[
https://issues.apache.org/jira/browse/HDFS-1111?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12894252#action_12894252
]
Sriram Rao commented on HDFS-1111:
----------------------------------
The case for paging was made by you (?) in one of the JIRAs on this issue. You
went looking for list of files in an important dir and found that the 500 limit
was getting in the way.
The patch that you have done has the namenode doing the filtering (and this has
caused problems).
What we are proposing instead, is to have the namenode return a list of corrupt
files to the client and then let the client do the filtering. The way we
envision using this feature is via an iterative approach to fixing corruption:
1. get a list of corrupt files for a certain path
2. fix up the corrupt files in that path
3. iterate; stop if the list of corrupt files is empty
By being iterative, this proposal also addresses one of the issues you had
brought up: namely, the list of corrupt files can change between successive
paging calls.
Fsck is a fall-back. With PBs that we have in our clusters, a full Fsck does
take a few hours to finish.
> getCorruptFiles() should give some hint that the list is not complete
> ---------------------------------------------------------------------
>
> Key: HDFS-1111
> URL: https://issues.apache.org/jira/browse/HDFS-1111
> Project: Hadoop HDFS
> Issue Type: New Feature
> Reporter: Rodrigo Schmidt
> Assignee: Rodrigo Schmidt
> Attachments: HADFS-1111.0.patch
>
>
> If the list of corruptfiles returned by the namenode doesn't say anything if
> the number of corrupted files is larger than the call output limit (which
> means the list is not complete). There should be a way to hint incompleteness
> to clients.
> A simple hack would be to add an extra entry to the array returned with the
> value null. Clients could interpret this as a sign that there are other
> corrupt files in the system.
> We should also do some rephrasing of the fsck output to make it more
> confident when the list is not complete and less confident when the list is
> known to be incomplete.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
