SPARK_MAJOR_VERSION=2 PYSPARK_DRIVER_PYTHON=jupyter PYSPARK_DRIVER_PYTHON_OPTS='notebook --ip=hadoop-edge-001 --no-browser --port=8888' pyspark --master yarn-client --driver-memory 25g --executor-memory 50g --num-executors 100 --conf "spark.executor.cores=10" --conf "spark.ui.port=8072" --conf "spark.driver.maxResultSize=0" --conf "spark.serializer=org.apache.spark.serializer.KryoSerializer" --conf "spark.kryoserializer.buffer.max=1024m" --conf "spark.shuffle.service.enabled=true" --conf "spark.dynamicAllocation.enabled=true" --conf "spark.dynamicAllocation.minExecutors=2" --conf "spark.dynamicAllocation.initialExecutors=100"
import pyspark
sc = pyspark.SparkContext(aplicationName="aerobus")
没有返回错误:
Py4JJavaError: An error occurred while calling None.org.apache.spark.api.java.JavaSparkContext.
: org.apache.spark.SparkException: Exception thrown in awaitResult
at org.apache.spark.rpc.RpcTimeout$$anonfun$1.applyOrElse(RpcTimeout.scala:77)
at org.apache.spark.rpc.RpcTimeout$$anonfun$1.applyOrElse(RpcTimeout.scala:75)
at scala.runtime.AbstractPartialFunction.apply(AbstractPartialFunction.scala:36)
at org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at org.apache.spark.rpc.RpcTimeout$$anonfun$addMessageIfTimeout$1.applyOrElse(RpcTimeout.scala:59)
at scala.PartialFunction$OrElse.apply(PartialFunction.scala:167)
at org.apache.spark.rpc.RpcTimeout.awaitResult(RpcTimeout.scala:83)
at org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend.requestTotalExecutors(CoarseGrainedSchedulerBackend.scala:512)
at org.apache.spark.ExecutorAllocationManager.start(ExecutorAllocationManager.scala:236)
at org.apache.spark.SparkContext$$anonfun$21.apply(SparkContext.scala:552)
at org.apache.spark.SparkContext$$anonfun$21.apply(SparkContext.scala:552)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.SparkContext.<init>(SparkContext.scala:552)
at org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:58)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:247)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:236)
at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)
at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: Failed to send RPC 5088920142760340842 to /192.168.1.64:54215: java.nio.channels.ClosedChannelException
at org.apache.spark.network.client.TransportClient$3.operationComplete(TransportClient.java:249)
at org.apache.spark.network.client.TransportClient$3.operationComplete(TransportClient.java:233)
at io.netty.util.concurrent.DefaultPromise.notifyListener0(DefaultPromise.java:514)
at io.netty.util.concurrent.DefaultPromise.notifyListenersNow(DefaultPromise.java:488)
at io.netty.util.concurrent.DefaultPromise.access$000(DefaultPromise.java:34)
at io.netty.util.concurrent.DefaultPromise$1.run(DefaultPromise.java:438)
at io.netty.util.concurrent.SingleThreadEventExecutor.runAllTasks(SingleThreadEventExecutor.java:408)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:455)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:140)
at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:144)
... 1 more
Caused by: java.nio.channels.ClosedChannelException
at io.netty.channel.AbstractChannel$AbstractUnsafe.write(...)(Unknown Source)
如何解决这个问题?
