[
https://issues.apache.org/jira/browse/TEZ-3440?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15536211#comment-15536211
]
Nathan Roberts commented on TEZ-3440:
-------------------------------------
Verified the fix resolved the problem for a large job that was using gzip for
intermediate data. Originally the job was seeing many thousands of fetch
failures due to the compression stream getting out-of-sync, after the fix there
were no fetch failures due to this particular issue.
I think it's good to go if someone has cycles to review.
> Shuffling to memory can get out-of-sync when fetching multiple compressed map
> outputs
> -------------------------------------------------------------------------------------
>
> Key: TEZ-3440
> URL: https://issues.apache.org/jira/browse/TEZ-3440
> Project: Apache Tez
> Issue Type: Bug
> Reporter: Nathan Roberts
> Assignee: Nathan Roberts
> Attachments: TEZ-3440.patch
>
>
> Haven't verified yet but certainly looks like tez needs same fix as
> MAPREDUCE-5308 in IFile.
> Specifically saw this because downstream tasks were reporting enough fetch
> failures that long-running upstream tasks had to be re-run, which makes job
> run for much longer than it needs.
> Usually shows itself as an "Invalid map id" error on a multi-map fetch on
> part 2-n (i.e. never the first one).
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
