[GitHub] spark pull request #18957: [SPARK-21744][CORE] Add retry logic for new broad...

[caneGuy]

Github user caneGuy closed the pull request at:

https://github.com/apache/spark/pull/18957


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

[GitHub] spark pull request #18957: [SPARK-21744][CORE] Add retry logic for new broad...

[caneGuy]

GitHub user caneGuy opened a pull request:

https://github.com/apache/spark/pull/18957

[SPARK-21744][CORE] Add retry logic for new broadcast in BroadcastManager

## What changes were proposed in this pull request?

When driver submit new stage and there is a bad disk before spark,then 
driver may will exit caused by exception below:

`Job aborted due to stage failure: Task serialization failed: 
java.io.IOException: Failed to create local dir in 
/home/work/hdd5/yarn/xxx/appcache/application_1463372393999_144979/blockmgr-1f96b724-3e16-4c09-8601-1a2e3b758185/3b.
org.apache.spark.storage.DiskBlockManager.getFile(DiskBlockManager.scala:73)
org.apache.spark.storage.DiskStore.contains(DiskStore.scala:173)

org.apache.spark.storage.BlockManager.org$apache$spark$storage$BlockManager$$getCurrentBlockStatus(BlockManager.scala:391)
org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:801)
org.apache.spark.storage.BlockManager.putIterator(BlockManager.scala:629)
org.apache.spark.storage.BlockManager.putSingle(BlockManager.scala:987)

org.apache.spark.broadcast.TorrentBroadcast.writeBlocks(TorrentBroadcast.scala:99)

org.apache.spark.broadcast.TorrentBroadcast.(TorrentBroadcast.scala:85)

org.apache.spark.broadcast.TorrentBroadcastFactory.newBroadcast(TorrentBroadcastFactory.scala:34)

org.apache.spark.broadcast.BroadcastManager.newBroadcast(BroadcastManager.scala:63)
org.apache.spark.SparkContext.broadcast(SparkContext.scala:1332)

org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$submitMissingTasks(DAGScheduler.scala:863)

org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$14$$anonfun$apply$1.apply$mcVI$sp(DAGScheduler.scala:1090)

org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$14$$anonfun$apply$1.apply(DAGScheduler.scala:1086)

org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$14$$anonfun$apply$1.apply(DAGScheduler.scala:1086)
scala.Option.foreach(Option.scala:236)

org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$14.apply(DAGScheduler.scala:1086)

org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskCompletion$14.apply(DAGScheduler.scala:1085)

scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)

org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1085)

org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1528)

org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1493)

org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1482)
org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)`

We can add retry logic when create broadcast to lower the probability of 
this scenario occurrence。And there is no side-effect for normal scenario.

## How was this patch tested?
Unit test in BroadcastSuite


You can merge this pull request into a Git repository by running:

$ git pull https://github.com/caneGuy/spark zhoukang/imporve-newbroadcast

Alternatively you can review and apply these changes as the patch at:

https://github.com/apache/spark/pull/18957.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

This closes #18957


commit 9083304b4b42357dc2717151db28882e01245838
Author: zhoukang 
Date:   2017-08-16T05:08:35Z

[SPARK][CORE] Add retry logic for new broadcast in BroadcastManager




---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org