Repository: spark Updated Branches: refs/heads/master 93338807a -> bcb0258ae
[SPARK-16080][YARN] Set correct link name for conf archive in executors. This makes sure the files are in the executor's classpath as they're expected to be. Also update the unit test to make sure the files are there as expected. Author: Marcelo Vanzin <van...@cloudera.com> Closes #13792 from vanzin/SPARK-16080. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/bcb0258a Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/bcb0258a Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/bcb0258a Branch: refs/heads/master Commit: bcb0258ae62f23f71a067c1304232f272d7374aa Parents: 9333880 Author: Marcelo Vanzin <van...@cloudera.com> Authored: Tue Jun 21 12:48:06 2016 -0500 Committer: Tom Graves <tgra...@yahoo-inc.com> Committed: Tue Jun 21 12:48:06 2016 -0500 ---------------------------------------------------------------------- .../apache/spark/deploy/yarn/ApplicationMaster.scala | 14 ++++++++++---- .../apache/spark/deploy/yarn/YarnClusterSuite.scala | 8 ++++++++ 2 files changed, 18 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/bcb0258a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala ---------------------------------------------------------------------- diff --git a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index 4df90d7..847d1de 100644 --- a/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/yarn/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -160,11 +160,17 @@ private[spark] class ApplicationMaster( } // Distribute the conf archive to executors. - sparkConf.get(CACHED_CONF_ARCHIVE).foreach { uri => - val fs = FileSystem.get(new URI(uri), yarnConf) + sparkConf.get(CACHED_CONF_ARCHIVE).foreach { path => + val uri = new URI(path) + val fs = FileSystem.get(uri, yarnConf) val status = fs.getFileStatus(new Path(uri)) - setupDistributedCache(uri, LocalResourceType.ARCHIVE, status.getModificationTime().toString, - status.getLen.toString, LocalResourceVisibility.PRIVATE.name()) + // SPARK-16080: Make sure to use the correct name for the destination when distributing the + // conf archive to executors. + val destUri = new URI(uri.getScheme(), uri.getRawSchemeSpecificPart(), + Client.LOCALIZED_CONF_DIR) + setupDistributedCache(destUri.toString(), LocalResourceType.ARCHIVE, + status.getModificationTime().toString, status.getLen.toString, + LocalResourceVisibility.PRIVATE.name()) } // Clean up the configuration so it doesn't show up in the Web UI (since it's really noisy). http://git-wip-us.apache.org/repos/asf/spark/blob/bcb0258a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala ---------------------------------------------------------------------- diff --git a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala b/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala index c465604..4ce33e0 100644 --- a/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala +++ b/yarn/src/test/scala/org/apache/spark/deploy/yarn/YarnClusterSuite.scala @@ -292,6 +292,14 @@ private object YarnClusterDriver extends Logging with Matchers { sc.stop() } + // Verify that the config archive is correctly placed in the classpath of all containers. + val confFile = "/" + Client.SPARK_CONF_FILE + assert(getClass().getResource(confFile) != null) + val configFromExecutors = sc.parallelize(1 to 4, 4) + .map { _ => Option(getClass().getResource(confFile)).map(_.toString).orNull } + .collect() + assert(configFromExecutors.find(_ == null) === None) + // verify log urls are present val listeners = sc.listenerBus.findListenersByClass[SaveExecutorInfo] assert(listeners.size === 1) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org