Skip to content

Instantly share code, notes, and snippets.

@MLnick
Created June 9, 2017 08:11
Show Gist options
  • Save MLnick/5f26152f97ae8473f807c6895817cf72 to your computer and use it in GitHub Desktop.
Save MLnick/5f26152f97ae8473f807c6895817cf72 to your computer and use it in GitHub Desktop.
Failed -------------------------------------------------------------------------
1. Error: gapply() and gapplyCollect() on a DataFrame (@test_sparkSQL.R#2853) --
org.apache.spark.SparkException: Job aborted due to stage failure: Task 40 in stage 985.0 failed 1 times, most recent failure: Lost task 40.0 in stage 985.0 (TID 13694, localhost, executor driver): org.apache.spark.SparkException: R computation failed with
[1] 2
[1] 1
[1] 3
[1] 2
[1] 1
[1] 3
[1] 2[1]
2
[1] 2
[1] 2
[1] 2
[1] 2
ignoring SIGPIPE signal
ignoring SIGPIPE signal
at org.apache.spark.api.r.RRunner.compute(RRunner.scala:108)
at org.apache.spark.sql.execution.FlatMapGroupsInRExec$$anonfun$13.apply(objects.scala:432)
at org.apache.spark.sql.execution.FlatMapGroupsInRExec$$anonfun$13.apply(objects.scala:414)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:335)
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$$failJobAndIndependentStages(DAGScheduler.scala:1499)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2043)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2062)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2087)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:936)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.collect(RDD.scala:935)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:278)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2851)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2388)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2388)
at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2835)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2834)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2388)
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.api.r.RBackendHandler.handleMethodCall(RBackendHandler.scala:167)
at org.apache.spark.api.r.RBackendHandler.channelRead0(RBackendHandler.scala:108)
at org.apache.spark.api.r.RBackendHandler.channelRead0(RBackendHandler.scala:40)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1294)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:911)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:131)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:643)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:566)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:480)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:442)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:131)
at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:144)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: R computation failed with
[1] 2
[1] 1
[1] 3
[1] 2
[1] 1
[1] 3
[1] 2[1]
2
[1] 2
[1] 2
[1] 2
[1] 2
ignoring SIGPIPE signal
ignoring SIGPIPE signal
at
1: gapplyCollect(df, c("a", "c"), function(key, x) {
y <- data.frame(key, mean(x$b), stringsAsFactors = FALSE)
colnames(y) <- c("a", "c", "avg")
y
}) at /home/npentreath/spark-2.2.0/R/lib/SparkR/tests/testthat/test_sparkSQL.R:2853
2: gapplyCollect(df, c("a", "c"), function(key, x) {
y <- data.frame(key, mean(x$b), stringsAsFactors = FALSE)
colnames(y) <- c("a", "c", "avg")
y
})
3: .local(x, ...)
4: gapplyCollect(grouped, func)
5: gapplyCollect(grouped, func)
6: .local(x, ...)
7: callJMethod(gdf@sdf, "collect")
8: invokeJava(isStatic = FALSE, objId$id, methodName, ...)
9: handleErrors(returnStatus, conn)
10: stop(readString(conn))
DONE ===========================================================================
Error: Test failures
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment