[ https://issues.apache.org/jira/browse/CASSANDRA-3723?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13187107#comment-13187107 ]
Peter Schuller commented on CASSANDRA-3723: ------------------------------------------- I'm very much +1 on await, including having it right there in tpstats (not just JMX), it's a very useful metric (not sure why we'd remove the latency though). As for performance: There are several things I've thought of that I want that are potentially performance impactful, yet useful even if just probabilistically sampled. I think there's a case to be made for using (thread-local, to avoid synchronization) randomization and probabilities in collecting statistics. This is one such case, if indeed there is a significant performance impact to begin with. > Include await for the queues in tpstats > --------------------------------------- > > Key: CASSANDRA-3723 > URL: https://issues.apache.org/jira/browse/CASSANDRA-3723 > Project: Cassandra > Issue Type: Bug > Components: Tools > Affects Versions: 1.2 > Reporter: Vijay > Assignee: Vijay > Priority: Minor > > Something simillar to IOSTAT await, there is an additional over head not sure > if we have to make an exception for this.... but i think this has a huge "+" > while troubleshooting.... > await > The average time (in milliseconds) for I/O requests issued to the request to > be served. This includes the time spent by the requests in queue and the time > spent servicing them > or we can also have a simple average of time spent in the queue before being > served. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira