GitHub user original-brownbear reopened a pull request:
https://github.com/apache/kafka/pull/2903
MINOR: Fix needless GC + Result time unit in JMH
Fixes two issues with the JMH benchmark example:
* Trivial: The output should be in `ops/ms` for readability reasons (it's
in the millions of operations per second)
* Important: The benchmark is not actually measuring the LRU-Cache
performance as most of the time in each run is wasted on concatenating `key +
counter` as well as `value + counter`. Fixed by pre-generating 10k K-V pairs
(100x the cache capacity) and iterating over them. This brings the performance
up by a factor of more than 5 on a standard 4 core i7 (`~6k/ms` before goes to
`~35k/ms`).
* Also made static what could be made static in the benchmark class to
lower the GC background noise
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/original-brownbear/kafka fix-jmh-example
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/kafka/pull/2903.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #2903
----
commit 8d30ef0f3e35f1fa03e035796f4e4d125bde4548
Author: Armin Braun <[email protected]>
Date: 2017-04-24T06:50:57Z
MINOR: Fix needless GC + Result time unit in JMH
commit 2dbbd4cf1d5d06bb154a3436aa8752d3bb89fc9e
Author: Armin Braun <[email protected]>
Date: 2017-04-24T09:10:21Z
MINOR: Fix needless GC + Result time unit in JMH
commit f5e46a7e2fbe3d8b4bc8f1817ce55cfbe821f067
Author: Armin Braun <[email protected]>
Date: 2017-04-24T09:13:44Z
MINOR: Fix needless GC + Result time unit in JMH
----
---
