Repository: spark Updated Branches: refs/heads/branch-1.0 a83a794f1 -> 6195fb8db
SPARK-1408 Modify Spark on Yarn to point to the history server when app ... ...finishes Note this is dependent on https://github.com/apache/spark/pull/204 to have a working history server, but there are no code dependencies. This also fixes SPARK-1288 yarn stable finishApplicationMaster incomplete. Since I was in there I made the diagnostic message be passed properly. Author: Thomas Graves <[email protected]> Closes #362 from tgravescs/SPARK-1408 and squashes the following commits: ec89705 [Thomas Graves] Fix typo. 446122d [Thomas Graves] Make config yarn specific f5d5373 [Thomas Graves] SPARK-1408 Modify Spark on Yarn to point to the history server when app finishes (cherry picked from commit 0058b5d2c74147d24b127a5432f89ebc7050dc18) Signed-off-by: Thomas Graves <[email protected]> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/6195fb8d Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/6195fb8d Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/6195fb8d Branch: refs/heads/branch-1.0 Commit: 6195fb8db9f194856df7f5c02f5023596d0c3253 Parents: a83a794 Author: Thomas Graves <[email protected]> Authored: Thu Apr 17 16:36:37 2014 -0500 Committer: Thomas Graves <[email protected]> Committed: Thu Apr 17 16:36:50 2014 -0500 ---------------------------------------------------------------------- docs/running-on-yarn.md | 1 + .../scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala | 3 +-- .../scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/6195fb8d/docs/running-on-yarn.md ---------------------------------------------------------------------- diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md index 9825143..9765062 100644 --- a/docs/running-on-yarn.md +++ b/docs/running-on-yarn.md @@ -42,6 +42,7 @@ System Properties: * `spark.yarn.preserve.staging.files`, set to true to preserve the staged files(spark jar, app jar, distributed cache files) at the end of the job rather then delete them. * `spark.yarn.scheduler.heartbeat.interval-ms`, the interval in ms in which the Spark application master heartbeats into the YARN ResourceManager. Default is 5 seconds. * `spark.yarn.max.executor.failures`, the maximum number of executor failures before failing the application. Default is the number of executors requested times 2 with minimum of 3. +* `spark.yarn.historyServer.address`, the address of the Spark history server (i.e. host.com:18080). The address should not contain a scheme (http://). Defaults to not being set since the history server is an optional service. This address is given to the Yarn ResourceManager when the Spark application finishes to link the application from the ResourceManager UI to the Spark history server UI. # Launching Spark on YARN http://git-wip-us.apache.org/repos/asf/spark/blob/6195fb8d/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala ---------------------------------------------------------------------- diff --git a/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index 67ec95c..f078d06 100644 --- a/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/yarn/alpha/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -366,8 +366,7 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration, finishReq.setAppAttemptId(appAttemptId) finishReq.setFinishApplicationStatus(status) finishReq.setDiagnostics(diagnostics) - // Set tracking url to empty since we don't have a history server. - finishReq.setTrackingUrl("") + finishReq.setTrackingUrl(sparkConf.get("spark.yarn.historyServer.address", "")) resourceManager.finishApplicationMaster(finishReq) } } http://git-wip-us.apache.org/repos/asf/spark/blob/6195fb8d/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala ---------------------------------------------------------------------- diff --git a/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala index 581cfe4..b225be6 100644 --- a/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala +++ b/yarn/stable/src/main/scala/org/apache/spark/deploy/yarn/ApplicationMaster.scala @@ -347,8 +347,8 @@ class ApplicationMaster(args: ApplicationMasterArguments, conf: Configuration, logInfo("finishApplicationMaster with " + status) if (registered) { - // Set tracking URL to empty since we don't have a history server. - amClient.unregisterApplicationMaster(status, "" /* appMessage */ , "" /* appTrackingUrl */) + val trackingUrl = sparkConf.get("spark.yarn.historyServer.address", "") + amClient.unregisterApplicationMaster(status, diagnostics, trackingUrl) } } }
