[
https://issues.apache.org/jira/browse/HDFS-14045?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16677090#comment-16677090
]
Íñigo Goiri commented on HDFS-14045:
------------------------------------
Thanks [~yangjiandan] for the updated version.
* We can fix the checkstyle for 80 characters.
* For the 3 seconds, it might be better to make it a much larger number (say 1
minute) if that's the intention (actually, it would be ideal if there was a way
to disable automatic heartbeats).
* We should assert the state in {{testNNRpcMetricsWithHA()}} between
{{triggerHeartbeats()}}. HeartbeatsNumOps should be 0 and
HeartbeatsForStandbyNumOps should be 4 I'm guessing?
> Use different metrics in DataNode to better measure latency of
> heartbeat/blockReports/incrementalBlockReports of Active/Standby NN
> ----------------------------------------------------------------------------------------------------------------------------------
>
> Key: HDFS-14045
> URL: https://issues.apache.org/jira/browse/HDFS-14045
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: datanode
> Reporter: Jiandan Yang
> Assignee: Jiandan Yang
> Priority: Major
> Attachments: HDFS-14045.001.patch, HDFS-14045.002.patch,
> HDFS-14045.003.patch
>
>
> Currently DataNode uses same metrics to measure rpc latency of NameNode, but
> Active and Standby usually have different performance at the same time,
> especially in large cluster. For example, rpc latency of Standby is very long
> when Standby is catching up editlog. We may misunderstand the state of HDFS.
> Using different metrics for Active and standby can help us obtain more
> precise metric data.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
