From: Waiman Long <longman@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>,
Davidlohr Bueso <dave@stgolabs.net>
Cc: Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
linux-kernel@vger.kernel.org, Phil Auld <pauld@redhat.com>
Subject: Re: [RFC PATCH 5/5] locking/rwsem: Remove reader optimistic spinning
Date: Fri, 20 Nov 2020 17:39:50 -0500 [thread overview]
Message-ID: <90e1bc43-fead-904f-3bed-a2fbadf9c1ac@redhat.com> (raw)
In-Reply-To: <20201120144408.GF3040@hirez.programming.kicks-ass.net>
On 11/20/20 9:44 AM, Peter Zijlstra wrote:
> On Tue, Nov 17, 2020 at 09:35:56PM -0800, Davidlohr Bueso wrote:
>> On Tue, 17 Nov 2020, Waiman Long wrote:
>>
>>> The column "CS Load" represents the number of pause instructions issued
>>> in the locking critical section. A CS load of 1 is extremely short and
>>> is not likey in real situations. A load of 20 (moderate) and 100 (long)
>>> are more realistic.
>>>
>>> It can be seen that the previous patches in this series have reduced
>>> performance in general except in highly contended cases with moderate
>>> or long critical sections that performance improves a bit. This change
>>> is mostly caused by the "Prevent potential lock starvation" patch that
>>> reduce reader optimistic spinning and hence reduce reader fragmentation.
>>>
>>> The patch that further limit reader optimistic spinning doesn't seem to
>>> have too much impact on overall performance as shown in the benchmark
>>> data.
>>>
>>> The patch that disables reader optimistic spinning shows reduced
>>> performance at lightly loaded cases, but comparable or slightly better
>>> performance on with heavier contention.
>> I'm not overly worried about the lightly loaded cases here as the users
>> (mostly thinking mmap_sem) most likely won't care for real workloads,
>> not, ie: will-it-scale type things.
>>
>> So at SUSE we also ran into this very same problem with reader optimistic
>> spinning and considering the fragmentation went with disabling it, much
>> like this patch - but without the reader optimistic lock stealing bits
>> you have. So far nothing has really shown to fall out in our performance
>> automation. And per your data a single reader spinner does not seem to be
>> worth the added complexity of keeping reader spinning vs ripping it out.
> I'm fine with ripping it... It was finnicky to begin with.
>
Good to know. I am going to sent out v2 with some update commit logs and
some !CONFIG_RWSEM_SPIN_ON_OWNER fixes.
Cheers,
Longman
next prev parent reply other threads:[~2020-11-20 22:40 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-18 3:04 [PATCH 0/5] locking/rwsem: Rework reader optimistic spinning Waiman Long
2020-11-18 3:04 ` [PATCH 1/5] locking/rwsem: Pass the current atomic count to rwsem_down_read_slowpath() Waiman Long
2020-11-18 3:04 ` [PATCH 2/5] locking/rwsem: Prevent potential lock starvation Waiman Long
2020-11-20 14:44 ` Peter Zijlstra
2020-11-20 17:27 ` Waiman Long
2020-11-18 3:04 ` [PATCH 3/5] locking/rwsem: Enable reader optimistic lock stealing Waiman Long
2020-11-20 14:36 ` Peter Zijlstra
2020-11-20 17:26 ` Waiman Long
2020-12-08 3:53 ` Davidlohr Bueso
2020-11-18 3:04 ` [PATCH 4/5] locking/rwsem: Wake up all waiting readers if RWSEM_WAKE_READ_OWNED Waiman Long
2020-11-18 4:53 ` Davidlohr Bueso
2020-11-19 18:37 ` Waiman Long
2020-11-18 3:04 ` [RFC PATCH 5/5] locking/rwsem: Remove reader optimistic spinning Waiman Long
2020-11-18 5:35 ` Davidlohr Bueso
2020-11-19 18:40 ` Waiman Long
2020-11-20 13:11 ` David Laight
2020-11-20 17:04 ` Waiman Long
2020-11-20 17:37 ` David Laight
2020-11-20 21:38 ` Davidlohr Bueso
2020-11-21 11:50 ` David Laight
2020-11-20 14:44 ` Peter Zijlstra
2020-11-20 22:39 ` Waiman Long [this message]
2020-11-20 14:42 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=90e1bc43-fead-904f-3bed-a2fbadf9c1ac@redhat.com \
--to=longman@redhat.com \
--cc=dave@stgolabs.net \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).