When I ran Spark SQL query (a simple group by query) via hive support, I have seen lots of failures in map phase.

I am not sure if that is specific to Spark SQL or general.

Any one has seen such errors before?

java.io.IOException: org.apache.spark.SparkException: Error sending message [message = GetLocations(broadcast_9_piece0)]

java.io.IOException: org.apache.spark.SparkException: Error sending message [message = GetLocations(broadcast_9_piece0)]
	at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1093)
	at org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:164)
	at org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
	at org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
	at org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:87)
	at org.apache.spark.broadcast.Broadcast.value(Broadcast.scala:70)
	at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:61)
	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$TaskRunner.run(Executor.scala:200)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
	at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Error sending message [message = GetLocations(broadcast_9_piece0)]
	at org.apache.spark.util.AkkaUtils$.askWithReply(AkkaUtils.scala:201)
	at org.apache.spark.storage.BlockManagerMaster.askDriverWithReply(BlockManagerMaster.scala:221)
	at org.apache.spark.storage.BlockManagerMaster.getLocations(BlockManagerMaster.scala:70)
	at org.apache.spark.storage.BlockManager.doGetRemote(BlockManager.scala:592)
	at org.apache.spark.storage.BlockManager.getRemoteBytes(BlockManager.scala:587)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.org$apache$spark$broadcast$TorrentBroadcast$$anonfun$$getRemote$1(TorrentBroadcast.scala:126)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$1.apply(TorrentBroadcast.scala:136)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$1.apply(TorrentBroadcast.scala:136)
	at scala.Option.orElse(Option.scala:257)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.scala:136)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:119)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:119)
	at scala.collection.immutable.List.foreach(List.scala:318)
	at org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:119)
	at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:174)
	at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1090)
	... 12 more
Caused by: java.util.concurrent.TimeoutException: Futures timed out after [30 seconds]
	at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
	at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
	at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107)
	at scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
	at scala.concurrent.Await$.result(package.scala:107)
	at org.apache.spark.util.AkkaUtils$.askWithReply(AkkaUtils.scala:187)
	... 27 more

--
Chen Song