[
https://issues.apache.org/jira/browse/HDFS-11615?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15966175#comment-15966175
]
Erik Krogen commented on HDFS-11615:
------------------------------------
Fair enough, I will change it to nanoseconds. I can put it in the variable
names, and I think that's a good idea - the mix of nano-level and milli-level
in the class is a little confusing.
The metric name is harder since {{MutableRate}} is used so you supply a base
name and then the {{MutableRate}} applies the suffix of {{AvgTime}} and
{{NumOps}}, so it would look like {{FSNWriteLockOperationNameNanosAvgTime}} and
{{FSNWriteLockOperationNameNanosNumOps}} which is a little awkward... I could
potentially create an additional constructor for {{MutableRate}} which allows
you to specify a time unit. Any thoughts, [~andrew.wang]?
> FSNamesystemLock metrics can be inaccurate due to millisecond precision
> -----------------------------------------------------------------------
>
> Key: HDFS-11615
> URL: https://issues.apache.org/jira/browse/HDFS-11615
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: hdfs
> Affects Versions: 2.7.4
> Reporter: Erik Krogen
> Assignee: Erik Krogen
> Attachments: HDFS-11615.000.patch
>
>
> Currently the {{FSNamesystemLock}} metrics created in HDFS-10872 track the
> lock hold time using {{Timer.monotonicNow()}}, which has millisecond-level
> precision. However, many of these operations hold the lock for less than a
> millisecond, making these metrics inaccurate. We should instead use
> {{System.nanoTime()}} for higher accuracy.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
