apache-spark - Spark 提交无法连接

Question

运行命令后

spark-submit --class org.apache.spark.examples.SparkPi --proxy-user yarn --master yarn --deploy-mode cluster --driver-memory 4g --executor-memory 2g --executor-cores 1 --queue default ./examples/jars/spark-examples_2.11-2.3.0.jar 10000

我在输出中得到了这个并且它一直在重试。我哪里错了？我是否缺少某些配置？

我为 yarn 创建了一个新用户并运行该用户。

WARN  Utils:66 - Your hostname, ukaleem-HP-EliteBook-850-G3 resolves to a loopback address: 127.0.1.1; using 10.XX.XX.XX instead (on interface enp0s31f6)
2018-06-14 16:50:41 WARN  Utils:66 - Set SPARK_LOCAL_IP if you need to bind to another address
Warning: Local jar /home/yarn/Documents/Scala-Examples/./examples/jars/spark-examples_2.11-2.3.0.jar does not exist, skipping.
2018-06-14 16:50:42 INFO  RMProxy:98 - Connecting to ResourceManager at /0.0.0.0:8032
2018-06-14 16:50:44 INFO  Client:871 - Retrying connect to server: 0.0.0.0/0.0.0.0:8032. Already tried 0 time(s); retry policy is RetryUpToMaximumCountWithFixedSleep(maxRetries=10, sleepTime=1000 MILLISECONDS)

最后，它给出了异常

    Exception in thread "main" java.net.ConnectException: Call From ukaleem-HP-EliteBook-850-G3/127.0.1.1 to 0.0.0.0:8032 failed on connection exception: java.net.ConnectException: Connection refused; For more details see:  http://wiki.apache.org/hadoop/ConnectionRefused
    at sun.reflect.GeneratedConstructorAccessor4.newInstance(Unknown Source)
    at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
    at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
    at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:792)
    at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:732)
    at org.apache.hadoop.ipc.Client.call(Client.java:1479)
    at org.apache.hadoop.ipc.Client.call(Client.java:1412)
    at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
    at com.sun.proxy.$Proxy8.getClusterMetrics(Unknown Source)
    at org.apache.hadoop.yarn.api.impl.pb.client.ApplicationClientProtocolPBClientImpl.getClusterMetrics(ApplicationClientProtocolPBClientImpl.java:206)
    at sun.reflect.GeneratedMethodAccessor7.invoke(Unknown Source)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191)
    at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
    at com.sun.proxy.$Proxy9.getClusterMetrics(Unknown Source)
    at org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.getYarnClusterMetrics(YarnClientImpl.java:487)
    at org.apache.spark.deploy.yarn.Client$$anonfun$submitApplication$1.apply(Client.scala:155)
    at org.apache.spark.deploy.yarn.Client$$anonfun$submitApplication$1.apply(Client.scala:155)
    at org.apache.spark.internal.Logging$class.logInfo(Logging.scala:54)
    at org.apache.spark.deploy.yarn.Client.logInfo(Client.scala:59)
    at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:154)
    at org.apache.spark.deploy.yarn.Client.run(Client.scala:1146)
    at org.apache.spark.deploy.yarn.YarnClusterApplication.start(Client.scala:1518)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:879)
    at org.apache.spark.deploy.SparkSubmit$$anon$1.run(SparkSubmit.scala:179)
    at org.apache.spark.deploy.SparkSubmit$$anon$1.run(SparkSubmit.scala:177)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:422)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:177)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:227)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.net.ConnectException: Connection refused
    at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
    at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
    at org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
    at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:531)
    at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:495)
    at org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:614)
    at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:712)
    at org.apache.hadoop.ipc.Client$Connection.access$2900(Client.java:375)
    at org.apache.hadoop.ipc.Client.getConnection(Client.java:1528)
    at org.apache.hadoop.ipc.Client.call(Client.java:1451)
    ... 28 more
2018-06-14 17:10:53 INFO  ShutdownHookManager:54 - Shutdown hook called
2018-06-14 17:10:53 INFO  ShutdownHookManager:54 - Deleting directory /tmp/spark-5bddb7f3-165f-451c-8ab4-bb7729f4237c

编辑:将配置文件添加到我的 spark/conf 目录后，我现在收到此错误。

我添加的文件是

*核心站点.xml

dfs.hosts

大师

奴隶

yarn-site.xml*

还有一些。我的理解是，我只需要 yarn-site.xml 来告诉 spark yarn 集群的位置。 (ID、地址、主机名等)。

一直以来，我一直在想，即使我们想在 Yarn 上提交作业，这些配置也需要放在/etc/Hadoop 目录中，而不是在 Spark/conf 中。那么安装 hadoop 的目的是什么(除了通信)？并关注这个问题。如果配置需要放在 spark/conf 中，那么 HADOOP_CONF_DIR 和 YARN_CONF_DIR 应该指向 etc/hadoop 目录还是 spark/conf？

