----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/34310/#review84353 -----------------------------------------------------------
src/slave/containerizer/isolators/cgroups/cpushare.cpp <https://reviews.apache.org/r/34310/#comment135566> Do you need a flag to control this? I would imagine some users might prefer not setting the scheduling policy for predictability and relying on the QoS controller to kill the revokable containers if resources used by PR tasks exceeds certain threshold. Instead of adding a new slave flag, do you think it makes sense to pull this logic into a separate isolator (e.g., cpu/revokable_idle)? - Jie Yu On May 18, 2015, 8:49 p.m., Ian Downes wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > https://reviews.apache.org/r/34310/ > ----------------------------------------------------------- > > (Updated May 18, 2015, 8:49 p.m.) > > > Review request for mesos, Joris Van Remoortere, Niklas Nielsen, and Vinod > Kone. > > > Bugs: MESOS-2652 > https://issues.apache.org/jira/browse/MESOS-2652 > > > Repository: mesos > > > Description > ------- > > Use IDLE scheduling for revocable CPU in cgroups isolator. > > > Diffs > ----- > > src/slave/containerizer/isolators/cgroups/cpushare.hpp > ff4a9dbdb1b655e71bf87dcee8fe62433d396f52 > src/slave/containerizer/isolators/cgroups/cpushare.cpp > 6a5b2b5c6e2844fe1a10815956569194b6f56681 > > Diff: https://reviews.apache.org/r/34310/diff/ > > > Testing > ------- > > > Thanks, > > Ian Downes > >
