From: Daniel Wagner <daniel.wagner@bmw-carit.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: <oleg@redhat.com>, <paulmck@linux.vnet.ibm.com>, <tj@kernel.org>,
<mingo@redhat.com>, <linux-kernel@vger.kernel.org>,
<der.herr@hofr.at>, <dave@stgolabs.net>, <riel@redhat.com>,
<viro@ZenIV.linux.org.uk>, <torvalds@linux-foundation.org>,
<jlayton@poochiereds.net>
Subject: Re: [RFC][PATCH 00/13] percpu rwsem -v2
Date: Tue, 23 Jun 2015 16:56:39 +0200 [thread overview]
Message-ID: <558973A7.6010407@bmw-carit.de> (raw)
In-Reply-To: <20150623143411.GA25159@twins.programming.kicks-ass.net>
On 06/23/2015 04:34 PM, Peter Zijlstra wrote:
> On Tue, Jun 23, 2015 at 11:35:24AM +0200, Daniel Wagner wrote:
>> flock01
>> mean variance sigma max min
>> 4.1.0 11.7075 816.3341 28.5716 125.6552 0.0021
>> 4.1.0+percpu-rwsem 11.4614 760.1345 27.5705 132.5030 0.0026
>> tip 6.8390 329.3037 18.1467 81.0373 0.0021
>> tip+percpu-rwsem 10.0870 546.7435 23.3825 106.2396 0.0026
>
>> posix01
>> mean variance sigma max min
>> 4.1.0 121.9020 27882.5260 166.9806 603.5509 0.0063
>> 4.1.0+percpu-rwsem 185.3981 38474.3836 196.1489 580.6532 0.0073
>> tip 129.2736 23752.7122 154.1191 474.0604 0.0063
>> tip+percpu-rwsem 142.6474 24732.1571 157.2646 468.7478 0.0072
>
> Both these tests are incredibly unstable for me (as well as for you it
> appears). Variance is through the roof on them.
Since on my test machine not all 4 socket have inter connection, I pinned the
tests down to one socket to see if that reduces the variance.
Expect flock01 and posix01 show now really low variances (3 runs):
[...]
flock02
mean variance sigma max min
tip-1 11.8994 0.5874 0.7664 13.2022 8.6324
tip-2 11.7394 0.5252 0.7247 13.2540 9.7513
tip-3 11.8155 0.5288 0.7272 13.2700 9.9480
tip+percpu-rswem-1 15.3601 0.8981 0.9477 16.8116 12.6910
tip+percpu-rswem-2 15.2558 0.8442 0.9188 17.0199 12.9586
tip+percpu-rswem-3 15.5297 0.6386 0.7991 17.4392 12.7992
lease01
mean variance sigma max min
tip-1 0.3424 0.0001 0.0110 0.3644 0.3088
tip-2 0.3627 0.0003 0.0185 0.4140 0.3312
tip-3 0.3446 0.0002 0.0125 0.3851 0.3155
tip+percpu-rswem-1 0.3464 0.0001 0.0116 0.3781 0.3113
tip+percpu-rswem-2 0.3597 0.0003 0.0162 0.3978 0.3250
tip+percpu-rswem-3 0.3513 0.0002 0.0151 0.3933 0.3122
[...]
So with this setup we can start to compare the numbers.
> I get runtimes like:
>
> root@ivb-ex:/usr/local/src/lockperf# ./flock01 -n 240 -l 32 /tmp/a
> 0.266157011
> root@ivb-ex:/usr/local/src/lockperf# ./flock01 -n 240 -l 32 /tmp/a
> 139.303399960
Same here:
flock01
mean variance sigma max min
tip-1 242.6147 3632.6201 60.2712 313.3081 86.3743
tip-2 233.1934 3850.1995 62.0500 318.2716 101.2738
tip-3 223.0392 3944.5220 62.8054 318.1932 110.8155
tip+percpu-rswem-1 276.5913 2145.0510 46.3147 317.5385 156.1318
tip+percpu-rswem-2 270.7089 2735.7635 52.3045 318.9418 154.5902
tip+percpu-rswem-3 267.8207 3028.3557 55.0305 320.2987 150.9659
posix01
mean variance sigma max min
tip-1 18.8729 151.2810 12.2996 37.3563 0.0060
tip-2 17.6894 140.9982 11.8743 37.2080 0.0060
tip-3 18.7785 145.1217 12.0466 35.5001 0.0060
tip+percpu-rswem-1 18.9970 163.8856 12.8018 35.8795 0.0069
tip+percpu-rswem-2 18.9594 147.3197 12.1375 35.4404 0.0069
tip+percpu-rswem-3 18.8366 126.5831 11.2509 35.9014 0.0069
next prev parent reply other threads:[~2015-06-23 14:56 UTC|newest]
