java.lang.OutOfMemoryError: GC overhead limit exceeded

DataStax JIRA | Rahul Shukla | 1 year ago
  1. 0

    I am trying to run below code with spark 1.4.0 and its not working {code:scala} import org.apache.spark.SparkConf import org.apache.spark.SparkContext import com.datastax.spark.connector._ object Hello { def main(args: Array[String]): Unit = { val conf = new SparkConf(true) .set("spark.cassandra.connection.host", "127.0.0.1") .setMaster("local") .setAppName("POS Producer") val sc = new SparkContext(conf) val rdd = sc.cassandraTable[POS]("store", "sales_fact"); println("count => "+rdd.count()) rdd.collect.foreach(println); } } {code} build file : {code:java} name := "hello-scala" version := "1.0" scalaVersion := "2.11.0" libraryDependencies += "org.scalatest" % "scalatest_2.11" % "2.1.3" % "test" libraryDependencies += "org.apache.spark" % "spark-core_2.11" % "1.4.0" libraryDependencies += "com.datastax.spark" % "spark-cassandra-connector_2.11" % "1.4.0-M1" {code} Console Log : {code:java} Connected to the target VM, address: '127.0.0.1:50502', transport: 'socket' Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties 15/07/09 16:23:18 INFO SparkContext: Running Spark version 1.4.0 15/07/09 16:23:18 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 15/07/09 16:23:19 WARN Utils: Your hostname, ULTP-438 resolves to a loopback address: 127.0.1.1; using 172.25.30.61 instead (on interface eth0) 15/07/09 16:23:19 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address 15/07/09 16:23:19 INFO SecurityManager: Changing view acls to: synerzip 15/07/09 16:23:19 INFO SecurityManager: Changing modify acls to: synerzip 15/07/09 16:23:19 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(synerzip); users with modify permissions: Set(synerzip) 15/07/09 16:23:20 INFO Slf4jLogger: Slf4jLogger started 15/07/09 16:23:20 INFO Remoting: Starting remoting 15/07/09 16:23:20 INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkDriver@172.25.30.61:38696] 15/07/09 16:23:20 INFO Utils: Successfully started service 'sparkDriver' on port 38696. 15/07/09 16:23:20 INFO SparkEnv: Registering MapOutputTracker 15/07/09 16:23:20 INFO SparkEnv: Registering BlockManagerMaster 15/07/09 16:23:20 INFO DiskBlockManager: Created local directory at /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db/blockmgr-0417ff5d-3866-41dd-b63f-da5f37dd0ca6 15/07/09 16:23:20 INFO MemoryStore: MemoryStore started with capacity 1915.4 MB 15/07/09 16:23:20 INFO HttpFileServer: HTTP File server directory is /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db/httpd-d0366739-785f-4a11-8c8c-ad6414a497e4 15/07/09 16:23:20 INFO HttpServer: Starting HTTP Server 15/07/09 16:23:20 INFO Utils: Successfully started service 'HTTP file server' on port 41201. 15/07/09 16:23:20 INFO SparkEnv: Registering OutputCommitCoordinator 15/07/09 16:23:21 INFO Utils: Successfully started service 'SparkUI' on port 4040. 15/07/09 16:23:21 INFO SparkUI: Started SparkUI at http://172.25.30.61:4040 15/07/09 16:23:21 INFO Executor: Starting executor ID driver on host localhost 15/07/09 16:23:21 INFO Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port 57362. 15/07/09 16:23:21 INFO NettyBlockTransferService: Server created on 57362 15/07/09 16:23:21 INFO BlockManagerMaster: Trying to register BlockManager 15/07/09 16:23:21 INFO BlockManagerMasterEndpoint: Registering block manager localhost:57362 with 1915.4 MB RAM, BlockManagerId(driver, localhost, 57362) 15/07/09 16:23:21 INFO BlockManagerMaster: Registered BlockManager 15/07/09 16:23:24 INFO Cluster: New Cassandra host /127.0.0.1:9042 added 15/07/09 16:23:24 INFO CassandraConnector: Connected to Cassandra cluster: Test Cluster 15/07/09 16:23:25 INFO CassandraConnector: Disconnected from Cassandra cluster: Test Cluster Exception in thread "main" java.lang.OutOfMemoryError: GC overhead limit exceeded at scala.collection.immutable.VectorBuilder.<init>(Vector.scala:706) at scala.collection.immutable.Vector$.newBuilder(Vector.scala:22) at scala.collection.generic.GenericTraversableTemplate$class.genericBuilder(GenericTraversableTemplate.scala:70) at scala.collection.AbstractTraversable.genericBuilder(Traversable.scala:104) at scala.collection.generic.GenTraversableFactory$GenericCanBuildFrom.apply(GenTraversableFactory.scala:57) at scala.collection.generic.GenTraversableFactory$GenericCanBuildFrom.apply(GenTraversableFactory.scala:52) at scala.collection.TraversableLike$class.builder$1(TraversableLike.scala:240) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at scala.collection.AbstractTraversable.map(Traversable.scala:104) at com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$$anonfun$partitions$2.apply(CassandraRDDPartitioner.scala:137) at com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$$anonfun$partitions$2.apply(CassandraRDDPartitioner.scala:135) at scala.collection.TraversableLike$WithFilter$$anonfun$map$2.apply(TraversableLike.scala:728) at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186) at scala.collection.TraversableLike$WithFilter.map(TraversableLike.scala:727) at com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner.partitions(CassandraRDDPartitioner.scala:135) at com.datastax.spark.connector.rdd.CassandraTableScanRDD.getPartitions(CassandraTableScanRDD.scala:120) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1802) at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:979) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109) at org.apache.spark.rdd.RDD.withScope(RDD.scala:286) at org.apache.spark.rdd.RDD.reduce(RDD.scala:961) at com.datastax.spark.connector.rdd.CassandraTableScanRDD.count(CassandraTableScanRDD.scala:247) at Hello$.main(Hello.scala:13) at Hello.main(Hello.scala) 15/07/09 16:29:57 INFO SparkContext: Invoking stop() from shutdown hook 15/07/09 16:29:57 INFO SparkUI: Stopped Spark web UI at http://172.25.30.61:4040 15/07/09 16:29:57 INFO DAGScheduler: Stopping DAGScheduler 15/07/09 16:29:57 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped! 15/07/09 16:29:57 INFO Utils: path = /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db/blockmgr-0417ff5d-3866-41dd-b63f-da5f37dd0ca6, already present as root for deletion. 15/07/09 16:29:57 INFO MemoryStore: MemoryStore cleared 15/07/09 16:29:57 INFO BlockManager: BlockManager stopped 15/07/09 16:29:57 INFO BlockManagerMaster: BlockManagerMaster stopped 15/07/09 16:29:57 INFO SparkContext: Successfully stopped SparkContext 15/07/09 16:29:57 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped! 15/07/09 16:29:57 INFO Utils: Shutdown hook called Disconnected from the target VM, address: '127.0.0.1:50502', transport: 'socket' 15/07/09 16:29:57 INFO Utils: Deleting directory /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db Process finished with exit code 1 {code} The same code is working with spark 1.3.1

