[
https://issues.apache.org/jira/browse/MAPREDUCE-1248?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12783593#action_12783593
]
Ruibang He commented on MAPREDUCE-1248:
---------------------------------------
I suggest to remove the two local byte-arrays, and replace the following code:
key.set(keyBytes);
val.set(valBytes);
with:
key.set(utf, start, keyLen);
val.set(utf, splitPos+separatorLength, valLen);
I have simply tested the above in my cluster. It works and the momery stops
keeping going up.
Any thoughts?
> Redundant memory copying in StreamKeyValUtil
> --------------------------------------------
>
> Key: MAPREDUCE-1248
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-1248
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Components: contrib/streaming
> Reporter: Ruibang He
> Priority: Minor
>
> I found that when MROutputThread collecting the output of Reducer, it calls
> StreamKeyValUtil.splitKeyVal() and two local byte-arrays are allocated there
> for each line of output. Later these two byte-arrays are passed to variable
> key and val. There are twice memory copying here, one is the
> System.arraycopy() method, the other is inside key.set() / val.set().
> This causes double times of memory copying for the whole output (may lead to
> higher CPU consumption), and frequent temporay object allocation.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
