[ https://issues.apache.org/jira/browse/CASSANDRA-8341?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14218149#comment-14218149 ]
Robert Stupp commented on CASSANDRA-8341: ----------------------------------------- FWIW it's not necessary to add another {{ThreadLocal}} to trace work-unit start time. Wrapping the {{Runnable}} using a static class containing the start-time feels cheaper. Adding to metrics code before or after work-unit execution "transparently" extends work-unit execution latency, which isn't measured. (Note that System.nanoTime() [may introduce latency|http://shipilev.net/blog/2014/nanotrusting-nanotime/]). > Expose time spent in each thread pool > ------------------------------------- > > Key: CASSANDRA-8341 > URL: https://issues.apache.org/jira/browse/CASSANDRA-8341 > Project: Cassandra > Issue Type: New Feature > Components: Core > Reporter: Chris Lohfink > Priority: Minor > Labels: metrics > Attachments: 8341.patch > > > Can increment a counter with time spent in each queue. This can provide > context on how much time is spent percentage wise in each stage. > Additionally can be used with littles law in future if ever want to try to > tune the size of the pools. -- This message was sent by Atlassian JIRA (v6.3.4#6332)