{"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":38523},"Maximum Memory":455501414,"Timestamp":1784546378140,"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":"38791","spark.rdd.compress":"True","spark.hadoop.fs.s3a.path.style.access":"true","spark.app.name":"dm_user_activity_summary","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":"1784546375619","spark.app.startTime":"1784546376677","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-20260720151938-0098"},"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_user_activity_summary","App ID":"app-20260720151938-0098","Timestamp":1784546376677,"User":"airflow"} {"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 (30)\n+- Execute InsertIntoHadoopFsRelationCommand (29)\n +- WriteFiles (28)\n +- Sort (27)\n +- Exchange (26)\n +- Project (25)\n +- HashAggregate (24)\n +- Exchange (23)\n +- HashAggregate (22)\n +- HashAggregate (21)\n +- Exchange (20)\n +- HashAggregate (19)\n +- Expand (18)\n +- Project (17)\n +- BroadcastHashJoin LeftOuter BuildRight (16)\n :- Project (12)\n : +- BroadcastHashJoin Inner BuildRight (11)\n : :- Project (7)\n : : +- BroadcastHashJoin Inner BuildLeft (6)\n : : :- BroadcastExchange (3)\n : : : +- Filter (2)\n : : : +- Scan csv (1)\n : : +- Filter (5)\n : : +- Scan csv (4)\n : +- BroadcastExchange (10)\n : +- Filter (9)\n : +- Scan csv (8)\n +- BroadcastExchange (15)\n +- Filter (14)\n +- Scan csv (13)\n\n\n(1) Scan csv \nOutput [2]: [id#0L, name#1]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/users.csv]\nPushedFilters: [IsNotNull(id)]\nReadSchema: struct\n\n(2) Filter\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(3) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]\n\n(4) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(5) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(6) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(7) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(8) Scan csv \nOutput [2]: [id#18L, course_id#19L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lessons.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct\n\n(9) Filter\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(10) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]\n\n(11) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(12) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(13) Scan csv \nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lesson_views.csv]\nPushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)]\nReadSchema: struct\n\n(14) Filter\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(15) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]\n\n(16) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(17) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(18) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(19) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(20) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]\n\n(21) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(22) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(23) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]\n\n(24) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(25) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(26) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]\n\n(27) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(28) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(29) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(30) 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/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#116L ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]","children":[{"nodeName":"Project","simpleString":"Project [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[max(lv.viewed_at#178), min(lv.viewed_at#178)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)])","children":[{"nodeName":"Expand","simpleString":"Expand [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#18L, id#0L], [lesson_id#28L, user_id#27L], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#12L], [course_id#19L], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#0L], [user_id#11L], Inner, BuildLeft, false","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(id#0L)","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#0L,name#1] Batched: false, DataFilters: [isnotnull(id#0L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv], PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(id)]","DataFilters":"[isnotnull(id#0L)]"},"metrics":[{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of files read","accumulatorId":111,"metricType":"sum"},{"name":"metadata time","accumulatorId":112,"metricType":"timing"},{"name":"size of files read","accumulatorId":113,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":109,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":108,"metricType":"timing"},{"name":"time to build","accumulatorId":107,"metricType":"timing"},{"name":"time to collect","accumulatorId":106,"metricType":"timing"},{"name":"number of output rows","accumulatorId":105,"metricType":"sum"},{"name":"data size","accumulatorId":104,"metricType":"size"}]},{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#11L) AND isnotnull(course_id#12L))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#11L,course_id#12L] Batched: false, DataFilters: [isnotnull(user_id#11L), isnotnull(course_id#12L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#11L), isnotnull(course_id#12L)]"},"metrics":[{"name":"number of output rows","accumulatorId":115,"metricType":"sum"},{"name":"number of files read","accumulatorId":116,"metricType":"sum"},{"name":"metadata time","accumulatorId":117,"metricType":"timing"},{"name":"size of files read","accumulatorId":118,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":114,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":103,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#19L)","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#18L,course_id#19L] Batched: false, DataFilters: [isnotnull(course_id#19L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#19L)]"},"metrics":[{"name":"number of output rows","accumulatorId":125,"metricType":"sum"},{"name":"number of files read","accumulatorId":126,"metricType":"sum"},{"name":"metadata time","accumulatorId":127,"metricType":"timing"},{"name":"size of files read","accumulatorId":128,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":124,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":123,"metricType":"timing"},{"name":"time to build","accumulatorId":122,"metricType":"timing"},{"name":"time to collect","accumulatorId":121,"metricType":"timing"},{"name":"number of output rows","accumulatorId":120,"metricType":"sum"},{"name":"data size","accumulatorId":119,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":102,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#27L,lesson_id#28L,viewed_at#29] Batched: false, DataFilters: [isnotnull(lesson_id#28L), isnotnull(user_id#27L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(lesson_id), IsNotNull(user_id)]","DataFilters":"[isnotnull(lesson_id#28L), isnotnull(user_id#27L)]"},"metrics":[{"name":"number of output rows","accumulatorId":135,"metricType":"sum"},{"name":"number of files read","accumulatorId":136,"metricType":"sum"},{"name":"metadata time","accumulatorId":137,"metricType":"timing"},{"name":"size of files read","accumulatorId":138,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":134,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":133,"metricType":"timing"},{"name":"time to build","accumulatorId":132,"metricType":"timing"},{"name":"time to collect","accumulatorId":131,"metricType":"timing"},{"name":"number of output rows","accumulatorId":130,"metricType":"sum"},{"name":"data size","accumulatorId":129,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":101,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"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":"spill size","accumulatorId":62,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":63,"metricType":"timing"},{"name":"peak memory","accumulatorId":61,"metricType":"size"},{"name":"number of output rows","accumulatorId":60,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":65,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":64,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":58,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":52,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":59,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":53,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":50,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":47,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":56,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":49,"metricType":"sum"},{"name":"records read","accumulatorId":46,"metricType":"sum"},{"name":"local bytes read","accumulatorId":44,"metricType":"size"},{"name":"fetch wait time","accumulatorId":45,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":42,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":48,"metricType":"sum"},{"name":"local blocks read","accumulatorId":41,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":51,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":40,"metricType":"sum"},{"name":"data size","accumulatorId":38,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":54,"metricType":"size"},{"name":"number of partitions","accumulatorId":39,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":55,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":43,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":57,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":34,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":35,"metricType":"timing"},{"name":"peak memory","accumulatorId":33,"metricType":"size"},{"name":"number of output rows","accumulatorId":32,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":37,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":36,"metricType":"average"}]}],"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":1784546383592,"modifiedConfigs":{},"jobTags":[]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (57)\n+- == Current Plan ==\n Execute InsertIntoHadoopFsRelationCommand (32)\n +- WriteFiles (31)\n +- Sort (30)\n +- Exchange (29)\n +- Project (28)\n +- HashAggregate (27)\n +- Exchange (26)\n +- HashAggregate (25)\n +- HashAggregate (24)\n +- Exchange (23)\n +- HashAggregate (22)\n +- Expand (21)\n +- Project (20)\n +- BroadcastHashJoin LeftOuter BuildRight (19)\n :- Project (14)\n : +- BroadcastHashJoin Inner BuildRight (13)\n : :- Project (8)\n : : +- BroadcastHashJoin Inner BuildLeft (7)\n : : :- BroadcastQueryStage (4)\n : : : +- BroadcastExchange (3)\n : : : +- * Filter (2)\n : : : +- Scan csv (1)\n : : +- Filter (6)\n : : +- Scan csv (5)\n : +- BroadcastQueryStage (12)\n : +- BroadcastExchange (11)\n : +- * Filter (10)\n : +- Scan csv (9)\n +- BroadcastQueryStage (18)\n +- BroadcastExchange (17)\n +- * Filter (16)\n +- Scan csv (15)\n+- == Initial Plan ==\n Execute InsertIntoHadoopFsRelationCommand (56)\n +- WriteFiles (55)\n +- Sort (54)\n +- Exchange (53)\n +- Project (52)\n +- HashAggregate (51)\n +- Exchange (50)\n +- HashAggregate (49)\n +- HashAggregate (48)\n +- Exchange (47)\n +- HashAggregate (46)\n +- Expand (45)\n +- Project (44)\n +- BroadcastHashJoin LeftOuter BuildRight (43)\n :- Project (40)\n : +- BroadcastHashJoin Inner BuildRight (39)\n : :- Project (36)\n : : +- BroadcastHashJoin Inner BuildLeft (35)\n : : :- BroadcastExchange (34)\n : : : +- Filter (33)\n : : : +- Scan csv (1)\n : : +- Filter (6)\n : : +- Scan csv (5)\n : +- BroadcastExchange (38)\n : +- Filter (37)\n : +- Scan csv (9)\n +- BroadcastExchange (42)\n +- Filter (41)\n +- Scan csv (15)\n\n\n(1) Scan csv \nOutput [2]: [id#0L, name#1]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/users.csv]\nPushedFilters: [IsNotNull(id)]\nReadSchema: struct\n\n(2) Filter [codegen id : 1]\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(3) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]\n\n(4) BroadcastQueryStage\nOutput [2]: [id#0L, name#1]\nArguments: 0\n\n(5) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(6) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(7) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(8) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(9) Scan csv \nOutput [2]: [id#18L, course_id#19L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lessons.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct\n\n(10) Filter [codegen id : 2]\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(11) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]\n\n(12) BroadcastQueryStage\nOutput [2]: [id#18L, course_id#19L]\nArguments: 1\n\n(13) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(14) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(15) Scan csv \nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lesson_views.csv]\nPushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)]\nReadSchema: struct\n\n(16) Filter [codegen id : 3]\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(17) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]\n\n(18) BroadcastQueryStage\nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: 2\n\n(19) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(20) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(21) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(22) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(23) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=214]\n\n(24) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(25) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(26) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=217]\n\n(27) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(28) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(29) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=220]\n\n(30) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(31) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(32) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(33) Filter\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(34) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]\n\n(35) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(36) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(37) Filter\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(38) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]\n\n(39) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(40) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(41) Filter\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(42) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]\n\n(43) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(44) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(45) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(46) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(47) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]\n\n(48) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(49) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(50) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]\n\n(51) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(52) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(53) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]\n\n(54) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(55) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(56) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(57) 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/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#116L ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=220]","children":[{"nodeName":"Project","simpleString":"Project [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=217]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[max(lv.viewed_at#178), min(lv.viewed_at#178)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=214]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)])","children":[{"nodeName":"Expand","simpleString":"Expand [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#18L, id#0L], [lesson_id#28L, user_id#27L], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#12L], [course_id#19L], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#0L], [user_id#11L], Inner, BuildLeft, false","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(id#0L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#0L,name#1] Batched: false, DataFilters: [isnotnull(id#0L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv], PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(id)]","DataFilters":"[isnotnull(id#0L)]"},"metrics":[{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of files read","accumulatorId":111,"metricType":"sum"},{"name":"metadata time","accumulatorId":112,"metricType":"timing"},{"name":"size of files read","accumulatorId":113,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":242,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":241,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":240,"metricType":"timing"},{"name":"time to build","accumulatorId":239,"metricType":"timing"},{"name":"time to collect","accumulatorId":238,"metricType":"timing"},{"name":"number of output rows","accumulatorId":237,"metricType":"sum"},{"name":"data size","accumulatorId":236,"metricType":"size"}]}],"metadata":{},"metrics":[]},{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#11L) AND isnotnull(course_id#12L))","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#11L,course_id#12L] Batched: false, DataFilters: [isnotnull(user_id#11L), isnotnull(course_id#12L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#11L), isnotnull(course_id#12L)]"},"metrics":[{"name":"number of output rows","accumulatorId":115,"metricType":"sum"},{"name":"number of files read","accumulatorId":116,"metricType":"sum"},{"name":"metadata time","accumulatorId":117,"metricType":"timing"},{"name":"size of files read","accumulatorId":118,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":114,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":235,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#19L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#18L,course_id#19L] Batched: false, DataFilters: [isnotnull(course_id#19L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#19L)]"},"metrics":[{"name":"number of output rows","accumulatorId":125,"metricType":"sum"},{"name":"number of files read","accumulatorId":126,"metricType":"sum"},{"name":"metadata time","accumulatorId":127,"metricType":"timing"},{"name":"size of files read","accumulatorId":128,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":249,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":248,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":247,"metricType":"timing"},{"name":"time to build","accumulatorId":246,"metricType":"timing"},{"name":"time to collect","accumulatorId":245,"metricType":"timing"},{"name":"number of output rows","accumulatorId":244,"metricType":"sum"},{"name":"data size","accumulatorId":243,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":234,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 2","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#27L,lesson_id#28L,viewed_at#29] Batched: false, DataFilters: [isnotnull(lesson_id#28L), isnotnull(user_id#27L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(lesson_id), IsNotNull(user_id)]","DataFilters":"[isnotnull(lesson_id#28L), isnotnull(user_id#27L)]"},"metrics":[{"name":"number of output rows","accumulatorId":135,"metricType":"sum"},{"name":"number of files read","accumulatorId":136,"metricType":"sum"},{"name":"metadata time","accumulatorId":137,"metricType":"timing"},{"name":"size of files read","accumulatorId":138,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":256,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":255,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":254,"metricType":"timing"},{"name":"time to build","accumulatorId":253,"metricType":"timing"},{"name":"time to collect","accumulatorId":252,"metricType":"timing"},{"name":"number of output rows","accumulatorId":251,"metricType":"sum"},{"name":"data size","accumulatorId":250,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":233,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":232,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":228,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":229,"metricType":"timing"},{"name":"peak memory","accumulatorId":227,"metricType":"size"},{"name":"number of output rows","accumulatorId":226,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":231,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":230,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":224,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":218,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":225,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":219,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":216,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":213,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":222,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":215,"metricType":"sum"},{"name":"records read","accumulatorId":212,"metricType":"sum"},{"name":"local bytes read","accumulatorId":210,"metricType":"size"},{"name":"fetch wait time","accumulatorId":211,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":208,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":214,"metricType":"sum"},{"name":"local