[
https://issues.apache.org/jira/browse/HTRACE-376?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15340959#comment-15340959
]
Pranavan commented on HTRACE-376:
---------------------------------
Hi Colin,
Thanks for helping me. The problem from phoenix side came when they are
calculating sum(endtime-starttime) for all trace logs with a particular id. You
can check the particular JIRA -
https://issues.apache.org/jira/browse/PHOENIX-2178
In my opinion, elapsed time became important here. For elapsed time, nanotime
is the accurate one.
Nano time call is pretty expensive because it will take like 100+ cpu clock
cycles whereas System.currentMillis() will just take 5 or 6 cpu clock cycles.
Nanotime is an expensive operation. (In my opinion calling nanotime is a
barrier for performance)
We can wait until JDK9 is supported in HTrace or I can check on reflections
whether we can fix it through it or not. Please direct me.
Thanks
> HTrace should support nanosecond time granularities
> ---------------------------------------------------
>
> Key: HTRACE-376
> URL: https://issues.apache.org/jira/browse/HTRACE-376
> Project: HTrace
> Issue Type: Improvement
> Components: core
> Affects Versions: 3.1.0
> Reporter: Colin Patrick McCabe
> Assignee: Pranavan
> Attachments: HTRACE-376.001.patch, HTRACE-376.002.patch
>
>
> HTrace should support nanosecond time granularities. Currently only a
> granularity of milliseconds is supported.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
