I'm running an ETL process that joins table1 with other tables (CSV files),
one table at time (for example table1 with table2, table1 with table3, and
so on). The join is written inside a PostgreSQL istance using JDBC.The
entire process runs successfully if I use table2, table3 and table4. If I
add table5, table6, table7, the process run successfully with table5, table6
and table7 but as soon as it reaches table2 it starts displaying a lot of
messagges like this:/16/10/27 17:33:47 WARN TaskMemoryManager: Failed to
allocate a page (33554432 bytes), try again.16/10/27 17:33:47 WARN
TaskMemoryManager: Failed to allocate a page (33554432 bytes), try
again.16/10/27 17:33:47 WARN TaskMemoryManager: Failed to allocate a page
(33554432 bytes), try again....16/10/27 17:33:47 WARN TaskMemoryManager:
Failed to allocate a page (33554432 bytes), try again....Traceback (most
recent call last): File "/Volumes/Data/www/beaver/tmp/ETL_Spark/etl.py",
line 1200, in sparkdf2database(flusso['sparkdf'], schema + "." +
postgresql_tabella, "append") File
"/Volumes/Data/www/beaver/tmp/ETL_Spark/etl.py", line 144, in
sparkdf2database properties={"ApplicationName":info["nome"] + " -
Scrittura della tabella " + dest, "disableColumnSanitiser":"true",
"reWriteBatchedInserts":"true"} File
"/Volumes/Data/www/beaver/tmp/ETL_Spark/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py",
line 762, in jdbc File
"/Volumes/Data/www/beaver/tmp/ETL_Spark/spark/python/lib/py4j-0.10.3-src.zip/py4j/java_gateway.py",
line 1133, in __call__ File
"/Volumes/Data/www/beaver/tmp/ETL_Spark/spark/python/lib/pyspark.zip/pyspark/sql/utils.py",
line 63, in deco File
"/Volumes/Data/www/beaver/tmp/ETL_Spark/spark/python/lib/py4j-0.10.3-src.zip/py4j/protocol.py",
line 319, in get_return_valuepy4j.protocol.Py4JJavaError: An error occurred
while calling o301.jdbc.: org.apache.spark.SparkException: Exception thrown
in awaitResult: at
org.apache.spark.util.ThreadUtils$.awaitResult(ThreadUtils.scala:194) at
org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.doExecuteBroadcast(BroadcastExchangeExec.scala:120)
at
org.apache.spark.sql.execution.InputAdapter.doExecuteBroadcast(WholeStageCodegenExec.scala:229)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeBroadcast$1.apply(SparkPlan.scala:125)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at
org.apache.spark.sql.execution.SparkPlan.executeBroadcast(SparkPlan.scala:124)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.prepareBroadcast(BroadcastHashJoinExec.scala:98)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.codegenSemi(BroadcastHashJoinExec.scala:318)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doConsume(BroadcastHashJoinExec.scala:84)
at
org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153)
at
org.apache.spark.sql.execution.FilterExec.consume(basicPhysicalOperators.scala:79)
at
org.apache.spark.sql.execution.FilterExec.doConsume(basicPhysicalOperators.scala:194)
at
org.apache.spark.sql.execution.CodegenSupport$class.consume(WholeStageCodegenExec.scala:153)
at
org.apache.spark.sql.execution.RowDataSourceScanExec.consume(ExistingRDD.scala:150)
at
org.apache.spark.sql.execution.RowDataSourceScanExec.doProduce(ExistingRDD.scala:217)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at
org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.RowDataSourceScanExec.produce(ExistingRDD.scala:150)
at
org.apache.spark.sql.execution.FilterExec.doProduce(basicPhysicalOperators.scala:113)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at
org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.FilterExec.produce(basicPhysicalOperators.scala:79)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.doProduce(BroadcastHashJoinExec.scala:77)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at
org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.joins.BroadcastHashJoinExec.produce(BroadcastHashJoinExec.scala:38)
at
org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:40)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:83)
at
org.apache.spark.sql.execution.CodegenSupport$$anonfun$produce$1.apply(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at
org.apache.spark.sql.execution.CodegenSupport$class.produce(WholeStageCodegenExec.scala:78)
at
org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:30)
at
org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:309)
at
org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:347)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.DeserializeToObjectExec.doExecute(objects.scala:88)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:86)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:86)
at org.apache.spark.sql.Dataset.rdd$lzycompute(Dataset.scala:2357) at
org.apache.spark.sql.Dataset.rdd(Dataset.scala:2354) at
org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply$mcV$sp(Dataset.scala:2127)
at
org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply(Dataset.scala:2127)
at
org.apache.spark.sql.Dataset$$anonfun$foreachPartition$1.apply(Dataset.scala:2127)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2546) at
org.apache.spark.sql.Dataset.foreachPartition(Dataset.scala:2126) at
org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$.saveTable(JdbcUtils.scala:299)
at org.apache.spark.sql.DataFrameWriter.jdbc(DataFrameWriter.scala:441) at
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237) at
py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at
py4j.Gateway.invoke(Gateway.java:280) at
py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at
py4j.commands.CallCommand.execute(CallCommand.java:79) at
py4j.GatewayConnection.run(GatewayConnection.java:214) at
java.lang.Thread.run(Thread.java:745)Caused by:
java.util.concurrent.TimeoutException: Futures timed out after [300 seconds]
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:219)
at
scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223) at
scala.concurrent.Await$$anonfun$result$1.apply(package.scala:190) at
scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:190) at
org.apache.spark.util.ThreadUtils$.awaitResult(ThreadUtils.scala:190) ... 86
more/With smaller datasets the entire process runs without any problem. What
does this mean and how can I solve the issue?Thank you Pietro
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/TaskMemoryManager-Failed-to-allocate-a-page-tp27969.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
