[
https://issues.apache.org/jira/browse/HDFS-3875?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13593583#comment-13593583
]
Kihwal Lee commented on HDFS-3875:
----------------------------------
Sorry for getting back to this so late and thank you Suresh for the feedback.
It made me think more about the non-leaf nodes in a pipeline. If the leaf node
disappears from the pipeline before reporting checksum error and recoverRbw()
is done, we can end up with latent checksum error in the block. This is because
datanodes won't discard already written data on pipeline recovery. It looks
like we have to make recoverRbw() to truncate blocks to the acked size to be
really safe.
Also, client should give up after certain number of pipeline reconstructions
for the same block.
> Issue handling checksum errors in write pipeline
> ------------------------------------------------
>
> Key: HDFS-3875
> URL: https://issues.apache.org/jira/browse/HDFS-3875
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode, hdfs-client
> Affects Versions: 2.0.2-alpha
> Reporter: Todd Lipcon
> Assignee: Kihwal Lee
> Priority: Critical
> Attachments: hdfs-3875.branch-0.23.no.test.patch.txt,
> hdfs-3875.branch-0.23.with.test.patch.txt, hdfs-3875.trunk.no.test.patch.txt,
> hdfs-3875.trunk.no.test.patch.txt, hdfs-3875.trunk.patch.txt,
> hdfs-3875.trunk.patch.txt, hdfs-3875.trunk.with.test.patch.txt,
> hdfs-3875.trunk.with.test.patch.txt, hdfs-3875-wip.patch
>
>
> We saw this issue with one block in a large test cluster. The client is
> storing the data with replication level 2, and we saw the following:
> - the second node in the pipeline detects a checksum error on the data it
> received from the first node. We don't know if the client sent a bad
> checksum, or if it got corrupted between node 1 and node 2 in the pipeline.
> - this caused the second node to get kicked out of the pipeline, since it
> threw an exception. The pipeline started up again with only one replica (the
> first node in the pipeline)
> - this replica was later determined to be corrupt by the block scanner, and
> unrecoverable since it is the only replica
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
