[
https://issues.apache.org/jira/browse/HDFS-12102?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16115059#comment-16115059
]
Arpit Agarwal commented on HDFS-12102:
--------------------------------------
Hi [~nroberts], we've seen single drive failures usually manifest as IO
slowness or failing IOs (of course occasionally a drive becomes completely
unresponsive).
The proposal makes sense for your failure mode. Also if multiple blocks on a
disk become corrupt in a single scan cycle then we could mark it as a failed
volume. Just curious, when you see this, what fraction of blocks on the disk
appear corrupt? I assume the blocks become unreadable and you don't actually
read corrupted data.
> VolumeScanner throttle dropped (fast scan enabled) when there is a corrupt
> block
> --------------------------------------------------------------------------------
>
> Key: HDFS-12102
> URL: https://issues.apache.org/jira/browse/HDFS-12102
> Project: Hadoop HDFS
> Issue Type: New Feature
> Components: datanode, hdfs
> Affects Versions: 2.8.2
> Reporter: Ashwin Ramesh
> Priority: Minor
> Fix For: 2.8.2
>
> Attachments: HDFS-12102-001.patch, HDFS-12102-002.patch,
> HDFS-12102-003.patch
>
>
> When the Volume scanner sees a corrupt block, it restarts the scan and scans
> the blocks at much faster rate with a negligible scan period. This is so that
> it doesn't take 3 weeks to report blocks since a corrupt block means
> increased likelihood that there are more corrupt blocks.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
