今天查看了一下spark任务提交任务源码，有点感想，来跟大家分享一下，有误还请指出来，谢谢
1、先来看一下spark-submit的这个类的起使代码
// Cluster managers
private val YARN = 1
private val STANDALONE = 2
private val MESOS = 4
private val LOCAL = 8
private val ALL_CLUSTER_MGRS = YARN | STANDALONE | MESOS | LOCAL
// Deploy modes
private val CLIENT = 1
private val CLUSTER = 2
private val ALL_DEPLOY_MODES = CLIENT | CLUSTER
// Special primary resource names that represent shells rather than application jars.
private val SPARK_SHELL = "spark-shell"
private val PYSPARK_SHELL = "pyspark-shell"
private val SPARKR_SHELL = "sparkr-shell"
private val SPARKR_PACKAGE_ARCHIVE = "sparkr.zip"
private val R_PACKAGE_ARCHIVE = "rpkg.zip"
private val CLASS_NOT_FOUND_EXIT_STATUS = 101
// scalastyle:off println
private[spark] def printVersionAndExit(): Unit = {
//这个类是一个object，相当于java的一个单例类，在调用的时候会加载上面一些配置
printStream.println("""Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version %s
/_/
""".format(SPARK_VERSION))
2、找到这个类的主方法main
override def main(args: Array[String]): Unit = {
//解析参数 赋给appArgs
val appArgs = new SparkSubmitArguments(args)
if (appArgs.verbose) {
//默认是false 如果参数太多的话，会达到一个阈值，则会退出程序
//查看这个printSteam 里面返回一个错误System.err
// scalastyle:off println
printStream.println(appArgs)
// scalastyle:on println
}
//判断动作类型
appArgs.action match {
//提交任务 开始执行submit方法，现在我们进入sbumit的代码看看
case SparkSubmitAction.SUBMIT => submit(appArgs)
case SparkSubmitAction.KILL => kill(appArgs)
case SparkSubmitAction.REQUEST_STATUS => requestStatus(appArgs)
}
}
3、看一下 printStream.println(appArgs)这个方法
private[spark] var printStream: PrintStream = System.err //返回一个错误
4、进入submit，查看执行流程
@tailrec
private def submit(args: SparkSubmitArguments): Unit = {
val (childArgs, childClasspath, sysProps, childMainClass) = prepareSubmitEnvironment(args)
//重写main方法 相当于执行了一个线程
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 = {
//执行main方法 在这里执行runmain方法，点进去一看
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()}: ${e.getMessage()}")
// scalastyle:on println
exitFn(1)
} else {
throw e
}
}
} else {
runMain(childArgs, childClasspath, sysProps, childMainClass, args.verbose)
}
}
5、查看runmain方法
private def runMain(
childArgs: Seq[String],
childClasspath: Seq[String],
sysProps: Map[String, String],
childMainClass: String,
verbose: Boolean): Unit = {
// scalastyle:off println
if (verbose) {
printStream.println(s"Main class:\n$childMainClass")
printStream.println(s"Arguments:\n${childArgs.mkString("\n")}")
// sysProps may contain sensitive information, so redact before printing
printStream.println(s"System properties:\n${Utils.redact(sysProps).mkString("\n")}")
printStream.println(s"Classpath elements:\n${childClasspath.mkString("\n")}")
printStream.println("\n")
}
// scalastyle:on println
val loader =
if (sysProps.getOrElse("spark.driver.userClassPathFirst", "false").toBoolean) {
new ChildFirstURLClassLoader(new Array[URL](0),
Thread.currentThread.getContextClassLoader)
} else {
new MutableURLClassLoader(new Array[URL](0),
Thread.currentThread.getContextClassLoader)
}
Thread.currentThread.setContextClassLoader(loader)
for (jar <- childClasspath) {
addJarToClasspath(jar, loader)
}
for ((key, value) <- sysProps) {
System.setProperty(key, value)
}
var mainClass: Class[_] = null
try {
//通过反射拿到目标类 这里是重要的
mainClass = Utils.classForName(childMainClass)
} catch {
case e: ClassNotFoundException =>
e.printStackTrace(printStream)
if (childMainClass.contains("thriftserver")) {
// scalastyle:off println
printStream.println(s"Failed to load main class $childMainClass.")
printStream.println("You need to build Spark with -Phive and -Phive-thriftserver.")
// scalastyle:on println
}
System.exit(CLASS_NOT_FOUND_EXIT_STATUS)
case e: NoClassDefFoundError =>
e.printStackTrace(printStream)
if (e.getMessage.contains("org/apache/hadoop/hive")) {
// scalastyle:off println
printStream.println(s"Failed to load hive class.")
printStream.println("You need to build Spark with -Phive and -Phive-thriftserver.")
// scalastyle:on println
}
System.exit(CLASS_NOT_FOUND_EXIT_STATUS)
}
// SPARK-4170
if (classOf[scala.App].isAssignableFrom(mainClass)) {
printWarning("Subclasses of scala.App may not work correctly. Use a main() method instead.")
}
//通过目标列获得main方法
val mainMethod = mainClass.getMethod("main", new Array[String](0).getClass)
if (!Modifier.isStatic(mainMethod.getModifiers)) {
throw new IllegalStateException("The main method in the given main class must be static")
}
@tailrec
def findCause(t: Throwable): Throwable = t match {
case e: UndeclaredThrowableException =>
if (e.getCause() != null) findCause(e.getCause()) else e
case e: InvocationTargetException =>
if (e.getCause() != null) findCause(e.getCause()) else e
case e: Throwable =>
e
}
try {
//调用目标类的Main方法
mainMethod.invoke(null, childArgs.toArray)
} catch {
case t: Throwable =>
findCause(t) match {
case SparkUserAppException(exitCode) =>
System.exit(exitCode)
case t: Throwable =>
throw t
}
}
这里主要做的就是通过反射拿到目标类，通过目标类获取main方法，然后调用目标类的main方法，开始执行任务