[
https://issues.apache.org/jira/browse/SPARK-23470?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Shixiong Zhu updated SPARK-23470:
---------------------------------
Description:
I was testing 2.3.0 RC3 and found that it's easy to hit "read timeout" when
accessing All Jobs page. The stack dump says it was running
"org.apache.spark.ui.jobs.ApiHelper.lastStageNameAndDescription".
{code}
"SparkUI-59" #59 daemon prio=5 os_prio=0 tid=0x00007fc15b0a3000 nid=0x8dc
runnable [0x00007fc0ce9f8000]
java.lang.Thread.State: RUNNABLE
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.util.kvstore.KVTypeInfo$MethodAccessor.get(KVTypeInfo.java:154)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryView.compare(InMemoryStore.java:248)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryView.lambda$iterator$2(InMemoryStore.java:214)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryView$$Lambda$36/1834982692.compare(Unknown
Source)
at java.util.TimSort.binarySort(TimSort.java:296)
at java.util.TimSort.sort(TimSort.java:239)
at java.util.Arrays.sort(Arrays.java:1512)
at java.util.ArrayList.sort(ArrayList.java:1460)
at java.util.stream.SortedOps$RefSortingSink.end(SortedOps.java:387)
at java.util.stream.Sink$ChainedReference.end(Sink.java:258)
at
java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.fillBuffer(StreamSpliterators.java:210)
at
java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.doAdvance(StreamSpliterators.java:161)
at
java.util.stream.StreamSpliterators$WrappingSpliterator.tryAdvance(StreamSpliterators.java:300)
at java.util.Spliterators$1Adapter.hasNext(Spliterators.java:681)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryIterator.hasNext(InMemoryStore.java:278)
at
org.apache.spark.status.AppStatusStore.lastStageAttempt(AppStatusStore.scala:101)
at
org.apache.spark.ui.jobs.ApiHelper$$anonfun$38.apply(StagePage.scala:1014)
at
org.apache.spark.ui.jobs.ApiHelper$$anonfun$38.apply(StagePage.scala:1014)
at
org.apache.spark.status.AppStatusStore.asOption(AppStatusStore.scala:408)
at
org.apache.spark.ui.jobs.ApiHelper$.lastStageNameAndDescription(StagePage.scala:1014)
at
org.apache.spark.ui.jobs.JobDataSource.org$apache$spark$ui$jobs$JobDataSource$$jobRow(AllJobsPage.scala:434)
at
org.apache.spark.ui.jobs.JobDataSource$$anonfun$24.apply(AllJobsPage.scala:412)
at
org.apache.spark.ui.jobs.JobDataSource$$anonfun$24.apply(AllJobsPage.scala:412)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at
scala.collection.generic.TraversableForwarder$class.foreach(TraversableForwarder.scala:35)
at scala.collection.mutable.ListBuffer.foreach(ListBuffer.scala:45)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.ui.jobs.JobDataSource.<init>(AllJobsPage.scala:412)
at org.apache.spark.ui.jobs.JobPagedTable.<init>(AllJobsPage.scala:504)
at org.apache.spark.ui.jobs.AllJobsPage.jobsTable(AllJobsPage.scala:246)
at org.apache.spark.ui.jobs.AllJobsPage.render(AllJobsPage.scala:295)
at org.apache.spark.ui.WebUI$$anonfun$3.apply(WebUI.scala:98)
at org.apache.spark.ui.WebUI$$anonfun$3.apply(WebUI.scala:98)
at org.apache.spark.ui.JettyUtils$$anon$3.doGet(JettyUtils.scala:90)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:687)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:790)
at
org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:848)
at
org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:584)
at
org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1180)
at
org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:512)
at
org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1112)
at
org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)
at
org.eclipse.jetty.server.handler.gzip.GzipHandler.handle(GzipHandler.java:493)
at
org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:213)
{code}
According to the heap dump, there are 954 JobDataWrapper and 54690
StageDataWrapper. It's obvious that the UI will be slow since we need to sort
54690 items for 954 jobs.
was:
I was testing 2.3.0 RC3 and found that it's easy to hit "read timeout" in Spark
UI. The stack dump says it was running
"org.apache.spark.ui.jobs.ApiHelper.lastStageNameAndDescription".
