[SPARK-4606] Send EOF to child JVM when there's no more data to read.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #3460 from vanzin/SPARK-4606 and squashes the following commits:

031207d [Marcelo Vanzin] [SPARK-4606] Send EOF to child JVM when there's no more data to read.

core/src/main/scala/org/apache/spark/deploy/SparkSubmitDriverBootstrapper.scala

@@ -151,7 +151,8 @@ private[spark] object SparkSubmitDriverBootstrapper {
     val isWindows = Utils.isWindows
     val isSubprocess = sys.env.contains("IS_SUBPROCESS")
     if (!isWindows) {
-      val stdinThread = new RedirectThread(System.in, process.getOutputStream, "redirect stdin")
+      val stdinThread = new RedirectThread(System.in, process.getOutputStream, "redirect stdin",
+        propagateEof = true)
       stdinThread.start()
       // Spark submit (JVM) may run as a subprocess, and so this JVM should terminate on
       // broken pipe, signaling that the parent process has exited. This is the case if the

core/src/main/scala/org/apache/spark/util/Utils.scala

@@ -1847,13 +1847,18 @@ private[spark] object Utils extends Logging {
 /**
  * A utility class to redirect the child process's stdout or stderr.
  */
-private[spark] class RedirectThread(in: InputStream, out: OutputStream, name: String)
+private[spark] class RedirectThread(
+    in: InputStream,
+    out: OutputStream,
+    name: String,
+    propagateEof: Boolean = false)
   extends Thread(name) {
 
   setDaemon(true)
   override def run() {
     scala.util.control.Exception.ignoring(classOf[IOException]) {
       // FIXME: We copy the stream on the level of bytes to avoid encoding problems.
+      try {
         val buf = new Array[Byte](1024)
         var len = in.read(buf)
         while (len != -1) {
@@ -1861,6 +1866,11 @@ private[spark] class RedirectThread(in: InputStream, out: OutputStream, name: St
           out.flush()
           len = in.read(buf)
         }
+      } finally {
+        if (propagateEof) {
+          out.close()
+        }
+      }
     }
   }
 }