blocks read","accumulatorId":207,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":217,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":206,"metricType":"sum"},{"name":"data size","accumulatorId":204,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":220,"metricType":"size"},{"name":"number of partitions","accumulatorId":205,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":221,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":209,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":223,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":200,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":201,"metricType":"timing"},{"name":"peak memory","accumulatorId":199,"metricType":"size"},{"name":"number of output rows","accumulatorId":198,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":203,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":202,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":194,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":195,"metricType":"timing"},{"name":"peak memory","accumulatorId":193,"metricType":"size"},{"name":"number of output rows","accumulatorId":192,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":197,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":196,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":190,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":184,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":191,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":185,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":182,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":179,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":188,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":181,"metricType":"sum"},{"name":"records read","accumulatorId":178,"metricType":"sum"},{"name":"local bytes read","accumulatorId":176,"metricType":"size"},{"name":"fetch wait time","accumulatorId":177,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":174,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":180,"metricType":"sum"},{"name":"local blocks read","accumulatorId":173,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":183,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":172,"metricType":"sum"},{"name":"data size","accumulatorId":170,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":186,"metricType":"size"},{"name":"number of partitions","accumulatorId":171,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":187,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":175,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":189,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":166,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":167,"metricType":"timing"},{"name":"peak memory","accumulatorId":165,"metricType":"size"},{"name":"number of output rows","accumulatorId":164,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":169,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":168,"metricType":"average"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":162,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":156,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":163,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":157,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":154,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":151,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":160,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":153,"metricType":"sum"},{"name":"records read","accumulatorId":150,"metricType":"sum"},{"name":"local bytes read","accumulatorId":148,"metricType":"size"},{"name":"fetch wait time","accumulatorId":149,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":146,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":152,"metricType":"sum"},{"name":"local blocks read","accumulatorId":145,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":155,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":144,"metricType":"sum"},{"name":"data size","accumulatorId":142,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":158,"metricType":"size"},{"name":"number of partitions","accumulatorId":143,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":159,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":147,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":161,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":139,"metricType":"timing"},{"name":"peak memory","accumulatorId":140,"metricType":"size"},{"name":"spill size","accumulatorId":141,"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":[[126,1],[127,6],[128,1057]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[136,1],[137,5],[138,1850]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[111,1],[112,4],[113,1032]]} {"Event":"SparkListenerJobStart","Job ID":2,"Submission Time":1784546384723,"Stage Infos":[{"Stage ID":0,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":9,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[6],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":6,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"5\",\"name\":\"WholeStageCodegen (2)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[4],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":4,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[0],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":0,"Name":"FileScanRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId d7e1203c-35b8-42b9-ad9b-bce67254c0de)","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$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":9,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[6],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":6,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"5\",\"name\":\"WholeStageCodegen (2)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[4],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":4,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[0],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":0,"Name":"FileScanRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":1784546384749,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId d7e1203c-35b8-42b9-ad9b-bce67254c0de)","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":1784546384878,"Stage Infos":[{"Stage ID":1,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[7],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":5,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"12\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"12\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":7,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (1)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[5],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId c218cc1d-6887-4300-a216-d6ca6010e804)","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$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[7],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":5,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"12\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"12\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":7,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (1)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[5],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":1784546384885,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId c218cc1d-6887-4300-a216-d6ca6010e804)","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":1,"Submission Time":1784546384910,"Stage Infos":[{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[8],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[2],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":8,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"3\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":2,"Name":"FileScanRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":[2],"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"2\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId 6aebbe1d-2f74-45da-9252-e165bae06c19)","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":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[8],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[2],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":8,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"3\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":2,"Name":"FileScanRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":1784546384911,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"2\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","spark.eventLog.compress":"true","spark.eventLog.enabled":"true","spark.job.tags":"broadcast exchange (runId 6aebbe1d-2f74-45da-9252-e165bae06c19)","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":"SparkListenerExecutorAdded","Timestamp":1784546397480,"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-20260720151938-0098&executorId=0&logType=stdout","stderr":"http://172.28.0.49:8081/logPage/?appId=app-20260720151938-0098&executorId=0&logType=stderr"},"Attributes":{},"Resources":{},"Resource Profile Id":0,"Registration Time":1784546397479}} {"Event":"SparkListenerBlockManagerAdded","Block Manager ID":{"Executor ID":"0","Host":"172.28.0.49","Port":35677},"Maximum Memory":455501414,"Timestamp":1784546397524,"Maximum Onheap Memory":455501414,"Maximum Offheap Memory":0} {"Event":"SparkListenerTaskStart","Stage ID":1,"Stage Attempt ID":0,"Task Info":{"Task ID":0,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546397567,"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":1,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546397578,"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":0,"Stage Attempt ID":0,"Task Info":{"Task ID":2,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546397578,"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":2,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546397578,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546399142,"Failed":false,"Killed":false,"Accumulables":[{"ID":125,"Name":"number of output rows","Update":"18","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":248,"Name":"duration","Update":"902","Value":"902","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":249,"Name":"number of output rows","Update":"18","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":257,"Name":"internal.metrics.executorDeserializeTime","Update":351,"Value":351,"Internal":true,"Count Failed Values":true},{"ID":258,"Name":"internal.metrics.executorDeserializeCpuTime","Update":175926762,"Value":175926762,"Internal":true,"Count Failed Values":true},{"ID":259,"Name":"internal.metrics.executorRunTime","Update":1176,"Value":1176,"Internal":true,"Count Failed Values":true},{"ID":260,"Name":"internal.metrics.executorCpuTime","Update":329010071,"Value":329010071,"Internal":true,"Count Failed Values":true},{"ID":261,"Name":"internal.metrics.resultSize","Update":1835,"Value":1835,"Internal":true,"Count Failed Values":true},{"ID":262,"Name":"internal.metrics.jvmGCTime","Update":13,"Value":13,"Internal":true,"Count Failed Values":true},{"ID":263,"Name":"internal.metrics.resultSerializationTime","Update":2,"Value":2,"Internal":true,"Count Failed Values":true},{"ID":288,"Name":"internal.metrics.input.bytesRead","Update":1057,"Value":1057,"Internal":true,"Count Failed Values":true},{"ID":289,"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":351,"Executor Deserialize CPU Time":175926762,"Executor Run Time":1176,"Executor CPU Time":329010071,"Peak Execution Memory":0,"Result Size":1835,"JVM GC Time":13,"Result Serialization Time":2,"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":1057,"Records Read":18},"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$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":9,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"1\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[6],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":6,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"5\",\"name\":\"WholeStageCodegen (2)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[4],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":4,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[0],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":0,"Name":"FileScanRDD","Scope":"{\"id\":\"14\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":1784546384749,"Completion Time":1784546399146,"Accumulables":[{"ID":125,"Name":"number of output rows","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":248,"Name":"duration","Value":"902","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":249,"Name":"number of output rows","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":257,"Name":"internal.metrics.executorDeserializeTime","Value":351,"Internal":true,"Count Failed Values":true},{"ID":258,"Name":"internal.metrics.executorDeserializeCpuTime","Value":175926762,"Internal":true,"Count Failed Values":true},{"ID":259,"Name":"internal.metrics.executorRunTime","Value":1176,"Internal":true,"Count Failed Values":true},{"ID":260,"Name":"internal.metrics.executorCpuTime","Value":329010071,"Internal":true,"Count Failed Values":true},{"ID":261,"Name":"internal.metrics.resultSize","Value":1835,"Internal":true,"Count Failed Values":true},{"ID":262,"Name":"internal.metrics.jvmGCTime","Value":13,"Internal":true,"Count Failed Values":true},{"ID":263,"Name":"internal.metrics.resultSerializationTime","Value":2,"Internal":true,"Count Failed Values":true},{"ID":288,"Name":"internal.metrics.input.bytesRead","Value":1057,"Internal":true,"Count Failed Values":true},{"ID":289,"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":1784546399148,"Job Result":{"Result":"JobSucceeded"}} {"Event":"SparkListenerTaskEnd","Stage ID":2,"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":1784546397578,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546399144,"Failed":false,"Killed":false,"Accumulables":[{"ID":135,"Name":"number of output rows","Update":"58","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":255,"Name":"duration","Update":"919","Value":"919","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":256,"Name":"number of output rows","Update":"58","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":327,"Name":"internal.metrics.executorDeserializeTime","Update":351,"Value":351,"Internal":true,"Count Failed Values":true},{"ID":328,"Name":"internal.metrics.executorDeserializeCpuTime","Update":178926107,"Value":178926107,"Internal":true,"Count Failed Values":true},{"ID":329,"Name":"internal.metrics.executorRunTime","Update":1188,"Value":1188,"Internal":true,"Count Failed Values":true},{"ID":330,"Name":"internal.metrics.executorCpuTime","Update":587034741,"Value":587034741,"Internal":true,"Count Failed Values":true},{"ID":331,"Name":"internal.metrics.resultSize","Update":2408,"Value":2408,"Internal":true,"Count Failed Values":true},{"ID":332,"Name":"internal.metrics.jvmGCTime","Update":13,"Value":13,"Internal":true,"Count Failed Values":true},{"ID":358,"Name":"internal.metrics.input.bytesRead","Update":1850,"Value":1850,"Internal":true,"Count Failed Values":true},{"ID":359,"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":351,"Executor Deserialize CPU Time":178926107,"Executor Run Time":1188,"Executor CPU Time":587034741,"Peak Execution Memory":0,"Result Size":2408,"JVM GC Time":13,"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":0,"Shuffle Write Time":0,"Shuffle Records Written":0},"Input Metrics":{"Bytes Read":1850,"Records Read":58},"Output Metrics":{"Bytes Written":0,"Records Written":0},"Updated Blocks":[]}} {"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":2,"Stage Attempt ID":0,"Stage Name":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":11,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"2\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[8],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":3,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[2],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":8,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"3\",\"name\":\"WholeStageCodegen (3)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[3],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":2,"Name":"FileScanRDD","Scope":"{\"id\":\"13\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":1784546384911,"Completion Time":1784546399149,"Accumulables":[{"ID":135,"Name":"number of output rows","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":255,"Name":"duration","Value":"919","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":256,"Name":"number of output rows","Value":"58","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":327,"Name":"internal.metrics.executorDeserializeTime","Value":351,"Internal":true,"Count Failed Values":true},{"ID":328,"Name":"internal.metrics.executorDeserializeCpuTime","Value":178926107,"Internal":true,"Count Failed Values":true},{"ID":329,"Name":"internal.metrics.executorRunTime","Value":1188,"Internal":true,"Count Failed Values":true},{"ID":330,"Name":"internal.metrics.executorCpuTime","Value":587034741,"Internal":true,"Count Failed Values":true},{"ID":331,"Name":"internal.metrics.resultSize","Value":2408,"Internal":true,"Count Failed Values":true},{"ID":332,"Name":"internal.metrics.jvmGCTime","Value":13,"Internal":true,"Count Failed Values":true},{"ID":358,"Name":"internal.metrics.input.bytesRead","Value":1850,"Internal":true,"Count Failed Values":true},{"ID":359,"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":1,"Completion Time":1784546399149,"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":0,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546397567,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546399144,"Failed":false,"Killed":false,"Accumulables":[{"ID":110,"Name":"number of output rows","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":241,"Name":"duration","Update":"901","Value":"901","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":242,"Name":"number of output rows","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":292,"Name":"internal.metrics.executorDeserializeTime","Update":351,"Value":351,"Internal":true,"Count Failed Values":true},{"ID":293,"Name":"internal.metrics.executorDeserializeCpuTime","Update":168452214,"Value":168452214,"Internal":true,"Count Failed Values":true},{"ID":294,"Name":"internal.metrics.executorRunTime","Update":1176,"Value":1176,"Internal":true,"Count Failed Values":true},{"ID":295,"Name":"internal.metrics.executorCpuTime","Update":512640013,"Value":512640013,"Internal":true,"Count Failed Values":true},{"ID":296,"Name":"internal.metrics.resultSize","Update":2035,"Value":2035,"Internal":true,"Count Failed Values":true},{"ID":297,"Name":"internal.metrics.jvmGCTime","Update":13,"Value":13,"Internal":true,"Count Failed Values":true},{"ID":298,"Name":"internal.metrics.resultSerializationTime","Update":2,"Value":2,"Internal":true,"Count Failed Values":true},{"ID":323,"Name":"internal.metrics.input.bytesRead","Update":1032,"Value":1032,"Internal":true,"Count Failed Values":true},{"ID":324,"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":351,"Executor Deserialize CPU Time":168452214,"Executor Run Time":1176,"Executor CPU Time":512640013,"Peak Execution Memory":0,"Result Size":2035,"JVM GC Time":13,"Result Serialization Time":2,"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":1032,"Records Read":20},"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$1 at FutureTask.java:264","Number of Tasks":1,"RDD Info":[{"RDD ID":10,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"0\",\"name\":\"BroadcastExchange\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[7],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":5,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"12\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[1],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":1,"Name":"FileScanRDD","Scope":"{\"id\":\"12\",\"name\":\"Scan csv \"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":7,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"4\",\"name\":\"WholeStageCodegen (1)\"}","Callsite":"$anonfun$withThreadLocalCaptured$1 at FutureTask.java:264","Parent IDs":[5],"Storage Level":{"Use Disk":false,"Use Memory":false,"Use Off Heap":false,"Deserialized":false,"Replication":1},"Barrier":false,"DeterministicLevel":"DETERMINATE","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[],"Details":"org.apache.spark.sql.execution.SQLExecution$.