{code}
"SparkUI-59" #59 daemon prio=5 os_prio=0 tid=0x00007fc15b0a3000 nid=0x8dc
runnable [0x00007fc0ce9f8000]
java.lang.Thread.State: RUNNABLE
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.util.kvstore.KVTypeInfo$MethodAccessor.get(KVTypeInfo.java:154)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryView.compare(InMemoryStore.java:248)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryView.lambda$iterator$2(InMemoryStore.java:214)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryView$$Lambda$36/1834982692.compare(Unknown
Source)
at java.util.TimSort.binarySort(TimSort.java:296)
at java.util.TimSort.sort(TimSort.java:239)
at java.util.Arrays.sort(Arrays.java:1512)
at java.util.ArrayList.sort(ArrayList.java:1460)
at java.util.stream.SortedOps$RefSortingSink.end(SortedOps.java:387)
at java.util.stream.Sink$ChainedReference.end(Sink.java:258)
at
java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.fillBuffer(StreamSpliterators.java:210)
at
java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.doAdvance(StreamSpliterators.java:161)
at
java.util.stream.StreamSpliterators$WrappingSpliterator.tryAdvance(StreamSpliterators.java:300)
at java.util.Spliterators$1Adapter.hasNext(Spliterators.java:681)
at
org.apache.spark.util.kvstore.InMemoryStore$InMemoryIterator.hasNext(InMemoryStore.java:278)
at
org.apache.spark.status.AppStatusStore.lastStageAttempt(AppStatusStore.scala:101)
at
org.apache.spark.ui.jobs.ApiHelper$$anonfun$38.apply(StagePage.scala:1014)
at
org.apache.spark.ui.jobs.ApiHelper$$anonfun$38.apply(StagePage.scala:1014)
at
org.apache.spark.status.AppStatusStore.asOption(AppStatusStore.scala:408)
at
org.apache.spark.ui.jobs.ApiHelper$.lastStageNameAndDescription(StagePage.scala:1014)
at
org.apache.spark.ui.jobs.JobDataSource.org$apache$spark$ui$jobs$JobDataSource$$jobRow(AllJobsPage.scala:434)
at
org.apache.spark.ui.jobs.JobDataSource$$anonfun$24.apply(AllJobsPage.scala:412)
at
org.apache.spark.ui.jobs.JobDataSource$$anonfun$24.apply(AllJobsPage.scala:412)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at
scala.collection.generic.TraversableForwarder$class.foreach(TraversableForwarder.scala:35)
at scala.collection.mutable.ListBuffer.foreach(ListBuffer.scala:45)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.ui.jobs.JobDataSource.<init>(AllJobsPage.scala:412)
at org.apache.spark.ui.jobs.JobPagedTable.<init>(AllJobsPage.scala:504)
at org.apache.spark.ui.jobs.AllJobsPage.jobsTable(AllJobsPage.scala:246)
at org.apache.spark.ui.jobs.AllJobsPage.render(AllJobsPage.scala:295)
at org.apache.spark.ui.WebUI$$anonfun$3.apply(WebUI.scala:98)
at org.apache.spark.ui.WebUI$$anonfun$3.apply(WebUI.scala:98)
at org.apache.spark.ui.JettyUtils$$anon$3.doGet(JettyUtils.scala:90)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:687)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:790)
at
org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:848)
at
org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:584)
at
org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1180)
at
org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:512)
at
org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1112)
at
org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)
at
org.eclipse.jetty.server.handler.gzip.GzipHandler.handle(GzipHandler.java:493)
at
org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:213)
{code}
According to the heap dump, there are 954 JobDataWrapper and 54690
StageDataWrapper. It's obvious that the UI will be slow since we need to sort
54690 items for 954 jobs.
> org.apache.spark.ui.jobs.ApiHelper.lastStageNameAndDescription is too slow
> --------------------------------------------------------------------------
>
> Key: SPARK-23470
> URL: https://issues.apache.org/jira/browse/SPARK-23470
> Project: Spark
> Issue Type: Bug
> Components: Web UI
> Affects Versions: 2.3.0
> Reporter: Shixiong Zhu
> Priority: Blocker
>
> I was testing 2.3.0 RC3 and found that it's easy to hit "read timeout" when
> accessing All Jobs page. The stack dump says it was running
> "org.apache.spark.ui.jobs.ApiHelper.lastStageNameAndDescription".
