[
https://issues.apache.org/jira/browse/SPARK-5314?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14282213#comment-14282213
]
Alex Baretta commented on SPARK-5314:
-------------------------------------
Per Akhil's comment on the dev list, "SET spark.sql.shuffle.partitions=1024"
resolves the OOM issue. I wonder if a more robust solution could be found.
> java.lang.OutOfMemoryError in SparkSQL with GROUP BY
> ----------------------------------------------------
>
> Key: SPARK-5314
> URL: https://issues.apache.org/jira/browse/SPARK-5314
> Project: Spark
> Issue Type: Bug
> Reporter: Alex Baretta
>
> I am running a SparkSQL GROUP BY query on a largish Parquet table (a few
> hundred million rows), weighing it at about 50GB. My cluster has 1.7 TB of
> RAM, so it should have more than plenty resources to cope with this query.
> WARN TaskSetManager: Lost task 279.0 in stage 22.0 (TID 1229,
> ds-model-w-21.c.eastern-gravity-771.internal): java.lang.OutOfMemoryError: GC
> overhead limit exceeded
> at scala.collection.SeqLike$class.distinct(SeqLike.scala:493)
> at scala.collection.AbstractSeq.distinct(Seq.scala:40)
> at
> org.apache.spark.sql.catalyst.expressions.Coalesce.resolved$lzycompute(nullFunctions.scala:33)
> at
> org.apache.spark.sql.catalyst.expressions.Coalesce.resolved(nullFunctions.scala:33)
> at
> org.apache.spark.sql.catalyst.expressions.Coalesce.dataType(nullFunctions.scala:37)
> at
> org.apache.spark.sql.catalyst.expressions.Expression.n2(Expression.scala:100)
> at
> org.apache.spark.sql.catalyst.expressions.Add.eval(arithmetic.scala:101)
> at
> org.apache.spark.sql.catalyst.expressions.Coalesce.eval(nullFunctions.scala:50)
> at
> org.apache.spark.sql.catalyst.expressions.MutableLiteral.update(literals.scala:81)
> at
> org.apache.spark.sql.catalyst.expressions.SumFunction.update(aggregates.scala:571)
> at
> org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:167)
> at
> org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$7.apply(Aggregate.scala:151)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:615)
> at org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:615)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:264)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:231)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:264)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:231)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:183)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