$anonfun$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":1784546384885,"Completion Time":1784546399150,"Accumulables":[{"ID":110,"Name":"number of output rows","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":241,"Name":"duration","Value":"901","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":242,"Name":"number of output rows","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":292,"Name":"internal.metrics.executorDeserializeTime","Value":351,"Internal":true,"Count Failed Values":true},{"ID":293,"Name":"internal.metrics.executorDeserializeCpuTime","Value":168452214,"Internal":true,"Count Failed Values":true},{"ID":294,"Name":"internal.metrics.executorRunTime","Value":1176,"Internal":true,"Count Failed Values":true},{"ID":295,"Name":"internal.metrics.executorCpuTime","Value":512640013,"Internal":true,"Count Failed Values":true},{"ID":296,"Name":"internal.metrics.resultSize","Value":2035,"Internal":true,"Count Failed Values":true},{"ID":297,"Name":"internal.metrics.jvmGCTime","Value":13,"Internal":true,"Count Failed Values":true},{"ID":298,"Name":"internal.metrics.resultSerializationTime","Value":2,"Internal":true,"Count Failed Values":true},{"ID":323,"Name":"internal.metrics.input.bytesRead","Value":1032,"Internal":true,"Count Failed Values":true},{"ID":324,"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":0,"Completion Time":1784546399150,"Job Result":{"Result":"JobSucceeded"}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[247,19],[246,25],[245,15427],[244,18],[243,1048616]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[240,21],[239,26],[238,15429],[237,20],[236,1048736]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[254,19],[253,27],[252,15423],[251,58],[250,2099184]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (60)\n+- == Current Plan ==\n Execute InsertIntoHadoopFsRelationCommand (33)\n +- WriteFiles (32)\n +- Sort (31)\n +- Exchange (30)\n +- Project (29)\n +- HashAggregate (28)\n +- Exchange (27)\n +- HashAggregate (26)\n +- HashAggregate (25)\n +- ShuffleQueryStage (24)\n +- Exchange (23)\n +- * HashAggregate (22)\n +- * Expand (21)\n +- * Project (20)\n +- * BroadcastHashJoin LeftOuter BuildRight (19)\n :- * Project (14)\n : +- * BroadcastHashJoin Inner BuildRight (13)\n : :- * Project (8)\n : : +- * BroadcastHashJoin Inner BuildLeft (7)\n : : :- BroadcastQueryStage (4), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n : : : +- BroadcastExchange (3)\n : : : +- * Filter (2)\n : : : +- Scan csv (1)\n : : +- * Filter (6)\n : : +- Scan csv (5)\n : +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=18)\n : +- BroadcastExchange (11)\n : +- * Filter (10)\n : +- Scan csv (9)\n +- BroadcastQueryStage (18), Statistics(sizeInBytes=2.0 MiB, rowCount=58)\n +- BroadcastExchange (17)\n +- * Filter (16)\n +- Scan csv (15)\n+- == Initial Plan ==\n Execute InsertIntoHadoopFsRelationCommand (59)\n +- WriteFiles (58)\n +- Sort (57)\n +- Exchange (56)\n +- Project (55)\n +- HashAggregate (54)\n +- Exchange (53)\n +- HashAggregate (52)\n +- HashAggregate (51)\n +- Exchange (50)\n +- HashAggregate (49)\n +- Expand (48)\n +- Project (47)\n +- BroadcastHashJoin LeftOuter BuildRight (46)\n :- Project (43)\n : +- BroadcastHashJoin Inner BuildRight (42)\n : :- Project (39)\n : : +- BroadcastHashJoin Inner BuildLeft (38)\n : : :- BroadcastExchange (35)\n : : : +- Filter (34)\n : : : +- Scan csv (1)\n : : +- Filter (37)\n : : +- Scan csv (36)\n : +- BroadcastExchange (41)\n : +- Filter (40)\n : +- Scan csv (9)\n +- BroadcastExchange (45)\n +- Filter (44)\n +- Scan csv (15)\n\n\n(1) Scan csv \nOutput [2]: [id#0L, name#1]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/users.csv]\nPushedFilters: [IsNotNull(id)]\nReadSchema: struct\n\n(2) Filter [codegen id : 1]\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(3) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]\n\n(4) BroadcastQueryStage\nOutput [2]: [id#0L, name#1]\nArguments: 0\n\n(5) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(6) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(7) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(8) Project [codegen id : 4]\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(9) Scan csv \nOutput [2]: [id#18L, course_id#19L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lessons.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct\n\n(10) Filter [codegen id : 2]\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(11) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]\n\n(12) BroadcastQueryStage\nOutput [2]: [id#18L, course_id#19L]\nArguments: 1\n\n(13) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(14) Project [codegen id : 4]\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(15) Scan csv \nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lesson_views.csv]\nPushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)]\nReadSchema: struct\n\n(16) Filter [codegen id : 3]\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(17) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]\n\n(18) BroadcastQueryStage\nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: 2\n\n(19) BroadcastHashJoin [codegen id : 4]\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(20) Project [codegen id : 4]\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(21) Expand [codegen id : 4]\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(22) HashAggregate [codegen id : 4]\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(23) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]\n\n(24) ShuffleQueryStage\nOutput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: 3\n\n(25) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(26) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(27) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=460]\n\n(28) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(29) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(30) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=463]\n\n(31) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(32) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(33) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(34) Filter\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(35) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]\n\n(36) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(37) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(38) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(39) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(40) Filter\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(41) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]\n\n(42) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(43) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(44) Filter\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(45) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]\n\n(46) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(47) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(48) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(49) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(50) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]\n\n(51) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(52) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(53) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]\n\n(54) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(55) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(56) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]\n\n(57) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(58) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(59) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(60) 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/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#116L ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=463]","children":[{"nodeName":"Project","simpleString":"Project [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)])","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=460]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[max(lv.viewed_at#178), min(lv.viewed_at#178)])","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)])","children":[{"nodeName":"Expand","simpleString":"Expand [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#18L, id#0L], [lesson_id#28L, user_id#27L], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#12L], [course_id#19L], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#0L], [user_id#11L], Inner, BuildLeft, false","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(id#0L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#0L,name#1] Batched: false, DataFilters: [isnotnull(id#0L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv], PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(id)]","DataFilters":"[isnotnull(id#0L)]"},"metrics":[{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of files read","accumulatorId":111,"metricType":"sum"},{"name":"metadata time","accumulatorId":112,"metricType":"timing"},{"name":"size of files read","accumulatorId":113,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":242,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":241,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":240,"metricType":"timing"},{"name":"time to build","accumulatorId":239,"metricType":"timing"},{"name":"time to collect","accumulatorId":238,"metricType":"timing"},{"name":"number of output rows","accumulatorId":237,"metricType":"sum"},{"name":"data size","accumulatorId":236,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]},{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#11L) AND isnotnull(course_id#12L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#11L,course_id#12L] Batched: false, DataFilters: [isnotnull(user_id#11L), isnotnull(course_id#12L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#11L), isnotnull(course_id#12L)]"},"metrics":[{"name":"number of output rows","accumulatorId":467,"metricType":"sum"},{"name":"number of files read","accumulatorId":468,"metricType":"sum"},{"name":"metadata time","accumulatorId":469,"metricType":"timing"},{"name":"size of files read","accumulatorId":470,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":466,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":465,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#19L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#18L,course_id#19L] Batched: false, DataFilters: [isnotnull(course_id#19L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#19L)]"},"metrics":[{"name":"number of output rows","accumulatorId":125,"metricType":"sum"},{"name":"number of files read","accumulatorId":126,"metricType":"sum"},{"name":"metadata time","accumulatorId":127,"metricType":"timing"},{"name":"size of files read","accumulatorId":128,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":249,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":248,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":247,"metricType":"timing"},{"name":"time to build","accumulatorId":246,"metricType":"timing"},{"name":"time to collect","accumulatorId":245,"metricType":"timing"},{"name":"number of output rows","accumulatorId":244,"metricType":"sum"},{"name":"data size","accumulatorId":243,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":464,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 2","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#27L,lesson_id#28L,viewed_at#29] Batched: false, DataFilters: [isnotnull(lesson_id#28L), isnotnull(user_id#27L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(lesson_id), IsNotNull(user_id)]","DataFilters":"[isnotnull(lesson_id#28L), isnotnull(user_id#27L)]"},"metrics":[{"name":"number of output rows","accumulatorId":135,"metricType":"sum"},{"name":"number of files read","accumulatorId":136,"metricType":"sum"},{"name":"metadata time","accumulatorId":137,"metricType":"timing"},{"name":"size of files read","accumulatorId":138,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":256,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":255,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":254,"metricType":"timing"},{"name":"time to build","accumulatorId":253,"metricType":"timing"},{"name":"time to collect","accumulatorId":252,"metricType":"timing"},{"name":"number of output rows","accumulatorId":251,"metricType":"sum"},{"name":"data size","accumulatorId":250,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":463,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":462,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":458,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":459,"metricType":"timing"},{"name":"peak memory","accumulatorId":457,"metricType":"size"},{"name":"number of output rows","accumulatorId":456,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":461,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":460,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":455,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":453,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":447,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":454,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":448,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":445,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":442,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":451,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":444,"metricType":"sum"},{"name":"records read","accumulatorId":441,"metricType":"sum"},{"name":"local bytes read","accumulatorId":439,"metricType":"size"},{"name":"fetch wait time","accumulatorId":440,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":437,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":443,"metricType":"sum"},{"name":"local blocks read","accumulatorId":436,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":446,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":435,"metricType":"sum"},{"name":"data size","accumulatorId":433,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":449,"metricType":"size"},{"name":"number of partitions","accumulatorId":434,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":450,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":438,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":452,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":429,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":430,"metricType":"timing"},{"name":"peak memory","accumulatorId":428,"metricType":"size"},{"name":"number of output rows","accumulatorId":427,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":432,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":431,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":423,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":424,"metricType":"timing"},{"name":"peak memory","accumulatorId":422,"metricType":"size"},{"name":"number of output rows","accumulatorId":421,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":426,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":425,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":419,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":413,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":420,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":414,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":411,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":408,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":417,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":410,"metricType":"sum"},{"name":"records read","accumulatorId":407,"metricType":"sum"},{"name":"local bytes read","accumulatorId":405,"metricType":"size"},{"name":"fetch wait time","accumulatorId":406,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":403,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":409,"metricType":"sum"},{"name":"local blocks read","accumulatorId":402,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":412,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":401,"metricType":"sum"},{"name":"data size","accumulatorId":399,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":415,"metricType":"size"},{"name":"number of partitions","accumulatorId":400,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":416,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":404,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":418,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":395,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":396,"metricType":"timing"},{"name":"peak memory","accumulatorId":394,"metricType":"size"},{"name":"number of output rows","accumulatorId":393,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":398,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":397,"metricType":"average"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":391,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":385,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":392,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":386,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":383,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":380,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":389,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":382,"metricType":"sum"},{"name":"records read","accumulatorId":379,"metricType":"sum"},{"name":"local bytes read","accumulatorId":377,"metricType":"size"},{"name":"fetch wait time","accumulatorId":378,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":375,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":381,"metricType":"sum"},{"name":"local blocks read","accumulatorId":374,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":384,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":373,"metricType":"sum"},{"name":"data size","accumulatorId":371,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":387,"metricType":"size"},{"name":"number of partitions","accumulatorId":372,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":388,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":376,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":390,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":368,"metricType":"timing"},{"name":"peak memory","accumulatorId":369,"metricType":"size"},{"name":"spill size","accumulatorId":370,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":366,"metricType":"timing"},{"name":"number of written files","accumulatorId":362,"metricType":"sum"},{"name":"job commit time","accumulatorId":367,"metricType":"timing"},{"name":"number of output rows","accumulatorId":364,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":365,"metricType":"sum"},{"name":"written output","accumulatorId":363,"metricType":"size"}]}],"metadata":{},"metrics":[]}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[468,1],[469,0],[470,1442]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[434,200]]} {"Event":"SparkListenerJobStart","Job ID":3,"Submission Time":1784546399444,"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\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"27\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":1784546399447,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"27\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":3,"Stage Attempt ID":0,"Task Info":{"Task ID":3,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546399470,"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":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":1784546399470,"Executor ID":"0","Host":"172.28.0.49","Locality":"PROCESS_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546399965,"Failed":false,"Killed":false,"Accumulables":[{"ID":433,"Name":"data size","Update":"24320","Value":"24320","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":452,"Name":"shuffle bytes written","Update":"18247","Value":"18247","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":453,"Name":"shuffle records written","Update":"304","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":454,"Name":"shuffle write time","Update":"23529202","Value":"23529202","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":455,"Name":"duration","Update":"206","Value":"206","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":456,"Name":"number of output rows","Update":"304","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":457,"Name":"peak memory","Update":"4456432","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":459,"Name":"time in aggregation build","Update":"55","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":460,"Name":"avg hash probes per key","Update":"10","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":462,"Name":"number of output rows","Update":"668","Value":"668","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":463,"Name":"number of output rows","Update":"167","Value":"167","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":464,"Name":"number of output rows","Update":"164","Value":"164","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":465,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":466,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":467,"Name":"number of output rows","Update":"45","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":471,"Name":"internal.metrics.executorDeserializeTime","Update":149,"Value":149,"Internal":true,"Count Failed Values":true},{"ID":472,"Name":"internal.metrics.executorDeserializeCpuTime","Update":118633279,"Value":118633279,"Internal":true,"Count Failed Values":true},{"ID":473,"Name":"internal.metrics.executorRunTime","Update":334,"Value":334,"Internal":true,"Count Failed Values":true},{"ID":474,"Name":"internal.metrics.executorCpuTime","Update":284852645,"Value":284852645,"Internal":true,"Count Failed Values":true},{"ID":475,"Name":"internal.metrics.resultSize","Update":4987,"Value":4987,"Internal":true,"Count Failed Values":true},{"ID":476,"Name":"internal.metrics.jvmGCTime","Update":13,"Value":13,"Internal":true,"Count Failed Values":true},{"ID":477,"Name":"internal.metrics.resultSerializationTime","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":480,"Name":"internal.metrics.peakExecutionMemory","Update":8654344,"Value":8654344,"Internal":true,"Count Failed Values":true},{"ID":499,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":18247,"Value":18247,"Internal":true,"Count Failed Values":true},{"ID":500,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":304,"Value":304,"Internal":true,"Count Failed Values":true},{"ID":501,"Name":"internal.metrics.shuffle.write.writeTime","Update":23529202,"Value":23529202,"Internal":true,"Count