[SPARK-11563][CORE][REPL] Use RpcEnv to transfer REPL-generated classes.

This avoids bringing up yet another HTTP server on the driver, and
instead reuses the file server already managed by the driver's
RpcEnv. As a bonus, the repl now inherits the security features of
the network library.

There's also a small change to create the directory for storing classes
under the root temp dir for the application (instead of directly
under java.io.tmpdir).

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #9923 from vanzin/SPARK-11563.

1 files changed, 12 insertions, 11 deletions

diff --git a/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala b/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala
index 455a6b9a93..44650f25f7 100644
--- a/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala
+++ b/repl/scala-2.11/src/main/scala/org/apache/spark/repl/Main.scala
@@ -28,11 +28,13 @@ import org.apache.spark.sql.SQLContext
 object Main extends Logging {
 
   val conf = new SparkConf()
-  val tmp = System.getProperty("java.io.tmpdir")
-  val rootDir = conf.get("spark.repl.classdir", tmp)
-  val outputDir = Utils.createTempDir(rootDir)
+  val rootDir = conf.getOption("spark.repl.classdir").getOrElse(Utils.getLocalDir(conf))
+  val outputDir = Utils.createTempDir(root = rootDir, namePrefix = "repl")
+  val s = new Settings()
+  s.processArguments(List("-Yrepl-class-based",
+    "-Yrepl-outdir", s"${outputDir.getAbsolutePath}",
+    "-classpath", getAddedJars.mkString(File.pathSeparator)), true)
   // the creation of SecurityManager has to be lazy so SPARK_YARN_MODE is set if needed
-  lazy val classServer = new HttpServer(conf, outputDir, new SecurityManager(conf))
   var sparkContext: SparkContext = _
   var sqlContext: SQLContext = _
   var interp = new SparkILoop // this is a public var because tests reset it.
@@ -45,7 +47,6 @@ object Main extends Logging {
   }
 
   def main(args: Array[String]) {
-   
     val interpArguments = List(
       "-Yrepl-class-based",
       "-Yrepl-outdir", s"${outputDir.getAbsolutePath}",
@@ -57,11 +58,7 @@ object Main extends Logging {
 
     if (!hasErrors) {
       if (getMaster == "yarn-client") System.setProperty("SPARK_YARN_MODE", "true")
-      // Start the classServer and store its URI in a spark system property
-      // (which will be passed to executors so that they can connect to it)
-      classServer.start()
       interp.process(settings) // Repl starts and goes in loop of R.E.P.L
-      classServer.stop()
       Option(sparkContext).map(_.stop)
     }
   }
@@ -82,9 +79,13 @@ object Main extends Logging {
     val conf = new SparkConf()
       .setMaster(getMaster)
       .setJars(jars)
-      .set("spark.repl.class.uri", classServer.uri)
       .setIfMissing("spark.app.name", "Spark shell")
-    logInfo("Spark class server started at " + classServer.uri)
+      // SparkContext will detect this configuration and register it with the RpcEnv's
+      // file server, setting spark.repl.class.uri to the actual URI for executors to
+      // use. This is sort of ugly but since executors are started as part of SparkContext
+      // initialization in certain cases, there's an initialization order issue that prevents
+      // this from being set after SparkContext is instantiated.
+      .set("spark.repl.class.outputDir", outputDir.getAbsolutePath())
     if (execUri != null) {
       conf.set("spark.executor.uri", execUri)
     }