cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "laneser kuo (JIRA)" <j...@apache.org>
Subject [jira] [Closed] (CASSANDRA-4653) nodetool cfstats Lantecy unit is wrong , it should be sec (seconds) instead of ms (micro seconds)
Date Fri, 14 Sep 2012 01:16:07 GMT

     [ https://issues.apache.org/jira/browse/CASSANDRA-4653?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

laneser kuo closed CASSANDRA-4653.
----------------------------------


Thanks reply, after taking more time to read code,
the latency data comes from addNano , which is 10^-9 seconds,
then histograms store data in micro seconds, which is 10^-6 seconds,
and cfstats shows milliseconds, which is 10^-3 seconds.
                
> nodetool cfstats Lantecy unit is wrong , it should be sec (seconds) instead of ms (micro
seconds)
> -------------------------------------------------------------------------------------------------
>
>                 Key: CASSANDRA-4653
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-4653
>             Project: Cassandra
>          Issue Type: Bug
>          Components: Tools
>            Reporter: laneser kuo
>            Priority: Trivial
>         Attachments: mstosec.txt
>
>
> I was mislead by the nodetool cfstats Read Latency and Write Latency data.
> Until I read the source code, it should display sec instead of ms.
> for example:
> outs.println("\t\tRead Latency: " + String.format("%01.3f", cfstore.getRecentReadLatencyMicros()
/ 1000) + " ms.");

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message