[
https://issues.apache.org/jira/browse/MAPREDUCE-3121?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13149914#comment-13149914
]
Hitesh Shah commented on MAPREDUCE-3121:
----------------------------------------
Some comments:
- DISKS_FAILED 144 is probably not a good idea. It clashes with SIGUSR1. We
could use EIO or any other relevant exit code related to file system errors.
Another option is to use a non-clashing exit code along the lines of container
aborted ( -100 ). Anyone have any preferences on which approach to leverage?
The latter will obviously be a more clear indicator on what the failure was and
allow easy blacklisting of this node/re-scheduling on other nodes.
- Should the the failed disks error information be propagated into the
app/container diagnostics?
- Should there be a check for whether there are any good dirs left in
ResourceLocalizationService before starting of localizing the resources?
> NodeManager should handle disk-failures
> ---------------------------------------
>
> Key: MAPREDUCE-3121
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3121
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mrv2, nodemanager
> Affects Versions: 0.23.0
> Reporter: Vinod Kumar Vavilapalli
> Assignee: Ravi Gummadi
> Fix For: 0.23.1
>
> Attachments: 3121.patch, 3121.v1.1.patch, 3121.v1.patch
>
>
> This is akin to MAPREDUCE-2413 but for YARN's NodeManager. We want to
> minimize the impact of transient/permanent disk failures on containers. With
> larger number of disks per node, the ability to continue to run containers on
> other disks is crucial.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
