[GitHub] spark pull request #17442: [SPARK-20107][SQL] Speed up HadoopMapReduceCommit...

[srowen]

Github user srowen commented on a diff in the pull request:

https://github.com/apache/spark/pull/17442#discussion_r108519339
  
--- Diff: docs/configuration.md ---
@@ -1137,6 +1137,17 @@ Apart from these, the following properties are also 
available, and may be useful
 mapping has high overhead for blocks close to or below the page size 
of the operating system.
   
 
+
+  
spark.hadoop.mapreduce.fileoutputcommitter.algorithm.version
+  1
+  
+The file output committer algorithm version, valid algorithm version 
number: 1 or 2.
+Algorithm version 1 has a performance regression and algorithm version 
2 more
--- End diff --

This is a bit glass-is-half-empty. Is it maybe more neutral to say that 
option 2 may have better performance, but version 1 may handle failures better 
in certain situations, as per MAPREDUCE-4815.


---
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 #17442: [SPARK-20107][SQL] Speed up HadoopMapReduceCommit...

[wangyum]

GitHub user wangyum opened a pull request:

https://github.com/apache/spark/pull/17442

[SPARK-20107][SQL] Speed up HadoopMapReduceCommitProtocol#commitJob for 
many output files

## What changes were proposed in this pull request?
Set `mapreduce.fileoutputcommitter.algorithm.version=2` to speed up 
[HadoopMapReduceCommitProtocol#commitJob](https://github.com/apache/spark/blob/v2.1.0/core/src/main/scala/org/apache/spark/internal/io/HadoopMapReduceCommitProtocol.scala#L121)
 for many output files.

It can speed up `11 minutes` for 216869 output files.

This improvement can effect all cloudera's hadoop cdh5-2.6.0_5.4.0 higher 
versions(see: 
https://github.com/cloudera/hadoop-common/commit/1c1236182304d4075276c00c4592358f428bc433
 and 
https://github.com/cloudera/hadoop-common/commit/16b2de27321db7ce2395c08baccfdec5562017f0)
 and apache's hadoop 2.7.0 higher versions.

## How was this patch tested?

Manual test and exist tests.



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

$ git pull https://github.com/wangyum/spark SPARK-20107

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

https://github.com/apache/spark/pull/17442.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 #17442


commit ad30e414d394018fb73a0a5b295542e5a5ec3255
Author: Yuming Wang 
Date:   2017-03-27T12:16:27Z

Speed up FileOutputCommitter#commitJob for many output files




---
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