Failed Values":true},{"ID":502,"Name":"internal.metrics.input.bytesRead","Update":1442,"Value":1442,"Internal":true,"Count Failed Values":true},{"ID":503,"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":149,"Executor Deserialize CPU Time":118633279,"Executor Run Time":334,"Executor CPU Time":284852645,"Peak Execution Memory":8654344,"Result Size":4987,"JVM GC Time":13,"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":18247,"Shuffle Write Time":23529202,"Shuffle Records Written":304},"Input Metrics":{"Bytes Read":1442,"Records Read":45},"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\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":1784546399447,"Completion Time":1784546399966,"Accumulables":[{"ID":433,"Name":"data size","Value":"24320","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":452,"Name":"shuffle bytes written","Value":"18247","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":453,"Name":"shuffle records written","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":454,"Name":"shuffle write time","Value":"23529202","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":455,"Name":"duration","Value":"206","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":456,"Name":"number of output rows","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":457,"Name":"peak memory","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":459,"Name":"time in aggregation build","Value":"55","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":460,"Name":"avg hash probes per key","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":462,"Name":"number of output rows","Value":"668","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":463,"Name":"number of output rows","Value":"167","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":464,"Name":"number of output rows","Value":"164","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":465,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":466,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":467,"Name":"number of output rows","Value":"45","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":471,"Name":"internal.metrics.executorDeserializeTime","Value":149,"Internal":true,"Count Failed Values":true},{"ID":472,"Name":"internal.metrics.executorDeserializeCpuTime","Value":118633279,"Internal":true,"Count Failed Values":true},{"ID":473,"Name":"internal.metrics.executorRunTime","Value":334,"Internal":true,"Count Failed Values":true},{"ID":474,"Name":"internal.metrics.executorCpuTime","Value":284852645,"Internal":true,"Count Failed Values":true},{"ID":475,"Name":"internal.metrics.resultSize","Value":4987,"Internal":true,"Count Failed Values":true},{"ID":476,"Name":"internal.metrics.jvmGCTime","Value":13,"Internal":true,"Count Failed Values":true},{"ID":477,"Name":"internal.metrics.resultSerializationTime","Value":1,"Internal":true,"Count Failed Values":true},{"ID":480,"Name":"internal.metrics.peakExecutionMemory","Value":8654344,"Internal":true,"Count Failed Values":true},{"ID":499,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":18247,"Internal":true,"Count Failed Values":true},{"ID":500,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":304,"Internal":true,"Count Failed Values":true},{"ID":501,"Name":"internal.metrics.shuffle.write.writeTime","Value":23529202,"Internal":true,"Count Failed Values":true},{"ID":502,"Name":"internal.metrics.input.bytesRead","Value":1442,"Internal":true,"Count Failed Values":true},{"ID":503,"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":3,"Completion Time":1784546399969,"Job Result":{"Result":"JobSucceeded"}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (62)\n+- == Current Plan ==\n Execute InsertIntoHadoopFsRelationCommand (35)\n +- WriteFiles (34)\n +- Sort (33)\n +- Exchange (32)\n +- Project (31)\n +- HashAggregate (30)\n +- ShuffleQueryStage (29)\n +- Exchange (28)\n +- * HashAggregate (27)\n +- * HashAggregate (26)\n +- AQEShuffleRead (25)\n +- ShuffleQueryStage (24), Statistics(sizeInBytes=23.8 KiB, rowCount=304)\n +- Exchange (23)\n +- * HashAggregate (22)\n +- * Expand (21)\n +- * Project (20)\n +- * BroadcastHashJoin LeftOuter BuildRight (19)\n :- * Project (14)\n : +- * BroadcastHashJoin Inner BuildRight (13)\n : :- * Project (8)\n : : +- * BroadcastHashJoin Inner BuildLeft (7)\n : : :- BroadcastQueryStage (4), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n : : : +- BroadcastExchange (3)\n : : : +- * Filter (2)\n : : : +- Scan csv (1)\n : : +- * Filter (6)\n : : +- Scan csv (5)\n : +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=18)\n : +- BroadcastExchange (11)\n : +- * Filter (10)\n : +- Scan csv (9)\n +- BroadcastQueryStage (18), Statistics(sizeInBytes=2.0 MiB, rowCount=58)\n +- BroadcastExchange (17)\n +- * Filter (16)\n +- Scan csv (15)\n+- == Initial Plan ==\n Execute InsertIntoHadoopFsRelationCommand (61)\n +- WriteFiles (60)\n +- Sort (59)\n +- Exchange (58)\n +- Project (57)\n +- HashAggregate (56)\n +- Exchange (55)\n +- HashAggregate (54)\n +- HashAggregate (53)\n +- Exchange (52)\n +- HashAggregate (51)\n +- Expand (50)\n +- Project (49)\n +- BroadcastHashJoin LeftOuter BuildRight (48)\n :- Project (45)\n : +- BroadcastHashJoin Inner BuildRight (44)\n : :- Project (41)\n : : +- BroadcastHashJoin Inner BuildLeft (40)\n : : :- BroadcastExchange (37)\n : : : +- Filter (36)\n : : : +- Scan csv (1)\n : : +- Filter (39)\n : : +- Scan csv (38)\n : +- BroadcastExchange (43)\n : +- Filter (42)\n : +- Scan csv (9)\n +- BroadcastExchange (47)\n +- Filter (46)\n +- Scan csv (15)\n\n\n(1) Scan csv \nOutput [2]: [id#0L, name#1]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/users.csv]\nPushedFilters: [IsNotNull(id)]\nReadSchema: struct\n\n(2) Filter [codegen id : 1]\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(3) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]\n\n(4) BroadcastQueryStage\nOutput [2]: [id#0L, name#1]\nArguments: 0\n\n(5) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(6) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(7) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(8) Project [codegen id : 4]\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(9) Scan csv \nOutput [2]: [id#18L, course_id#19L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lessons.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct\n\n(10) Filter [codegen id : 2]\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(11) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]\n\n(12) BroadcastQueryStage\nOutput [2]: [id#18L, course_id#19L]\nArguments: 1\n\n(13) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(14) Project [codegen id : 4]\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(15) Scan csv \nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lesson_views.csv]\nPushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)]\nReadSchema: struct\n\n(16) Filter [codegen id : 3]\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(17) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]\n\n(18) BroadcastQueryStage\nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: 2\n\n(19) BroadcastHashJoin [codegen id : 4]\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(20) Project [codegen id : 4]\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(21) Expand [codegen id : 4]\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(22) HashAggregate [codegen id : 4]\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(23) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]\n\n(24) ShuffleQueryStage\nOutput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: 3\n\n(25) AQEShuffleRead\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: coalesced\n\n(26) HashAggregate [codegen id : 5]\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(27) HashAggregate [codegen id : 5]\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(28) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=513]\n\n(29) ShuffleQueryStage\nOutput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: 4\n\n(30) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(31) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(32) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=526]\n\n(33) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(34) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(35) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(36) Filter\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(37) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]\n\n(38) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(39) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(40) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(41) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(42) Filter\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(43) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]\n\n(44) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(45) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(46) Filter\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(47) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]\n\n(48) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(49) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(50) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(51) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(52) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]\n\n(53) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(54) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(55) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]\n\n(56) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(57) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(58) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]\n\n(59) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(60) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(61) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(62) 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/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#116L ASC NULLS FIRST], true, 0","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=526]","children":[{"nodeName":"Project","simpleString":"Project [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)])","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 4","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=513]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[max(lv.viewed_at#178), min(lv.viewed_at#178)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)])","children":[{"nodeName":"Expand","simpleString":"Expand [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#18L, id#0L], [lesson_id#28L, user_id#27L], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#12L], [course_id#19L], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#0L], [user_id#11L], Inner, BuildLeft, false","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(id#0L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#0L,name#1] Batched: false, DataFilters: [isnotnull(id#0L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv], PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(id)]","DataFilters":"[isnotnull(id#0L)]"},"metrics":[{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of files read","accumulatorId":111,"metricType":"sum"},{"name":"metadata time","accumulatorId":112,"metricType":"timing"},{"name":"size of files read","accumulatorId":113,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":242,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":241,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":240,"metricType":"timing"},{"name":"time to build","accumulatorId":239,"metricType":"timing"},{"name":"time to collect","accumulatorId":238,"metricType":"timing"},{"name":"number of output rows","accumulatorId":237,"metricType":"sum"},{"name":"data size","accumulatorId":236,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]},{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#11L) AND isnotnull(course_id#12L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#11L,course_id#12L] Batched: false, DataFilters: [isnotnull(user_id#11L), isnotnull(course_id#12L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#11L), isnotnull(course_id#12L)]"},"metrics":[{"name":"number of output rows","accumulatorId":467,"metricType":"sum"},{"name":"number of files read","accumulatorId":468,"metricType":"sum"},{"name":"metadata time","accumulatorId":469,"metricType":"timing"},{"name":"size of files read","accumulatorId":470,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":466,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":465,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#19L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#18L,course_id#19L] Batched: false, DataFilters: [isnotnull(course_id#19L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#19L)]"},"metrics":[{"name":"number of output rows","accumulatorId":125,"metricType":"sum"},{"name":"number of files read","accumulatorId":126,"metricType":"sum"},{"name":"metadata time","accumulatorId":127,"metricType":"timing"},{"name":"size of files read","accumulatorId":128,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":249,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":248,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":247,"metricType":"timing"},{"name":"time to build","accumulatorId":246,"metricType":"timing"},{"name":"time to collect","accumulatorId":245,"metricType":"timing"},{"name":"number of output rows","accumulatorId":244,"metricType":"sum"},{"name":"data size","accumulatorId":243,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":464,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 2","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#27L,lesson_id#28L,viewed_at#29] Batched: false, DataFilters: [isnotnull(lesson_id#28L), isnotnull(user_id#27L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(lesson_id), IsNotNull(user_id)]","DataFilters":"[isnotnull(lesson_id#28L), isnotnull(user_id#27L)]"},"metrics":[{"name":"number of output rows","accumulatorId":135,"metricType":"sum"},{"name":"number of files read","accumulatorId":136,"metricType":"sum"},{"name":"metadata time","accumulatorId":137,"metricType":"timing"},{"name":"size of files read","accumulatorId":138,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":256,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":255,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":254,"metricType":"timing"},{"name":"time to build","accumulatorId":253,"metricType":"timing"},{"name":"time to collect","accumulatorId":252,"metricType":"timing"},{"name":"number of output rows","accumulatorId":251,"metricType":"sum"},{"name":"data size","accumulatorId":250,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":463,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":462,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":458,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":459,"metricType":"timing"},{"name":"peak memory","accumulatorId":457,"metricType":"size"},{"name":"number of output rows","accumulatorId":456,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":461,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":460,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":455,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":453,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":447,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":454,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":448,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":445,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":442,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":451,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":444,"metricType":"sum"},{"name":"records read","accumulatorId":441,"metricType":"sum"},{"name":"local bytes read","accumulatorId":439,"metricType":"size"},{"name":"fetch wait time","accumulatorId":440,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":437,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":443,"metricType":"sum"},{"name":"local blocks read","accumulatorId":436,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":446,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":435,"metricType":"sum"},{"name":"data size","accumulatorId":433,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":449,"metricType":"size"},{"name":"number of partitions","accumulatorId":434,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":450,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":438,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":452,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":578,"metricType":"sum"},{"name":"partition data size","accumulatorId":579,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":580,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":574,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":575,"metricType":"timing"},{"name":"peak memory","accumulatorId":573,"metricType":"size"},{"name":"number of output rows","accumulatorId":572,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":577,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":576,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":568,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":569,"metricType":"timing"},{"name":"peak memory","accumulatorId":567,"metricType":"size"},{"name":"number of output rows","accumulatorId":566,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":571,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":570,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":565,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":563,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":557,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":564,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":558,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":555,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":552,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":561,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":554,"metricType":"sum"},{"name":"records read","accumulatorId":551,"metricType":"sum"},{"name":"local bytes read","accumulatorId":549,"metricType":"size"},{"name":"fetch wait time","accumulatorId":550,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":547,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":553,"metricType":"sum"},{"name":"local blocks read","accumulatorId":546,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":556,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":545,"metricType":"sum"},{"name":"data size","accumulatorId":543,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":559,"metricType":"size"},{"name":"number of partitions","accumulatorId":544,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":560,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":548,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":562,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":539,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":540,"metricType":"timing"},{"name":"peak memory","accumulatorId":538,"metricType":"size"},{"name":"number of output rows","accumulatorId":537,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":542,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":541,"metricType":"average"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":535,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":529,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":536,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":530,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":527,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":524,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":533,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":526,"metricType":"sum"},{"name":"records read","accumulatorId":523,"metricType":"sum"},{"name":"local bytes read","accumulatorId":521,"metricType":"size"},{"name":"fetch wait time","accumulatorId":522,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":519,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":525,"metricType":"sum"},{"name":"local blocks read","accumulatorId":518,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":528,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":517,"metricType":"sum"},{"name":"data size","accumulatorId":515,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":531,"metricType":"size"},{"name":"number of partitions","accumulatorId":516,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":532,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":520,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":534,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":512,"metricType":"timing"},{"name":"peak memory","accumulatorId":513,"metricType":"size"},{"name":"spill size","accumulatorId":514,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":510,"metricType":"timing"},{"name":"number of written files","accumulatorId":506,"metricType":"sum"},{"name":"job commit time","accumulatorId":511,"metricType":"timing"},{"name":"number of output rows","accumulatorId":508,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":509,"metricType":"sum"},{"name":"written output","accumulatorId":507,"metricType":"size"}]}],"metadata":{},"metrics":[]}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[578,1],[580,1],[579,18972]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[544,200]]} {"Event":"SparkListenerJobStart","Job