We should start recording queue metrics since cluster start.
lgtm, kick jenkins
This message was automatically generated.
The checkstyle output is inaccessible now.
Need to rekick jenkins to check if these issues are relevant.
Also, it seems a duplicate to keep referring "counter.queues." when defining these counter names:
"counter.queue." + queueName + ".pending.memory",
"counter.queue." + queueName + ".pending.cores",
"counter.queue." + queueName + ".allocated.memory",
"counter.queue." + queueName + ".allocated.cores" };
Uploaded patch addressing checkstyle and review.
Thanks review from Min Shen and patch uploaded by Jonathan Hung, missed this JIRA previously.
Latest patch LGTM, will commit later.
Committed to trunk, thanks Jonathan Hung and thanks reviews from Jian He Min Shen
SUCCESS: Integrated in Jenkins build Hadoop-trunk-Commit #11073 (See https://builds.apache.org/job/Hadoop-trunk-Commit/11073/)
YARN-4899. Queue metrics of SLS capacity scheduler only activated after (wangda: rev 5ed63e3e9d9937cf7441b7ceb5feafbf486f3387)