spark 1.6.0 core源码分析5 spark提交框架

从sparkSubmit脚本中可以看到现在spark提交任务都是是用：

exec "${SPARK_HOME}"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

首先来看main方法：

def main(args: Array[String]): Unit = {
    val appArgs = new SparkSubmitArguments(args)
    if (appArgs.verbose) {
      // scalastyle:off println
      printStream.println(appArgs)
      // scalastyle:on println
    }
    appArgs.action match {
      case SparkSubmitAction.SUBMIT => submit(appArgs)
      case SparkSubmitAction.KILL => kill(appArgs)
      case SparkSubmitAction.REQUEST_STATUS => requestStatus(appArgs)
    }
  }

提交流程如下：

 private def submit(args: SparkSubmitArguments): Unit = {

//需要注意的是，childMainClass是根据部署的模式来区分的  
  //deployMode == CLIENT,childMainClass直接取jar包中的mainclass  
  //deployMode == cluster且是部署为standalone模式，childMainClass = "org.apache.spark.deploy.Client"  
  //部署为Yarn模式，childMainClass = "org.apache.spark.deploy.yarn.Client"
    val (childArgs, childClasspath, sysProps, childMainClass) = prepareSubmitEnvironment(args)

    def doRunMain(): Unit = {
      if (args.proxyUser != null) {
        val proxyUser = UserGroupInformation.createProxyUser(args.proxyUser,
          UserGroupInformation.getCurrentUser())
        try {
          proxyUser.doAs(new PrivilegedExceptionAction[Unit]() {
            override def run(): Unit = {
              runMain(childArgs, childClasspath, sysProps, childMainClass, args.verbose)
            }
          })
        } catch {
          case e: Exception =>
            // Hadoop's AuthorizationException suppresses the exception's stack trace, which
            // makes the message printed to the output by the JVM not very helpful. Instead,
            // detect exceptions with empty stack traces here, and treat them differently.
            if (e.getStackTrace().length == 0) {
              // scalastyle:off println
              printStream.println(s"ERROR: ${e.getClass().getName()}: ${e.getMessage()}")
              // scalastyle:on println
              exitFn(1)
            } else {
              throw e
            }
        }
      } else {
        runMain(childArgs, childClasspath, sysProps, childMainClass, args.verbose)
      }
    }

     // In standalone cluster mode, there are two submission gateways:
     //   (1) The traditional Akka gateway using o.a.s.deploy.Client as a wrapper
     //   (2) The new REST-based gateway introduced in Spark 1.3
     // The latter is the default behavior as of Spark 1.3, but Spark submit will fail over
     // to use the legacy gateway if the master endpoint turns out to be not a REST server.
    if (args.isStandaloneCluster && args.useRest) {
      try {
        // scalastyle:off println
        printStream.println("Running Spark using the REST application submission protocol.")
        // scalastyle:on println
        doRunMain()
      } catch {
        // Fail over to use the legacy submission gateway
        case e: SubmitRestConnectionException =>
          printWarning(s"Master endpoint ${args.master} was not a REST server. " +
            "Falling back to legacy submission gateway instead.")
          args.useRest = false
          submit(args)
      }
    // In all other modes, just run the main class as prepared
    } else {
      doRunMain()
    }
  }