[jira] [Commented] (HBASE-8744) Enable HBase to log the entire latency profile for HDFS packets resulting in slow writes.

["stack (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HBASE-8744?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13684056#comment-13684056 ] 

stack commented on HBASE-8744:
------------------------------

[~blackpearl] Have you seen http://hbase.apache.org/book.html#tracing and https://github.com/cloudera/htrace ?
                
> Enable HBase to log the entire latency profile for HDFS packets resulting in slow writes.
> -----------------------------------------------------------------------------------------
>
>                 Key: HBASE-8744
>                 URL: https://issues.apache.org/jira/browse/HBASE-8744
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: Pritam Damania
>            Priority: Minor
>
> When we see WAL outliers in HBase, at times it is not clear which component in the whole stack is slow. At facebook we are implementing per request profiling which passes profiling information throughout the entire stack. This information can be used to determine the outliers in HBase.

--
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