Re: [PATCH v2] locking/percpu-rwsem: Optimize readers and reduce global impact

From	Om Dhyade <odhyade@codeaurora.org>
Newsgroups	linux.kernel
Subject	Re: [PATCH v2] locking/percpu-rwsem: Optimize readers and reduce global impact
Date	2016-08-13 03:50 +0200
Message-ID	<s5wfg-1k5-5@gated-at.bofh.it> (permalink)
References	(1 earlier) <s4oWt-5LB-3@gated-at.bofh.it> <s4Gqm-b4-49@gated-at.bofh.it> <s4Gqm-b4-47@gated-at.bofh.it> <s5wfg-1k5-7@gated-at.bofh.it> <s5wfg-1k5-9@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Thank you Dimtry for sharing the patches.

Update from my tests:
Use-case: Android application launches.

I tested the patches on android N build, i see max latency ~7ms.
In my tests, the wait is due to: copy_process(fork.c) blocks all threads 
in __cgroup_procs_write including threads which are not part of the 
forking process's thread-group.

Dimtry had provided a hack patch which reverts to per-process rw-sem 
which had max latency of ~2ms.

android user-space binder library does 2 cgroup write operations per 
transaction, apart from the copy_process(fork.c) wait, i see pre-emption 
in _cgroup_procs_write causing waits.

Thanks.

-- 
The Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

Re: [PATCH v2] locking/percpu-rwsem: Optimize readers and reduce  global impact Om Dhyade <odhyade@codeaurora.org> - 2016-08-13 03:50 +0200
  Re: [PATCH v2] locking/percpu-rwsem: Optimize readers and reduce  global impact John Stultz <john.stultz@linaro.org> - 2016-08-24 23:20 +0200
    Re: [PATCH v2] locking/percpu-rwsem: Optimize readers and reduce  global impact Tejun Heo <tj@kernel.org> - 2016-08-24 23:40 +0200
      Re: [PATCH v2] locking/percpu-rwsem: Optimize readers and reduce  global impact John Stultz <john.stultz@linaro.org> - 2016-08-25 01:00 +0200

csiph-web