ID":4,"Submission Time":1784546400077,"Stage Infos":[{"Stage ID":5,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"46\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"51\",\"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":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"47\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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}],"Parent IDs":[4],"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":4,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"46\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":5,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"46\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"51\",\"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":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"47\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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}],"Parent IDs":[4],"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":1784546400087,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"46\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":5,"Stage Attempt ID":0,"Task Info":{"Task ID":4,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400100,"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":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":4,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400100,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546400337,"Failed":false,"Killed":false,"Accumulables":[{"ID":436,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":439,"Name":"local bytes read","Update":"18247","Value":"18247","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":440,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":441,"Name":"records read","Update":"304","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":543,"Name":"data size","Update":"1760","Value":"1760","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":562,"Name":"shuffle bytes written","Update":"1782","Value":"1782","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":563,"Name":"shuffle records written","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":564,"Name":"shuffle write time","Update":"4576593","Value":"4576593","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":565,"Name":"duration","Update":"53","Value":"53","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":566,"Name":"number of output rows","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":567,"Name":"peak memory","Update":"262144","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":569,"Name":"time in aggregation build","Update":"13","Value":"13","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":572,"Name":"number of output rows","Update":"304","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":573,"Name":"peak memory","Update":"4456432","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":575,"Name":"time in aggregation build","Update":"8","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":576,"Name":"avg hash probes per key","Update":"10","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":581,"Name":"internal.metrics.executorDeserializeTime","Update":85,"Value":85,"Internal":true,"Count Failed Values":true},{"ID":582,"Name":"internal.metrics.executorDeserializeCpuTime","Update":37109412,"Value":37109412,"Internal":true,"Count Failed Values":true},{"ID":583,"Name":"internal.metrics.executorRunTime","Update":141,"Value":141,"Internal":true,"Count Failed Values":true},{"ID":584,"Name":"internal.metrics.executorCpuTime","Update":124624672,"Value":124624672,"Internal":true,"Count Failed Values":true},{"ID":585,"Name":"internal.metrics.resultSize","Update":7976,"Value":7976,"Internal":true,"Count Failed Values":true},{"ID":590,"Name":"internal.metrics.peakExecutionMemory","Update":4718576,"Value":4718576,"Internal":true,"Count Failed Values":true},{"ID":592,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":593,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":594,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":595,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":596,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":18247,"Value":18247,"Internal":true,"Count Failed Values":true},{"ID":597,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":598,"Name":"internal.metrics.shuffle.read.recordsRead","Update":304,"Value":304,"Internal":true,"Count Failed Values":true},{"ID":599,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":600,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":601,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":602,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":603,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":604,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":605,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":606,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":607,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":608,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":609,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":1782,"Value":1782,"Internal":true,"Count Failed Values":true},{"ID":610,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":20,"Value":20,"Internal":true,"Count Failed Values":true},{"ID":611,"Name":"internal.metrics.shuffle.write.writeTime","Update":4576593,"Value":4576593,"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":85,"Executor Deserialize CPU Time":37109412,"Executor Run Time":141,"Executor CPU Time":124624672,"Peak Execution Memory":4718576,"Result Size":7976,"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":18247,"Total Records Read":304,"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":1782,"Shuffle Write Time":4576593,"Shuffle Records Written":20},"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":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"46\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"51\",\"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":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"47\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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}],"Parent IDs":[4],"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":1784546400087,"Completion Time":1784546400339,"Accumulables":[{"ID":436,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":439,"Name":"local bytes read","Value":"18247","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":440,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":441,"Name":"records read","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":543,"Name":"data size","Value":"1760","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":562,"Name":"shuffle bytes written","Value":"1782","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":563,"Name":"shuffle records written","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":564,"Name":"shuffle write time","Value":"4576593","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":565,"Name":"duration","Value":"53","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":566,"Name":"number of output rows","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":567,"Name":"peak memory","Value":"262144","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":569,"Name":"time in aggregation build","Value":"13","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":572,"Name":"number of output rows","Value":"304","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":573,"Name":"peak memory","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":575,"Name":"time in aggregation build","Value":"8","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":576,"Name":"avg hash probes per key","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":581,"Name":"internal.metrics.executorDeserializeTime","Value":85,"Internal":true,"Count Failed Values":true},{"ID":582,"Name":"internal.metrics.executorDeserializeCpuTime","Value":37109412,"Internal":true,"Count Failed Values":true},{"ID":583,"Name":"internal.metrics.executorRunTime","Value":141,"Internal":true,"Count Failed Values":true},{"ID":584,"Name":"internal.metrics.executorCpuTime","Value":124624672,"Internal":true,"Count Failed Values":true},{"ID":585,"Name":"internal.metrics.resultSize","Value":7976,"Internal":true,"Count Failed Values":true},{"ID":590,"Name":"internal.metrics.peakExecutionMemory","Value":4718576,"Internal":true,"Count Failed Values":true},{"ID":592,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":593,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":594,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":595,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":596,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":18247,"Internal":true,"Count Failed Values":true},{"ID":597,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":598,"Name":"internal.metrics.shuffle.read.recordsRead","Value":304,"Internal":true,"Count Failed Values":true},{"ID":599,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":600,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":601,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":602,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":603,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":604,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":605,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":606,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":607,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":608,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":609,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":1782,"Internal":true,"Count Failed Values":true},{"ID":610,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":20,"Internal":true,"Count Failed Values":true},{"ID":611,"Name":"internal.metrics.shuffle.write.writeTime","Value":4576593,"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":1784546400341,"Job Result":{"Result":"JobSucceeded"}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (64)\n+- == Current Plan ==\n Execute InsertIntoHadoopFsRelationCommand (37)\n +- WriteFiles (36)\n +- Sort (35)\n +- ShuffleQueryStage (34)\n +- Exchange (33)\n +- * Project (32)\n +- * HashAggregate (31)\n +- AQEShuffleRead (30)\n +- ShuffleQueryStage (29), Statistics(sizeInBytes=1760.0 B, rowCount=20)\n +- Exchange (28)\n +- * HashAggregate (27)\n +- * HashAggregate (26)\n +- AQEShuffleRead (25)\n +- ShuffleQueryStage (24), Statistics(sizeInBytes=23.8 KiB, rowCount=304)\n +- Exchange (23)\n +- * HashAggregate (22)\n +- * Expand (21)\n +- * Project (20)\n +- * BroadcastHashJoin LeftOuter BuildRight (19)\n :- * Project (14)\n : +- * BroadcastHashJoin Inner BuildRight (13)\n : :- * Project (8)\n : : +- * BroadcastHashJoin Inner BuildLeft (7)\n : : :- BroadcastQueryStage (4), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n : : : +- BroadcastExchange (3)\n : : : +- * Filter (2)\n : : : +- Scan csv (1)\n : : +- * Filter (6)\n : : +- Scan csv (5)\n : +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=18)\n : +- BroadcastExchange (11)\n : +- * Filter (10)\n : +- Scan csv (9)\n +- BroadcastQueryStage (18), Statistics(sizeInBytes=2.0 MiB, rowCount=58)\n +- BroadcastExchange (17)\n +- * Filter (16)\n +- Scan csv (15)\n+- == Initial Plan ==\n Execute InsertIntoHadoopFsRelationCommand (63)\n +- WriteFiles (62)\n +- Sort (61)\n +- Exchange (60)\n +- Project (59)\n +- HashAggregate (58)\n +- Exchange (57)\n +- HashAggregate (56)\n +- HashAggregate (55)\n +- Exchange (54)\n +- HashAggregate (53)\n +- Expand (52)\n +- Project (51)\n +- BroadcastHashJoin LeftOuter BuildRight (50)\n :- Project (47)\n : +- BroadcastHashJoin Inner BuildRight (46)\n : :- Project (43)\n : : +- BroadcastHashJoin Inner BuildLeft (42)\n : : :- BroadcastExchange (39)\n : : : +- Filter (38)\n : : : +- Scan csv (1)\n : : +- Filter (41)\n : : +- Scan csv (40)\n : +- BroadcastExchange (45)\n : +- Filter (44)\n : +- Scan csv (9)\n +- BroadcastExchange (49)\n +- Filter (48)\n +- Scan csv (15)\n\n\n(1) Scan csv \nOutput [2]: [id#0L, name#1]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/users.csv]\nPushedFilters: [IsNotNull(id)]\nReadSchema: struct\n\n(2) Filter [codegen id : 1]\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(3) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]\n\n(4) BroadcastQueryStage\nOutput [2]: [id#0L, name#1]\nArguments: 0\n\n(5) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(6) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(7) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(8) Project [codegen id : 4]\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(9) Scan csv \nOutput [2]: [id#18L, course_id#19L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lessons.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct\n\n(10) Filter [codegen id : 2]\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(11) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]\n\n(12) BroadcastQueryStage\nOutput [2]: [id#18L, course_id#19L]\nArguments: 1\n\n(13) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(14) Project [codegen id : 4]\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(15) Scan csv \nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lesson_views.csv]\nPushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)]\nReadSchema: struct\n\n(16) Filter [codegen id : 3]\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(17) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]\n\n(18) BroadcastQueryStage\nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: 2\n\n(19) BroadcastHashJoin [codegen id : 4]\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(20) Project [codegen id : 4]\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(21) Expand [codegen id : 4]\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(22) HashAggregate [codegen id : 4]\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(23) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]\n\n(24) ShuffleQueryStage\nOutput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: 3\n\n(25) AQEShuffleRead\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: coalesced\n\n(26) HashAggregate [codegen id : 5]\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(27) HashAggregate [codegen id : 5]\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(28) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=513]\n\n(29) ShuffleQueryStage\nOutput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: 4\n\n(30) AQEShuffleRead\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: coalesced\n\n(31) HashAggregate [codegen id : 6]\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(32) Project [codegen id : 6]\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(33) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=561]\n\n(34) ShuffleQueryStage\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: 5\n\n(35) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(36) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(37) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(38) Filter\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(39) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]\n\n(40) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(41) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(42) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(43) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(44) Filter\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(45) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]\n\n(46) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(47) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(48) Filter\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(49) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]\n\n(50) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(51) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(52) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(53) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(54) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]\n\n(55) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(56) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(57) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]\n\n(58) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(59) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(60) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]\n\n(61) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(62) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(63) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(64) 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/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#116L ASC NULLS FIRST], true, 0","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 5","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=561]","children":[{"nodeName":"WholeStageCodegen (6)","simpleString":"WholeStageCodegen (6)","children":[{"nodeName":"Project","simpleString":"Project [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 4","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=513]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[max(lv.viewed_at#178), min(lv.viewed_at#178)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)])","children":[{"nodeName":"Expand","simpleString":"Expand [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#18L, id#0L], [lesson_id#28L, user_id#27L], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#12L], [course_id#19L], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#0L], [user_id#11L], Inner, BuildLeft, false","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(id#0L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#0L,name#1] Batched: false, DataFilters: [isnotnull(id#0L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv], PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(id)]","DataFilters":"[isnotnull(id#0L)]"},"metrics":[{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of files read","accumulatorId":111,"metricType":"sum"},{"name":"metadata time","accumulatorId":112,"metricType":"timing"},{"name":"size of files read","accumulatorId":113,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":242,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":241,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":240,"metricType":"timing"},{"name":"time to build","accumulatorId":239,"metricType":"timing"},{"name":"time to collect","accumulatorId":238,"metricType":"timing"},{"name":"number of output rows","accumulatorId":237,"metricType":"sum"},{"name":"data size","accumulatorId":236,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]},{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#11L) AND isnotnull(course_id#12L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#11L,course_id#12L] Batched: false, DataFilters: [isnotnull(user_id#11L), isnotnull(course_id#12L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#11L), isnotnull(course_id#12L)]"},"metrics":[{"name":"number of output rows","accumulatorId":467,"metricType":"sum"},{"name":"number of files read","accumulatorId":468,"metricType":"sum"},{"name":"metadata time","accumulatorId":469,"metricType":"timing"},{"name":"size of files read","accumulatorId":470,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":466,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":465,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#19L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#18L,course_id#19L] Batched: false, DataFilters: [isnotnull(course_id#19L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#19L)]"},"metrics":[{"name":"number of output rows","accumulatorId":125,"metricType":"sum"},{"name":"number of files read","accumulatorId":126,"metricType":"sum"},{"name":"metadata time","accumulatorId":127,"metricType":"timing"},{"name":"size of files read","accumulatorId":128,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":249,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":248,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":247,"metricType":"timing"},{"name":"time to build","accumulatorId":246,"metricType":"timing"},{"name":"time to collect","accumulatorId":245,"metricType":"timing"},{"name":"number of output rows","accumulatorId":244,"metricType":"sum"},{"name":"data size","accumulatorId":243,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":464,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 2","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#27L,lesson_id#28L,viewed_at#29] Batched: false, DataFilters: [isnotnull(lesson_id#28L), isnotnull(user_id#27L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(lesson_id), IsNotNull(user_id)]","DataFilters":"[isnotnull(lesson_id#28L), isnotnull(user_id#27L)]"},"metrics":[{"name":"number of output rows","accumulatorId":135,"metricType":"sum"},{"name":"number of files read","accumulatorId":136,"metricType":"sum"},{"name":"metadata time","accumulatorId":137,"metricType":"timing"},{"name":"size of files read","accumulatorId":138,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":256,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":255,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":254,"metricType":"timing"},{"name":"time to build","accumulatorId":253,"metricType":"timing"},{"name":"time to collect","accumulatorId":252,"metricType":"timing"},{"name":"number of output rows","accumulatorId":251,"metricType":"sum"},{"name":"data