[
https://issues.apache.org/jira/browse/HDFS-6937?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15400752#comment-15400752
]
Yongjun Zhang commented on HDFS-6937:
-------------------------------------
Hi [~brahmareddy],
Thanks for reporting the issue you ran into.
If your problem is really a network issue, then your proposed solution sounds
reasonable to me. However, it seems different than what HDFS-6937 intends to
solve, and I think we can create a new jira for your issue. Here is why:
HDFS-6937's scenario is that we keep replacing the third node in recovery, and
did not detect that the middle node is corrupt. Thus adding a corruption
checking for the middle node would solve the issue; In your case, even if we
try to check the middle node, it would appear as not corrupt. The problem is
that, we don't have a check for network issue (and probably adding a network
check may not be feasible here).
On the other hand, if it's not a network issue, then it could be caused by
HDFS-4660, if you don't already have the fix.
Hope my explanation makes sense.
> Another issue in handling checksum errors in write pipeline
> -----------------------------------------------------------
>
> Key: HDFS-6937
> URL: https://issues.apache.org/jira/browse/HDFS-6937
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode, hdfs-client
> Affects Versions: 2.5.0
> Reporter: Yongjun Zhang
> Assignee: Wei-Chiu Chuang
> Attachments: HDFS-6937.001.patch, HDFS-6937.002.patch
>
>
> Given a write pipeline:
> DN1 -> DN2 -> DN3
> DN3 detected cheksum error and terminate, DN2 truncates its replica to the
> ACKed size. Then a new pipeline is attempted as
> DN1 -> DN2 -> DN4
> DN4 detects checksum error again. Later when replaced DN4 with DN5 (and so
> on), it failed for the same reason. This led to the observation that DN2's
> data is corrupted.
> Found that the software currently truncates DN2's replca to the ACKed size
> after DN3 terminates. But it doesn't check the correctness of the data
> already written to disk.
> So intuitively, a solution would be, when downstream DN (DN3 here) found
> checksum error, propagate this info back to upstream DN (DN2 here), DN2
> checks the correctness of the data already written to disk, and truncate the
> replica to to MIN(correctDataSize, ACKedSize).
> Found this issue is similar to what was reported by HDFS-3875, and the
> truncation at DN2 was actually introduced as part of the HDFS-3875 solution.
> Filing this jira for the issue reported here. HDFS-3875 was filed by
> [~tlipcon]
> and found he proposed something similar there.
> {quote}
> if the tail node in the pipeline detects a checksum error, then it returns a
> special error code back up the pipeline indicating this (rather than just
> disconnecting)
> if a non-tail node receives this error code, then it immediately scans its
> own block on disk (from the beginning up through the last acked length). If
> it detects a corruption on its local copy, then it should assume that it is
> the faulty one, rather than the downstream neighbor. If it detects no
> corruption, then the faulty node is either the downstream mirror or the
> network link between the two, and the current behavior is reasonable.
> {quote}
> Thanks.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