    DataStax JIRA | 1 year ago | Rahul Shukla
    java.lang.OutOfMemoryError: GC overhead limit exceeded
  2. 0

    I am trying to run below code with spark 1.4.0 and its not working {code:scala} import org.apache.spark.SparkConf import org.apache.spark.SparkContext import com.datastax.spark.connector._ object Hello { def main(args: Array[String]): Unit = { val conf = new SparkConf(true) .set("spark.cassandra.connection.host", "127.0.0.1") .setMaster("local") .setAppName("POS Producer") val sc = new SparkContext(conf) val rdd = sc.cassandraTable[POS]("store", "sales_fact"); println("count => "+rdd.count()) rdd.collect.foreach(println); } } {code} build file : {code:java} name := "hello-scala" version := "1.0" scalaVersion := "2.11.0" libraryDependencies += "org.scalatest" % "scalatest_2.11" % "2.1.3" % "test" libraryDependencies += "org.apache.spark" % "spark-core_2.11" % "1.4.0" libraryDependencies += "com.datastax.spark" % "spark-cassandra-connector_2.11" % "1.4.0-M1" {code} Console Log : {code:java} Connected to the target VM, address: '127.0.0.1:50502', transport: 'socket' Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties 15/07/09 16:23:18 INFO SparkContext: Running Spark version 1.4.0 15/07/09 16:23:18 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 15/07/09 16:23:19 WARN Utils: Your hostname, ULTP-438 resolves to a loopback address: 127.0.1.1; using 172.25.30.61 instead (on interface eth0) 15/07/09 16:23:19 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address 15/07/09 16:23:19 INFO SecurityManager: Changing view acls to: synerzip 15/07/09 16:23:19 INFO SecurityManager: Changing modify acls to: synerzip 15/07/09 16:23:19 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(synerzip); users with modify permissions: Set(synerzip) 15/07/09 16:23:20 INFO Slf4jLogger: Slf4jLogger started 15/07/09 16:23:20 INFO Remoting: Starting remoting 15/07/09 16:23:20 INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkDriver@172.25.30.61:38696] 15/07/09 16:23:20 INFO Utils: Successfully started service 'sparkDriver' on port 38696. 15/07/09 16:23:20 INFO SparkEnv: Registering MapOutputTracker 15/07/09 16:23:20 INFO SparkEnv: Registering BlockManagerMaster 15/07/09 16:23:20 INFO DiskBlockManager: Created local directory at /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db/blockmgr-0417ff5d-3866-41dd-b63f-da5f37dd0ca6 15/07/09 16:23:20 INFO MemoryStore: MemoryStore started with capacity 1915.4 MB 15/07/09 16:23:20 INFO HttpFileServer: HTTP File server directory is /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db/httpd-d0366739-785f-4a11-8c8c-ad6414a497e4 15/07/09 16:23:20 INFO HttpServer: Starting HTTP Server 15/07/09 16:23:20 INFO Utils: Successfully started service 'HTTP file server' on port 41201. 15/07/09 16:23:20 INFO SparkEnv: Registering OutputCommitCoordinator 15/07/09 16:23:21 INFO Utils: Successfully started service 'SparkUI' on port 4040. 15/07/09 16:23:21 INFO SparkUI: Started SparkUI at http://172.25.30.61:4040 15/07/09 16:23:21 INFO Executor: Starting executor ID driver on host localhost 15/07/09 16:23:21 INFO Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port 57362. 