[
https://issues.apache.org/jira/browse/HDFS-10301?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15546390#comment-15546390
]
Vinitha Reddy Gankidi commented on HDFS-10301:
----------------------------------------------
Patch 15 has the changes mentioned in
https://issues.apache.org/jira/browse/HDFS-10301?focusedCommentId=15536676&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-15536676.
Kindly review.
??It does not solve the race between a timed out BR and the repeating BR in
multi-RPC BR case.??
When there is a race, the per-storage BRs that arrive after the removal of the
node lease would not be processed. I think that is okay. BR retransmissions are
handled by the underlying RPC layer. The same RPC request is retried as per the
specified Retry policy. Since these retransmitted BRs are identical, it is
sufficient if we process all the per-storage BRs once. It seems okay to ignore
the subsequent retransmitted BRs from the same node once {{curRpc + 1 ==
totalRpcs}} is satisfied. Does that sound reasonable?
> BlockReport retransmissions may lead to storages falsely being declared
> zombie if storage report processing happens out of order
> --------------------------------------------------------------------------------------------------------------------------------
>
> Key: HDFS-10301
> URL: https://issues.apache.org/jira/browse/HDFS-10301
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: namenode
> Affects Versions: 2.6.1
> Reporter: Konstantin Shvachko
> Assignee: Vinitha Reddy Gankidi
> Priority: Critical
> Attachments: HDFS-10301.002.patch, HDFS-10301.003.patch,
> HDFS-10301.004.patch, HDFS-10301.005.patch, HDFS-10301.006.patch,
> HDFS-10301.007.patch, HDFS-10301.008.patch, HDFS-10301.009.patch,
> HDFS-10301.01.patch, HDFS-10301.010.patch, HDFS-10301.011.patch,
> HDFS-10301.012.patch, HDFS-10301.013.patch, HDFS-10301.014.patch,
> HDFS-10301.branch-2.7.patch, HDFS-10301.branch-2.patch,
> HDFS-10301.sample.patch, zombieStorageLogs.rtf
>
>
> When NameNode is busy a DataNode can timeout sending a block report. Then it
> sends the block report again. Then NameNode while process these two reports
> at the same time can interleave processing storages from different reports.
> This screws up the blockReportId field, which makes NameNode think that some
> storages are zombie. Replicas from zombie storages are immediately removed,
> causing missing blocks.
--
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