    INFO client.ConfiguredRMFailoverProxyProvider: Failing over to rm2
18/06/19 11:04:50 INFO retry.RetryInvocationHandler: Exception while invoking getClusterMetrics of class ApplicationClientProtocolPBClientImpl over rm2 after 1 fail over attempts. Trying to fail over after sleeping for 38176ms.
java.net.ConnectException: Call From ukaleem-HP-EliteBook-850-G3/127.0.1.1 to svc-hadoop-mgnt-pre-c2-01.jamba.net:8032 failed on connection exception: java.net.ConnectException: Connection refused; For more details see:  http://wiki.apache.org/hadoop/ConnectionRefused
    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 org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:792)
    at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:732)
    at org.apache.hadoop.ipc.Client.call(Client.java:1479)
    at org.apache.hadoop.ipc.Client.call(Client.java:1412)
    at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
    at com.sun.proxy.$Proxy13.getClusterMetrics(Unknown Source)
    at org.apache.hadoop.yarn.api.impl.pb.client.ApplicationClientProtocolPBClientImpl.getClusterMetrics(ApplicationClientProtocolPBClientImpl.java:206)
    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.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:191)
    at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
    at com.sun.proxy.$Proxy14.getClusterMetrics(Unknown Source)
    at org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.getYarnClusterMetrics(YarnClientImpl.java:487)
    at org.apache.spark.deploy.yarn.Client$$anonfun$submitApplication$1.apply(Client.scala:155)
    at org.apache.spark.deploy.yarn.Client$$anonfun$submitApplication$1.apply(Client.scala:155)
    at org.apache.spark.internal.Logging$class.logInfo(Logging.scala:54)
    at org.apache.spark.deploy.yarn.Client.logInfo(Client.scala:59)
    at org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:154)
    at org.apache.spark.deploy.yarn.Client.run(Client.scala:1146)
    at org.apache.spark.deploy.yarn.YarnClusterApplication.start(Client.scala:1518)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:879)
    at org.apache.spark.deploy.SparkSubmit$$anon$1.run(SparkSubmit.scala:179)
    at org.apache.spark.deploy.SparkSubmit$$anon$1.run(SparkSubmit.scala:177)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:422)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:177)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:227)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:136)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.net.ConnectException: Connection refused
    at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
    at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
    at org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
    at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:531)
    at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:495)
    at org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:614)
    at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:712)
    at org.apache.hadoop.ipc.Client$Connection.access$2900(Client.java:375)
    at org.apache.hadoop.ipc.Client.getConnection(Client.java:1528)
    at org.apache.hadoop.ipc.Client.call(Client.java:1451)
    ... 29 more

Answer 1

假设您有一个完全分布式的 yarn 集群:您的 spark-submit 脚本无法找到 yarn 资源管理器(基本上是 yarn 主节点)的配置。确保您在环境中正确设置了 HADOOP_CONF_DIR，并且它指向集群的配置。特别是你的 yarn-site.xml。

编辑:更多细节

hadoop 软件包包含服务器 和客户端 软件。 服务器 软件将是构成集群的许多运行的守护进程。如果您的工作站充当客户端(松散地使用该术语，与 spark --deploy-mode 不完全相关)，则 hadoop 客户端 软件必须知道集群中运行的服务器守护进程的网络位置。如果您的 yarn-site.xml 是空的，那么它将从 yarn-defauls.xml 中提取默认值。 (我相信这是硬编码的)。

假设您的集群未在 HA 模式下运行，并且大部分是默认配置，那么您工作站的 yarn-site.xml 应该至少包含如下条目:

<property>
  <name>yarn.resourcemanager.hostname</name>
  <value>rm-host.yourdomain.com</value>
</property>

显然，将主机名替换为实际运行资源管理器的主机名。当然，与 HDFS 的任何 spark 交互都需要正确配置的 hdfs-site.xml 等。

一些集群管理软件会有类似“生成客户端配置”的东西(具体考虑我的 cloudera 经验)，它会给你一个 .tar.gz，所有配置文件都正确填充到从外部工作站访问集群。

进一步的建议:如果你打算在这个集群中大量使用 spark on yarn，spark 建议确保你有 external shuffle service配置为与您的 yarn 节点管理器一起启动。 (请记住，此配置指令必须出现在运行 yarn 的节点管理器服务的 yarn-site.xml 中，而不是在您的工作站上。