15/07/09 16:23:21 INFO NettyBlockTransferService: Server created on 57362 15/07/09 16:23:21 INFO BlockManagerMaster: Trying to register BlockManager 15/07/09 16:23:21 INFO BlockManagerMasterEndpoint: Registering block manager localhost:57362 with 1915.4 MB RAM, BlockManagerId(driver, localhost, 57362) 15/07/09 16:23:21 INFO BlockManagerMaster: Registered BlockManager 15/07/09 16:23:24 INFO Cluster: New Cassandra host /127.0.0.1:9042 added 15/07/09 16:23:24 INFO CassandraConnector: Connected to Cassandra cluster: Test Cluster 15/07/09 16:23:25 INFO CassandraConnector: Disconnected from Cassandra cluster: Test Cluster Exception in thread "main" java.lang.OutOfMemoryError: GC overhead limit exceeded at scala.collection.immutable.VectorBuilder.<init>(Vector.scala:706) at scala.collection.immutable.Vector$.newBuilder(Vector.scala:22) at scala.collection.generic.GenericTraversableTemplate$class.genericBuilder(GenericTraversableTemplate.scala:70) at scala.collection.AbstractTraversable.genericBuilder(Traversable.scala:104) at scala.collection.generic.GenTraversableFactory$GenericCanBuildFrom.apply(GenTraversableFactory.scala:57) at scala.collection.generic.GenTraversableFactory$GenericCanBuildFrom.apply(GenTraversableFactory.scala:52) at scala.collection.TraversableLike$class.builder$1(TraversableLike.scala:240) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at scala.collection.AbstractTraversable.map(Traversable.scala:104) at com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$$anonfun$partitions$2.apply(CassandraRDDPartitioner.scala:137) at com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$$anonfun$partitions$2.apply(CassandraRDDPartitioner.scala:135) at scala.collection.TraversableLike$WithFilter$$anonfun$map$2.apply(TraversableLike.scala:728) at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186) at scala.collection.TraversableLike$WithFilter.map(TraversableLike.scala:727) at com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner.partitions(CassandraRDDPartitioner.scala:135) at com.datastax.spark.connector.rdd.CassandraTableScanRDD.getPartitions(CassandraTableScanRDD.scala:120) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217) at scala.Option.getOrElse(Option.scala:121) at org.apache.spark.rdd.RDD.partitions(RDD.scala:217) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1802) at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:979) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109) at org.apache.spark.rdd.RDD.withScope(RDD.scala:286) at org.apache.spark.rdd.RDD.reduce(RDD.scala:961) at com.datastax.spark.connector.rdd.CassandraTableScanRDD.count(CassandraTableScanRDD.scala:247) at Hello$.main(Hello.scala:13) at Hello.main(Hello.scala) 15/07/09 16:29:57 INFO SparkContext: Invoking stop() from shutdown hook 15/07/09 16:29:57 INFO SparkUI: Stopped Spark web UI at http://172.25.30.61:4040 15/07/09 16:29:57 INFO DAGScheduler: Stopping DAGScheduler 15/07/09 16:29:57 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped! 15/07/09 16:29:57 INFO Utils: path = /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db/blockmgr-0417ff5d-3866-41dd-b63f-da5f37dd0ca6, already present as root for deletion. 15/07/09 16:29:57 INFO MemoryStore: MemoryStore cleared 15/07/09 16:29:57 INFO BlockManager: BlockManager stopped 15/07/09 16:29:57 INFO BlockManagerMaster: BlockManagerMaster stopped 15/07/09 16:29:57 INFO SparkContext: Successfully stopped SparkContext 15/07/09 16:29:57 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped! 15/07/09 16:29:57 INFO Utils: Shutdown hook called Disconnected from the target VM, address: '127.0.0.1:50502', transport: 'socket' 15/07/09 16:29:57 INFO Utils: Deleting directory /tmp/spark-6e06440e-2351-4063-a6fa-3e809f3d50db Process finished with exit code 1 {code} The same code is working with spark 1.3.1

