----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/36951/#review93641 -----------------------------------------------------------
Saw from your comment [here](https://issues.apache.org/jira/browse/MESOS-3052?focusedCommentId=14648283&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-14648283) that this was mostly for posterity, and you'll be following up with organizing filters by slaves. I will hold off on reviewing this, hoping that storing filters keyed by SlaveID avoids the need for this kind of hack :) - Ben Mahler On July 30, 2015, 8:43 p.m., James Peach wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > https://reviews.apache.org/r/36951/ > ----------------------------------------------------------- > > (Updated July 30, 2015, 8:43 p.m.) > > > Review request for mesos and Ben Mahler. > > > Bugs: MESOS-3052 > https://issues.apache.org/jira/browse/MESOS-3052 > > > Repository: mesos > > > Description > ------- > > MESOS-3052: optimize slave ID comparisons > > > Diffs > ----- > > src/master/allocator/mesos/hierarchical.hpp > e278139f856888d6c6f538f7c0f664087e97f629 > > Diff: https://reviews.apache.org/r/36951/diff/ > > > Testing > ------- > > Running in production for a few weeks, yields ~10% CPU reduction. Tested with > make check and make bench. > > > Thanks, > > James Peach > >