Glenn Weidner created SYSTEMML-911:
--------------------------------------
Summary: GC overhead limit exceeded running LinearRegressionCG
from MLContext
Key: SYSTEMML-911
URL: https://issues.apache.org/jira/browse/SYSTEMML-911
Project: SystemML
Issue Type: Bug
Components: APIs, Runtime
Reporter: Glenn Weidner
Running attached scala from spark-shell using original MLContext against Spark
1.6 (or 2.0) encountered out-of-memory GC overhead limit exceeded:
uncaught exception during compilation: java.lang.AssertionError
org.apache.sysml.runtime.DMLRuntimeException:
org.apache.sysml.runtime.DMLRuntimeException: ERROR: Runtime error in program
block generated from statement block between lines 3 and 9 -- Error evaluating
instruction: SPARK°rblk°X·MATRIX·DOUBLE°_mVar2·MATRIX·DOUBLE°1000°1000°true
at
org.apache.sysml.runtime.controlprogram.Program.execute(Program.java:152)
at
org.apache.sysml.api.MLContext.executeUsingSimplifiedCompilationChain(MLContext.java:1398)
at
org.apache.sysml.api.MLContext.compileAndExecuteScript(MLContext.java:1257)
at org.apache.sysml.api.MLContext.executeScript(MLContext.java:1146)
at org.apache.sysml.api.MLContext.executeScript(MLContext.java:1136)
at org.apache.sysml.api.MLContext.executeScript(MLContext.java:1131)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:41)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:43)
at $iwC$$iwC$$iwC.<init>(<console>:45)
at $iwC$$iwC.<init>(<console>:47)
at $iwC.<init>(<console>:49)
at <init>(<console>:51)
at .<init>(<console>:55)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at
org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
at
org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at
org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at
org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.apache.sysml.runtime.DMLRuntimeException: ERROR: Runtime error
in program block generated from statement block between lines 3 and 9 -- Error
evaluating instruction:
SPARK°rblk°X·MATRIX·DOUBLE°_mVar2·MATRIX·DOUBLE°1000°1000°true
at
org.apache.sysml.runtime.controlprogram.ProgramBlock.executeSingleInstruction(ProgramBlock.java:333)
at
org.apache.sysml.runtime.controlprogram.ProgramBlock.executeInstructions(ProgramBlock.java:222)
at
org.apache.sysml.runtime.controlprogram.ProgramBlock.execute(ProgramBlock.java:166)
at
org.apache.sysml.runtime.controlprogram.Program.execute(Program.java:145)
... 51 more
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure:
Task 0 in stage 6.0 failed 1 times, most recent failure: Lost task 0.0 in stage
6.0 (TID 10, localhost): java.lang.OutOfMemoryError: GC overhead limit exceeded
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$RowToBinaryBlockFunctionHelper.flushBlocksToList(RDDConverterUtilsExt.java:800)
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$RowToBinaryBlockFunctionHelper.convertToBinaryBlock(RDDConverterUtilsExt.java:736)
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$DataFrameToBinaryBlockFunction.call(RDDConverterUtilsExt.java:463)
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$DataFrameToBinaryBlockFunction.call(RDDConverterUtilsExt.java:448)
at
org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:192)
at
org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:192)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1952)
at org.apache.spark.rdd.RDD$$anonfun$aggregate$1.apply(RDD.scala:1114)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.aggregate(RDD.scala:1107)
at
org.apache.spark.api.java.JavaRDDLike$class.aggregate(JavaRDDLike.scala:411)
at
org.apache.spark.api.java.AbstractJavaRDDLike.aggregate(JavaRDDLike.scala:46)
at
org.apache.sysml.runtime.instructions.spark.utils.SparkUtils.computeNNZFromBlocks(SparkUtils.java:458)
at
org.apache.sysml.runtime.controlprogram.context.SparkExecutionContext.writeRDDtoHDFS(SparkExecutionContext.java:802)
at
org.apache.sysml.runtime.controlprogram.caching.MatrixObject.readBlobFromRDD(MatrixObject.java:612)
at
org.apache.sysml.runtime.controlprogram.caching.MatrixObject.readBlobFromRDD(MatrixObject.java:62)
at
org.apache.sysml.runtime.controlprogram.caching.CacheableData.acquireRead(CacheableData.java:440)
at
org.apache.sysml.hops.recompile.Recompiler.executeInMemoryReblock(Recompiler.java:2067)
at
org.apache.sysml.runtime.instructions.spark.ReblockSPInstruction.processInstruction(ReblockSPInstruction.java:100)
at
org.apache.sysml.runtime.controlprogram.ProgramBlock.executeSingleInstruction(ProgramBlock.java:303)
... 54 more
Caused by: java.lang.OutOfMemoryError: GC overhead limit exceeded
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$RowToBinaryBlockFunctionHelper.flushBlocksToList(RDDConverterUtilsExt.java:800)
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$RowToBinaryBlockFunctionHelper.convertToBinaryBlock(RDDConverterUtilsExt.java:736)
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$DataFrameToBinaryBlockFunction.call(RDDConverterUtilsExt.java:463)
at
org.apache.sysml.runtime.instructions.spark.utils.RDDConverterUtilsExt$DataFrameToBinaryBlockFunction.call(RDDConverterUtilsExt.java:448)
at
org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:192)
at
org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$7$1.apply(JavaRDDLike.scala:192)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