size","accumulatorId":250,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":463,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":462,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":458,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":459,"metricType":"timing"},{"name":"peak memory","accumulatorId":457,"metricType":"size"},{"name":"number of output rows","accumulatorId":456,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":461,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":460,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":455,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":453,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":447,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":454,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":448,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":445,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":442,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":451,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":444,"metricType":"sum"},{"name":"records read","accumulatorId":441,"metricType":"sum"},{"name":"local bytes read","accumulatorId":439,"metricType":"size"},{"name":"fetch wait time","accumulatorId":440,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":437,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":443,"metricType":"sum"},{"name":"local blocks read","accumulatorId":436,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":446,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":435,"metricType":"sum"},{"name":"data size","accumulatorId":433,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":449,"metricType":"size"},{"name":"number of partitions","accumulatorId":434,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":450,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":438,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":452,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":578,"metricType":"sum"},{"name":"partition data size","accumulatorId":579,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":580,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":574,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":575,"metricType":"timing"},{"name":"peak memory","accumulatorId":573,"metricType":"size"},{"name":"number of output rows","accumulatorId":572,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":577,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":576,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":568,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":569,"metricType":"timing"},{"name":"peak memory","accumulatorId":567,"metricType":"size"},{"name":"number of output rows","accumulatorId":566,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":571,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":570,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":565,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":563,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":557,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":564,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":558,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":555,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":552,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":561,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":554,"metricType":"sum"},{"name":"records read","accumulatorId":551,"metricType":"sum"},{"name":"local bytes read","accumulatorId":549,"metricType":"size"},{"name":"fetch wait time","accumulatorId":550,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":547,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":553,"metricType":"sum"},{"name":"local blocks read","accumulatorId":546,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":556,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":545,"metricType":"sum"},{"name":"data size","accumulatorId":543,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":559,"metricType":"size"},{"name":"number of partitions","accumulatorId":544,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":560,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":548,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":562,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":654,"metricType":"sum"},{"name":"partition data size","accumulatorId":655,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":656,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":650,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":651,"metricType":"timing"},{"name":"peak memory","accumulatorId":649,"metricType":"size"},{"name":"number of output rows","accumulatorId":648,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":653,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":652,"metricType":"average"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":647,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":645,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":639,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":646,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":640,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":637,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":634,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":643,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":636,"metricType":"sum"},{"name":"records read","accumulatorId":633,"metricType":"sum"},{"name":"local bytes read","accumulatorId":631,"metricType":"size"},{"name":"fetch wait time","accumulatorId":632,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":629,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":635,"metricType":"sum"},{"name":"local blocks read","accumulatorId":628,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":638,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":627,"metricType":"sum"},{"name":"data size","accumulatorId":625,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":641,"metricType":"size"},{"name":"number of partitions","accumulatorId":626,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":642,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":630,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":644,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":622,"metricType":"timing"},{"name":"peak memory","accumulatorId":623,"metricType":"size"},{"name":"spill size","accumulatorId":624,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":620,"metricType":"timing"},{"name":"number of written files","accumulatorId":616,"metricType":"sum"},{"name":"job commit time","accumulatorId":621,"metricType":"timing"},{"name":"number of output rows","accumulatorId":618,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":619,"metricType":"sum"},{"name":"written output","accumulatorId":617,"metricType":"size"}]}],"metadata":{},"metrics":[]}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[654,1],[656,1],[655,1841]]} {"Event":"SparkListenerJobStart","Job ID":5,"Submission Time":1784546400431,"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\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"46\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"51\",\"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":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"47\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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}],"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 ID":8,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":23,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":22,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[7],"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":[6,7,8],"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"52\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":8,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":23,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":22,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[7],"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":1784546400433,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"52\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":8,"Stage Attempt ID":0,"Task Info":{"Task ID":5,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400446,"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":8,"Stage Attempt ID":0,"Task Type":"ResultTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":5,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400446,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546400561,"Failed":false,"Killed":false,"Accumulables":[{"ID":546,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":549,"Name":"local bytes read","Update":"1782","Value":"1782","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":550,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":551,"Name":"records read","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":647,"Name":"duration","Update":"18","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":648,"Name":"number of output rows","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":649,"Name":"peak memory","Update":"4456432","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":651,"Name":"time in aggregation build","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":652,"Name":"avg hash probes per key","Update":"10","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":657,"Name":"internal.metrics.executorDeserializeTime","Update":55,"Value":55,"Internal":true,"Count Failed Values":true},{"ID":658,"Name":"internal.metrics.executorDeserializeCpuTime","Update":47937131,"Value":47937131,"Internal":true,"Count Failed Values":true},{"ID":659,"Name":"internal.metrics.executorRunTime","Update":48,"Value":48,"Internal":true,"Count Failed Values":true},{"ID":660,"Name":"internal.metrics.executorCpuTime","Update":42106972,"Value":42106972,"Internal":true,"Count Failed Values":true},{"ID":661,"Name":"internal.metrics.resultSize","Update":10032,"Value":10032,"Internal":true,"Count Failed Values":true},{"ID":666,"Name":"internal.metrics.peakExecutionMemory","Update":4456432,"Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":668,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":669,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":670,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":671,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":672,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":1782,"Value":1782,"Internal":true,"Count Failed Values":true},{"ID":673,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":674,"Name":"internal.metrics.shuffle.read.recordsRead","Update":20,"Value":20,"Internal":true,"Count Failed Values":true},{"ID":675,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":676,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":677,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":678,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":679,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":680,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":681,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":682,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":683,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":684,"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":55,"Executor Deserialize CPU Time":47937131,"Executor Run Time":48,"Executor CPU Time":42106972,"Peak Execution Memory":4456432,"Result Size":10032,"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":1782,"Total Records Read":20,"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":8,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":23,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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},{"RDD ID":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":22,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":21,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[7],"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":1784546400433,"Completion Time":1784546400563,"Accumulables":[{"ID":546,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":549,"Name":"local bytes read","Value":"1782","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":550,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":551,"Name":"records read","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":647,"Name":"duration","Value":"18","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":648,"Name":"number of output rows","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":649,"Name":"peak memory","Value":"4456432","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":651,"Name":"time in aggregation build","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":652,"Name":"avg hash probes per key","Value":"10","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":657,"Name":"internal.metrics.executorDeserializeTime","Value":55,"Internal":true,"Count Failed Values":true},{"ID":658,"Name":"internal.metrics.executorDeserializeCpuTime","Value":47937131,"Internal":true,"Count Failed Values":true},{"ID":659,"Name":"internal.metrics.executorRunTime","Value":48,"Internal":true,"Count Failed Values":true},{"ID":660,"Name":"internal.metrics.executorCpuTime","Value":42106972,"Internal":true,"Count Failed Values":true},{"ID":661,"Name":"internal.metrics.resultSize","Value":10032,"Internal":true,"Count Failed Values":true},{"ID":666,"Name":"internal.metrics.peakExecutionMemory","Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":668,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":669,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":670,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":671,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":672,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":1782,"Internal":true,"Count Failed Values":true},{"ID":673,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":674,"Name":"internal.metrics.shuffle.read.recordsRead","Value":20,"Internal":true,"Count Failed Values":true},{"ID":675,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":676,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":677,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":678,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":679,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":680,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":681,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":682,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":683,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":684,"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":5,"Completion Time":1784546400563,"Job Result":{"Result":"JobSucceeded"}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[626,20]]} {"Event":"SparkListenerJobStart","Job ID":6,"Submission Time":1784546400573,"Stage Infos":[{"Stage ID":9,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":10,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"46\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"51\",\"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":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"47\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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}],"Parent IDs":[9],"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":11,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[10],"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":[9,10,11],"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"52\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[10],"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":1784546400575,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","spark.rdd.scope":"{\"id\":\"52\",\"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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":6,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400591,"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":11,"Stage Attempt ID":0,"Task Type":"ShuffleMapTask","Task End Reason":{"Reason":"Success"},"Task Info":{"Task ID":6,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400591,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546400658,"Failed":false,"Killed":false,"Accumulables":[{"ID":546,"Name":"local blocks read","Update":"1","Value":"2","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":549,"Name":"local bytes read","Update":"1782","Value":"3564","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":550,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":551,"Name":"records read","Update":"20","Value":"40","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":625,"Name":"data size","Update":"1440","Value":"1440","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":644,"Name":"shuffle bytes written","Update":"1831","Value":"1831","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":645,"Name":"shuffle records written","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":646,"Name":"shuffle write time","Update":"2055785","Value":"2055785","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":647,"Name":"duration","Update":"13","Value":"31","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":648,"Name":"number of output rows","Update":"20","Value":"40","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":649,"Name":"peak memory","Update":"4456432","Value":"8912864","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":651,"Name":"time in aggregation build","Update":"0","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":652,"Name":"avg hash probes per key","Update":"10","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":692,"Name":"internal.metrics.executorDeserializeTime","Update":36,"Value":36,"Internal":true,"Count Failed Values":true},{"ID":693,"Name":"internal.metrics.executorDeserializeCpuTime","Update":29534652,"Value":29534652,"Internal":true,"Count Failed Values":true},{"ID":694,"Name":"internal.metrics.executorRunTime","Update":19,"Value":19,"Internal":true,"Count Failed Values":true},{"ID":695,"Name":"internal.metrics.executorCpuTime","Update":18772440,"Value":18772440,"Internal":true,"Count Failed Values":true},{"ID":696,"Name":"internal.metrics.resultSize","Update":9417,"Value":9417,"Internal":true,"Count Failed Values":true},{"ID":701,"Name":"internal.metrics.peakExecutionMemory","Update":4456432,"Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":703,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":704,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":705,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":706,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":707,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":1782,"Value":1782,"Internal":true,"Count Failed Values":true},{"ID":708,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":709,"Name":"internal.metrics.shuffle.read.recordsRead","Update":20,"Value":20,"Internal":true,"Count Failed Values":true},{"ID":710,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":711,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":712,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":713,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":714,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":715,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":716,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":717,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":718,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":719,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":720,"Name":"internal.metrics.shuffle.write.bytesWritten","Update":1831,"Value":1831,"Internal":true,"Count Failed Values":true},{"ID":721,"Name":"internal.metrics.shuffle.write.recordsWritten","Update":20,"Value":20,"Internal":true,"Count Failed Values":true},{"ID":722,"Name":"internal.metrics.shuffle.write.writeTime","Update":2055785,"Value":2055785,"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":36,"Executor Deserialize CPU Time":29534652,"Executor Run Time":19,"Executor CPU Time":18772440,"Peak Execution Memory":4456432,"Result Size":9417,"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":1782,"Total Records Read":20,"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":1831,"Shuffle Write Time":2055785,"Shuffle Records Written":20},"Input Metrics":{"Bytes Read":0,"Records Read":0},"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":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[10],"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":1784546400575,"Completion Time":1784546400660,"Accumulables":[{"ID":546,"Name":"local blocks read","Value":"2","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":549,"Name":"local bytes read","Value":"3564","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":550,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":551,"Name":"records read","Value":"40","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":625,"Name":"data size","Value":"1440","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":644,"Name":"shuffle bytes written","Value":"1831","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":645,"Name":"shuffle records written","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":646,"Name":"shuffle write time","Value":"2055785","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":647,"Name":"duration","Value":"31","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":648,"Name":"number of output rows","Value":"40","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":649,"Name":"peak