[
https://issues.apache.org/jira/browse/HDFS-13053?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16336187#comment-16336187
]
Íñigo Goiri commented on HDFS-13053:
------------------------------------
When the Datanode replies with a Pipeline ACK, it can include how long it took
for it to process the packet.
Each datanode in the pipeline would extend this with its own information so if
we have 3 DNs, we would have the time for each of them.
This would help detecting slow Datanodes and in conjunction to the total time,
we can also estimate the communication times.
> Track time to process packet in Datanode
> ----------------------------------------
>
> Key: HDFS-13053
> URL: https://issues.apache.org/jira/browse/HDFS-13053
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: datanode
> Reporter: Íñigo Goiri
> Priority: Minor
>
> We should track the time that each datanode takes to process a packet.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]