[
https://issues.apache.org/jira/browse/HDFS-1172?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13021966#comment-13021966
]
Todd Lipcon commented on HDFS-1172:
-----------------------------------
This patch looks good. Only question: does the new unit test properly fail if
you remove the fix in BlockManager? It seems we should be doing something to
artifically delay the block report of of the DataNodes. In HDFS-1197 there is
some test code that allows one to specify a delay in the DN configuration to
simulate this kind of condition.
> Blocks in newly completed files are considered under-replicated too quickly
> ---------------------------------------------------------------------------
>
> Key: HDFS-1172
> URL: https://issues.apache.org/jira/browse/HDFS-1172
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: name-node
> Affects Versions: 0.21.0
> Reporter: Todd Lipcon
> Assignee: Hairong Kuang
> Fix For: 0.23.0
>
> Attachments: HDFS-1172.patch, replicateBlocksFUC.patch,
> replicateBlocksFUC1.patch, replicateBlocksFUC1.patch
>
>
> I've seen this for a long time, and imagine it's a known issue, but couldn't
> find an existing JIRA. It often happens that we see the NN schedule
> replication on the last block of files very quickly after they're completed,
> before the other DNs in the pipeline have a chance to report the new block.
> This results in a lot of extra replication work on the cluster, as we
> replicate the block and then end up with multiple excess replicas which are
> very quickly deleted.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
