[
https://issues.apache.org/jira/browse/HADOOP-17531?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17286281#comment-17286281
]
Ayush Saxena commented on HADOOP-17531:
---------------------------------------
Thanx [[email protected]] for the pointers,
I tried using the {{listStatusIterator}} along with the previous code, pre
HADOOP-11827, post that I was able to copy around 3.8 Million, with client opts
set to only 512 MB, where as before, for just 1 Million it was giving me OOM,
it required around 700-800Mb for 1 Million,
Speed wise too, it took me less than a minute only to get the listing done.
I have attached the GC log and the patch that I used for reference
> DistCp: Reduce memory usage on copying huge directories
> -------------------------------------------------------
>
> Key: HADOOP-17531
> URL: https://issues.apache.org/jira/browse/HADOOP-17531
> Project: Hadoop Common
> Issue Type: Improvement
> Reporter: Ayush Saxena
> Priority: Critical
> Attachments: MoveToStackIterator.patch, gc-NewD-512M-3.8ML.log
>
>
> Presently distCp, uses the producer-consumer kind of setup while building the
> listing, the input queue and output queue are both unbounded, thus the
> listStatus grows quite huge.
> Rel Code Part :
> https://github.com/apache/hadoop/blob/trunk/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/SimpleCopyListing.java#L635
> This goes on bredth-first traversal kind of stuff(uses queue instead of
> earlier stack), so if you have files at lower depth, it will like open up the
> entire tree and the start processing....
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
