From: Ingo Molnar <mingo@kernel.org> To: Tim Chen <tim.c.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu>, Andrea Arcangeli <aarcange@redhat.com>, Mel Gorman <mgorman@suse.de>, "Shi, Alex" <alex.shi@intel.com>, Andi Kleen <andi@firstfloor.org>, Andrew Morton <akpm@linux-foundation.org>, Michel Lespinasse <walken@google.com>, Davidlohr Bueso <davidlohr.bueso@hp.com>, "Wilcox, Matthew R" <matthew.r.wilcox@intel.com>, Dave Hansen <dave.hansen@intel.com>, Peter Zijlstra <a.p.zijlstra@chello.nl>, Rik van Riel <riel@redhat.com>, linux-kernel@vger.kernel.org, linux-mm <linux-mm@kvack.org> Subject: Re: Performance regression from switching lock to rw-sem for anon-vma tree Date: Tue, 23 Jul 2013 11:45:13 +0200 [thread overview] Message-ID: <20130723094513.GA24522@gmail.com> (raw) In-Reply-To: <1373997195.22432.297.camel@schen9-DESK> * Tim Chen <tim.c.chen@linux.intel.com> wrote: > Ingo, > > I tried MCS locking to order the writers but it didn't make much > difference on my particular workload. After thinking about this some > more, a likely explanation of the performance difference between mutex > and rwsem performance is: > > 1) Jobs acquiring mutex put itself on the wait list only after > optimistic spinning. That's only 2% of the time on my test workload so > they access the wait list rarely. > > 2) Jobs acquiring rw-sem for write *always* put itself on the wait list > first before trying lock stealing and optimistic spinning. This creates > a bottleneck at the wait list, and also more cache bouncing. Indeed ... > One possible optimization is to delay putting the writer on the wait > list till after optimistic spinning, but we may need to keep track of > the number of writers waiting. We could add a WAIT_BIAS to count for > each write waiter and remove the WAIT_BIAS each time a writer job > completes. This is tricky as I'm changing the semantics of the count > field and likely will require a number of changes to rwsem code. Your > thoughts on a better way to do this? Why not just try the delayed addition approach first? The spinning is time limited AFAICS, so we don't _have to_ recognize those as writers per se, only if the spinning fails and it wants to go on the waitlist. Am I missing something? It will change patterns, it might even change the fairness balance - but is a legit change otherwise, especially if it helps performance. Thanks, Ingo
WARNING: multiple messages have this Message-ID (diff)
From: Ingo Molnar <mingo@kernel.org> To: Tim Chen <tim.c.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu>, Andrea Arcangeli <aarcange@redhat.com>, Mel Gorman <mgorman@suse.de>, "Shi, Alex" <alex.shi@intel.com>, Andi Kleen <andi@firstfloor.org>, Andrew Morton <akpm@linux-foundation.org>, Michel Lespinasse <walken@google.com>, Davidlohr Bueso <davidlohr.bueso@hp.com>, "Wilcox, Matthew R" <matthew.r.wilcox@intel.com>, Dave Hansen <dave.hansen@intel.com>, Peter Zijlstra <a.p.zijlstra@chello.nl>, Rik van Riel <riel@redhat.com>, linux-kernel@vger.kernel.org, linux-mm <linux-mm@kvack.org> Subject: Re: Performance regression from switching lock to rw-sem for anon-vma tree Date: Tue, 23 Jul 2013 11:45:13 +0200 [thread overview] Message-ID: <20130723094513.GA24522@gmail.com> (raw) In-Reply-To: <1373997195.22432.297.camel@schen9-DESK> * Tim Chen <tim.c.chen@linux.intel.com> wrote: > Ingo, > > I tried MCS locking to order the writers but it didn't make much > difference on my particular workload. After thinking about this some > more, a likely explanation of the performance difference between mutex > and rwsem performance is: > > 1) Jobs acquiring mutex put itself on the wait list only after > optimistic spinning. That's only 2% of the time on my test workload so > they access the wait list rarely. > > 2) Jobs acquiring rw-sem for write *always* put itself on the wait list > first before trying lock stealing and optimistic spinning. This creates > a bottleneck at the wait list, and also more cache bouncing. Indeed ... > One possible optimization is to delay putting the writer on the wait > list till after optimistic spinning, but we may need to keep track of > the number of writers waiting. We could add a WAIT_BIAS to count for > each write waiter and remove the WAIT_BIAS each time