Exception from container-launch: org.apache.hadoop.util.Shell$ExitCodeException

原创已于 2022-09-27 20:47:09 修改 · 1.5w 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#mapreduce #application #集群 #测试 #jar

于 2014-08-24 15:26:58 首次发布

Hadoop 专栏收录该内容

72 篇文章

订阅专栏

本文记录了一次Hadoop MapReduce任务运行失败的排查过程，发现是由于yarn-site.xml中配置了未验证的yarn.application.classpath参数导致。通过注释掉该配置解决了问题。

新搭建了个集群，搭建完了，运行

hadoop jar /opt/hadoop-2.4.1/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.4.1.jar pi 10 100

测试一下，却爆出下面的错误：

2014-08-24 02:24:02,456 INFO org.apache.hadoop.yarn.server.resourcemanager.rmapp.RMAppImpl: Application application_1408860487557_0002 failed 2 times due to AM Container for appattempt_1408860487557_0002_000002 exited with  exitCode: 1 due to: Exception from container-launch: org.apache.hadoop.util.Shell$ExitCodeException:
org.apache.hadoop.util.Shell$ExitCodeException:
        at org.apache.hadoop.util.Shell.runCommand(Shell.java:505)
        at org.apache.hadoop.util.Shell.run(Shell.java:418)
        at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:650)
        at org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor.launchContainer(DefaultContainerExecutor.java:195)
        at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:300)
        at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:81)
        at java.util.concurrent.FutureTask.run(FutureTask.java:262)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
        at java.lang.Thread.run(Thread.java:745)


Container exited with a non-zero exit code 1
.Failing this attempt.. Failing the application.
2014-08-24 02:24:02,457 INFO org.apache.hadoop.yarn.server.resourcemanager.rmapp.RMAppImpl: application_1408860487557_0002 State change from FINAL_SAVING to FAILED
2014-08-24 02:24:02,457 WARN org.apache.hadoop.yarn.server.resourcemanager.RMAuditLogger: USER=mapred   OPERATION=Application Finished - Failed TARGET=RMAppManager     RESULT=FAILURE  DESCRIPTION=App failed with state: FAILED       PERMISSIONS=Application application_1408860487557_0002 failed 2 times due to AM Container for appattempt_1408860487557_0002_000002 exited with  exitCode: 1 due to: Exception from container-launch: org.apache.hadoop.util.Shell$ExitCodeException:
org.apache.hadoop.util.Shell$ExitCodeException:
        at org.apache.hadoop.util.Shell.runCommand(Shell.java:505)
        at org.apache.hadoop.util.Shell.run(Shell.java:418)
        at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:650)
        at org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor.launchContainer(DefaultContainerExecutor.java:195)
        at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:300)
        at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:81)
        at java.util.concurrent.FutureTask.run(FutureTask.java:262)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)

想到yarn-site.xml中使用了一个以前没配置过的参数：

<property>
    <name>yarn.application.classpath</name>
    <value>
        $HADOOP_CONF_DIR,
        $HADOOP_COMMON_HOME/*,$HADOOP_COMMON_HOME/lib/*,
        $HADOOP_HDFS_HOME/*,$HADOOP_HDFS_HOME/lib/*,
        $HADOOP_MAPRED_HOME/*,$HADOOP_MAPRED_HOME/lib/*,
        $HADOOP_YARN_HOME/*,$HADOOP_YARN_HOME/lib/*
    </value>
  </property>

注释掉这个配置，重新运行MR任务，不报错了，毋庸置疑就是路径的问题了。先记录下来，以后再找具体原因。