linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Waiman Long <longman@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>,
	linux-kernel@vger.kernel.org, x86@kernel.org,
	linux-alpha@vger.kernel.org, linux-ia64@vger.kernel.org,
	linux-s390@vger.kernel.org, linux-arch@vger.kernel.org,
	Davidlohr Bueso <dave@stgolabs.net>,
	Dave Chinner <david@fromorbit.com>
Subject: Re: [PATCH v6 00/11] locking/rwsem: Rework rwsem-xadd & enable new rwsem features
Date: Wed, 11 Oct 2017 14:50:34 -0400	[thread overview]
Message-ID: <abbad63a-1026-6ff9-334e-9e4486b4f689@redhat.com> (raw)
In-Reply-To: <20171011184840.3uomgj3hxxzernfd@hirez.programming.kicks-ass.net>

On 10/11/2017 02:48 PM, Peter Zijlstra wrote:
> On Wed, Oct 11, 2017 at 02:01:51PM -0400, Waiman Long wrote:
>>   # of Patches		   Reader 		  Writer
>>     Applied		Locking Rate		Locking Rate
>>   ------------		------------		------------
>> 	0	5,155/    5,155/    5,155    5,154/248,852/346,281
>> 	7	5,696/    5,697/    5,698  113,500/215,826/320,872
>> 	8	4,827/    5,047/    5,215    4,826/176,797/284,069
>> 	9     211,276/  509,712/1,134,007    4,894/221,839/246,818
>>        11     884,513/1,043,989/1,252,533    9,604/ 11,105/ 25,225
>>
>> It can be seen that rwsem changes from writer-preferring to
>> reader-preferring.
> A bit radically so, you almost starve the writers there.

Yes, almost, but the lock handoff code will make sure that it won't
actually get starved. That is why I added aggressive reader lock
stealing after the lock handoff code.

Cheers,
Longman

  parent reply	other threads:[~2017-10-11 18:50 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-11 18:01 [PATCH v6 00/11] locking/rwsem: Rework rwsem-xadd & enable new rwsem features Waiman Long
2017-10-11 18:01 ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 01/11] locking/rwsem: relocate rwsem_down_read_failed() Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 02/11] locking/rwsem: Implement a new locking scheme Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:40   ` Peter Zijlstra
2017-10-11 18:58     ` Waiman Long
2017-10-11 18:58       ` Waiman Long
2017-10-11 19:05       ` Waiman Long
2017-10-11 19:36       ` Peter Zijlstra
2017-10-11 18:01 ` [PATCH v6 03/11] locking/rwsem: Move owner setting code from rwsem.c to rwsem-xadd.h Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 04/11] locking/rwsem: Remove kernel/locking/rwsem.h Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 05/11] locking/rwsem: Move rwsem internal function declarations to rwsem-xadd.h Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 06/11] locking/rwsem: Remove arch specific rwsem files Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 07/11] locking/rwsem: Implement lock handoff to prevent lock starvation Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:01 ` [PATCH v6 08/11] locking/rwsem: Enable readers spinning on writer Waiman Long
2017-10-11 18:01   ` Waiman Long
2017-10-11 18:02 ` [PATCH v6 09/11] locking/rwsem: Enable time-based reader lock stealing Waiman Long
2017-10-11 18:02 ` [PATCH v6 10/11] locking/rwsem: Make rwsem_spin_on_owner() return a tri-state value Waiman Long
2017-10-11 18:02   ` Waiman Long
2017-10-11 18:02 ` [PATCH v6 11/11] locking/rwsem: Enable count-based spinning on reader Waiman Long
2017-10-11 18:02   ` Waiman Long
2017-10-11 18:48 ` [PATCH v6 00/11] locking/rwsem: Rework rwsem-xadd & enable new rwsem features Peter Zijlstra
2017-10-11 18:48   ` Peter Zijlstra
2017-10-11 18:50   ` Waiman Long [this message]
2017-10-11 18:50     ` Waiman Long
2017-10-11 20:45   ` Dave Chinner
2017-10-11 20:45     ` Dave Chinner
2017-10-11 20:50 ` Dave Chinner
2017-10-11 20:50   ` Dave Chinner
2017-10-11 20:57   ` Waiman Long
2017-10-11 20:57     ` Waiman Long

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=abbad63a-1026-6ff9-334e-9e4486b4f689@redhat.com \
    --to=longman@redhat.com \
    --cc=dave@stgolabs.net \
    --cc=david@fromorbit.com \
    --cc=linux-alpha@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-ia64@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=x86@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).