hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Steve Loughran (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAPREDUCE-7029) FileOutputCommitter is slow on filesystems lacking recursive delete
Date Tue, 23 Jan 2018 17:00:00 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-7029?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16336069#comment-16336069

Steve Loughran commented on MAPREDUCE-7029:

bq. I don't think I could have delved into the code without some help from teammate

second piece of corerecusive code I've actually encountered in the real world; this one appears
to have evolved that way rather than designed. It works, its just we fear changing it...which
is why the S3a stuff added a new plugin/factory point: making changes to the FO committer
ran too much risk of breaking everything else.

yeah, I'm planning to add fault injection to my committer just to see how things handle failures
halfway through commits, in cleanup, etc. 

You might find [Committer Architecture|https://github.com/apache/hadoop/blob/trunk/hadoop-tools/hadoop-aws/src/site/markdown/tools/hadoop-aws/committer_architecture.md]
useful, though there's an error in one of the code snippets which HADOOP-15107 patches

> FileOutputCommitter is slow on filesystems lacking recursive delete
> -------------------------------------------------------------------
>                 Key: MAPREDUCE-7029
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-7029
>             Project: Hadoop Map/Reduce
>          Issue Type: Improvement
>    Affects Versions: 2.8.2
>         Environment: - Google Cloud Storage (with the GCS connector: https://github.com/GoogleCloudPlatform/bigdata-interop/tree/master/gcs)
for HCFS compatibility.
> - FileOutputCommitter algorithm v2.
> - Running on Google Compute Engine with Java 8, Debian 8, Hadoop 2.8.2, Spark 2.2.0.
>            Reporter: Karthik Palaniappan
>            Assignee: Karthik Palaniappan
>            Priority: Minor
>             Fix For: 3.1.0, 2.10.0
>         Attachments: MAPREDUCE-7029-branch-2.004.patch, MAPREDUCE-7029-branch-2.005.patch,
MAPREDUCE-7029-branch-2.005.patch, MAPREDUCE-7029.001.patch, MAPREDUCE-7029.002.patch, MAPREDUCE-7029.003.patch,
MAPREDUCE-7029.004.patch, MAPREDUCE-7029.005.patch
> I ran a Spark job that outputs thousands of parquet files (aka there are thousands of
reducers), and it hung for several minutes in the driver after all tasks were complete. Here
is a very simple repro of the job (to be run in a spark-shell):
> {code:scala}
> spark.range(1L << 20).repartition(1 << 14).write.save("gs://some/path")
> {code}
> Spark actually calls into Mapreduce's FileOuputCommitter. Job committing (specifically
cleanupJob()) recursively deletes the job temporary directory, which is something like "gs://some/path/_temporary".
If I understand correctly, on HDFS, this would be O(1), but on GCS (and every HCFS I know),
this requires a full file tree walk. Deleting tens of thousands of objects in GCS takes several
> I propose that commitTask() recursively deletes its the task attempt temp directory (something
like "gs://some/path/_temporary/attempt1/task1"). On HDFS, this is O(1) per task, so this
is very little overhead per task. On GCS (and other HCFSs), this adds parallelism for deleting
the job temp directory.
> With the attached patch, the repro above went from taking ~10 minutes to taking ~5 minutes,
and task time did not significantly change.
> Side note: I found this issue with Spark, but I assume it applies to a Mapreduce job
with thousands of reducers as well.

This message was sent by Atlassian JIRA

To unsubscribe, e-mail: mapreduce-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: mapreduce-issues-help@hadoop.apache.org

View raw message