peak memory","accumulatorId":261,"metricType":"size"},{"name":"number of output rows","accumulatorId":260,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":265,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":264,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":259,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":257,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":251,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":258,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":252,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":249,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":246,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":255,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":248,"metricType":"sum"},{"name":"records read","accumulatorId":245,"metricType":"sum"},{"name":"local bytes read","accumulatorId":243,"metricType":"size"},{"name":"fetch wait time","accumulatorId":244,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":241,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":247,"metricType":"sum"},{"name":"local blocks read","accumulatorId":240,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":250,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":239,"metricType":"sum"},{"name":"data size","accumulatorId":237,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":253,"metricType":"size"},{"name":"number of partitions","accumulatorId":238,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":254,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":242,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":256,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":534,"metricType":"sum"},{"name":"partition data size","accumulatorId":535,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":536,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":530,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":531,"metricType":"timing"},{"name":"peak memory","accumulatorId":529,"metricType":"size"},{"name":"number of output rows","accumulatorId":528,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":533,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":532,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":527,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":526,"metricType":"timing"},{"name":"time to build","accumulatorId":525,"metricType":"timing"},{"name":"time to collect","accumulatorId":524,"metricType":"timing"},{"name":"number of output rows","accumulatorId":523,"metricType":"sum"},{"name":"data size","accumulatorId":522,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":824,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 6","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=702]","children":[{"nodeName":"WholeStageCodegen (7)","simpleString":"WholeStageCodegen (7)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 5","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]","children":[{"nodeName":"WholeStageCodegen (6)","simpleString":"WholeStageCodegen (6)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":341,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":337,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":338,"metricType":"timing"},{"name":"peak memory","accumulatorId":336,"metricType":"size"},{"name":"number of output rows","accumulatorId":335,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":340,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":339,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":334,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":332,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":326,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":333,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":327,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":324,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":321,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":330,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":323,"metricType":"sum"},{"name":"records read","accumulatorId":320,"metricType":"sum"},{"name":"local bytes read","accumulatorId":318,"metricType":"size"},{"name":"fetch wait time","accumulatorId":319,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":316,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":322,"metricType":"sum"},{"name":"local blocks read","accumulatorId":315,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":325,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":314,"metricType":"sum"},{"name":"data size","accumulatorId":312,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":328,"metricType":"size"},{"name":"number of partitions","accumulatorId":313,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":329,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":317,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":331,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":628,"metricType":"sum"},{"name":"partition data size","accumulatorId":629,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":630,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":624,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":625,"metricType":"timing"},{"name":"peak memory","accumulatorId":623,"metricType":"size"},{"name":"number of output rows","accumulatorId":622,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":627,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":626,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":618,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":619,"metricType":"timing"},{"name":"peak memory","accumulatorId":617,"metricType":"size"},{"name":"number of output rows","accumulatorId":616,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":621,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":620,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":615,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":613,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":607,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":614,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":608,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":605,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":602,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":611,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":604,"metricType":"sum"},{"name":"records read","accumulatorId":601,"metricType":"sum"},{"name":"local bytes read","accumulatorId":599,"metricType":"size"},{"name":"fetch wait time","accumulatorId":600,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":597,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":603,"metricType":"sum"},{"name":"local blocks read","accumulatorId":596,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":606,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":595,"metricType":"sum"},{"name":"data size","accumulatorId":593,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":609,"metricType":"size"},{"name":"number of partitions","accumulatorId":594,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":610,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":598,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":612,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":753,"metricType":"sum"},{"name":"partition data size","accumulatorId":754,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":755,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":749,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":750,"metricType":"timing"},{"name":"peak memory","accumulatorId":748,"metricType":"size"},{"name":"number of output rows","accumulatorId":747,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":752,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":751,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":746,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":745,"metricType":"timing"},{"name":"time to build","accumulatorId":744,"metricType":"timing"},{"name":"time to collect","accumulatorId":743,"metricType":"timing"},{"name":"number of output rows","accumulatorId":742,"metricType":"sum"},{"name":"data size","accumulatorId":741,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":823,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":822,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":820,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":814,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":821,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":815,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":812,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":809,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":818,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":811,"metricType":"sum"},{"name":"records