[
https://issues.apache.org/jira/browse/FLINK-2299?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14609140#comment-14609140
]
Andra Lungu commented on FLINK-2299:
------------------------------------
Hi [~StephanEwen],
First of all, thanks a lot for looking into this! I know you're super busy.
Let me try to answer your questions.
For the `heavy collisions in keys` issue, I actually followed the ML
discussions - otherwise the code wouldn't have worked at all. What I did was to
add a join hint : .join(this.vertices,
JoinOperatorBase.JoinHint.BROADCAST_HASH_SECOND).where(1).equalTo(0). The
problem is that I was just doing that for one case; I will apply the same fix
for all the others and include this job in my nightly build.
Yes, so the problem there (GroupReduce at main(TriangleCount.java:51)) is that
it takes pairs of type (5,1) (5,2) (5,3) etc and does a grouBy.reduce to create
a TreeMap which for a highly skewed node in the twitter follower graph will
result in a huge data structure. Is TreeMap not the right candidate for the job
because of its memory implications? Anyway, your assumption is true. This is,
however what I am trying to prove; that skewed nodes drastically affect
computation...
> The slot on which the task maanger was scheduled was killed
> -----------------------------------------------------------
>
> Key: FLINK-2299
> URL: https://issues.apache.org/jira/browse/FLINK-2299
> Project: Flink
> Issue Type: Bug
> Affects Versions: 0.9, 0.10
> Reporter: Andra Lungu
> Priority: Critical
> Fix For: 0.9.1
>
>
> The following code:
> https://github.com/andralungu/gelly-partitioning/blob/master/src/main/java/example/GSATriangleCount.java
> Ran on the twitter follower graph:
> http://twitter.mpi-sws.org/data-icwsm2010.html
> With a similar configuration to the one in FLINK-2293
> fails with the following exception:
> java.lang.Exception: The slot in which the task was executed has been
> released. Probably loss of TaskManager 57c67d938c9144bec5ba798bb8ebe636 @
> wally025 - 8 slots - URL:
> akka.tcp://[email protected]:56135/user/taskmanager
> at
> org.apache.flink.runtime.instance.SimpleSlot.releaseSlot(SimpleSlot.java:151)
> at
> org.apache.flink.runtime.instance.SlotSharingGroupAssignment.releaseSharedSlot(SlotSharingGroupAssignment.java:547)
> at
> org.apache.flink.runtime.instance.SharedSlot.releaseSlot(SharedSlot.java:119)
> at
> org.apache.flink.runtime.instance.Instance.markDead(Instance.java:154)
> at
> org.apache.flink.runtime.instance.InstanceManager.unregisterTaskManager(InstanceManager.java:182)
> at
> org.apache.flink.runtime.jobmanager.JobManager$$anonfun$receiveWithLogMessages$1.applyOrElse(JobManager.scala:421)
> at
> scala.runtime.AbstractPartialFunction$mcVL$sp.apply$mcVL$sp(AbstractPartialFunction.scala:33)
> at
> scala.runtime.AbstractPartialFunction$mcVL$sp.apply(AbstractPartialFunction.scala:33)
> at
> scala.runtime.AbstractPartialFunction$mcVL$sp.apply(AbstractPartialFunction.scala:25)
> at
> org.apache.flink.runtime.ActorLogMessages$$anon$1.apply(ActorLogMessages.scala:36)
> at
> org.apache.flink.runtime.ActorLogMessages$$anon$1.apply(ActorLogMessages.scala:29)
> at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:118)
> at
> org.apache.flink.runtime.ActorLogMessages$$anon$1.applyOrElse(ActorLogMessages.scala:29)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
> at
> org.apache.flink.runtime.jobmanager.JobManager.aroundReceive(JobManager.scala:92)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
> at
> akka.actor.dungeon.DeathWatch$class.receivedTerminated(DeathWatch.scala:46)
> at akka.actor.ActorCell.receivedTerminated(ActorCell.scala:369)
> at akka.actor.ActorCell.autoReceiveMessage(ActorCell.scala:501)
> at akka.actor.ActorCell.invoke(ActorCell.scala:486)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:254)
> at akka.dispatch.Mailbox.run(Mailbox.scala:221)
> at akka.dispatch.Mailbox.exec(Mailbox.scala:231)
> at
> scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at
> scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> 06/29/2015 10:33:46 Job execution switched to status FAILING.
> The logs are here:
> https://drive.google.com/file/d/0BwnaKJcSLc43M1BhNUt5NWdINHc/view?usp=sharing
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
