[
https://issues.apache.org/jira/browse/HADOOP-18776?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17734071#comment-17734071
]
Syed Shameerur Rahman commented on HADOOP-18776:
------------------------------------------------
[~ste...@apache.org] , It would be great if you review the above PR.
Note: It is a WIP PR (need to add unit tests and integration tests). I would
like to get the communities though on this before taking this forward.
Thanks
> Add OptimizedS3AMagicCommitter For Zero Rename Commits to S3 Endpoints
> ----------------------------------------------------------------------
>
> Key: HADOOP-18776
> URL: https://issues.apache.org/jira/browse/HADOOP-18776
> Project: Hadoop Common
> Issue Type: New Feature
> Components: fs/s3
> Reporter: Syed Shameerur Rahman
> Priority: Major
> Labels: pull-request-available
>
> The goal is to add a new S3A committer named *OptimizedS3AMagicCommitter*
> which is an another type of S3 Magic committer but with a better performance
> by taking in few tradeoffs.
> The following are the differences in MagicCommitter vs OptimizedMagicCommitter
>
> ||Operation||Magic Committer||*OptimizedS3AMagicCommitter*||
> |commitTask |1. Lists all {{.pending}} files in its attempt directory.
>
> 2. The contents are loaded into a list of single pending uploads.
>
> 3. Saved to a {{.pendingset}} file in the job attempt directory.|1. Lists all
> {{.pending}} files in its attempt directory
>
> 2. The contents are loaded into a list of single pending uploads.
>
> 3. For each pending upload, commit operation is called (complete
> multiPartUpload)|
> |commitJob|1. Loads all {{.pendingset}} files in its job attempt directory
>
> 2. Then every pending commit in the job will be committed.
>
> 3. "SUCCESS" marker is created (if config is enabled)
>
> 4. "__magic" directory is cleaned up.|1. "SUCCESS" marker is created (if
> config is enabled)
>
> 2. "__magic" directory is cleaned up.|
>
> *Performance Benefits :-*
> # The primary performance boost due to distributed complete multiPartUpload
> call being made in the taskAttempts(Task containers/Executors) rather than a
> single job driver. In case of MagicCommitter it is O(files/threads).
> # It also saves a couple of S3 calls needed to PUT the "{{{}.pendingset{}}}"
> files and READ call to read them in the Job Driver.
>
> *TradeOffs :-*
> The tradeoffs are similar to the one in FileOutputCommitter V2 version. Users
> migrating from FileOutputCommitter V2 to OptimizedS3AMagicCommitter will no
> see behavioral change as such
> # During execution, intermediate data becomes visible after commitTask
> operation
> # On a failure, all output must be deleted and the job needs to be restarted.
>
> *Performance Benchmark :-*
> Cluster : c4.8x large (ec2-instance)
> Instance : 1 (primary) + 5 (core)
> Data Size : 3TB (TPC-DS store_sales data)
> Engine : Apache Spark 3.3.1
> Query: The following query inserts around 3000+ files into the table
> directory (ran for 3 iterations)
> {code:java}
> insert into <table> select ss_quantity from store_sales; {code}
> ||Committer||Iteration 1||Iteration 2||Iteration 3||
> |Magic|126|127|122|
> |OptimizedMagic|50|51|58|
> So on an average, OptimizedMagicCommitter was *~2.3x* faster as compared to
> MagicCommitter.
>
> _*Note: Unlike MagicCommitter , OptimizedMagicCommitter is not suitable for
> all the cases where in user requires the guarantees of file not being visible
> in failure scenarios. Given the performance benefit, user can may choose to
> use this if they don't require any guarantees or have some mechanism to clean
> up the data before retrying.*_
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org
