Repository: spark Updated Branches: refs/heads/master 5c99d8bf9 -> 741a29f98
[SPARK-9575] [MESOS] Add docuemntation around Mesos shuffle service. andrewor14 Author: Timothy Chen <tnac...@gmail.com> Closes #7907 from tnachen/mesos_shuffle. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/741a29f9 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/741a29f9 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/741a29f9 Branch: refs/heads/master Commit: 741a29f98945538a475579ccc974cd42c1613be4 Parents: 5c99d8b Author: Timothy Chen <tnac...@gmail.com> Authored: Tue Aug 11 23:33:22 2015 -0700 Committer: Andrew Or <and...@databricks.com> Committed: Tue Aug 11 23:33:22 2015 -0700 ---------------------------------------------------------------------- docs/running-on-mesos.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/741a29f9/docs/running-on-mesos.md ---------------------------------------------------------------------- diff --git a/docs/running-on-mesos.md b/docs/running-on-mesos.md index 55e6d4e..cfd219a 100644 --- a/docs/running-on-mesos.md +++ b/docs/running-on-mesos.md @@ -216,6 +216,20 @@ node. Please refer to [Hadoop on Mesos](https://github.com/mesos/hadoop). In either case, HDFS runs separately from Hadoop MapReduce, without being scheduled through Mesos. +# Dynamic Resource Allocation with Mesos + +Mesos supports dynamic allocation only with coarse grain mode, which can resize the number of executors based on statistics +of the application. While dynamic allocation supports both scaling up and scaling down the number of executors, the coarse grain scheduler only supports scaling down +since it is already designed to run one executor per slave with the configured amount of resources. However, after scaling down the number of executors the coarse grain scheduler +can scale back up to the same amount of executors when Spark signals more executors are needed. + +Users that like to utilize this feature should launch the Mesos Shuffle Service that +provides shuffle data cleanup functionality on top of the Shuffle Service since Mesos doesn't yet support notifying another framework's +termination. To launch/stop the Mesos Shuffle Service please use the provided sbin/start-mesos-shuffle-service.sh and sbin/stop-mesos-shuffle-service.sh +scripts accordingly. + +The Shuffle Service is expected to be running on each slave node that will run Spark executors. One way to easily achieve this with Mesos +is to launch the Shuffle Service with Marathon with a unique host constraint. # Configuration --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org