read","accumulatorId":808,"metricType":"sum"},{"name":"local bytes read","accumulatorId":806,"metricType":"size"},{"name":"fetch wait time","accumulatorId":807,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":804,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":810,"metricType":"sum"},{"name":"local blocks read","accumulatorId":803,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":813,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":802,"metricType":"sum"},{"name":"data size","accumulatorId":800,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":816,"metricType":"size"},{"name":"number of partitions","accumulatorId":801,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":817,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":805,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":819,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":797,"metricType":"timing"},{"name":"peak memory","accumulatorId":798,"metricType":"size"},{"name":"spill size","accumulatorId":799,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":795,"metricType":"timing"},{"name":"number of written files","accumulatorId":791,"metricType":"sum"},{"name":"job commit time","accumulatorId":796,"metricType":"timing"},{"name":"number of output rows","accumulatorId":793,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":794,"metricType":"sum"},{"name":"written output","accumulatorId":792,"metricType":"size"}]}],"metadata":{},"metrics":[]}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[829,1],[830,0],[831,1453]]}
{"Event":"SparkListenerJobStart","Job ID":7,"Submission Time":1784106882473,"Stage Infos":[{"Stage ID":11,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":30,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[29],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":29,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[28],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":28,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[11],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":11,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":30,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[29],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":29,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[28],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":28,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106882474,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":11,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106882490,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskEnd","Stage ID":11,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":7,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106882490,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106882739,"Failed":false,"Killed":false,"Accumulables":[{"ID":822,"Name":"duration","Update":"161","Value":"161","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":823,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":824,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":825,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":826,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":827,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":828,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":832,"Name":"internal.metrics.executorDeserializeTime","Update":39,"Value":39,"Internal":true,"Count Failed Values":true},{"ID":833,"Name":"internal.metrics.executorDeserializeCpuTime","Update":22327399,"Value":22327399,"Internal":true,"Count Failed Values":true},{"ID":834,"Name":"internal.metrics.executorRunTime","Update":196,"Value":196,"Internal":true,"Count Failed Values":true},{"ID":835,"Name":"internal.metrics.executorCpuTime","Update":99846771,"Value":99846771,"Internal":true,"Count Failed Values":true},{"ID":836,"Name":"internal.metrics.resultSize","Update":3514,"Value":3514,"Internal":true,"Count Failed Values":true},{"ID":838,"Name":"internal.metrics.resultSerializationTime","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":841,"Name":"internal.metrics.peakExecutionMemory","Update":3568,"Value":3568,"Internal":true,"Count Failed Values":true},{"ID":863,"Name":"internal.metrics.input.bytesRead","Update":1453,"Value":1453,"Internal":true,"Count Failed Values":true},{"ID":864,"Name":"internal.metrics.input.recordsRead","Update":45,"Value":45,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":39,"Executor Deserialize CPU Time":22327399,"Executor Run Time":196,"Executor CPU Time":99846771,"Peak Execution Memory":3568,"Result Size":3514,"JVM GC Time":0,"Result Serialization Time":1,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":0,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":0,"Total Records Read":0,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":1453,"Records Read":45},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":11,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":30,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[29],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":29,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[28],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":28,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106882474,"Completion Time":1784106882745,"Accumulables":[{"ID":822,"Name":"duration","Value":"161","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":823,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":824,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":825,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":826,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":827,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":828,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":832,"Name":"internal.metrics.executorDeserializeTime","Value":39,"Internal":true,"Count Failed Values":true},{"ID":833,"Name":"internal.metrics.executorDeserializeCpuTime","Value":22327399,"Internal":true,"Count Failed Values":true},{"ID":834,"Name":"internal.metrics.executorRunTime","Value":196,"Internal":true,"Count Failed Values":true},{"ID":835,"Name":"internal.metrics.executorCpuTime","Value":99846771,"Internal":true,"Count Failed Values":true},{"ID":836,"Name":"internal.metrics.resultSize","Value":3514,"Internal":true,"Count Failed Values":true},{"ID":838,"Name":"internal.metrics.resultSerializationTime","Value":1,"Internal":true,"Count Failed Values":true},{"ID":841,"Name":"internal.metrics.peakExecutionMemory","Value":3568,"Internal":true,"Count Failed Values":true},{"ID":863,"Name":"internal.metrics.input.bytesRead","Value":1453,"Internal":true,"Count Failed Values":true},{"ID":864,"Name":"internal.metrics.input.recordsRead","Value":45,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":7,"Completion Time":1784106882745,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[801,21]]}
{"Event":"SparkListenerJobStart","Job ID":8,"Submission Time":1784106882753,"Stage Infos":[{"Stage ID":12,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":31,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[12],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":12,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":31,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106882754,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.rdd.scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.rdd.scope.noOverride":"true","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":12,"Stage Attempt ID":0,"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106882766,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskEnd","Stage ID":12,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":8,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106882766,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106882852,"Failed":false,"Killed":false,"Accumulables":[{"ID":800,"Name":"data size","Update":"4848","Value":"4848","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":819,"Name":"shuffle bytes written","Update":"4012","Value":"4012","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":820,"Name":"shuffle records written","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":821,"Name":"shuffle write time","Update":"1613840","Value":"1613840","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":822,"Name":"duration","Update":"31","Value":"192","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":823,"Name":"number of output rows","Update":"45","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":824,"Name":"number