> {code}
> "SparkUI-59" #59 daemon prio=5 os_prio=0 tid=0x00007fc15b0a3000 nid=0x8dc
> runnable [0x00007fc0ce9f8000]
> java.lang.Thread.State: RUNNABLE
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> org.apache.spark.util.kvstore.KVTypeInfo$MethodAccessor.get(KVTypeInfo.java:154)
> at
> org.apache.spark.util.kvstore.InMemoryStore$InMemoryView.compare(InMemoryStore.java:248)
> at
> org.apache.spark.util.kvstore.InMemoryStore$InMemoryView.lambda$iterator$2(InMemoryStore.java:214)
> at
> org.apache.spark.util.kvstore.InMemoryStore$InMemoryView$$Lambda$36/1834982692.compare(Unknown
> Source)
> at java.util.TimSort.binarySort(TimSort.java:296)
> at java.util.TimSort.sort(TimSort.java:239)
> at java.util.Arrays.sort(Arrays.java:1512)
> at java.util.ArrayList.sort(ArrayList.java:1460)
> at java.util.stream.SortedOps$RefSortingSink.end(SortedOps.java:387)
> at java.util.stream.Sink$ChainedReference.end(Sink.java:258)
> at
> java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.fillBuffer(StreamSpliterators.java:210)
> at
> java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.doAdvance(StreamSpliterators.java:161)
> at
> java.util.stream.StreamSpliterators$WrappingSpliterator.tryAdvance(StreamSpliterators.java:300)
> at java.util.Spliterators$1Adapter.hasNext(Spliterators.java:681)
> at
> org.apache.spark.util.kvstore.InMemoryStore$InMemoryIterator.hasNext(InMemoryStore.java:278)
> at
> org.apache.spark.status.AppStatusStore.lastStageAttempt(AppStatusStore.scala:101)
> at
> org.apache.spark.ui.jobs.ApiHelper$$anonfun$38.apply(StagePage.scala:1014)
> at
> org.apache.spark.ui.jobs.ApiHelper$$anonfun$38.apply(StagePage.scala:1014)
> at
> org.apache.spark.status.AppStatusStore.asOption(AppStatusStore.scala:408)
> at
> org.apache.spark.ui.jobs.ApiHelper$.lastStageNameAndDescription(StagePage.scala:1014)
> at
> org.apache.spark.ui.jobs.JobDataSource.org$apache$spark$ui$jobs$JobDataSource$$jobRow(AllJobsPage.scala:434)
> at
> org.apache.spark.ui.jobs.JobDataSource$$anonfun$24.apply(AllJobsPage.scala:412)
> at
> org.apache.spark.ui.jobs.JobDataSource$$anonfun$24.apply(AllJobsPage.scala:412)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at
> scala.collection.generic.TraversableForwarder$class.foreach(TraversableForwarder.scala:35)
> at scala.collection.mutable.ListBuffer.foreach(ListBuffer.scala:45)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.AbstractTraversable.map(Traversable.scala:104)
> at org.apache.spark.ui.jobs.JobDataSource.<init>(AllJobsPage.scala:412)
> at org.apache.spark.ui.jobs.JobPagedTable.<init>(AllJobsPage.scala:504)
> at org.apache.spark.ui.jobs.AllJobsPage.jobsTable(AllJobsPage.scala:246)
> at org.apache.spark.ui.jobs.AllJobsPage.render(AllJobsPage.scala:295)
> at org.apache.spark.ui.WebUI$$anonfun$3.apply(WebUI.scala:98)
> at org.apache.spark.ui.WebUI$$anonfun$3.apply(WebUI.scala:98)
> at org.apache.spark.ui.JettyUtils$$anon$3.doGet(JettyUtils.scala:90)
> at javax.servlet.http.HttpServlet.service(HttpServlet.java:687)
> at javax.servlet.http.HttpServlet.service(HttpServlet.java:790)
> at
> org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:848)
> at
> org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:584)
> at
> org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1180)
> at
> org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:512)
> at
> org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1112)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)
> at
> org.eclipse.jetty.server.handler.gzip.GzipHandler.handle(GzipHandler.java:493)
> at
> org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:213)
> {code}
> According to the heap dump, there are 954 JobDataWrapper and 54690
> StageDataWrapper. It's obvious that the UI will be slow since we need to sort
> 54690 items for 954 jobs.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
