mesos-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Benjamin Mahler <bmah...@apache.org>
Subject Re: Review Request 64969: Added an performance benchmark for master `getstate` v1 api.
Date Sat, 06 Jan 2018 03:20:09 GMT

-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/64969/#review194923
-----------------------------------------------------------



- Can you measure with optimization turned on?
- No need to include the test setup in the output multiple times
- No need to include the messages in the output

- Benjamin Mahler


On Jan. 6, 2018, 1:40 a.m., Meng Zhu wrote:
> 
> -----------------------------------------------------------
> This is an automatically generated e-mail. To reply, visit:
> https://reviews.apache.org/r/64969/
> -----------------------------------------------------------
> 
> (Updated Jan. 6, 2018, 1:40 a.m.)
> 
> 
> Review request for mesos, Benjamin Mahler, Michael Park, and Jiang Yan Xu.
> 
> 
> Bugs: MESOS-8344
>     https://issues.apache.org/jira/browse/MESOS-8344
> 
> 
> Repository: mesos
> 
> 
> Description
> -------
> 
> This test is based on the MasterFailover benchmark which
> currently lacks things like executor. It is possible
> to add these when needed.
> 
> 
> Diffs
> -----
> 
>   src/tests/master_benchmarks.cpp 7d69588b3a4090ad1a755b592d2f8756ad6dff9e 
> 
> 
> Diff: https://reviews.apache.org/r/64969/diff/1/
> 
> 
> Testing
> -------
> 
> Output from running on MacBook Pro with 3.3 GHz Intel Core i7:
> 
> [==========] Running 6 tests from 1 test case.
> [----------] Global test environment set-up.
> [----------] 6 tests from AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test
> [ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/0
> Test setup: 2000 agents with a total of 100000 running tasks and 100000 completed tasks.
> Starting reregistration for all agents...
> All reregistration completed. Starting querying master...
> Getstate application/x-protobuf query response took 10.716890195secs with the following
test setup:
> 2000 agents with a total of 100000 running tasks and 100000 completed tasks.
> [       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/0
(36683 ms)
> [ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/1
> Test setup: 2000 agents with a total of 200000 running tasks and 0 completed tasks.
> Starting reregistration for all agents...
> All reregistration completed. Starting querying master...
> Getstate application/x-protobuf query response took 21.103205786secs with the following
test setup:
> 2000 agents with a total of 200000 running tasks and 0 completed tasks.
> [       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/1
(62539 ms)
> [ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/2
> Test setup: 20000 agents with a total of 100000 running tasks and 0 completed tasks.
> Starting reregistration for all agents...
> All reregistration completed. Starting querying master...
> Getstate application/x-protobuf query response took 14.185437528secs with the following
test setup:
> 20000 agents with a total of 100000 running tasks and 0 completed tasks.
> [       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/2
(48821 ms)
> [ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/3
> Test setup: 2000 agents with a total of 100000 running tasks and 100000 completed tasks.
> Starting reregistration for all agents...
> All reregistration completed. Starting querying master...
> Getstate application/json query response took 2.46403078761667mins with the following
test setup:
> 2000 agents with a total of 100000 running tasks and 100000 completed tasks.
> [       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/3
(176789 ms)
> [ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/4
> Test setup: 2000 agents with a total of 200000 running tasks and 0 completed tasks.
> Starting reregistration for all agents...
> All reregistration completed. Starting querying master...
> Getstate application/json query response took 5.05502142155mins with the following test
setup:
> 2000 agents with a total of 200000 running tasks and 0 completed tasks.
> [       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/4
(351393 ms)
> [ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/5
> Test setup: 20000 agents with a total of 100000 running tasks and 0 completed tasks.
> Starting reregistration for all agents...
> All reregistration completed. Starting querying master...
> Getstate application/json query response took 3.26795947955mins with the following test
setup:
> 20000 agents with a total of 100000 running tasks and 0 completed tasks.
> [       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.GetstateV1/5
(236676 ms)
> [----------] 6 tests from AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test
(912902 ms total)
> 
> [----------] Global test environment tear-down
> [==========] 6 tests from 1 test case ran. (912933 ms total)
> [  PASSED  ] 6 tests.
> 
> 
> Thanks,
> 
> Meng Zhu
> 
>


Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message