[SPARK-18160][CORE][YARN] spark.files & spark.jars should not be pass…

…ed to driver in yarn mode ## What changes were proposed in this pull request? spark.files is still passed to driver in yarn mode, so SparkContext will still handle it which cause the error in the jira desc. ## How was this patch tested? Tested manually in a 5 node cluster. As this issue only happens in multiple node cluster, so I didn't write test for it. Author: Jeff Zhang <[email protected]> Closes #15669 from zjffdu/SPARK-18160. (cherry picked from commit 3c24299) Signed-off-by: Marcelo Vanzin <[email protected]>
apache · Nov 2, 2016 · 1696bcf · 1696bcf
1 parent eb790c5
commit 1696bcf
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 24 deletions.
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -1705,29 +1705,12 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
         key = uri.getScheme match {
           // A JAR file which exists only on the driver node
           case null | "file" =>
-            if (master == "yarn" && deployMode == "cluster") {
-              // In order for this to work in yarn cluster mode the user must specify the
-              // --addJars option to the client to upload the file into the distributed cache
-              // of the AM to make it show up in the current working directory.
-              val fileName = new Path(uri.getPath).getName()
-              try {
-                env.rpcEnv.fileServer.addJar(new File(fileName))
-              } catch {
-                case e: Exception =>
-                  // For now just log an error but allow to go through so spark examples work.
-                  // The spark examples don't really need the jar distributed since its also
-                  // the app jar.
-                  logError("Error adding jar (" + e + "), was the --addJars option used?")
-                  null
-              }
-            } else {
-              try {
-                env.rpcEnv.fileServer.addJar(new File(uri.getPath))
-              } catch {
-                case exc: FileNotFoundException =>
-                  logError(s"Jar not found at $path")
-                  null
-              }
+            try {
+              env.rpcEnv.fileServer.addJar(new File(uri.getPath))
+            } catch {
+              case exc: FileNotFoundException =>
+                logError(s"Jar not found at $path")
+                null
             }
           // A JAR file which exists locally on every worker node
           case "local" =>

diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
@@ -1170,7 +1170,10 @@ private object Client extends Logging {
     // Note that any env variable with the SPARK_ prefix gets propagated to all (remote) processes
     System.setProperty("SPARK_YARN_MODE", "true")
     val sparkConf = new SparkConf
-
+    // SparkSubmit would use yarn cache to distribute files & jars in yarn mode,
+    // so remove them from sparkConf here for yarn mode.
+    sparkConf.remove("spark.jars")
+    sparkConf.remove("spark.files")
     val args = new ClientArguments(argStrings)
     new Client(args, sparkConf).run()
   }