[
https://issues.apache.org/jira/browse/HDFS-14997?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16999809#comment-16999809
]
Xiaoqiao He commented on HDFS-14997:
------------------------------------
Some more information in our production cluster: we have deployed this feature
for nearly one month, and we do not any DataNode heartbeat exception even dead
state due to no heartbeat more than 630s(by default) since long time to wait
process command finished.(The main reason is that some command need to wait
{{datasetLock}} for long time if IO load is very high).
Furthermore, we have make BlockReport async also in our internal version, gain
the effect was very obvious. If any interesting, I would like to push forward
it at next JIRA.
> BPServiceActor process command from NameNode asynchronously
> -----------------------------------------------------------
>
> Key: HDFS-14997
> URL: https://issues.apache.org/jira/browse/HDFS-14997
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: datanode
> Reporter: Xiaoqiao He
> Assignee: Xiaoqiao He
> Priority: Major
> Attachments: HDFS-14997.001.patch, HDFS-14997.002.patch,
> HDFS-14997.003.patch, HDFS-14997.004.patch, HDFS-14997.005.patch
>
>
> There are two core functions, report(#sendHeartbeat, #blockReport,
> #cacheReport) and #processCommand in #BPServiceActor main process flow. If
> processCommand cost long time it will block send report flow. Meanwhile
> processCommand could cost long time(over 1000s the worst case I meet) when IO
> load of DataNode is very high. Since some IO operations are under
> #datasetLock, So it has to wait to acquire #datasetLock long time when
> process some of commands(such as #DNA_INVALIDATE). In such case, #heartbeat
> will not send to NameNode in-time, and trigger other disasters.
> I propose to improve #processCommand asynchronously and not block
> #BPServiceActor to send heartbeat back to NameNode when meet high IO load.
> Notes:
> 1. Lifeline could be one effective solution, however some old branches are
> not support this feature.
> 2. IO operations under #datasetLock is another issue, I think we should solve
> it at another JIRA.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
