mesos-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Meng Zhu <m...@mesosphere.io>
Subject Re: Review Request 64969: Added an performance benchmark for master `Getstate` v1 api.
Date Wed, 17 Jan 2018 01:29:35 GMT

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

(Updated Jan. 17, 2018, 1:29 a.m.)


Review request for mesos, Benjamin Mahler, Michael Park, and Jiang Yan Xu.


Changes
-------

Updated the testing done numbers

--bmahler


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/3/


Testing (updated)
-------

Example output from optimized build:

[ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/0
Test setup: 1000 agents with a total of 10000 running tasks and 10000 completed tasks.
v0 "/state" query response took 367.331953ms
v1 Getstate application/x-protobuf query response took 312.803708ms
v1 Getstate application/json query response took 732.807684ms
[       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/0
(8105 ms)
[ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/1
Test setup: 10000 agents with a total of 100000 running tasks and 100000 completed tasks.
v0 "/state" query response took 3.591473849secs
v1 Getstate application/x-protobuf query response took 3.661784437secs
v1 Getstate application/json query response took 6.905652075secs
[       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/1
(83974 ms)
[ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/2
Test setup: 20000 agents with a total of 200000 running tasks and 200000 completed tasks.
v0 "/state" query response took 7.049141398secs
v1 Getstate application/x-protobuf query response took 8.918444916secs
v1 Getstate application/json query response took 13.443727676secs
[       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/2
(174468 ms)
[ RUN      ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/3
Test setup: 40000 agents with a total of 400000 running tasks and 400000 completed tasks.
v0 "/state" query response took 14.37652117secs
v1 Getstate application/x-protobuf query response took 15.759739083secs
v1 Getstate application/json query response took 29.837744733secs
[       OK ] AgentFrameworkTaskCountContentType/MasterStateQuery_BENCHMARK_Test.Getstate/3
(368313 ms)


Thanks,

Meng Zhu


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