[
https://issues.apache.org/jira/browse/MAPREDUCE-64?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12793578#action_12793578
]
Hong Tang commented on MAPREDUCE-64:
------------------------------------
bq. This is an interesting idea. Clever implementations could also avoid
skewing the average record size disproportionately (possibly an independent
issue). Please file a JIRA.
Will do.
bq. The distinction between flush and close is not clear for a Collector.
The reason I find it odd is that conventionally one can flush a stream an
arbitrary number of times without destroying the stream. This is clearly not
the case here. Yes, I agree that MAPREDUCE-1211 would be relevant here. I am
also fine with deferring the work of making the distinction between close and
flush consistent with java io stream convention to MAPREDUCE-1324 (assuming
that is your intention).
bq. Since the testing/validation of this patch is difficult, and you've already
done the work, I'd like to postpone this to a separate issue if that's OK.
That is fine. Would you please file a jira wrt this?
> Map-side sort is hampered by io.sort.record.percent
> ---------------------------------------------------
>
> Key: MAPREDUCE-64
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-64
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Reporter: Arun C Murthy
> Assignee: Chris Douglas
> Attachments: M64-0.patch, M64-0i.png, M64-1.patch, M64-1i.png,
> M64-2.patch, M64-2i.png, M64-3.patch, M64-4.patch, M64-5.patch
>
>
> Currently io.sort.record.percent is a fairly obscure, per-job configurable,
> expert-level parameter which controls how much accounting space is available
> for records in the map-side sort buffer (io.sort.mb). Typically values for
> io.sort.mb (100) and io.sort.record.percent (0.05) imply that we can store
> ~350,000 records in the buffer before necessitating a sort/combine/spill.
> However for many applications which deal with small records e.g. the
> world-famous wordcount and it's family this implies we can only use 5-10% of
> io.sort.mb i.e. (5-10M) before we spill inspite of having _much_ more memory
> available in the sort-buffer. The word-count for e.g. results in ~12 spills
> (given hdfs block size of 64M). The presence of a combiner exacerbates the
> problem by piling serialization/deserialization of records too...
> Sure, jobs can configure io.sort.record.percent, but it's tedious and
> obscure; we really can do better by getting the framework to automagically
> pick it by using all available memory (upto io.sort.mb) for either the data
> or accounting.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