memory","Value":"8912864","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":651,"Name":"time in aggregation build","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":652,"Name":"avg hash probes per key","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":692,"Name":"internal.metrics.executorDeserializeTime","Value":36,"Internal":true,"Count Failed Values":true},{"ID":693,"Name":"internal.metrics.executorDeserializeCpuTime","Value":29534652,"Internal":true,"Count Failed Values":true},{"ID":694,"Name":"internal.metrics.executorRunTime","Value":19,"Internal":true,"Count Failed Values":true},{"ID":695,"Name":"internal.metrics.executorCpuTime","Value":18772440,"Internal":true,"Count Failed Values":true},{"ID":696,"Name":"internal.metrics.resultSize","Value":9417,"Internal":true,"Count Failed Values":true},{"ID":701,"Name":"internal.metrics.peakExecutionMemory","Value":4456432,"Internal":true,"Count Failed Values":true},{"ID":703,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":704,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":705,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":706,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":707,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":1782,"Internal":true,"Count Failed Values":true},{"ID":708,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":709,"Name":"internal.metrics.shuffle.read.recordsRead","Value":20,"Internal":true,"Count Failed Values":true},{"ID":710,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":711,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":712,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":713,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":714,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":715,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":716,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":717,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":718,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":719,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":720,"Name":"internal.metrics.shuffle.write.bytesWritten","Value":1831,"Internal":true,"Count Failed Values":true},{"ID":721,"Name":"internal.metrics.shuffle.write.recordsWritten","Value":20,"Internal":true,"Count Failed Values":true},{"ID":722,"Name":"internal.metrics.shuffle.write.writeTime","Value":2055785,"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":1784546400661,"Job Result":{"Result":"JobSucceeded"}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate","executionId":0,"physicalPlanDescription":"== Physical Plan ==\nAdaptiveSparkPlan (65)\n+- == Final Plan ==\n Execute InsertIntoHadoopFsRelationCommand (38)\n +- WriteFiles (37)\n +- * Sort (36)\n +- AQEShuffleRead (35)\n +- ShuffleQueryStage (34), Statistics(sizeInBytes=1440.0 B, rowCount=20)\n +- Exchange (33)\n +- * Project (32)\n +- * HashAggregate (31)\n +- AQEShuffleRead (30)\n +- ShuffleQueryStage (29), Statistics(sizeInBytes=1760.0 B, rowCount=20)\n +- Exchange (28)\n +- * HashAggregate (27)\n +- * HashAggregate (26)\n +- AQEShuffleRead (25)\n +- ShuffleQueryStage (24), Statistics(sizeInBytes=23.8 KiB, rowCount=304)\n +- Exchange (23)\n +- * HashAggregate (22)\n +- * Expand (21)\n +- * Project (20)\n +- * BroadcastHashJoin LeftOuter BuildRight (19)\n :- * Project (14)\n : +- * BroadcastHashJoin Inner BuildRight (13)\n : :- * Project (8)\n : : +- * BroadcastHashJoin Inner BuildLeft (7)\n : : :- BroadcastQueryStage (4), Statistics(sizeInBytes=1024.2 KiB, rowCount=20)\n : : : +- BroadcastExchange (3)\n : : : +- * Filter (2)\n : : : +- Scan csv (1)\n : : +- * Filter (6)\n : : +- Scan csv (5)\n : +- BroadcastQueryStage (12), Statistics(sizeInBytes=1024.0 KiB, rowCount=18)\n : +- BroadcastExchange (11)\n : +- * Filter (10)\n : +- Scan csv (9)\n +- BroadcastQueryStage (18), Statistics(sizeInBytes=2.0 MiB, rowCount=58)\n +- BroadcastExchange (17)\n +- * Filter (16)\n +- Scan csv (15)\n+- == Initial Plan ==\n Execute InsertIntoHadoopFsRelationCommand (64)\n +- WriteFiles (63)\n +- Sort (62)\n +- Exchange (61)\n +- Project (60)\n +- HashAggregate (59)\n +- Exchange (58)\n +- HashAggregate (57)\n +- HashAggregate (56)\n +- Exchange (55)\n +- HashAggregate (54)\n +- Expand (53)\n +- Project (52)\n +- BroadcastHashJoin LeftOuter BuildRight (51)\n :- Project (48)\n : +- BroadcastHashJoin Inner BuildRight (47)\n : :- Project (44)\n : : +- BroadcastHashJoin Inner BuildLeft (43)\n : : :- BroadcastExchange (40)\n : : : +- Filter (39)\n : : : +- Scan csv (1)\n : : +- Filter (42)\n : : +- Scan csv (41)\n : +- BroadcastExchange (46)\n : +- Filter (45)\n : +- Scan csv (9)\n +- BroadcastExchange (50)\n +- Filter (49)\n +- Scan csv (15)\n\n\n(1) Scan csv \nOutput [2]: [id#0L, name#1]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/users.csv]\nPushedFilters: [IsNotNull(id)]\nReadSchema: struct\n\n(2) Filter [codegen id : 1]\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(3) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]\n\n(4) BroadcastQueryStage\nOutput [2]: [id#0L, name#1]\nArguments: 0\n\n(5) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(6) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(7) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(8) Project [codegen id : 4]\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(9) Scan csv \nOutput [2]: [id#18L, course_id#19L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lessons.csv]\nPushedFilters: [IsNotNull(course_id)]\nReadSchema: struct\n\n(10) Filter [codegen id : 2]\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(11) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]\n\n(12) BroadcastQueryStage\nOutput [2]: [id#18L, course_id#19L]\nArguments: 1\n\n(13) BroadcastHashJoin [codegen id : 4]\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(14) Project [codegen id : 4]\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(15) Scan csv \nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/lesson_views.csv]\nPushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)]\nReadSchema: struct\n\n(16) Filter [codegen id : 3]\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(17) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]\n\n(18) BroadcastQueryStage\nOutput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: 2\n\n(19) BroadcastHashJoin [codegen id : 4]\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(20) Project [codegen id : 4]\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(21) Expand [codegen id : 4]\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(22) HashAggregate [codegen id : 4]\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(23) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]\n\n(24) ShuffleQueryStage\nOutput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: 3\n\n(25) AQEShuffleRead\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: coalesced\n\n(26) HashAggregate [codegen id : 5]\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(27) HashAggregate [codegen id : 5]\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(28) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=513]\n\n(29) ShuffleQueryStage\nOutput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: 4\n\n(30) AQEShuffleRead\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: coalesced\n\n(31) HashAggregate [codegen id : 6]\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(32) Project [codegen id : 6]\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(33) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=561]\n\n(34) ShuffleQueryStage\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: 5\n\n(35) AQEShuffleRead\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: coalesced\n\n(36) Sort [codegen id : 7]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(37) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(38) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(39) Filter\nInput [2]: [id#0L, name#1]\nCondition : isnotnull(id#0L)\n\n(40) BroadcastExchange\nInput [2]: [id#0L, name#1]\nArguments: HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=105]\n\n(41) Scan csv \nOutput [2]: [user_id#11L, course_id#12L]\nBatched: false\nLocation: InMemoryFileIndex [s3a://apavlovets-bucket/raw/enrollments.csv]\nPushedFilters: [IsNotNull(user_id), IsNotNull(course_id)]\nReadSchema: struct\n\n(42) Filter\nInput [2]: [user_id#11L, course_id#12L]\nCondition : (isnotnull(user_id#11L) AND isnotnull(course_id#12L))\n\n(43) BroadcastHashJoin\nLeft keys [1]: [id#0L]\nRight keys [1]: [user_id#11L]\nJoin type: Inner\nJoin condition: None\n\n(44) Project\nOutput [3]: [id#0L, name#1, course_id#12L]\nInput [4]: [id#0L, name#1, user_id#11L, course_id#12L]\n\n(45) Filter\nInput [2]: [id#18L, course_id#19L]\nCondition : isnotnull(course_id#19L)\n\n(46) BroadcastExchange\nInput [2]: [id#18L, course_id#19L]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=109]\n\n(47) BroadcastHashJoin\nLeft keys [1]: [course_id#12L]\nRight keys [1]: [course_id#19L]\nJoin type: Inner\nJoin condition: None\n\n(48) Project\nOutput [4]: [id#0L, name#1, course_id#12L, id#18L]\nInput [5]: [id#0L, name#1, course_id#12L, id#18L, course_id#19L]\n\n(49) Filter\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nCondition : (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))\n\n(50) BroadcastExchange\nInput [3]: [user_id#27L, lesson_id#28L, viewed_at#29]\nArguments: HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=113]\n\n(51) BroadcastHashJoin\nLeft keys [2]: [id#18L, id#0L]\nRight keys [2]: [lesson_id#28L, user_id#27L]\nJoin type: LeftOuter\nJoin condition: None\n\n(52) Project\nOutput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nInput [7]: [id#0L, name#1, course_id#12L, id#18L, user_id#27L, lesson_id#28L, viewed_at#29]\n\n(53) Expand\nInput [6]: [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]\nArguments: [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\n\n(54) HashAggregate\nInput [7]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max#197, min#198]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\n\n(55) Exchange\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nArguments: hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=119]\n\n(56) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max#199, min#200]\nKeys [6]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174]\nFunctions [2]: [max(lv.viewed_at#178), min(lv.viewed_at#178)]\nAggregate Attributes [2]: [max(lv.viewed_at#178)#136, min(lv.viewed_at#178)#138]\nResults [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at#178)#136 AS max(lv.viewed_at)#179, min(lv.viewed_at#178)#138 AS min(lv.viewed_at)#181]\n\n(57) HashAggregate\nInput [8]: [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, max(lv.viewed_at)#179, min(lv.viewed_at)#181]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))]\nAggregate Attributes [7]: [count#183L, count#184L, first#185, valueSet#186, first#187, valueSet#188, count#189L]\nResults [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\n\n(58) Exchange\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nArguments: hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=123]\n\n(59) HashAggregate\nInput [9]: [id#0L, name#1, count#190L, count#191L, first#192, valueSet#193, first#194, valueSet#195, count#196L]\nKeys [2]: [id#0L, name#1]\nFunctions [5]: [count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)]\nAggregate Attributes [5]: [count(e.course_id#175L)#141L, count(lv.lesson_id#176L)#142L, first(max(lv.viewed_at)#179) ignore nulls#180, first(min(lv.viewed_at)#181) ignore nulls#182, count(l.id#177L)#143L]\nResults [7]: [id#0L AS user_id#116L, name#1, count(e.course_id#175L)#141L AS enrollment_count#134L, count(lv.lesson_id#176L)#142L AS viewed_lessons_count#135L, first(max(lv.viewed_at)#179) ignore nulls#180 AS last_view#137, first(min(lv.viewed_at)#181) ignore nulls#182 AS first_view#139, count(l.id#177L)#143L AS total_lessons#140L]\n\n(60) Project\nOutput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, total_lessons#140L]\n\n(61) Exchange\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=127]\n\n(62) Sort\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\nArguments: [user_id#116L ASC NULLS FIRST], true, 0\n\n(63) WriteFiles\nInput [7]: [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, engagement_rate#151]\n\n(64) Execute InsertIntoHadoopFsRelationCommand\nInput: []\nArguments: s3a://apavlovets-bucket/marts/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]\n\n(65) 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/user_activity_summary.parquet, false, Parquet, [path=s3a://apavlovets-bucket/marts/user_activity_summary.parquet], Overwrite, [user_id, name, enrollment_count, viewed_lessons_count, last_view, first_view, engagement_rate]","children":[{"nodeName":"WriteFiles","simpleString":"WriteFiles","children":[{"nodeName":"WholeStageCodegen (7)","simpleString":"WholeStageCodegen (7)","children":[{"nodeName":"Sort","simpleString":"Sort [user_id#116L ASC NULLS FIRST], true, 0","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 5","children":[{"nodeName":"Exchange","simpleString":"Exchange rangepartitioning(user_id#116L ASC NULLS FIRST, 200), ENSURE_REQUIREMENTS, [plan_id=561]","children":[{"nodeName":"WholeStageCodegen (6)","simpleString":"WholeStageCodegen (6)","children":[{"nodeName":"Project","simpleString":"Project [user_id#116L, name#1, enrollment_count#134L, viewed_lessons_count#135L, last_view#137, first_view#139, CASE WHEN NOT (total_lessons#140L = 0) THEN round(((cast(viewed_lessons_count#135L as double) * 100.0) / cast(total_lessons#140L as double)), 2) ELSE 0.0 END AS engagement_rate#151]","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[count(e.course_id#175L), count(lv.lesson_id#176L), first(max(lv.viewed_at)#179, true), first(min(lv.viewed_at)#181, true), count(l.id#177L)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 4","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, 200), ENSURE_REQUIREMENTS, [plan_id=513]","children":[{"nodeName":"WholeStageCodegen (5)","simpleString":"WholeStageCodegen (5)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1], functions=[partial_count(e.course_id#175L) FILTER (WHERE (gid#174 = 1)), partial_count(lv.lesson_id#176L) FILTER (WHERE (gid#174 = 2)), partial_first(max(lv.viewed_at)#179, true) FILTER (WHERE (gid#174 = 0)), partial_first(min(lv.viewed_at)#181, true) FILTER (WHERE (gid#174 = 0)), partial_count(l.id#177L) FILTER (WHERE (gid#174 = 3))])","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[max(lv.viewed_at#178), min(lv.viewed_at#178)])","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"AQEShuffleRead","simpleString":"AQEShuffleRead coalesced","children":[{"nodeName":"ShuffleQueryStage","simpleString":"ShuffleQueryStage 3","children":[{"nodeName":"Exchange","simpleString":"Exchange hashpartitioning(id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, 200), ENSURE_REQUIREMENTS, [plan_id=431]","children":[{"nodeName":"WholeStageCodegen (4)","simpleString":"WholeStageCodegen (4)","children":[{"nodeName":"HashAggregate","simpleString":"HashAggregate(keys=[id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174], functions=[partial_max(lv.viewed_at#178), partial_min(lv.viewed_at#178)])","children":[{"nodeName":"Expand","simpleString":"Expand [[id#0L, name#1, null, null, null, 0, viewed_at#29], [id#0L, name#1, course_id#12L, null, null, 1, null], [id#0L, name#1, null, lesson_id#28L, null, 2, null], [id#0L, name#1, null, null, id#18L, 3, null]], [id#0L, name#1, e.course_id#175L, lv.lesson_id#176L, l.id#177L, gid#174, lv.viewed_at#178]","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L, lesson_id#28L, viewed_at#29]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#18L, id#0L], [lesson_id#28L, user_id#27L], LeftOuter, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L, id#18L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [course_id#12L], [course_id#19L], Inner, BuildRight, false","children":[{"nodeName":"Project","simpleString":"Project [id#0L, name#1, course_id#12L]","children":[{"nodeName":"BroadcastHashJoin","simpleString":"BroadcastHashJoin [id#0L], [user_id#11L], Inner, BuildLeft, false","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 0","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[0, bigint, false]),false), [plan_id=179]","children":[{"nodeName":"WholeStageCodegen (1)","simpleString":"WholeStageCodegen (1)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(id#0L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#0L,name#1] Batched: false, DataFilters: [isnotnull(id#0L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv], PartitionFilters: [], PushedFilters: [IsNotNull(id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/users.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(id)]","DataFilters":"[isnotnull(id#0L)]"},"metrics":[{"name":"number of output rows","accumulatorId":110,"metricType":"sum"},{"name":"number of files read","accumulatorId":111,"metricType":"sum"},{"name":"metadata time","accumulatorId":112,"metricType":"timing"},{"name":"size of files read","accumulatorId":113,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":242,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":241,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":240,"metricType":"timing"},{"name":"time to build","accumulatorId":239,"metricType":"timing"},{"name":"time to collect","accumulatorId":238,"metricType":"timing"},{"name":"number of output rows","accumulatorId":237,"metricType":"sum"},{"name":"data size","accumulatorId":236,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]},{"nodeName":"Filter","simpleString":"Filter (isnotnull(user_id#11L) AND isnotnull(course_id#12L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#11L,course_id#12L] Batched: false, DataFilters: [isnotnull(user_id#11L), isnotnull(course_id#12L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv], PartitionFilters: [], PushedFilters: [IsNotNull(user_id), IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/enrollments.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(user_id), IsNotNull(course_id)]","DataFilters":"[isnotnull(user_id#11L), isnotnull(course_id#12L)]"},"metrics":[{"name":"number of output rows","accumulatorId":467,"metricType":"sum"},{"name":"number of files read","accumulatorId":468,"metricType":"sum"},{"name":"metadata time","accumulatorId":469,"metricType":"timing"},{"name":"size of files read","accumulatorId":470,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":466,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":465,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 1","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false]),false), [plan_id=191]","children":[{"nodeName":"WholeStageCodegen (2)","simpleString":"WholeStageCodegen (2)","children":[{"nodeName":"Filter","simpleString":"Filter isnotnull(course_id#19L)","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [id#18L,course_id#19L] Batched: false, DataFilters: [isnotnull(course_id#19L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv], PartitionFilters: [], PushedFilters: [IsNotNull(course_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lessons.