> On Aug. 6, 2014, 6:37 a.m., Adam B wrote: > > src/master/hierarchical_allocator_process.hpp, line 729 > > <https://reviews.apache.org/r/24356/diff/1/?file=653338#file653338line729> > > > > In what order are you iterating through the slaves? What order should > > it be?
good point. right now it's the order in which the keys are stored in hashet which is undefined. maybe one option is to shuffle the slaves during every allocation for some sort of fairness. or we could sort them by available resources on a slave. not sure which one gels well with the DRF algorithm. i'm open to suggestions here. - Vinod ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/24356/#review49700 ----------------------------------------------------------- On Aug. 6, 2014, 12:49 a.m., Vinod Kone wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > https://reviews.apache.org/r/24356/ > ----------------------------------------------------------- > > (Updated Aug. 6, 2014, 12:49 a.m.) > > > Review request for mesos and Benjamin Hindman. > > > Bugs: MESOS-1119 > https://issues.apache.org/jira/browse/MESOS-1119 > > > Repository: mesos-git > > > Description > ------- > > The allocator now updates the DRF algorithm after every allocation of a > slave's resources. This will make the allocation more granular and fair. > > > Diffs > ----- > > src/master/hierarchical_allocator_process.hpp > 35d1579bbd665dfdd238932902ae16880dadeb66 > src/tests/allocator_tests.cpp b920533bbc36a154c02b467673bc7a0d50d65bc7 > > Diff: https://reviews.apache.org/r/24356/diff/ > > > Testing > ------- > > make check > > make check GTEST_FILTER="*PerSlaveAllocation*" GTEST_REPEAT=1000 > GTEST_BREAK_ON_FAILURE=1 GTEST_VERBOSE=1 MESOS_VERBOSE=1 GLOG_v=1 > > > Thanks, > > Vinod Kone > >
