java.lang.NullPointerException
at org.apache.flink.api.common.accumulators.SerializedListAccumulator.deserializeList(SerializedListAccumulator.java:93)
at org.apache.flink.api.scala.DataSet.collect(DataSet.scala:549)
at .<init>(<console>:22)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:734)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:983)
at scala.tools.nsc.interpreter.IMain.loadAndRunReq$1(IMain.scala:573)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:604)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:568)
at scala.tools.nsc.interpreter.ILoop.reallyInterpret$1(ILoop.scala:760)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:805)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:717)
at scala.tools.nsc.interpreter.ILoop.processLine$1(ILoop.scala:581)
at scala.tools.nsc.interpreter.ILoop.innerLoop$1(ILoop.scala:588)
at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:591)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(ILoop.scala:601)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(ILoop.scala:598)
at scala.reflect.io.Streamable$Chars$class.applyReader(Streamable.scala:104)
at scala.reflect.io.File.applyReader(File.scala:82)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ILoop.scala:598)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(ILoop.scala:598)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(ILoop.scala:598)
at scala.tools.nsc.interpreter.ILoop.savingReplayStack(ILoop.scala:130)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1.apply(ILoop.scala:597)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1.apply(ILoop.scala:597)
at scala.tools.nsc.interpreter.ILoop.savingReader(ILoop.scala:135)
at scala.tools.nsc.interpreter.ILoop.interpretAllFrom(ILoop.scala:596)
at scala.tools.nsc.interpreter.ILoop$$anonfun$loadCommand$1.apply(ILoop.scala:660)
at scala.tools.nsc.interpreter.ILoop$$anonfun$loadCommand$1.apply(ILoop.scala:659)
at scala.tools.nsc.interpreter.ILoop.withFile(ILoop.scala:653)
at scala.tools.nsc.interpreter.ILoop.loadCommand(ILoop.scala:659)
at scala.tools.nsc.interpreter.ILoop$$anonfun$standardCommands$7.apply(ILoop.scala:262)
at scala.tools.nsc.interpreter.ILoop$$anonfun$standardCommands$7.apply(ILoop.scala:262)
at scala.tools.nsc.interpreter.LoopCommands$LineCmd.apply(LoopCommands.scala:81)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:712)
at scala.tools.nsc.interpreter.ILoop.processLine$1(ILoop.scala:581)
at scala.tools.nsc.interpreter.ILoop.innerLoop$1(ILoop.scala:588)
at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:591)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:882)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:837)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:837)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:837)
at org.apache.flink.api.scala.FlinkShell$.startShell(FlinkShell.scala:84)
at org.apache.flink.api.scala.FlinkShell$.main(FlinkShell.scala:54)
at org.apache.flink.api.scala.FlinkShell.main(FlinkShell.scala)
我在linux系统（16MB RAM）上工作。那可能是什么问题？
我的代码（改编自https://ci.apache.org/projects/flink/flink-docs-release-0.9/quickstart/scala_api_quickstart.html）：
var filename = new String(<myFileName>)
var text = env.readTextFile(filename)
var counts = text.flatMap { _.toLowerCase.split("\\W+") }.map { (_, 1) }.groupBy(0).sum(1)
var result = counts.collect()
第1部分：
org.apache.flink.client.program.ProgramInvocationException: The program execution failed: Job execution failed.