of output rows","Update":"45","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":825,"Name":"number of output rows","Update":"45","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":826,"Name":"number of output rows","Update":"45","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":827,"Name":"number of output rows","Update":"45","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":828,"Name":"number of output rows","Update":"45","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":867,"Name":"internal.metrics.executorDeserializeTime","Update":44,"Value":44,"Internal":true,"Count Failed Values":true},{"ID":868,"Name":"internal.metrics.executorDeserializeCpuTime","Update":33595545,"Value":33595545,"Internal":true,"Count Failed Values":true},{"ID":869,"Name":"internal.metrics.executorRunTime","Update":35,"Value":35,"Internal":true,"Count Failed Values":true},{"ID":870,"Name":"internal.metrics.executorCpuTime","Update":23146391,"Value":23146391,"Internal":true,"Count Failed Values":true},{"ID":871,"Name":"internal.metrics.resultSize","Update":2124,"Value":2124,"Internal":true,"Count Failed Values":true},{"ID":876,"Name":"internal.metrics.peakExecutionMemory","Update":3568,"Value":3568,"Internal":true,"Count Failed Values":true},{"ID":895,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":4012,"Value":4012,"Internal":true,"Count Failed Values":true},{"ID":896,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":45,"Value":45,"Internal":true,"Count Failed Values":true},{"ID":897,"Name":"internal.metrics.shuffle.write.writeTime","Update":1613840,"Value":1613840,"Internal":true,"Count Failed Values":true},{"ID":898,"Name":"internal.metrics.input.bytesRead","Update":1453,"Value":1453,"Internal":true,"Count Failed Values":true},{"ID":899,"Name":"internal.metrics.input.recordsRead","Update":45,"Value":45,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":44,"Executor Deserialize CPU Time":33595545,"Executor Run Time":35,"Executor CPU Time":23146391,"Peak Execution Memory":3568,"Result Size":2124,"JVM GC Time":0,"Result Serialization Time":0,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":0,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":0,"Total Records Read":0,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":4012,"Shuffle Write Time":1613840,"Shuffle Records Written":45},"Input Metrics":{"Bytes Read":1453,"Records Read":45},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":12,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":31,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106882754,"Completion Time":1784106882853,"Accumulables":[{"ID":800,"Name":"data size","Value":"4848","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":819,"Name":"shuffle bytes written","Value":"4012","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":820,"Name":"shuffle records written","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":821,"Name":"shuffle write time","Value":"1613840","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":822,"Name":"duration","Value":"192","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":823,"Name":"number of output rows","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":824,"Name":"number of output rows","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":825,"Name":"number of output rows","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":826,"Name":"number of output rows","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":827,"Name":"number of output rows","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":828,"Name":"number of output rows","Value":"90","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":867,"Name":"internal.metrics.executorDeserializeTime","Value":44,"Internal":true,"Count Failed Values":true},{"ID":868,"Name":"internal.metrics.executorDeserializeCpuTime","Value":33595545,"Internal":true,"Count Failed Values":true},{"ID":869,"Name":"internal.metrics.executorRunTime","Value":35,"Internal":true,"Count Failed Values":true},{"ID":870,"Name":"internal.metrics.executorCpuTime","Value":23146391,"Internal":true,"Count Failed Values":true},{"ID":871,"Name":"internal.metrics.resultSize","Value":2124,"Internal":true,"Count Failed Values":true},{"ID":876,"Name":"internal.metrics.peakExecutionMemory","Value":3568,"Internal":true,"Count Failed Values":true},{"ID":895,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":4012,"Internal":true,"Count Failed Values":true},{"ID":896,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":45,"Internal":true,"Count Failed Values":true},{"ID":897,"Name":"internal.metrics.shuffle.write.writeTime","Value":1613840,"Internal":true,"Count Failed Values":true},{"ID":898,"Name":"internal.metrics.input.bytesRead","Value":1453,"Internal":true,"Count Failed Values":true},{"ID":899,"Name":"internal.metrics.input.recordsRead","Value":45,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":8,"Completion Time":1784106882854,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (81)\n+- == Final Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (48)\n   +- WriteFiles (47)\n      +- * Sort (46)\n         +- AQEShuffleRead (45)\n            +- ShuffleQueryStage (44), Statistics(sizeInBytes=4.7 KiB, rowCount=45)\n               +- Exchange (43)\n                  +- * Project (42)\n                     +- * Project (41)\n                        +- * BroadcastHashJoin LeftOuter BuildRight (40)\n                           :- * Project (25)\n                           :  +- * BroadcastHashJoin LeftOuter BuildRight (24)\n                           :     :- * Project (14)\n                           :     :  +- * BroadcastHashJoin Inner BuildRight (13)\n                           :     :     :- * Project (8)\n                           :     :     :  +- * BroadcastHashJoin Inner BuildRight (7)\n                           :     :     :     :- * Filter (2)\n                           :     :     :     :  +- Scan csv  (1)\n                           :     :     :     +- BroadcastQueryStage (6), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n                           :     :     :        +- BroadcastExchange (5)\n                           :     :     :           +- * Filter (4)\n                           :     :     :              +- Scan csv  (3)\n                           :     :     +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                           :     :        +- BroadcastExchange (11)\n                           :     :           +- * Filter (10)\n                           :     :              +- Scan csv  (9)\n                           :     +- BroadcastQueryStage (23), Statistics(sizeInBytes=1024.0 KiB, rowCount=5)\n                           :        +- BroadcastExchange (22)\n                           :           +- * HashAggregate (21)\n                           :              +- AQEShuffleRead (20)\n                           :                 +- ShuffleQueryStage (19), Statistics(sizeInBytes=120.0 B, rowCount=5)\n                           :                    +- Exchange (18)\n                           :                       +- * HashAggregate (17)\n                           :                          +- * Filter (16)\n                           :                             +- Scan csv  (15)\n                           +- BroadcastQueryStage (39), Statistics(sizeInBytes=1025.0 KiB, rowCount=25)\n                              +- BroadcastExchange (38)\n                                 +- * HashAggregate (37)\n                                    +- AQEShuffleRead (36)\n                                       +- ShuffleQueryStage (35), Statistics(sizeInBytes=800.0 B, rowCount=25)\n                                          +- Exchange (34)\n                                             +- * HashAggregate (33)\n                                                +- * HashAggregate (32)\n                                                   +- AQEShuffleRead (31)\n                                                      +- ShuffleQueryStage (30), Statistics(sizeInBytes=1760.0 B, rowCount=55)\n                                                         +- Exchange (29)\n                                                            +- * HashAggregate (28)\n                                                               +- * Filter (27)\n                                                                  +- Scan csv  (26)\n+- == Initial Plan ==\n   Execute InsertIntoHadoopFsRelationCommand (80)\n   +- WriteFiles (79)\n      +- Sort (78)\n         +- Exchange (77)\n            +- Project (76)\n               +- Project (75)\n                  +- BroadcastHashJoin LeftOuter BuildRight (74)\n                     :- Project (65)\n                     :  +- BroadcastHashJoin LeftOuter BuildRight (64)\n                     :     :- Project (58)\n                     :     :  +- BroadcastHashJoin Inner BuildRight (57)\n                     :     :     :- Project (54)\n                     :     :     :  +- BroadcastHashJoin Inner BuildRight (53)\n                     :     :     :     :- Filter (50)\n                     :     :     :     :  +- Scan csv  (49)\n                     :     :     :     +- BroadcastExchange (52)\n                     :     :     :        +- Filter (51)\n                     :     :     :           +- Scan csv  (3)\n                     :     :     +- BroadcastExchange (56)\n                     :     :        +- Filter (55)\n                     :     :           +- Scan csv  (9)\n                     :     +- BroadcastExchange (63)\n                     :        +- HashAggregate (62)\n                     :           +- Exchange (61)\n                     :              +- HashAggregate (60)\n                     :                 +- Filter (59)\n                     :                    +- Scan csv  (15)\n                     +- BroadcastExchange (73)\n                        +- HashAggregate (72)\n                           +- Exchange (71)\n                              +- HashAggregate (70)\n                                 +- HashAggregate (69)\n                                    +- Exchange (68)\n                                       +- HashAggregate (67)\n                                          +- Filter (66)\n                                             +- Scan csv  (26)\n\n\n(1) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(2) Filter [codegen id : 8]\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(3) Scan csv \nOutput [2]: [user_id#26, name#27]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_user.csv]\nPushedFilters: [IsNotNull(user_id)]\nReadSchema: struct<user_id:int,name:string>\n\n(4) Filter [codegen id : 1]\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(5) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]\n\n(6) BroadcastQueryStage\nOutput [2]: [user_id#26, name#27]\nArguments: 0\n\n(7) BroadcastHashJoin [codegen id : 8]\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(8) Project [codegen id : 8]\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(9) Scan csv \nOutput [2]: [course_id#18, title#19]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_course.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int,title:string>\n\n(10) Filter [codegen id : 2]\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(11) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]\n\n(12) BroadcastQueryStage\nOutput [2]: [course_id#18, title#19]\nArguments: 1\n\n(13) BroadcastHashJoin [codegen id : 8]\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(14) Project [codegen id : 8]\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(15) Scan csv \nOutput [1]: [course_id#9]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/dim_lesson.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct<course_id:int>\n\n(16) Filter [codegen id : 3]\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(17) HashAggregate [codegen id : 3]\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(18) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]\n\n(19) ShuffleQueryStage\nOutput [2]: [course_id#9, count#207L]\nArguments: 2\n\n(20) AQEShuffleRead\nInput [2]: [course_id#9, count#207L]\nArguments: coalesced\n\n(21) HashAggregate [codegen id : 5]\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(22) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]\n\n(23) BroadcastQueryStage\nOutput [2]: [course_id#9, lessons_in_course#50L]\nArguments: 4\n\n(24) BroadcastHashJoin [codegen id : 8]\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(25) Project [codegen id : 8]\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(26) Scan csv \nOutput [3]: [user_id#0, lesson_id#1, course_id#2]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_lesson_views.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,lesson_id:int,course_id:int>\n\n(27) Filter [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(28) HashAggregate [codegen id : 4]\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(29) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]\n\n(30) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: 3\n\n(31) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: coalesced\n\n(32) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(33) HashAggregate [codegen id : 6]\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(34) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]\n\n(35) ShuffleQueryStage\nOutput [3]: [user_id#0, course_id#2, count#210L]\nArguments: 5\n\n(36) AQEShuffleRead\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: coalesced\n\n(37) HashAggregate [codegen id : 7]\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(38) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=702]\n\n(39) BroadcastQueryStage\nOutput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: 6\n\n(40) BroadcastHashJoin [codegen id : 8]\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(41) Project [codegen id : 8]\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(42) Project [codegen id : 8]\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(43) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=820]\n\n(44) ShuffleQueryStage\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: 7\n\n(45) AQEShuffleRead\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: coalesced\n\n(46) Sort [codegen id : 9]\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(47) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(48) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(49) Scan csv \nOutput [2]: [user_id#37, course_id#38]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/core/fact_enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct<user_id:int,course_id:int>\n\n(50) Filter\nInput [2]: [user_id#37, course_id#38]\nCondition : (isnotnull(user_id#37) AND isnotnull(course_id#38))\n\n(51) Filter\nInput [2]: [user_id#26, name#27]\nCondition : isnotnull(user_id#26)\n\n(52) BroadcastExchange\nInput [2]: [user_id#26, name#27]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=126]\n\n(53) BroadcastHashJoin\nLeft keys [1]: [user_id#37]\nRight keys [1]: [user_id#26]\nJoin type: Inner\nJoin condition: None\n\n(54) Project\nOutput [3]: [user_id#37, course_id#38, name#27]\nInput [4]: [user_id#37, course_id#38, user_id#26, name#27]\n\n(55) Filter\nInput [2]: [course_id#18, title#19]\nCondition : isnotnull(course_id#18)\n\n(56) BroadcastExchange\nInput [2]: [course_id#18, title#19]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=130]\n\n(57) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#18]\nJoin type: Inner\nJoin condition: None\n\n(58) Project\nOutput [4]: [user_id#37, course_id#38, name#27, title#19]\nInput [5]: [user_id#37, course_id#38, name#27, course_id#18, title#19]\n\n(59) Filter\nInput [1]: [course_id#9]\nCondition : isnotnull(course_id#9)\n\n(60) HashAggregate\nInput [1]: [course_id#9]\nKeys [1]: [course_id#9]\nFunctions [1]: [partial_count(1)]\nAggregate Attributes [1]: [count#206L]\nResults [2]: [course_id#9, count#207L]\n\n(61) Exchange\nInput [2]: [course_id#9, count#207L]\nArguments: hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=133]\n\n(62) HashAggregate\nInput [2]: [course_id#9, count#207L]\nKeys [1]: [course_id#9]\nFunctions [1]: [count(1)]\nAggregate Attributes [1]: [count(1)#49L]\nResults [2]: [course_id#9, count(1)#49L AS lessons_in_course#50L]\n\n(63) BroadcastExchange\nInput [2]: [course_id#9, lessons_in_course#50L]\nArguments: HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=136]\n\n(64) BroadcastHashJoin\nLeft keys [1]: [course_id#38]\nRight keys [1]: [course_id#9]\nJoin type: LeftOuter\nJoin condition: None\n\n(65) Project\nOutput [5]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]\nInput [6]: [user_id#37, course_id#38, name#27, title#19, course_id#9, lessons_in_course#50L]\n\n(66) Filter\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nCondition : (isnotnull(user_id#0) AND isnotnull(course_id#2))\n\n(67) HashAggregate\nInput [3]: [user_id#0, lesson_id#1, course_id#2]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(68) Exchange\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nArguments: hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=139]\n\n(69) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [3]: [user_id#0, course_id#2, lesson_id#1]\nFunctions: []\nAggregate Attributes: []\nResults [3]: [user_id#0, course_id#2, lesson_id#1]\n\n(70) HashAggregate\nInput [3]: [user_id#0, course_id#2, lesson_id#1]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [partial_count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count#210L]\n\n(71) Exchange\nInput [3]: [user_id#0, course_id#2, count#210L]\nArguments: hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=143]\n\n(72) HashAggregate\nInput [3]: [user_id#0, course_id#2, count#210L]\nKeys [2]: [user_id#0, course_id#2]\nFunctions [1]: [count(distinct lesson_id#1)]\nAggregate Attributes [1]: [count(lesson_id#1)#61L]\nResults [3]: [user_id#0, course_id#2, count(lesson_id#1)#61L AS lessons_viewed#60L]\n\n(73) BroadcastExchange\nInput [3]: [user_id#0, course_id#2, lessons_viewed#60L]\nArguments: HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=146]\n\n(74) BroadcastHashJoin\nLeft keys [2]: [user_id#37, course_id#38]\nRight keys [2]: [user_id#0, course_id#2]\nJoin type: LeftOuter\nJoin condition: None\n\n(75) Project\nOutput [6]: [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]\nInput [8]: [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L, user_id#0, course_id#2, lessons_viewed#60L]\n\n(76) Project\nOutput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]\nInput [6]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L]\n\n(77) Exchange\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=151]\n\n(78) Sort\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\nArguments: [user_id#37 ASC NULLS FIRST], true, 0\n\n(79) WriteFiles\nInput [7]: [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, completion_rate#191]\n\n(80) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]\n\n(81) AdaptiveSparkPlan\nOutput: []\nArguments: isFinalPlan=true\n\n","sparkPlanInfo":{"nodeName":"AdaptiveSparkPlan","simpleString":"AdaptiveSparkPlan isFinalPlan=true","children":[{"nodeName":"Execute InsertIntoHadoopFsRelationCommand","simpleString":"Execute InsertIntoHadoopFsRelationCommand s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts_gp/course_completion_rate.parquet], Overwrite, [user_id, user_name, course_id, course_title, lessons_in_course, lessons_viewed, completion_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"WholeStageCodegen (9)","simpleString":"WholeStageCodegen (9)","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#37 ASC NULLS FIRST], true, 0","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 7","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#37 ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=820]","children":[{"nodeName":"WholeStageCodegen (8)","simpleString":"WholeStageCodegen (8)","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, user_name#182, course_id#38, course_title#183, lessons_in_course#50L, lessons_viewed#184L, CASE WHEN NOT (lessons_in_course#50L = 0) THEN round(((cast(lessons_viewed#184L as double) * 1.0) / cast(lessons_in_course#50L as double)), 2) END AS completion_rate#191]","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, name#27 AS user_name#182, course_id#38, title#19 AS course_title#183, lessons_in_course#50L, coalesce(lessons_viewed#60L, 0) AS lessons_viewed#184L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37, course_id#38], [user_id#0, course_id#2], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19, lessons_in_course#50L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#9], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27, title#19]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#38], [course_id#18], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [user_id#37, course_id#38, name#27]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [user_id#37], [user_id#26], Inner, BuildRight, false","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#37) AND isnotnull(course_id#38))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#37,course_id#38] Batched: false, DataFilters: [isnotnull(user_id#37), isnotnull(course_id#38)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_enrollments.csv]","ReadSchema":"struct<user_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#37), isnotnull(course_id#38)]"},"metrics":[{"name":"number of output rows","accumulatorId":828,"metricType":"sum"},{"name":"number of files read","accumulatorId":829,"metricType":"sum"},{"name":"metadata time","accumulatorId":830,"metricType":"timing"},{"name":"size of files read","accumulatorId":831,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":827,"metricType":"sum"}]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=215]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(user_id#26)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#26,name#27] Batched: false, DataFilters: [isnotnull(user_id#26)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id)], ReadSchema: struct<user_id:int,name:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_user.csv]","ReadSchema":"struct<user_id:int,name:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id)]","DataFilters":"[isnotnull(user_id#26)]"},"metrics":[{"name":"number of output rows","accumulatorId":47,"metricType":"sum"},{"name":"number of files read","accumulatorId":48,"metricType":"sum"},{"name":"metadata time","accumulatorId":49,"metricType":"timing"},{"name":"size of files read","accumulatorId":50,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":218,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":217,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":216,"metricType":"timing"},{"name":"time to build","accumulatorId":215,"metricType":"timing"},{"name":"time to collect","accumulatorId":214,"metricType":"timing"},{"name":"number of output rows","accumulatorId":213,"metricType":"sum"},{"name":"data size","accumulatorId":212,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":826,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, false] as bigint)),false), [plan_id=227]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#18)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#18,title#19] Batched: false, DataFilters: [isnotnull(course_id#18)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int,title:string>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_course.csv]","ReadSchema":"struct<course_id:int,title:string>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#18)]"},"metrics":[{"name":"number of output rows","accumulatorId":57,"metricType":"sum"},{"name":"number of files read","accumulatorId":58,"metricType":"sum"},{"name":"metadata time","accumulatorId":59,"metricType":"timing"},{"name":"size of files read","accumulatorId":60,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":225,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":224,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":223,"metricType":"timing"},{"name":"time to build","accumulatorId":222,"metricType":"timing"},{"name":"time to collect","accumulatorId":221,"metricType":"timing"},{"name":"number of output rows","accumulatorId":220,"metricType":"sum"},{"name":"data size","accumulatorId":219,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":825,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 4","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(cast(input[0, int, true] as bigint)),false), [plan_id=394]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[count(1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 2","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(course_id#9, 200), ENSURE_REQUIREMENTS, [plan_id=240]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[course_id#9], functions=[partial_count(1)])","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#9)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [course_id#9] Batched: false, DataFilters: [isnotnull(course_id#9)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct<course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/dim_lesson.csv]","ReadSchema":"struct<course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#9)]"},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"},{"name":"number of files read","accumulatorId":102,"metricType":"sum"},{"name":"metadata time","accumulatorId":103,"metricType":"timing"},{"name":"size of files read","accumulatorId":104,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":266,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":262,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":263,"metricType":"timing"},{"name":"peak memory","accumulatorId":261,"metricType":"size"},{"name":"number