    DataStax JIRA | 1 year ago | Rahul Shukla
    java.lang.OutOfMemoryError: GC overhead limit exceeded
  3. 0

    0.13.7-M3 - memory leak, or large increase in memory usage?

    GitHub | 2 years ago | paddymahoney
    java.lang.OutOfMemoryError: GC overhead limit exceeded
  4. Speed up your debug routine!

    Automated exception search integrated into your IDE

  5. 0

    GC overhead error in scala while computing strongly connected components of graph

    Stack Overflow | 2 years ago | user2460990
    java.lang.OutOfMemoryError: GC overhead limit exceeded

    Not finding the right solution?
    Take a tour to get the most out of Samebug.

    Tired of useless tips?

    Automated exception search integrated into your IDE

    Root Cause Analysis

    1. java.lang.OutOfMemoryError

      GC overhead limit exceeded

      at scala.collection.immutable.VectorBuilder.<init>()
    2. Scala
      AbstractTraversable.map
      1. scala.collection.immutable.VectorBuilder.<init>(Vector.scala:706)
      2. scala.collection.immutable.Vector$.newBuilder(Vector.scala:22)
      3. scala.collection.generic.GenericTraversableTemplate$class.genericBuilder(GenericTraversableTemplate.scala:70)
      4. scala.collection.AbstractTraversable.genericBuilder(Traversable.scala:104)
      5. scala.collection.generic.GenTraversableFactory$GenericCanBuildFrom.apply(GenTraversableFactory.scala:57)
      6. scala.collection.generic.GenTraversableFactory$GenericCanBuildFrom.apply(GenTraversableFactory.scala:52)
      7. scala.collection.TraversableLike$class.builder$1(TraversableLike.scala:240)
      8. scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
      9. scala.collection.AbstractTraversable.map(Traversable.scala:104)
      9 frames
    3. spark-cassandra-connector
      CassandraRDDPartitioner$$anonfun$partitions$2.apply
      1. com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$$anonfun$partitions$2.apply(CassandraRDDPartitioner.scala:137)
      2. com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner$$anonfun$partitions$2.apply(CassandraRDDPartitioner.scala:135)
      2 frames
    4. Scala
      TraversableLike$WithFilter.map
      1. scala.collection.TraversableLike$WithFilter$$anonfun$map$2.apply(TraversableLike.scala:728)
      2. scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
      3. scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
      4. scala.collection.TraversableLike$WithFilter.map(TraversableLike.scala:727)
      4 frames
    5. spark-cassandra-connector
      CassandraTableScanRDD.getPartitions
      1. com.datastax.spark.connector.rdd.partitioner.CassandraRDDPartitioner.partitions(CassandraRDDPartitioner.scala:135)
      2. com.datastax.spark.connector.rdd.CassandraTableScanRDD.getPartitions(CassandraTableScanRDD.scala:120)
      2 frames
    6. Spark
      RDD$$anonfun$partitions$2.apply
      1. org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
      2. org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
      2 frames
    7. Scala
      Option.getOrElse
      1. scala.Option.getOrElse(Option.scala:121)
      1 frame
    8. Spark
      RDD.reduce
      1. org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
      2. org.apache.spark.SparkContext.runJob(SparkContext.scala:1802)
      3. org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:979)
      4. org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
      5. org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:109)
      6. org.apache.spark.rdd.RDD.withScope(RDD.scala:286)
      7. org.apache.spark.rdd.RDD.reduce(RDD.scala:961)
      7 frames
    9. spark-cassandra-connector
      CassandraTableScanRDD.count
      1. com.datastax.spark.connector.rdd.CassandraTableScanRDD.count(CassandraTableScanRDD.scala:247)
      1 frame
    10. Unknown
      Hello.main
      1. Hello$.main(Hello.scala:13)
      2. Hello.main(Hello.scala)
      2 frames