You can change "spark.sql.broadcastTimeout" to increase the timeout. The
default value is 300 seconds.
Best Regards,
Shixiong Zhu
2015-09-24 15:16 GMT+08:00 Eyad Sibai <eyad.alsi...@gmail.com>:
> I am trying to join two tables using dataframes using python 3.4 and I am
> getting the following error
>
>
> I ran it on my localhost machine with 2 workers, spark 1.5
>
>
> I always get timeout if the job takes more than 5 minutes.
>
>
>
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:49)
>
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate.doExecute(TungstenAggregate.scala:69)
>
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
>
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
>
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
>
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
>
> at
> org.apache.spark.sql.execution.Exchange$$anonfun$doExecute$1.apply(Exchange.scala:142)
>
> at
> org.apache.spark.sql.execution.Exchange$$anonfun$doExecute$1.apply(Exchange.scala:141)
>
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
>
> ... 33 more
>
> Caused by: java.util.concurrent.TimeoutException: Futures timed out after
> [300 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$$anonfun$result$1.apply(package.scala:107)
>
> at
> scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
>
> at scala.concurrent.Await$.result(package.scala:107)
>
> at
> org.apache.spark.sql.execution.joins.BroadcastHashJoin.doExecute(BroadcastHashJoin.scala:110)
>
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
>
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
>
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
>
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
>
> at
> org.apache.spark.sql.execution.TungstenProject.doExecute(basicOperators.scala:86)
>
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
>
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
>
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
>
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
>
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1.apply(TungstenAggregate.scala:119)
>
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1.apply(TungstenAggregate.scala:69)
>
> at
> org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:48)
>
> ... 41 more
>
>
> 2015-09-23 15:44:09,536 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/static/sql,null}
>
> 2015-09-23 15:44:09,537 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL1/execution/json,null}
>
> 2015-09-23 15:44:09,538 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL1/execution,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL1/json,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL1,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/static/sql,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL/execution/json,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL/execution,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL/json,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/SQL,null}
>
> 2015-09-23 15:44:09,539 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/metrics/json,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages/stage/kill,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/api,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/static,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/executors/threadDump/json,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/executors/threadDump,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/executors/json,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/executors,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/environment/json,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/environment,null}
>
> 2015-09-23 15:44:09,540 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/storage/rdd/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/storage/rdd,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/storage/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/storage,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages/pool/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages/pool,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages/stage/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages/stage,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/stages,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/jobs/job/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/jobs/job,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/jobs/json,null}
>
> 2015-09-23 15:44:09,541 INFO ContextHandler: stopped
> o.s.j.s.ServletContextHandler{/jobs,null}
>
> 2015-09-23 15:44:09,595 ERROR DAGScheduler: Failed to update accumulators
> for ResultTask(0, 177)
>
> org.apache.spark.SparkException: EOF reached before Python server
> acknowledged
>
> at
> org.apache.spark.api.python.PythonAccumulatorParam.addInPlace(PythonRDD.scala:830)
>
> at
> org.apache.spark.api.python.PythonAccumulatorParam.addInPlace(PythonRDD.scala:788)
>
> at org.apache.spark.Accumulable.$plus$plus$eq(Accumulators.scala:100)
>
> at
> org.apache.spark.Accumulators$$anonfun$add$2.apply(Accumulators.scala:351)
>
> at
> org.apache.spark.Accumulators$$anonfun$add$2.apply(Accumulators.scala:346)
>
> at
> scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
>
> at
> scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
>
> at
> scala.collection.mutable.HashMap$$anonfun$foreach$1.apply(HashMap.scala:98)
>
> at
> scala.collection.mutable.HashTable$class.foreachEntry(HashTable.scala:226)
>
> at scala.collection.mutable.HashMap.foreachEntry(HashMap.scala:39)
>
> at scala.collection.mutable.HashMap.foreach(HashMap.scala:98)
>
> at
> scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
>
> at org.apache.spark.Accumulators$.add(Accumulators.scala:346)
>
> at
> org.apache.spark.scheduler.DAGScheduler.updateAccumulators(DAGScheduler.scala:934)
>
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1003)
>
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1490)
>
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
>
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
>
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
>
> 2015-09-23 15:44:09,689 ERROR Executor: Exception in task 178.0 in stage
> 0.0 (TID 178)
>
> java.net.SocketException: Broken pipe
>
> at java.net.SocketOutputStream.socketWrite0(Native Method)
>
> at java.net.SocketOutputStream.socketWrite(SocketOutputStream.java:109)
>
> at java.net.SocketOutputStream.write(SocketOutputStream.java:153)
>
> at java.io.BufferedOutputStream.flushBuffer(BufferedOutputStream.java:82)
>
> at java.io.BufferedOutputStream.write(BufferedOutputStream.java:126)
>
> at java.io.DataOutputStream.write(DataOutputStream.java:107)
>
> at java.io.FilterOutputStream.write(FilterOutputStream.java:97)
>
> at org.apache.spark.api.python.PythonRDD$.writeUTF(PythonRDD.scala:590)
>
> at
> org.apache.spark.api.python.PythonRDD$.org$apache$spark$api$python$PythonRDD$$write$1(PythonRDD.scala:410)
>
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:420)
>
> at
> org.apache.spark.api.python.PythonRDD$$anonfun$writeIteratorToStream$1.apply(PythonRDD.scala:420)
>
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
>
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
>
> at
> org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:420)
>
> at
> org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:249)
>
> at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1699)
>
> at
> org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:208)
>
> EYAD SIBAI
> Risk Engineer
>
> *iZettle ®*
> ––
>
> Mobile: +46 72 911 60 54 <+46%2072%20911%2060%2054>
> Web: www.izettle.com <http://izettle.com/>
>
