-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/70884/
-----------------------------------------------------------

(Updated June 26, 2019, 1:37 p.m.)


Review request for mesos, Benjamin Mahler, Joseph Wu, and Till Toenshoff.


Changes
-------

Added benchmark results.


Bugs: MESOS-9858
    https://issues.apache.org/jira/browse/MESOS-9858


Repository: mesos


Description
-------

This allows client code to access the original hostname
that was used to specify a libprocess address.


Diffs
-----

  3rdparty/libprocess/include/process/pid.hpp 
9f09ab46fa3ceaeac09b0fbf9f532728c4ed2d7a 
  3rdparty/libprocess/src/pid.cpp fdc61b5ab6c75b33ce33de7edd11e9302550f300 
  3rdparty/libprocess/src/process.cpp 799666f03d6a78708aa9336c2dd04bc9b5023aa0 


Diff: https://reviews.apache.org/r/70884/diff/3/


Testing (updated)
-------

Results from running the `Process_BENCHMARK_ThroughputPerformance` with 
`--gtest_repeat=10`. There seems to be a slight degradation of performance on 
average, but the benchmark runtime seems to be dominated by other factors, as 
indicated by the large variance and presence of outliers on both sides.


# Master
2519083.849973
2401163.451671
2322734.358626
2285763.292828
1883268.801707
2179436.004374
2071825.301714
2105588.897964
2067228.706673


# Including UPID changes
2305142.571762
2194902.761484
2139113.533129
2024036.049603
1765327.993699
2172592.534808
2053217.096855
2103817.232509
1480080.596818
1808977.015807


Thanks,

Benno Evers

Reply via email to