[
https://issues.apache.org/jira/browse/GEODE-8213?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17123942#comment-17123942
]
Jacob Barrett commented on GEODE-8213:
--------------------------------------
It isn't a very heavily utilized thing so in case you haven't noticed:
* In cppcache/benchmark are unit style benchmarks. These are intended to
benchmark the scope of things to just one or few types similar to unit tests.
You could probably refactor the registry to benchmark access with one of these.
* in cppcache/integration/benchmark are integration style benchmarks. They are
for benchmarking things that need more functionality than a unit test, like
needing a running cluster.
Both of these are based on Google's C\+\+ Benchmark suite.
> C++ native client performance bottleneck in access to serialization registry
> ----------------------------------------------------------------------------
>
> Key: GEODE-8213
> URL: https://issues.apache.org/jira/browse/GEODE-8213
> Project: Geode
> Issue Type: Improvement
> Components: native client
> Reporter: Alberto Gomez
> Assignee: Alberto Gomez
> Priority: Major
> Fix For: 1.14.0
>
>
> It's been observed that when the number of threads used in a Geode client
> using PdxSerialization is greater than 8, there is an important drop in
> performance.
> Analysing the client process behavior with perf, it has been observed a very
> high CPU consumption by a spinlock
> (apache::geode::util::concurrent::spinlock_mutex::lock) used when accessing
> the serialization registry .
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