of output rows","accumulatorId":260,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":265,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":264,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":259,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":257,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":251,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":258,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":252,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":249,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":246,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":255,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":248,"metricType":"sum"},{"name":"records read","accumulatorId":245,"metricType":"sum"},{"name":"local bytes read","accumulatorId":243,"metricType":"size"},{"name":"fetch wait time","accumulatorId":244,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":241,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":247,"metricType":"sum"},{"name":"local blocks read","accumulatorId":240,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":250,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":239,"metricType":"sum"},{"name":"data size","accumulatorId":237,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":253,"metricType":"size"},{"name":"number of partitions","accumulatorId":238,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":254,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":242,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":256,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":534,"metricType":"sum"},{"name":"partition data size","accumulatorId":535,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":536,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":530,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":531,"metricType":"timing"},{"name":"peak memory","accumulatorId":529,"metricType":"size"},{"name":"number of output rows","accumulatorId":528,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":533,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":532,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":527,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":526,"metricType":"timing"},{"name":"time to build","accumulatorId":525,"metricType":"timing"},{"name":"time to collect","accumulatorId":524,"metricType":"timing"},{"name":"number of output rows","accumulatorId":523,"metricType":"sum"},{"name":"data size","accumulatorId":522,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":824,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 6","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List((shiftleft(cast(input[0, int, true] as bigint), 32) | (cast(input[1, int, true] as bigint) & 4294967295))),false), [plan_id=702]","children":[{"nodeName":"WholeStageCodegen (7)","simpleString":"WholeStageCodegen (7)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[count(distinct lesson_id#1)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 5","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, 200), ENSURE_REQUIREMENTS, [plan_id=512]","children":[{"nodeName":"WholeStageCodegen (6)","simpleString":"WholeStageCodegen (6)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2], functions=[partial_count(distinct lesson_id#1)])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(user_id#0, course_id#2, lesson_id#1, 200), ENSURE_REQUIREMENTS, [plan_id=258]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[user_id#0, course_id#2, lesson_id#1], functions=[])","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#0) AND isnotnull(course_id#2))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#0,lesson_id#1,course_id#2] Batched: false, DataFilters: [isnotnull(user_id#0), isnotnull(course_id#2)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct<user_id:int,lesson_id:int,course_id:int>","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/core/fact_lesson_views.csv]","ReadSchema":"struct<user_id:int,lesson_id:int,course_id:int>","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#0), isnotnull(course_id#2)]"},"metrics":[{"name":"number of output rows","accumulatorId":179,"metricType":"sum"},{"name":"number of files read","accumulatorId":180,"metricType":"sum"},{"name":"metadata time","accumulatorId":181,"metricType":"timing"},{"name":"size of files read","accumulatorId":182,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":341,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":337,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":338,"metricType":"timing"},{"name":"peak memory","accumulatorId":336,"metricType":"size"},{"name":"number of output rows","accumulatorId":335,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":340,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":339,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":334,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":332,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":326,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":333,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":327,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":324,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":321,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":330,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":323,"metricType":"sum"},{"name":"records read","accumulatorId":320,"metricType":"sum"},{"name":"local bytes read","accumulatorId":318,"metricType":"size"},{"name":"fetch wait time","accumulatorId":319,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":316,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":322,"metricType":"sum"},{"name":"local blocks read","accumulatorId":315,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":325,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":314,"metricType":"sum"},{"name":"data size","accumulatorId":312,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":328,"metricType":"size"},{"name":"number of partitions","accumulatorId":313,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":329,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":317,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":331,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":628,"metricType":"sum"},{"name":"partition data size","accumulatorId":629,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":630,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":624,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":625,"metricType":"timing"},{"name":"peak memory","accumulatorId":623,"metricType":"size"},{"name":"number of output rows","accumulatorId":622,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":627,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":626,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":618,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":619,"metricType":"timing"},{"name":"peak memory","accumulatorId":617,"metricType":"size"},{"name":"number of output rows","accumulatorId":616,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":621,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":620,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":615,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":613,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":607,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":614,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":608,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":605,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":602,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":611,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":604,"metricType":"sum"},{"name":"records read","accumulatorId":601,"metricType":"sum"},{"name":"local bytes read","accumulatorId":599,"metricType":"size"},{"name":"fetch wait time","accumulatorId":600,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":597,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":603,"metricType":"sum"},{"name":"local blocks read","accumulatorId":596,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":606,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":595,"metricType":"sum"},{"name":"data size","accumulatorId":593,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":609,"metricType":"size"},{"name":"number of partitions","accumulatorId":594,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":610,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":598,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":612,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":753,"metricType":"sum"},{"name":"partition