at org.apache.flink.client.program.Client.run(Client.java:413)
at org.apache.flink.client.program.Client.run(Client.java:356)
at org.apache.flink.client.program.Client.run(Client.java:349)
at org.apache.flink.client.RemoteExecutor.executePlanWithJars(RemoteExecutor.java:89)
at org.apache.flink.client.RemoteExecutor.executePlan(RemoteExecutor.java:82)
at org.apache.flink.api.java.ScalaShellRemoteEnvironment.execute(ScalaShellRemoteEnvironment.java:68)
at org.apache.flink.api.java.ExecutionEnvironment.execute(ExecutionEnvironment.java:789)
at org.apache.flink.api.scala.ExecutionEnvironment.execute(ExecutionEnvironment.scala:576)
at org.apache.flink.api.scala.DataSet.collect(DataSet.scala:544)
at .<init>(<console>:28)
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:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:734)
at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:983)
at scala.tools.nsc.interpreter.IMain.loadAndRunReq$1(IMain.scala:573)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:604)
at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:568)
at scala.tools.nsc.interpreter.ILoop.reallyInterpret$1(ILoop.scala:760)
at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:805)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:717)
at scala.tools.nsc.interpreter.ILoop.processLine$1(ILoop.scala:581)
at scala.tools.nsc.interpreter.ILoop.innerLoop$1(ILoop.scala:588)
at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:591)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(ILoop.scala:601)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1$$anonfun$apply$mcV$sp$2.apply(ILoop.scala:598)
at scala.reflect.io.Streamable$Chars$class.applyReader(Streamable.scala:104)
at scala.reflect.io.File.applyReader(File.scala:82)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(ILoop.scala:598)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(ILoop.scala:598)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1$$anonfun$apply$mcV$sp$1.apply(ILoop.scala:598)
at scala.tools.nsc.interpreter.ILoop.savingReplayStack(ILoop.scala:130)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1.apply(ILoop.scala:597)
at scala.tools.nsc.interpreter.ILoop$$anonfun$interpretAllFrom$1.apply(ILoop.scala:597)
at scala.tools.nsc.interpreter.ILoop.savingReader(ILoop.scala:135)
at scala.tools.nsc.interpreter.ILoop.interpretAllFrom(ILoop.scala:596)
at scala.tools.nsc.interpreter.ILoop$$anonfun$loadCommand$1.apply(ILoop.scala:660)
at scala.tools.nsc.interpreter.ILoop$$anonfun$loadCommand$1.apply(ILoop.scala:659)
at scala.tools.nsc.interpreter.ILoop.withFile(ILoop.scala:653)
at scala.tools.nsc.interpreter.ILoop.loadCommand(ILoop.scala:659)
at scala.tools.nsc.interpreter.ILoop$$anonfun$standardCommands$7.apply(ILoop.scala:262)
at scala.tools.nsc.interpreter.ILoop$$anonfun$standardCommands$7.apply(ILoop.scala:262)
at scala.tools.nsc.interpreter.LoopCommands$LineCmd.apply(LoopCommands.scala:81)
at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:712)
at scala.tools.nsc.interpreter.ILoop.processLine$1(ILoop.scala:581)
at scala.tools.nsc.interpreter.ILoop.innerLoop$1(ILoop.scala:588)
at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:591)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:882)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:837)
at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:837)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:837)
at org.apache.flink.api.scala.FlinkShell$.startShell(FlinkShell.scala:84)
at org.apache.flink.api.scala.FlinkShell$.main(FlinkShell.scala:54)
