From bd3ea6595788a4fe5399e6c6c666618d8cb6872c Mon Sep 17 00:00:00 2001 From: Jeff Zhang <zjffdu@apache.org> Date: Wed, 2 Nov 2016 11:47:45 -0700 Subject: [PATCH] [SPARK-18160][CORE][YARN] spark.files & spark.jars should not be passed 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 <zjffdu@apache.org> Closes #15669 from zjffdu/SPARK-18160. (cherry picked from commit 3c24299b71e23e159edbb972347b13430f92a465) Signed-off-by: Marcelo Vanzin <vanzin@cloudera.com> --- .../scala/org/apache/spark/SparkContext.scala | 29 ++++--------------- .../org/apache/spark/deploy/yarn/Client.scala | 5 +++- 2 files changed, 10 insertions(+), 24 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index 4694790c72..63478c88b0 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -1716,29 +1716,12 @@ class SparkContext(config: SparkConf) extends Logging { 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 index 55e4a833b6..053a78617d 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala @@ -1202,7 +1202,10 @@ 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() } -- GitLab