data size","accumulatorId":754,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":755,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":749,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":750,"metricType":"timing"},{"name":"peak memory","accumulatorId":748,"metricType":"size"},{"name":"number of output rows","accumulatorId":747,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":752,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":751,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":746,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":745,"metricType":"timing"},{"name":"time to build","accumulatorId":744,"metricType":"timing"},{"name":"time to collect","accumulatorId":743,"metricType":"timing"},{"name":"number of output rows","accumulatorId":742,"metricType":"sum"},{"name":"data size","accumulatorId":741,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":823,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":822,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":820,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":814,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":821,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":815,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":812,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":809,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":818,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":811,"metricType":"sum"},{"name":"records read","accumulatorId":808,"metricType":"sum"},{"name":"local bytes read","accumulatorId":806,"metricType":"size"},{"name":"fetch wait time","accumulatorId":807,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":804,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":810,"metricType":"sum"},{"name":"local blocks read","accumulatorId":803,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":813,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":802,"metricType":"sum"},{"name":"data size","accumulatorId":800,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":816,"metricType":"size"},{"name":"number of partitions","accumulatorId":801,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":817,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":805,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":819,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":912,"metricType":"sum"},{"name":"partition data size","accumulatorId":913,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":914,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":909,"metricType":"timing"},{"name":"peak memory","accumulatorId":910,"metricType":"size"},{"name":"spill size","accumulatorId":911,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":908,"metricType":"timing"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":906,"metricType":"timing"},{"name":"number of written files","accumulatorId":902,"metricType":"sum"},{"name":"job commit time","accumulatorId":907,"metricType":"timing"},{"name":"number of output rows","accumulatorId":904,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":905,"metricType":"sum"},{"name":"written output","accumulatorId":903,"metricType":"size"}]}],"metadata":{},"metrics":[]}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[912,1],[914,1],[913,4209]]}
{"Event":"SparkListenerJobStart","Job ID":9,"Submission Time":1784106883114,"Stage Infos":[{"Stage ID":13,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":31,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"63\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[27],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"64\",\"name\":\"WholeStageCodegen (8)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[26],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"FileScanRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"92\",\"name\":\"Scan csv \"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[25],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},{"Stage ID":14,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":34,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"99\",\"name\":\"WriteFiles\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[33],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":32,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"103\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[31],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":33,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"100\",\"name\":\"WholeStageCodegen (9)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[32],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[13],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}],"Stage IDs":[13,14],"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerStageSubmitted","Stage Info":{"Stage ID":14,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":34,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"99\",\"name\":\"WriteFiles\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[33],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":32,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"103\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[31],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":33,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"100\",\"name\":\"WholeStageCodegen (9)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[32],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[13],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106883116,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"34401","spark.submit.pyFiles":"","spark.app.startTime":"1784106872542","spark.hadoop.fs.s3a.endpoint":"http://minio:9000","spark.rdd.compress":"True","spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem","spark.app.submitTime":"1784106871422","spark.eventLog.dir":"file:/opt/spark-events","spark.hadoop.fs.s3a.aws.credentials.provider":"org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider","spark.sql.execution.id":"0","spark.sql.warehouse.dir":"file:/opt/airflow/spark-warehouse","spark.master":"spark://spark-master:7077","spark.hadoop.fs.s3a.secret.key":"*********(redacted)","spark.executor.id":"driver","spark.app.name":"dm_course_completion_rate","spark.hadoop.fs.s3a.access.key":"*********(redacted)","spark.submit.deployMode":"client","spark.hadoop.fs.s3a.path.style.access":"true","spark.driver.host":"73850a3d530b","spark.app.id":"app-20260715131433-0082","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","__fetch_continuous_blocks_in_batch_enabled":"true","spark.executor.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false","spark.sql.execution.root.id":"0","spark.hadoop.fs.s3a.connection.ssl.enabled":"false","spark.serializer.objectStreamReset":"100","spark.driver.extraJavaOptions":"-Djava.net.preferIPv6Addresses=false -XX:+IgnoreUnrecognizedVMOptions --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED -Djdk.reflect.useDirectMethodHandle=false"}}
{"Event":"SparkListenerTaskStart","Stage ID":14,"Stage Attempt ID":0,"Task Info":{"Task ID":9,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106883143,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":0,"Failed":false,"Killed":false,"Accumulables":[]}}
{"Event":"SparkListenerTaskEnd","Stage ID":14,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":9,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784106883143,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784106884257,"Failed":false,"Killed":false,"Accumulables":[{"ID":803,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":806,"Name":"local bytes read","Update":"4012","Value":"4012","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":807,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":808,"Name":"records read","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":906,"Name":"task commit time","Update":"129","Value":"129","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":908,"Name":"duration","Update":"485","Value":"485","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":909,"Name":"sort time","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":910,"Name":"peak memory","Update":"4259824","Value":"4259824","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":911,"Name":"spill size","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":915,"Name":"internal.metrics.executorDeserializeTime","Update":147,"Value":147,"Internal":true,"Count Failed Values":true},{"ID":916,"Name":"internal.metrics.executorDeserializeCpuTime","Update":120771487,"Value":120771487,"Internal":true,"Count Failed Values":true},{"ID":917,"Name":"internal.metrics.executorRunTime","Update":952,"Value":952,"Internal":true,"Count Failed Values":true},{"ID":918,"Name":"internal.metrics.executorCpuTime","Update":662557609,"Value":662557609,"Internal":true,"Count Failed Values":true},{"ID":919,"Name":"internal.metrics.resultSize","Update":14370,"Value":14370,"Internal":true,"Count Failed Values":true},{"ID":920,"Name":"internal.metrics.jvmGCTime","Update":19,"Value":19,"Internal":true,"Count Failed Values":true},{"ID":921,"Name":"internal.metrics.resultSerializationTime","Update":3,"Value":3,"Internal":true,"Count Failed Values":true},{"ID":924,"Name":"internal.metrics.peakExecutionMemory","Update":4259824,"Value":4259824,"Internal":true,"Count Failed Values":true},{"ID":926,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":927,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":928,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":929,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":930,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":4012,"Value":4012,"Internal":true,"Count Failed Values":true},{"ID":931,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":932,"Name":"internal.metrics.shuffle.read.recordsRead","Update":45,"Value":45,"Internal":true,"Count Failed Values":true},{"ID":933,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":934,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":935,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":936,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":937,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":938,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":939,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":940,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":941,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":942,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":948,"Name":"internal.metrics.output.bytesWritten","Update":3010,"Value":3010,"Internal":true,"Count Failed Values":true},{"ID":949,"Name":"internal.metrics.output.recordsWritten","Update":45,"Value":45,"Internal":true,"Count Failed Values":true}]},"Task Executor Metrics":{"JVMHeapMemory":0,"JVMOffHeapMemory":0,"OnHeapExecutionMemory":0,"OffHeapExecutionMemory":0,"OnHeapStorageMemory":0,"OffHeapStorageMemory":0,"OnHeapUnifiedMemory":0,"OffHeapUnifiedMemory":0,"DirectPoolMemory":0,"MappedPoolMemory":0,"ProcessTreeJVMVMemory":0,"ProcessTreeJVMRSSMemory":0,"ProcessTreePythonVMemory":0,"ProcessTreePythonRSSMemory":0,"ProcessTreeOtherVMemory":0,"ProcessTreeOtherRSSMemory":0,"MinorGCCount":0,"MinorGCTime":0,"MajorGCCount":0,"MajorGCTime":0,"TotalGCTime":0},"Task Metrics":{"Executor Deserialize Time":147,"Executor Deserialize CPU Time":120771487,"Executor Run Time":952,"Executor CPU Time":662557609,"Peak Execution Memory":4259824,"Result Size":14370,"JVM GC Time":19,"Result Serialization Time":3,"Memory Bytes Spilled":0,"Disk Bytes Spilled":0,"Shuffle Read Metrics":{"Remote Blocks Fetched":0,"Local Blocks Fetched":1,"Fetch Wait Time":0,"Remote Bytes Read":0,"Remote Bytes Read To Disk":0,"Local Bytes Read":4012,"Total Records Read":45,"Remote Requests Duration":0,"Push Based Shuffle":{"Corrupt Merged Block Chunks":0,"Merged Fetch Fallback Count":0,"Merged Remote Blocks Fetched":0,"Merged Local Blocks Fetched":0,"Merged Remote Chunks Fetched":0,"Merged Local Chunks Fetched":0,"Merged Remote Bytes Read":0,"Merged Local Bytes Read":0,"Merged Remote Requests Duration":0}},"Shuffle Write Metrics":{"Shuffle Bytes Written":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":0,"Records Read":0},"Output Metrics":{"Bytes Written":3010,"Records Written":45},"Updated Blocks":[]}}
{"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":14,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":34,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"99\",\"name\":\"WriteFiles\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[33],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":32,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"103\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[31],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":33,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"100\",\"name\":\"WholeStageCodegen (9)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[32],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[13],"Details":"org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:792)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)\njava.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77)\njava.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)\njava.base/java.lang.reflect.Method.invoke(Method.java:569)\npy4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)\npy4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:374)\npy4j.Gateway.invoke(Gateway.java:282)\npy4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)\npy4j.commands.CallCommand.execute(CallCommand.java:79)\npy4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)\npy4j.ClientServerConnection.run(ClientServerConnection.java:106)\njava.base/java.lang.Thread.run(Thread.java:840)","Submission Time":1784106883116,"Completion Time":1784106884258,"Accumulables":[{"ID":803,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":806,"Name":"local bytes read","Value":"4012","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":807,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":808,"Name":"records read","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":906,"Name":"task commit time","Value":"129","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":908,"Name":"duration","Value":"485","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":909,"Name":"sort time","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":910,"Name":"peak memory","Value":"4259824","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":911,"Name":"spill size","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":915,"Name":"internal.metrics.executorDeserializeTime","Value":147,"Internal":true,"Count Failed Values":true},{"ID":916,"Name":"internal.metrics.executorDeserializeCpuTime","Value":120771487,"Internal":true,"Count Failed Values":true},{"ID":917,"Name":"internal.metrics.executorRunTime","Value":952,"Internal":true,"Count Failed Values":true},{"ID":918,"Name":"internal.metrics.executorCpuTime","Value":662557609,"Internal":true,"Count Failed Values":true},{"ID":919,"Name":"internal.metrics.resultSize","Value":14370,"Internal":true,"Count Failed Values":true},{"ID":920,"Name":"internal.metrics.jvmGCTime","Value":19,"Internal":true,"Count Failed Values":true},{"ID":921,"Name":"internal.metrics.resultSerializationTime","Value":3,"Internal":true,"Count Failed Values":true},{"ID":924,"Name":"internal.metrics.peakExecutionMemory","Value":4259824,"Internal":true,"Count Failed Values":true},{"ID":926,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":927,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":928,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":929,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":930,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":4012,"Internal":true,"Count Failed Values":true},{"ID":931,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":932,"Name":"internal.metrics.shuffle.read.recordsRead","Value":45,"Internal":true,"Count Failed Values":true},{"ID":933,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":934,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":935,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":936,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":937,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":938,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":939,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":940,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":941,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":942,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":948,"Name":"internal.metrics.output.bytesWritten","Value":3010,"Internal":true,"Count Failed Values":true},{"ID":949,"Name":"internal.metrics.output.recordsWritten","Value":45,"Internal":true,"Count Failed Values":true}],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0}}
{"Event":"SparkListenerJobEnd","Job ID":9,"Completion Time":1784106884259,"Job Result":{"Result":"JobSucceeded"}}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[902,1],[907,139],[904,45],[905,0],[903,3010]]}
{"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionEnd","executionId":0,"time":1784106884408,"errorMessage":""}
{"Event":"SparkListenerApplicationEnd","Timestamp":1784106884412}