a writer job > completes. This is tricky as I'm changing the semantics of the count > field and likely will require a number of changes to rwsem code. Your > thoughts on a better way to do this? Why not just try the delayed addition approach first? The spinning is time limited AFAICS, so we don't _have to_ recognize those as writers per se, only if the spinning fails and it wants to go on the waitlist. Am I missing something? It will change patterns, it might even change the fairness balance - but is a legit change otherwise, especially if it helps performance. Thanks, Ingo -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2013-07-23 9:45 UTC|newest] Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top 2013-06-13 23:26 Performance regression from switching lock to rw-sem for anon-vma tree Tim Chen 2013-06-13 23:26 ` Tim Chen 2013-06-19 13:16 ` Ingo Molnar 2013-06-19 13:16 ` Ingo Molnar 2013-06-19 16:53 ` Tim Chen 2013-06-19 16:53 ` Tim Chen 2013-06-26 0:19 ` Tim Chen 2013-06-26 0:19 ` Tim Chen 2013-06-26 9:51 ` Ingo Molnar 2013-06-26 9:51 ` Ingo Molnar 2013-06-26 21:36 ` Tim Chen 2013-06-26 21:36 ` Tim Chen 2013-06-27 0:25 ` Tim Chen 2013-06-27 0:25 ` Tim Chen 2013-06-27 8:36 ` Ingo Molnar 2013-06-27 8:36 ` Ingo Molnar 2013-06-27 20:53 ` Tim Chen 2013-06-27 20:53 ` Tim Chen 2013-06-27 23:31 ` Tim Chen 2013-06-27 23:31 ` Tim Chen 2013-06-28 9:38 ` Ingo Molnar 2013-06-28 9:38 ` Ingo Molnar 2013-06-28 21:04 ` Tim Chen 2013-06-28 21:04 ` Tim Chen 2013-06-29 7:12 ` Ingo Molnar 2013-06-29 7:12 ` Ingo Molnar 2013-07-01 20:28 ` Tim Chen 2013-07-01 20:28 ` Tim Chen 2013-07-02 6:45 ` Ingo Molnar 2013-07-02 6:45 ` Ingo Molnar 2013-07-16 17:53 ` Tim Chen 2013-07-16 17:53 ` Tim Chen 2013-07-23 9:45 ` Ingo Molnar [this message] 2013-07-23 9:45 ` Ingo Molnar 2013-07-23 9:51 ` Peter Zijlstra 2013-07-23 9:51 ` Peter Zijlstra 2013-07-23 9:53 ` Ingo Molnar 2013-07-23 9:53 ` Ingo Molnar 2013-07-30 0:13 ` Tim Chen 2013-07-30 0:13 ` Tim Chen 2013-07-30 19:24 ` Ingo Molnar 2013-07-30 19:24 ` Ingo Molnar 2013-08-05 22:08 ` Tim Chen 2013-08-05 22:08 ` Tim Chen 2013-07-30 19:59 ` Davidlohr Bueso 2013-07-30 19:59 ` Davidlohr Bueso 2013-07-30 20:34 ` Tim Chen 2013-07-30 20:34 ` Tim Chen 2013-07-30 21:45 ` Davidlohr Bueso 2013-07-30 21:45 ` Davidlohr Bueso 2013-08-06 23:55 ` Davidlohr Bueso 2013-08-06 23:55 ` Davidlohr Bueso 2013-08-07 0:56 ` Tim Chen 2013-08-07 0:56 ` Tim Chen 2013-08-12 18:52 ` Ingo Molnar 2013-08-12 18:52 ` Ingo Molnar 2013-08-12 20:10 ` Tim Chen 2013-08-12 20:10 ` Tim Chen 2013-06-28 9:20 ` Ingo Molnar 2013-06-28 9:20 ` Ingo Molnar [not found] <1371165333.27102.568.camel@schen9-DESK> [not found] ` <1371167015.1754.14.camel@buesod1.americas.hpqcorp.net> 2013-06-14 16:09 ` Tim Chen 2013-06-14 16:09 ` Tim Chen 2013-06-14 22:31 ` Davidlohr Bueso 2013-06-14 22:31 ` Davidlohr Bueso 2013-06-14 22:44 ` Tim Chen 2013-06-14 22:44 ` Tim Chen 2013-06-14 22:47 ` Michel Lespinasse 2013-06-14 22:47 ` Michel Lespinasse 2013-06-17 22:27 ` Tim Chen 2013-06-17 22:27 ` Tim Chen 2013-06-16 9:50 ` Alex Shi 2013-06-16 9:50 ` Alex Shi 2013-06-17 16:22 ` Davidlohr Bueso 2013-06-17 16:22 ` Davidlohr Bueso 2013-06-17 18:45 ` Tim Chen 2013-06-17 18:45 ` Tim Chen 2013-06-17 19:05 ` Davidlohr Bueso 2013-06-17 19:05 ` Davidlohr Bueso 2013-06-17 22:28 ` Tim Chen 2013-06-17 22:28 ` Tim Chen 2013-06-17 23:18 ` Alex Shi 2013-06-17 23:18 ` Alex Shi 2013-06-17 23:20 ` Alex Shi 2013-06-17 23:20 ` Alex Shi 2013-06-17 23:35 ` Davidlohr Bueso 2013-06-17 23:35 ` Davidlohr Bueso 2013-06-18 0:08 ` Tim Chen 2013-06-18 0:08 ` Tim Chen 2013-06-19 23:11 ` Davidlohr Bueso 2013-06-19 23:11 ` Davidlohr Bueso 2013-06-19 23:24 ` Tim Chen 2013-06-19 23:24 ` Tim Chen
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=20130723094513.GA24522@gmail.com \ --to=mingo@kernel.org \ --cc=a.p.zijlstra@chello.nl \ --cc=aarcange@redhat.com \ --cc=akpm@linux-foundation.org \ --cc=alex.shi@intel.com \ --cc=andi@firstfloor.org \ --cc=dave.hansen@intel.com \ --cc=davidlohr.bueso@hp.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=matthew.r.wilcox@intel.com \ --cc=mgorman@suse.de \ --cc=mingo@elte.hu \ --cc=riel@redhat.com \ --cc=tim.c.chen@linux.intel.com \ --cc=walken@google.com \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.