[
https://issues.apache.org/jira/browse/HBASE-15614?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15231598#comment-15231598
]
stack commented on HBASE-15614:
-------------------------------
No magic to JvmPauseMonitor. If it is seeing pauses that are not in GC, that is
interesting. On article, how you think blocked i/o would manifest in the GC
log? Wouldn't the timestamps be just off? Just trying to avoid double metric on
same base phenomenon.
You running an hbase cluster now [~ndimiduk] If so, i defer to your operator
self... don't mind my dev BS.
> Report metrics from JvmPauseMonitor
> -----------------------------------
>
> Key: HBASE-15614
> URL: https://issues.apache.org/jira/browse/HBASE-15614
> Project: HBase
> Issue Type: Improvement
> Components: metrics, regionserver
> Reporter: Nick Dimiduk
>
> We have {{JvmPauseMonitor}} for detecting JVM pauses; pauses are logged at
> WARN. Would also be good to expose this information on a dashboard via
> metrics system -- make it easier to get this info off the host and into a
> central location for the operator.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
