tez-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Gopal Vijayaraghavan <gop...@apache.org>
Subject Re: Hive over Tez shuffle OOM
Date Mon, 27 Jan 2014 04:59:02 GMT
Hi,

This is somewhat unusual, but perhaps it is due to the
shuffle.input.buffer.percent settings (is it set to 0.5?).

To root-cause this properly, you can set the reduce java opts to contain

hive> set mapred.reduce.child.java.opts=-server -Xmx...
-XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/tmp/

And collect the heap dump (the *.hprof file).

You can load that up into jvisualvm & find out exactly what's
occupying the memory.

Cheers,
Gopal

On Sat, Jan 25, 2014 at 10:46 PM, Manu Zhang <owenzhang1990@gmail.com> wrote:
> Hi all,
>
> My Hive over Tez job fails with the following error while the same Hive
> over MR  job succeeds, given the same input data and configurations.
>
>
> *2014-01-26 13:46:19,823 ERROR [main]
> org.apache.hadoop.security.UserGroupInformation: PriviledgedActionException
> as:hive (auth:SIMPLE)
> cause:org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$ShuffleError:
> error in shuffle in fetcher#115*
> *    2014-01-26 13:46:19,824 FATAL [main]
> org.apache.hadoop.mapred.YarnTezDagChild: Error running child :
> org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$ShuffleError:
> error in shuffle in fetcher#115*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$RunShuffleCallable.call(Shuffle.java:224)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.Shuffle$RunShuffleCallable.call(Shuffle.java:204)*
> *            at
> java.util.concurrent.FutureTask$Sync.innerRun(FutureTask.java:303)*
> *            at java.util.concurrent.FutureTask.run(FutureTask.java:138)*
> *            at java.lang.Thread.run(Thread.java:662)*
> *    Caused by: java.lang.OutOfMemoryError: Java heap space*
> *            at
> org.apache.hadoop.io.BoundedByteArrayOutputStream.<init>(BoundedByteArrayOutputStream.java:56)*
> *            at
> org.apache.hadoop.io.BoundedByteArrayOutputStream.<init>(BoundedByteArrayOutputStream.java:46)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.MapOutput.<init>(MapOutput.java:98)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.MergeManager.unconditionalReserve(MergeManager.java:295)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.MergeManager.reserve(MergeManager.java:285)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.Fetcher.copyMapOutput(Fetcher.java:395)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.Fetcher.copyFromHost(Fetcher.java:325)*
> *            at
> org.apache.tez.runtime.library.common.shuffle.impl.Fetcher.run(Fetcher.java:173)*
>
> Is it merely a jvm configuration issue (like a larger heap memory) ?
>
> Thanks,
> Manu Zhang

-- 
CONFIDENTIALITY NOTICE
NOTICE: This message is intended for the use of the individual or entity to 
which it is addressed and may contain information that is confidential, 
privileged and exempt from disclosure under applicable law. If the reader 
of this message is not the intended recipient, you are hereby notified that 
any printing, copying, dissemination, distribution, disclosure or 
forwarding of this communication is strictly prohibited. If you have 
received this communication in error, please contact the sender immediately 
and delete it from your system. Thank You.

Mime
View raw message