[root@node1 ~]# /export/server/spark/bin/spark-submit --master yarn --py-files /home/projects/01_RDD/example/defs.py /home/projects/01_RDD/example/main.py
24/04/18 11:04:11 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
24/04/18 11:05:01 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0) (node3 executor 1): java.io.IOException: Cannot run program "python3": error=2, 没有那个文件或目录
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1048)
at org.apache.spark.api.python.PythonWorkerFactory.startDaemon(PythonWorkerFactory.scala:209)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:132)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:105)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:119)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:145)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:386)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$6(BlockManager.scala:1461)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$6$adapted(BlockManager.scala:1459)
at org.apache.spark.storage.DiskStore.put(DiskStore.scala:70)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1459)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1350)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1414)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1237)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:384)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:335)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: error=2, 没有那个文件或目录
at java.lang.UNIXProcess.forkAndExec(Native Method)
at java.lang.UNIXProcess.<init>(UNIXProcess.java:247)
at java.lang.ProcessImpl.start(ProcessImpl.java:134)
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1029)
... 28 more
24/04/18 11:05:01 ERROR TaskSetManager: Task 0 in stage 0.0 failed 4 times; aborting job
Traceback (most recent call last):
File "/home/projects/01_RDD/example/main.py", line 31, in <module>
print(context_rdd.take(5))
File "/export/server/spark/python/lib/pyspark.zip/pyspark/rdd.py", line 1566, in take
File "/export/server/spark/python/lib/pyspark.zip/pyspark/context.py", line 1233, in runJob
File "/export/server/spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py", line 1304, in __call__
File "/export/server/spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py", line 326, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.runJob.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 3) (node3 executor 1): java.io.IOException: Cannot run program "python3": error=2, 没有那个文件或目录
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1048)
at org.apache.spark.api.python.PythonWorkerFactory.startDaemon(PythonWorkerFactory.scala:209)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:132)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:105)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:119)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:145)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:386)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$6(BlockManager.scala:1461)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$6$adapted(BlockManager.scala:1459)
at org.apache.spark.storage.DiskStore.put(DiskStore.scala:70)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1459)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1350)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1414)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1237)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:384)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:335)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: error=2, 没有那个文件或目录
at java.lang.UNIXProcess.forkAndExec(Native Method)
at java.lang.UNIXProcess.<init>(UNIXProcess.java:247)
at java.lang.ProcessImpl.start(ProcessImpl.java:134)
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1029)
... 28 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2258)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2207)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2206)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2206)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1079)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1079)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1079)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2445)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2387)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2376)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:868)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2196)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2217)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2236)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: Cannot run program "python3": error=2, 没有那个文件或目录
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1048)
at org.apache.spark.api.python.PythonWorkerFactory.startDaemon(PythonWorkerFactory.scala:209)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:132)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:105)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:119)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:145)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.$anonfun$getOrCompute$1(RDD.scala:386)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$6(BlockManager.scala:1461)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$6$adapted(BlockManager.scala:1459)
at org.apache.spark.storage.DiskStore.put(DiskStore.scala:70)
at org.apache.spark.storage.BlockManager.$anonfun$doPutIterator$1(BlockManager.scala:1459)
at org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$doPut(BlockManager.scala:1350)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1414)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:1237)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:384)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:335)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.io.IOException: error=2, 没有那个文件或目录
at java.lang.UNIXProcess.forkAndExec(Native Method)
at java.lang.UNIXProcess.<init>(UNIXProcess.java:247)
at java.lang.ProcessImpl.start(ProcessImpl.java:134)
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1029)
... 28 more
加上环境变量
import os
os.environ['HADOOP_CONF_DIR'] = "/export/server/hadoop/etc/hadoop"
import sys
os.environ['PYSPARK_PYTHON'] = sys.executable
os.environ['PYSPARK_DRIVER_PYTHON'] = sys.executable