aboutsummaryrefslogtreecommitdiff
path: root/docs/running-on-yarn.md
diff options
context:
space:
mode:
authorArtur Sukhenko <artur.sukhenko@gmail.com>2016-11-16 15:08:01 -0800
committerReynold Xin <rxin@databricks.com>2016-11-16 15:08:01 -0800
commit55589987be89ff78dadf44498352fbbd811a206e (patch)
treef15651b6feac7a401997fb5b234ec7fde0e5fc20 /docs/running-on-yarn.md
parent2ca8ae9aa1b29bf1f46d0b656d9885e438e67f53 (diff)
downloadspark-55589987be89ff78dadf44498352fbbd811a206e.tar.gz
spark-55589987be89ff78dadf44498352fbbd811a206e.tar.bz2
spark-55589987be89ff78dadf44498352fbbd811a206e.zip
[YARN][DOC] Increasing NodeManager's heap size with External Shuffle Service
## What changes were proposed in this pull request? Suggest users to increase `NodeManager's` heap size if `External Shuffle Service` is enabled as `NM` can spend a lot of time doing GC resulting in shuffle operations being a bottleneck due to `Shuffle Read blocked time` bumped up. Also because of GC `NodeManager` can use an enormous amount of CPU and cluster performance will suffer. I have seen NodeManager using 5-13G RAM and up to 2700% CPU with `spark_shuffle` service on. ## How was this patch tested? #### Added step 5: ![shuffle_service](https://cloud.githubusercontent.com/assets/15244468/20355499/2fec0fde-ac2a-11e6-8f8b-1c80daf71be1.png) Author: Artur Sukhenko <artur.sukhenko@gmail.com> Closes #15906 from Devian-ua/nmHeapSize.
Diffstat (limited to 'docs/running-on-yarn.md')
-rw-r--r--docs/running-on-yarn.md2
1 files changed, 2 insertions, 0 deletions
diff --git a/docs/running-on-yarn.md b/docs/running-on-yarn.md
index cd18808681..fe0221ce7c 100644
--- a/docs/running-on-yarn.md
+++ b/docs/running-on-yarn.md
@@ -559,6 +559,8 @@ pre-packaged distribution.
1. In the `yarn-site.xml` on each node, add `spark_shuffle` to `yarn.nodemanager.aux-services`,
then set `yarn.nodemanager.aux-services.spark_shuffle.class` to
`org.apache.spark.network.yarn.YarnShuffleService`.
+1. Increase `NodeManager's` heap size by setting `YARN_HEAPSIZE` (1000 by default) in `etc/hadoop/yarn-env.sh`
+to avoid garbage collection issues during shuffle.
1. Restart all `NodeManager`s in your cluster.
The following extra configuration options are available when the shuffle service is running on YARN: