spark cluster error：ClassNotFoundException

Question

我使用spark框架来处理bigdata，hadoop文件系统和集群管理器YARN。当我尝试使用命令spark-submit --deploy-mode cluster运行我的python应用程序时--master yarn streaming.py 我收到一个错误：

 16/12/19 15:42:44 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Exception in thread "main" java.lang.RuntimeException: java.lang.ClassNotFoundException: Class org.apache.hadoop.hdfs.DistributedAvatarFileSystem not found
    at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2195)
    at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:2654)
    at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2667)
    at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:94)
    at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2703)
    at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2685)
    at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:373)
    at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:172)
    at org.apache.spark.deploy.yarn.Client$$anonfun$7.apply(Client.scala:123)
    at org.apache.spark.deploy.yarn.Client$$anonfun$7.apply(Client.scala:123)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.deploy.yarn.Client.<init>(Client.scala:123)
    at org.apache.spark.deploy.yarn.Client.<init>(Client.scala:70)
    at org.apache.spark.deploy.yarn.Client$.main(Client.scala:1178)
    at org.apache.spark.deploy.yarn.Client.main(Client.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 org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:736)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.ClassNotFoundException: Class org.apache.hadoop.hdfs.DistributedAvatarFileSystem not found
    at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:2101)
    at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:2193)
    ... 23 more

在Spark Standalone模式下，一切正常。

我的配置：

纱-site.xml中

<configuration>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>

    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>localhost</value>
    </property>

    <property>
        <name>yarn.resourcemanager.scheduler.class</name>
        <value>CapacityScheduler</value>
    </property>

</configuration>

HDFS-site.xml中

<configuration>

 <property>
<name>dfs.replication</name>
<value>1</value>
</property>

<property>
  <name>dfs.http.address</name>
  <value>127.0.0.1:50070</value>
</property>

<property>
  <name>dfs.secondary.http.address</name>
  <value>0.0.0.0:0</value>
</property>

<property>
  <name>dfs.blockreport.intervalMsec</name>
  <value>300000</value>
</property>

<property>
  <name>dfs.fullblockreport.magnifier</name>
  <value>2</value>
</property>

<property>
  <name>dfs.datanode.address</name>
  <value>0.0.0.0:0</value>
</property>

<property>
  <name>dfs.datanode.http.address</name>
  <value>0.0.0.0:0</value>
</property>

<property>
  <name>dfs.datanode.ipc.address</name>
  <value>0.0.0.0:0</value>
</property>

<property>
  <name>dfs.datanode.handler.count</name>
  <value>3</value>
</property>

<property>
  <name>dfs.permissions</name>
  <value>false</value>
</property>

<property>
  <name>dfs.data.dir</name>
  <value>{{DataNode-volumes}}</value>
</property>

<property>
 <name>dfs.block.invalidate.limit</name>
 <value>100</value>
</property>

<property>
  <name>dfs.safemode.extension</name>
  <value>10000</value>
</property>

<property>
  <name>dfs.namenode.dn-address</name>
  <value>0.0.0.0:9015</value>
</property>

</configuration>

芯-site.xml中

<configuration>
    <property>
      <name>fs.default.name</name>
      <value>hdfs://0.0.0.0:9000</value>
    </property>

    <property>
      <name>fs.default.name0</name>
      <value>hdfs://0.0.0.0:9000</value>
    </property>

    <property>
      <name>fs.default.name1</name>
      <value>hdfs://0.0.0.0:9010</value>
    </property>

    <property>
      <name>fs.checkpoint.period</name>
      <value>600</value>
    </property>

    <property>
      <name>fs.checkpoint.size</name>
      <value>10000000</value>
    </property>

    <property>
      <name>fs.ha.zookeeper.quorum</name>
      <value>{{zookeeper-quorum}}</value>
    </property>

    <property>
      <name>ipc.client.connect.max.retries</name>
      <value>10</value>
    </property>

    <property>
      <name>ipc.client.connect.timeout</name>
      <value>5</value>
    </property>

    <property>
      <name>fs.hdfs.impl</name>
      <value>org.apache.hadoop.hdfs.DistributedAvatarFileSystem</value>
    </property>

    <property>
      <name>fs.ha.zookeeper.cache</name>
      <value>true</value>
    </property>

    <property>
      <name>fs.ha.zookeeper.timeout</name>
      <value>30000</value>
    </property>

    <property>
      <name>fs.ha.retrywrites</name>
      <value>true</value>
    </property>
</configuration>

Answer 1

在我的案例中帮助替换了

芯-site.xml中

<property>
  <name>fs.hdfs.impl</name>
  <value>org.apache.hadoop.hdfs.DistributedAvatarFileSystem</value>
</property>

  

DistributedAvatarFileSystem

在

  

DistributedFileSystem