----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/25105/#review51678 -----------------------------------------------------------
Please close issues once you've addressed them. src/slave/containerizer/isolators/cgroups/blkio.cpp <https://reviews.apache.org/r/25105/#comment90201> Correct alphabetical ordering. src/slave/containerizer/isolators/cgroups/blkio.cpp <https://reviews.apache.org/r/25105/#comment90203> This shouldn't be a check. Just return a Failure("Pid ... for container ... has already been isolated") src/slave/containerizer/isolators/cgroups/blkio.cpp <https://reviews.apache.org/r/25105/#comment90206> Can you push this into linux/cgroups.cpp and namespace appropriately. See the memory and cpu for guidance. src/slave/containerizer/isolators/cgroups/blkio.cpp <https://reviews.apache.org/r/25105/#comment90207> Push into linux/cgroups.{c,h}pp - Ian Downes On Aug. 27, 2014, 11:50 a.m., Patrick Reilly wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > https://reviews.apache.org/r/25105/ > ----------------------------------------------------------- > > (Updated Aug. 27, 2014, 11:50 a.m.) > > > Review request for mesos, Adam B and Benjamin Hindman. > > > Bugs: MESOS-350 > https://issues.apache.org/jira/browse/MESOS-350 > > > Repository: mesos-git > > > Description > ------- > > Currently there is no disk isolation in place and this affects an executor to > be starved of disk when another disk heavy operation such as copying a multi > gigabyte file is being performed by another executor. > > > Diffs > ----- > > include/mesos/mesos.proto dea51f9 > src/Makefile.am 40b9f6b > src/slave/containerizer/isolators/cgroups/blkio.hpp PRE-CREATION > src/slave/containerizer/isolators/cgroups/blkio.cpp PRE-CREATION > src/slave/containerizer/mesos/containerizer.cpp 5116b14 > > Diff: https://reviews.apache.org/r/25105/diff/ > > > Testing > ------- > > In progress. > > > Thanks, > > Patrick Reilly > >