> On June 14, 2016, 10:50 p.m., Jiang Yan Xu wrote: > > src/master/allocator/sorter/drf/sorter.cpp, lines 457-467 > > <https://reviews.apache.org/r/45961/diff/3/?file=1390649#file1390649line457> > > > > For this we need to > > > > 1. Run existing benchmarks to see how much performance degradation is > > there for clusters (large number of agents or frameworks) that are not > > using shared resources. Ideally there should be negligible performance > > impact for such clusters. > > 2. Create a benchmark that uses shared resources in a realistic way. > > > > In implementing this patch we do have the options to store shared > > resources separately in a few places (e.g., store shared resources outside > > of `allocations[name].resources`) that can help with performance but the > > trade off is that it may increase code complexity. Benchmarks can help us > > address these tradeoffs. > > Anindya Sinha wrote: > Verified that changes in allocator and sorter does not affect run time > performance adversely for regular resources. I will add a benchmark for > shared resources in the next update.
Added a new benchmark test in https://reviews.apache.org/r/49571/, and verifies allocation times over a large number of agents and frameworks is not impacted adversely with this change. - Anindya ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/45961/#review136970 ----------------------------------------------------------- On July 1, 2016, 10:28 p.m., Anindya Sinha wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > https://reviews.apache.org/r/45961/ > ----------------------------------------------------------- > > (Updated July 1, 2016, 10:28 p.m.) > > > Review request for mesos, Benjamin Mahler, Joris Van Remoortere, Michael > Park, and Jiang Yan Xu. > > > Bugs: MESOS-4431 > https://issues.apache.org/jira/browse/MESOS-4431 > > > Repository: mesos > > > Description > ------- > > o Each shared resource is accouted via its share count. This count is > updated based on the resource operations (such as add and subtract) > in various scenarios such as task launch and terminate at multiple > modules such as master, allocator, sorter, etc. > o Only allow DESTROY if there are no running or pending tasks using > the volume. However, if the volume is in a pending offer to one or > more frameworks, resind that offer before processing the DESTROY. > > > Diffs > ----- > > src/common/resources.cpp f6ff92b591c15bc8e93fd85e1896349c3a7bb968 > src/common/resources_utils.cpp 8e881a09500b0966b577e514077460f724868a8d > src/master/allocator/mesos/hierarchical.cpp > eca949e07abb00423a2f35a56eedc5d4287d81f3 > src/master/allocator/sorter/drf/sorter.hpp > 0aa1a71da4501a3b469d07538a043b4c1d74d688 > src/master/allocator/sorter/drf/sorter.cpp > 967290d4d1100208900b4b724422c3218abc23cb > src/master/http.cpp 7b2f77b9264242f31ab62eb9db7c621a1b8aa2fe > src/master/master.hpp be7cd239c49a0710a29a8187c01484f9f6d615e1 > src/master/master.cpp 78a8889313179b4509a6657e6c61d9f6d3bb99c0 > src/master/validation.hpp 43d876b00511d4ef652c2685d4950c994b5eef31 > src/master/validation.cpp 50ba372d1301d16d1738a3e4f4882b51f9ce06cd > src/tests/master_validation_tests.cpp > 9eb82a569f7c48caa96d4d54a93b199ccac74385 > src/tests/sorter_tests.cpp 6fc58829892dc0223140f1b47593a3e5853cace5 > src/v1/resources.cpp 8c3f2d1c1529915a59d47fe37bb3fc7a3267079a > > Diff: https://reviews.apache.org/r/45961/diff/ > > > Testing > ------- > > Tests successful. > > > Thanks, > > Anindya Sinha > >