at org.apache.flink.api.scala.FlinkShell.main(FlinkShell.scala)
第2部分：
Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$receiveWithLogMessages$1.applyOrElse(JobManager.scala:314)
at scala.runtime.AbstractPartialFunction$mcVL$sp.apply$mcVL$sp(AbstractPartialFunction.scala:33)
at scala.runtime.AbstractPartialFunction$mcVL$sp.apply(AbstractPartialFunction.scala:33)
at scala.runtime.AbstractPartialFunction$mcVL$sp.apply(AbstractPartialFunction.scala:25)
at org.apache.flink.runtime.ActorLogMessages$$anon$1.apply(ActorLogMessages.scala:43)
at org.apache.flink.runtime.ActorLogMessages$$anon$1.apply(ActorLogMessages.scala:29)
at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:118)
at org.apache.flink.runtime.ActorLogMessages$$anon$1.applyOrElse(ActorLogMessages.scala:29)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at org.apache.flink.runtime.jobmanager.JobManager.aroundReceive(JobManager.scala:92)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:254)
at akka.dispatch.Mailbox.run(Mailbox.scala:221)
at akka.dispatch.Mailbox.exec(Mailbox.scala:231)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException: Not enough free slots available to run the job. You can decrease the operator parallelism or increase the number of slots per TaskManager in the configuration. Task to schedule: < Attempt #0 (CHAIN DataSource (at .<init>(<console>:26) (org.apache.flink.api.java.io.TextInputFormat)) -> FlatMap (FlatMap at .<init>(<console>:27)) -> Map (Map at .<init>(<console>:27)) -> Combine(SUM(1)) (2/4)) @ (unassigned) - [SCHEDULED] > with groupID < fc507fbb50fea681c726ca1d824c7577 > in sharing group < SlotSharingGroup [fc507fbb50fea681c726ca1d824c7577, fb90f780c9d5a4a9dbf983cb06bec946, 52b8abe5a21ed808f0473a599d89f046] >. Resources available to scheduler: Number of instances=1, total number of slots=1, available slots=0
at org.apache.flink.runtime.jobmanager.scheduler.Scheduler.scheduleTask(Scheduler.java:250)
at org.apache.flink.runtime.jobmanager.scheduler.Scheduler.scheduleImmediately(Scheduler.java:126)
at org.apache.flink.runtime.executiongraph.Execution.scheduleForExecution(Execution.java:271)
at org.apache.flink.runtime.executiongraph.ExecutionVertex.scheduleForExecution(ExecutionVertex.java:430)
at org.apache.flink.runtime.executiongraph.ExecutionJobVertex.scheduleAll(ExecutionJobVertex.java:307)
at org.apache.flink.runtime.executiongraph.ExecutionGraph.scheduleForExecution(ExecutionGraph.java:508)
at org.apache.flink.runtime.jobmanager.JobManager.org$apache$flink$runtime$jobmanager$JobManager$$submitJob(JobManager.scala:606)
at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$receiveWithLogMessages$1.applyOrElse(JobManager.scala:190)
... 18 more
这是否意味着taskmanager.numberOfTaskSlots？在我的flink-conf.yaml中将此键设置为4.但是如何在shell中设置它？
答案 0 :(得分：3)
你问了两个问题：
print()不能用于大DataSet s？在count()上使用collect()，print()或DataSet时，必须通过作业管理器传输已在任务管理器上分区的所有数据给客户。最好是仅使用这些方法进行测试或实现小DataSet个。对于大数据，请使用Apache Flink中提供的其中一个接收器，例如： writeAsTextFile(..)。对于每个并行任务，将创建一个输出文件。
如果您仍想将所有数据传输到客户端，可以通过增加Akka的帧大小来实现。 Akka是Flink在引擎盖下使用的消息传递库。为此，请在akka.framesize中设置flink-conf.yaml。默认值为10485760字节（10 MB）。 akka.framesize: 100mb会将其增加到100 MB。
对于Apache Flink 1.0，一些提交者已考虑删除此限制，并且已经有拉动请求使用其他传输方式来处理大型物化数据集。
Flink的默认配置为每个任务管理器启动一个任务槽。在本地模式下启动Scala shell时，它只启动一个任务管理器。因此，任务槽的总数是一个。将并行度更改为N时，至少需要N个任务槽才能并行执行此操作。因此，要么增加flink-conf.yaml中的任务槽数，要么启动其他任务管理器。如果你只是在本地运行，我建议只增加任务槽的数量。有关详细信息，请参阅http://flink.apache.org上的Flink文档。
编辑：如果运行Scala-Shell，则只使用一个任务管理器启动嵌入式Flink集群。您可以使用./bin/start-local.sh启动本地群集，然后使用Scala shell的主机和端口参数（host：localhost，port：6123）连接到它。