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(course_id)]","DataFilters":"[isnotnull(course_id#19L)]"},"metrics":[{"name":"number of output rows","accumulatorId":125,"metricType":"sum"},{"name":"number of files read","accumulatorId":126,"metricType":"sum"},{"name":"metadata time","accumulatorId":127,"metricType":"timing"},{"name":"size of files read","accumulatorId":128,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":249,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":248,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":247,"metricType":"timing"},{"name":"time to build","accumulatorId":246,"metricType":"timing"},{"name":"time to collect","accumulatorId":245,"metricType":"timing"},{"name":"number of output rows","accumulatorId":244,"metricType":"sum"},{"name":"data size","accumulatorId":243,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":464,"metricType":"sum"}]}],"metadata":{},"metrics":[]},{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"BroadcastQueryStage","simpleString":"BroadcastQueryStage 2","children":[{"nodeName":"BroadcastExchange","simpleString":"BroadcastExchange HashedRelationBroadcastMode(List(input[1, bigint, false], input[0, bigint, false]),false), [plan_id=203]","children":[{"nodeName":"WholeStageCodegen (3)","simpleString":"WholeStageCodegen (3)","children":[{"nodeName":"Filter","simpleString":"Filter (isnotnull(lesson_id#28L) AND isnotnull(user_id#27L))","children":[{"nodeName":"InputAdapter","simpleString":"InputAdapter","children":[{"nodeName":"Scan csv ","simpleString":"FileScan csv [user_id#27L,lesson_id#28L,viewed_at#29] Batched: false, DataFilters: [isnotnull(lesson_id#28L), isnotnull(user_id#27L)], Format: CSV, Location: InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv], PartitionFilters: [], PushedFilters: [IsNotNull(lesson_id), IsNotNull(user_id)], ReadSchema: struct","children":[],"metadata":{"Location":"InMemoryFileIndex(1 paths)[s3a://apavlovets-bucket/raw/lesson_views.csv]","ReadSchema":"struct","Format":"CSV","Batched":"false","PartitionFilters":"[]","PushedFilters":"[IsNotNull(lesson_id), IsNotNull(user_id)]","DataFilters":"[isnotnull(lesson_id#28L), isnotnull(user_id#27L)]"},"metrics":[{"name":"number of output rows","accumulatorId":135,"metricType":"sum"},{"name":"number of files read","accumulatorId":136,"metricType":"sum"},{"name":"metadata time","accumulatorId":137,"metricType":"timing"},{"name":"size of files read","accumulatorId":138,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":256,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":255,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"time to broadcast","accumulatorId":254,"metricType":"timing"},{"name":"time to build","accumulatorId":253,"metricType":"timing"},{"name":"time to collect","accumulatorId":252,"metricType":"timing"},{"name":"number of output rows","accumulatorId":251,"metricType":"sum"},{"name":"data size","accumulatorId":250,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":463,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of output rows","accumulatorId":462,"metricType":"sum"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":458,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":459,"metricType":"timing"},{"name":"peak memory","accumulatorId":457,"metricType":"size"},{"name":"number of output rows","accumulatorId":456,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":461,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":460,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":455,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":453,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":447,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":454,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":448,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":445,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":442,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":451,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":444,"metricType":"sum"},{"name":"records read","accumulatorId":441,"metricType":"sum"},{"name":"local bytes read","accumulatorId":439,"metricType":"size"},{"name":"fetch wait time","accumulatorId":440,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":437,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":443,"metricType":"sum"},{"name":"local blocks read","accumulatorId":436,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":446,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":435,"metricType":"sum"},{"name":"data size","accumulatorId":433,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":449,"metricType":"size"},{"name":"number of partitions","accumulatorId":434,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":450,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":438,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":452,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":578,"metricType":"sum"},{"name":"partition data size","accumulatorId":579,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":580,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":574,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":575,"metricType":"timing"},{"name":"peak memory","accumulatorId":573,"metricType":"size"},{"name":"number of output rows","accumulatorId":572,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":577,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":576,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":568,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":569,"metricType":"timing"},{"name":"peak memory","accumulatorId":567,"metricType":"size"},{"name":"number of output rows","accumulatorId":566,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":571,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":570,"metricType":"average"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":565,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":563,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":557,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":564,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":558,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":555,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":552,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":561,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":554,"metricType":"sum"},{"name":"records read","accumulatorId":551,"metricType":"sum"},{"name":"local bytes read","accumulatorId":549,"metricType":"size"},{"name":"fetch wait time","accumulatorId":550,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":547,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":553,"metricType":"sum"},{"name":"local blocks read","accumulatorId":546,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":556,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":545,"metricType":"sum"},{"name":"data size","accumulatorId":543,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":559,"metricType":"size"},{"name":"number of partitions","accumulatorId":544,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":560,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":548,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":562,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":654,"metricType":"sum"},{"name":"partition data size","accumulatorId":655,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":656,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"spill size","accumulatorId":650,"metricType":"size"},{"name":"time in aggregation build","accumulatorId":651,"metricType":"timing"},{"name":"peak memory","accumulatorId":649,"metricType":"size"},{"name":"number of output rows","accumulatorId":648,"metricType":"sum"},{"name":"number of sort fallback tasks","accumulatorId":653,"metricType":"sum"},{"name":"avg hash probes per key","accumulatorId":652,"metricType":"average"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":647,"metricType":"timing"}]}],"metadata":{},"metrics":[{"name":"shuffle records written","accumulatorId":645,"metricType":"sum"},{"name":"local merged chunks fetched","accumulatorId":639,"metricType":"sum"},{"name":"shuffle write time","accumulatorId":646,"metricType":"nsTiming"},{"name":"remote merged bytes read","accumulatorId":640,"metricType":"size"},{"name":"local merged blocks fetched","accumulatorId":637,"metricType":"sum"},{"name":"corrupt merged block chunks","accumulatorId":634,"metricType":"sum"},{"name":"remote merged reqs duration","accumulatorId":643,"metricType":"timing"},{"name":"remote merged blocks fetched","accumulatorId":636,"metricType":"sum"},{"name":"records read","accumulatorId":633,"metricType":"sum"},{"name":"local bytes read","accumulatorId":631,"metricType":"size"},{"name":"fetch wait time","accumulatorId":632,"metricType":"timing"},{"name":"remote bytes read","accumulatorId":629,"metricType":"size"},{"name":"merged fetch fallback count","accumulatorId":635,"metricType":"sum"},{"name":"local blocks read","accumulatorId":628,"metricType":"sum"},{"name":"remote merged chunks fetched","accumulatorId":638,"metricType":"sum"},{"name":"remote blocks read","accumulatorId":627,"metricType":"sum"},{"name":"data size","accumulatorId":625,"metricType":"size"},{"name":"local merged bytes read","accumulatorId":641,"metricType":"size"},{"name":"number of partitions","accumulatorId":626,"metricType":"sum"},{"name":"remote reqs duration","accumulatorId":642,"metricType":"timing"},{"name":"remote bytes read to disk","accumulatorId":630,"metricType":"size"},{"name":"shuffle bytes written","accumulatorId":644,"metricType":"size"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"number of partitions","accumulatorId":737,"metricType":"sum"},{"name":"partition data size","accumulatorId":738,"metricType":"size"},{"name":"number of coalesced partitions","accumulatorId":739,"metricType":"sum"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"sort time","accumulatorId":734,"metricType":"timing"},{"name":"peak memory","accumulatorId":735,"metricType":"size"},{"name":"spill size","accumulatorId":736,"metricType":"size"}]}],"metadata":{},"metrics":[{"name":"duration","accumulatorId":733,"metricType":"timing"}]}],"metadata":{},"metrics":[]}],"metadata":{},"metrics":[{"name":"task commit time","accumulatorId":731,"metricType":"timing"},{"name":"number of written files","accumulatorId":727,"metricType":"sum"},{"name":"job commit time","accumulatorId":732,"metricType":"timing"},{"name":"number of output rows","accumulatorId":729,"metricType":"sum"},{"name":"number of dynamic part","accumulatorId":730,"metricType":"sum"},{"name":"written output","accumulatorId":728,"metricType":"size"}]}],"metadata":{},"metrics":[]}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[737,1],[739,1],[738,1940]]} {"Event":"SparkListenerJobStart","Job ID":7,"Submission Time":1784546400834,"Stage Infos":[{"Stage ID":15,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"70\",\"name\":\"WriteFiles\"}","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":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"74\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[24],"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":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"71\",\"name\":\"WholeStageCodegen (7)\"}","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":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[14],"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":12,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":15,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"27\",\"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":14,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"28\",\"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},{"RDD ID":12,"Name":"FileScanRDD","Scope":"{\"id\":\"45\",\"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\":\"45\",\"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}],"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":13,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":18,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"46\",\"name\":\"Exchange\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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":16,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"51\",\"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":17,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"47\",\"name\":\"WholeStageCodegen (5)\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","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}],"Parent IDs":[12],"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":24,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"52\",\"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":20,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"53\",\"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},{"RDD ID":19,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"57\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[18],"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":[15,12,13,14],"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":15,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"70\",\"name\":\"WriteFiles\"}","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":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"74\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[24],"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":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"71\",\"name\":\"WholeStageCodegen (7)\"}","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":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[14],"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":1784546400835,"Accumulables":[],"Resource Profile Id":0,"Shuffle Push Enabled":false,"Shuffle Push Mergers Count":0},"Properties":{"spark.driver.port":"38791","spark.submit.pyFiles":"","spark.app.startTime":"1784546376677","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":"1784546375619","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_user_activity_summary","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-20260720151938-0098","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":15,"Stage Attempt ID":0,"Task Info":{"Task ID":7,"Index":0,"Attempt":0,"Partition ID":0,"Launch Time":1784546400855,"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":15,"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":1784546400855,"Executor ID":"0","Host":"172.28.0.49","Locality":"NODE_LOCAL","Speculative":false,"Getting Result Time":0,"Finish Time":1784546401770,"Failed":false,"Killed":false,"Accumulables":[{"ID":628,"Name":"local blocks read","Update":"1","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":631,"Name":"local bytes read","Update":"1831","Value":"1831","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":632,"Name":"fetch wait time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":633,"Name":"records read","Update":"20","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":731,"Name":"task commit time","Update":"92","Value":"92","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":733,"Name":"duration","Update":"487","Value":"487","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":734,"Name":"sort time","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":735,"Name":"peak memory","Update":"4259824","Value":"4259824","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":736,"Name":"spill size","Update":"0","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":740,"Name":"internal.metrics.executorDeserializeTime","Update":60,"Value":60,"Internal":true,"Count Failed Values":true},{"ID":741,"Name":"internal.metrics.executorDeserializeCpuTime","Update":48465885,"Value":48465885,"Internal":true,"Count Failed Values":true},{"ID":742,"Name":"internal.metrics.executorRunTime","Update":842,"Value":842,"Internal":true,"Count Failed Values":true},{"ID":743,"Name":"internal.metrics.executorCpuTime","Update":708985721,"Value":708985721,"Internal":true,"Count Failed Values":true},{"ID":744,"Name":"internal.metrics.resultSize","Update":11794,"Value":11794,"Internal":true,"Count Failed Values":true},{"ID":745,"Name":"internal.metrics.jvmGCTime","Update":13,"Value":13,"Internal":true,"Count Failed Values":true},{"ID":746,"Name":"internal.metrics.resultSerializationTime","Update":2,"Value":2,"Internal":true,"Count Failed Values":true},{"ID":749,"Name":"internal.metrics.peakExecutionMemory","Update":4259824,"Value":4259824,"Internal":true,"Count Failed Values":true},{"ID":751,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":752,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Update":1,"Value":1,"Internal":true,"Count Failed Values":true},{"ID":753,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":754,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":755,"Name":"internal.metrics.shuffle.read.localBytesRead","Update":1831,"Value":1831,"Internal":true,"Count Failed Values":true},{"ID":756,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":757,"Name":"internal.metrics.shuffle.read.recordsRead","Update":20,"Value":20,"Internal":true,"Count Failed Values":true},{"ID":758,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":759,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":760,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":761,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":762,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":763,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":764,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":765,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":766,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":767,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Update":0,"Value":0,"Internal":true,"Count Failed Values":true},{"ID":773,"Name":"internal.metrics.output.bytesWritten","Update":2745,"Value":2745,"Internal":true,"Count Failed Values":true},{"ID":774,"Name":"internal.metrics.output.recordsWritten","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":60,"Executor Deserialize CPU Time":48465885,"Executor Run Time":842,"Executor CPU Time":708985721,"Peak Execution Memory":4259824,"Result Size":11794,"JVM GC Time":13,"Result Serialization Time":2,"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":1831,"Total Records Read":20,"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":2745,"Records Written":20},"Updated Blocks":[]}} {"Event":"SparkListenerStageCompleted","Stage Info":{"Stage ID":15,"Stage Attempt ID":0,"Stage Name":"parquet at NativeMethodAccessorImpl.java:0","Number of Tasks":1,"RDD Info":[{"RDD ID":27,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"70\",\"name\":\"WriteFiles\"}","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":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0},{"RDD ID":25,"Name":"ShuffledRowRDD","Scope":"{\"id\":\"74\",\"name\":\"AQEShuffleRead\"}","Callsite":"parquet at NativeMethodAccessorImpl.java:0","Parent IDs":[24],"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":26,"Name":"MapPartitionsRDD","Scope":"{\"id\":\"71\",\"name\":\"WholeStageCodegen (7)\"}","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":"UNORDERED","Number of Partitions":1,"Number of Cached Partitions":0,"Memory Size":0,"Disk Size":0}],"Parent IDs":[14],"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":1784546400835,"Completion Time":1784546401772,"Accumulables":[{"ID":628,"Name":"local blocks read","Value":"1","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":631,"Name":"local bytes read","Value":"1831","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":632,"Name":"fetch wait time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":633,"Name":"records read","Value":"20","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":731,"Name":"task commit time","Value":"92","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":733,"Name":"duration","Value":"487","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":734,"Name":"sort time","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":735,"Name":"peak memory","Value":"4259824","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":736,"Name":"spill size","Value":"0","Internal":true,"Count Failed Values":true,"Metadata":"sql"},{"ID":740,"Name":"internal.metrics.executorDeserializeTime","Value":60,"Internal":true,"Count Failed Values":true},{"ID":741,"Name":"internal.metrics.executorDeserializeCpuTime","Value":48465885,"Internal":true,"Count Failed Values":true},{"ID":742,"Name":"internal.metrics.executorRunTime","Value":842,"Internal":true,"Count Failed Values":true},{"ID":743,"Name":"internal.metrics.executorCpuTime","Value":708985721,"Internal":true,"Count Failed Values":true},{"ID":744,"Name":"internal.metrics.resultSize","Value":11794,"Internal":true,"Count Failed Values":true},{"ID":745,"Name":"internal.metrics.jvmGCTime","Value":13,"Internal":true,"Count Failed Values":true},{"ID":746,"Name":"internal.metrics.resultSerializationTime","Value":2,"Internal":true,"Count Failed Values":true},{"ID":749,"Name":"internal.metrics.peakExecutionMemory","Value":4259824,"Internal":true,"Count Failed Values":true},{"ID":751,"Name":"internal.metrics.shuffle.read.remoteBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":752,"Name":"internal.metrics.shuffle.read.localBlocksFetched","Value":1,"Internal":true,"Count Failed Values":true},{"ID":753,"Name":"internal.metrics.shuffle.read.remoteBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":754,"Name":"internal.metrics.shuffle.read.remoteBytesReadToDisk","Value":0,"Internal":true,"Count Failed Values":true},{"ID":755,"Name":"internal.metrics.shuffle.read.localBytesRead","Value":1831,"Internal":true,"Count Failed Values":true},{"ID":756,"Name":"internal.metrics.shuffle.read.fetchWaitTime","Value":0,"Internal":true,"Count Failed Values":true},{"ID":757,"Name":"internal.metrics.shuffle.read.recordsRead","Value":20,"Internal":true,"Count Failed Values":true},{"ID":758,"Name":"internal.metrics.shuffle.push.read.corruptMergedBlockChunks","Value":0,"Internal":true,"Count Failed Values":true},{"ID":759,"Name":"internal.metrics.shuffle.push.read.mergedFetchFallbackCount","Value":0,"Internal":true,"Count Failed Values":true},{"ID":760,"Name":"internal.metrics.shuffle.push.read.remoteMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":761,"Name":"internal.metrics.shuffle.push.read.localMergedBlocksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":762,"Name":"internal.metrics.shuffle.push.read.remoteMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":763,"Name":"internal.metrics.shuffle.push.read.localMergedChunksFetched","Value":0,"Internal":true,"Count Failed Values":true},{"ID":764,"Name":"internal.metrics.shuffle.push.read.remoteMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":765,"Name":"internal.metrics.shuffle.push.read.localMergedBytesRead","Value":0,"Internal":true,"Count Failed Values":true},{"ID":766,"Name":"internal.metrics.shuffle.read.remoteReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":767,"Name":"internal.metrics.shuffle.push.read.remoteMergedReqsDuration","Value":0,"Internal":true,"Count Failed Values":true},{"ID":773,"Name":"internal.metrics.output.bytesWritten","Value":2745,"Internal":true,"Count Failed Values":true},{"ID":774,"Name":"internal.metrics.output.recordsWritten","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":7,"Completion Time":1784546401772,"Job Result":{"Result":"JobSucceeded"}} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerDriverAccumUpdates","executionId":0,"accumUpdates":[[727,1],[732,119],[729,20],[730,0],[728,2745]]} {"Event":"org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionEnd","executionId":0,"time":1784546401896,"errorMessage":""} {"Event":"SparkListenerApplicationEnd","Timestamp":1784546401899}