[ https://issues.apache.org/jira/browse/SPARK-16870?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Liang Ke updated SPARK-16870: ----------------------------- Description: here my workload and what I found I run a large number jobs with spark-sql at the same time. and meet the error that print timeout (some job contains the broadcast-join operator) : 16/08/03 15:43:23 ERROR SparkExecuteStatementOperation: Error executing query, currentState RUNNING, 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$$anonfun$result$1.apply(package.scala:107) at scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53) at scala.concurrent.Await$.result(package.scala:107) at org.apache.spark.sql.execution.joins.BroadcastHashOuterJoin.doExecute(BroadcastHashOuterJoin.scala:113) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.Filter.doExecute(basicOperators.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.Project.doExecute(basicOperators.scala:46) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.ConvertToSafe.doExecute(rowFormatConverters.scala:56) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:201) at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127) at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52) at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecute StatementOperation$$execute(SparkExecuteStatementOperation.scala:211) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:154) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:151) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1793) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1.run(SparkExecuteStatementOperation.scala:16 4) at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 16/08/03 15:43:23 ERROR SparkExecuteStatementOperation: Error running hive query: org.apache.hive.service.cli.HiveSQLException: java.util.concurrent.TimeoutException: Futures timed out after [300 seconds] at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecute StatementOperation$$execute(SparkExecuteStatementOperation.scala:246) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:154) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:151) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1793) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1.run(SparkExecuteStatementOperation.scala:16 4) was: 16/08/03 15:43:23 ERROR SparkExecuteStatementOperation: Error executing query, currentState RUNNING, java.util.concurrent.TimeoutException: Futures timed out after [300 seconds] at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219) at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) at scala.concurrent.Await$$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.BroadcastHashOuterJoin.doExecute(BroadcastHashOuterJoin.scala:113) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.Filter.doExecute(basicOperators.scala:70) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.Project.doExecute(basicOperators.scala:46) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.ConvertToSafe.doExecute(rowFormatConverters.scala:56) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:201) at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127) at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52) at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecute StatementOperation$$execute(SparkExecuteStatementOperation.scala:211) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:154) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:151) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1793) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1.run(SparkExecuteStatementOperation.scala:16 4) at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 16/08/03 15:43:23 ERROR SparkExecuteStatementOperation: Error running hive query: org.apache.hive.service.cli.HiveSQLException: java.util.concurrent.TimeoutException: Futures timed out after [300 seconds] at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecute StatementOperation$$execute(SparkExecuteStatementOperation.scala:246) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:154) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. scala:151) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1793) at org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1.run(SparkExecuteStatementOperation.scala:16 4) Summary: add "spark.sql.broadcastTimeout" into docs/sql-programming-guide.md to help people to how to fix this timeout error when it happenned (was: Timeout in seconds for the broadcast wait time in broadcast joins ) > add "spark.sql.broadcastTimeout" into docs/sql-programming-guide.md to help > people to how to fix this timeout error when it happenned > ------------------------------------------------------------------------------------------------------------------------------------- > > Key: SPARK-16870 > URL: https://issues.apache.org/jira/browse/SPARK-16870 > Project: Spark > Issue Type: Improvement > Reporter: Liang Ke > Priority: Trivial > > here my workload and what I found > I run a large number jobs with spark-sql at the same time. and meet the error > that print timeout (some job contains the broadcast-join operator) : > 16/08/03 15:43:23 ERROR SparkExecuteStatementOperation: Error executing > query, currentState RUNNING, > java.util.concurrent.TimeoutException: Futures timed out after [300 seconds] > at > scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219) > at > scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) > at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:107) > at > scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53) > at scala.concurrent.Await$.result(package.scala:107) > at > org.apache.spark.sql.execution.joins.BroadcastHashOuterJoin.doExecute(BroadcastHashOuterJoin.scala:113) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at > org.apache.spark.sql.execution.Filter.doExecute(basicOperators.scala:70) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at > org.apache.spark.sql.execution.Project.doExecute(basicOperators.scala:46) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at > org.apache.spark.sql.execution.ConvertToSafe.doExecute(rowFormatConverters.scala:56) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at > org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:201) > at > org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:127) > at > org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:276) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at > org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) > at > org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:145) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:130) > at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52) > at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:817) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecute > StatementOperation$$execute(SparkExecuteStatementOperation.scala:211) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. > scala:154) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. > scala:151) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1793) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1.run(SparkExecuteStatementOperation.scala:16 > 4) > at > java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) > at java.util.concurrent.FutureTask.run(FutureTask.java:262) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:745) > 16/08/03 15:43:23 ERROR SparkExecuteStatementOperation: Error running hive > query: > org.apache.hive.service.cli.HiveSQLException: > java.util.concurrent.TimeoutException: Futures timed out after [300 seconds] > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecute > StatementOperation$$execute(SparkExecuteStatementOperation.scala:246) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. > scala:154) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1$$anon$2.run(SparkExecuteStatementOperation. > scala:151) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1793) > at > org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$1.run(SparkExecuteStatementOperation.scala:16 > 4) -- 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