Thread overview: 106+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-22 12:16 Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 01/13] rcu: Create rcu_sync infrastructure Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 02/13] rcusync: Introduce struct rcu_sync_ops Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 03/13] rcusync: Add the CONFIG_PROVE_RCU checks Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 04/13] rcusync: Introduce rcu_sync_dtor() Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 05/13] percpu-rwsem: Optimize readers and reduce global impact Peter Zijlstra
2015-06-22 23:02 ` Oleg Nesterov
2015-06-23 7:28 ` Nicholas Mc Guire
2015-06-25 19:08 ` Peter Zijlstra
2015-06-25 19:17 ` Tejun Heo
2015-06-29 9:32 ` Peter Zijlstra
2015-06-29 15:12 ` Tejun Heo
2015-06-29 15:14 ` Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 06/13] percpu-rwsem: Provide percpu_down_read_trylock() Peter Zijlstra
2015-06-22 23:08 ` Oleg Nesterov
2015-06-22 12:16 ` [RFC][PATCH 07/13] sched: Reorder task_struct Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 08/13] percpu-rwsem: DEFINE_STATIC_PERCPU_RWSEM Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 09/13] hotplug: Replace hotplug lock with percpu-rwsem Peter Zijlstra
2015-06-22 22:57 ` Oleg Nesterov
2015-06-23 7:16 ` Peter Zijlstra
2015-06-23 17:01 ` Oleg Nesterov
2015-06-23 17:53 ` Peter Zijlstra
2015-06-24 13:50 ` Oleg Nesterov
2015-06-24 14:13 ` Peter Zijlstra
2015-06-24 15:12 ` Oleg Nesterov
2015-06-24 16:15 ` Peter Zijlstra
2015-06-28 23:56 ` [PATCH 0/3] percpu-rwsem: introduce percpu_rw_semaphore->recursive mode Oleg Nesterov
2015-06-28 23:56 ` [PATCH 1/3] rcusync: introduce rcu_sync_struct->exclusive mode Oleg Nesterov
2015-06-28 23:56 ` [PATCH 2/3] percpu-rwsem: don't use percpu_rw_semaphore->rw_sem to exclude writers Oleg Nesterov
2015-06-28 23:56 ` [PATCH 3/3] percpu-rwsem: introduce percpu_rw_semaphore->recursive mode Oleg Nesterov
2015-06-22 12:16 ` [RFC][PATCH 10/13] fs/locks: Replace lg_global with a percpu-rwsem Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 11/13] fs/locks: Replace lg_local with a per-cpu spinlock Peter Zijlstra
2015-06-23 0:19 ` Oleg Nesterov
2015-06-22 12:16 ` [RFC][PATCH 12/13] stop_machine: Remove lglock Peter Zijlstra
2015-06-22 22:21 ` Oleg Nesterov
2015-06-23 10:09 ` Peter Zijlstra
2015-06-23 10:55 ` Peter Zijlstra
2015-06-23 11:20 ` Peter Zijlstra
2015-06-23 13:08 ` Peter Zijlstra
2015-06-23 16:36 ` Oleg Nesterov
2015-06-23 17:30 ` Paul E. McKenney
2015-06-23 18:04 ` Peter Zijlstra
2015-06-23 18:26 ` Paul E. McKenney
2015-06-23 19:05 ` Paul E. McKenney
2015-06-24 2:23 ` Paul E. McKenney
2015-06-24 8:32 ` Peter Zijlstra
2015-06-24 9:31 ` Peter Zijlstra
2015-06-24 13:48 ` Paul E. McKenney
2015-06-24 15:01 ` Paul E. McKenney
2015-06-24 15:34 ` Peter Zijlstra
2015-06-24 7:35 ` Peter Zijlstra
2015-06-24 8:42 ` Ingo Molnar
2015-06-24 13:39 ` Paul E. McKenney
2015-06-24 13:43 ` Ingo Molnar
2015-06-24 14:03 ` Paul E. McKenney
2015-06-24 14:50 ` Paul E. McKenney
2015-06-24 15:01 ` Peter Zijlstra
2015-06-24 15:27 ` Paul E. McKenney
2015-06-24 15:40 ` Peter Zijlstra
2015-06-24 16:09 ` Paul E. McKenney
2015-06-24 16:42 ` Peter Zijlstra
2015-06-24 17:10 ` Paul E. McKenney
2015-06-24 17:20 ` Paul E. McKenney
2015-06-24 17:29 ` Peter Zijlstra
2015-06-24 17:28 ` Peter Zijlstra
2015-06-24 17:32 ` Peter Zijlstra
2015-06-24 18:14 ` Peter Zijlstra
2015-06-24 17:58 ` Peter Zijlstra
2015-06-25 3:23 ` Paul E. McKenney
2015-06-25 11:07 ` Peter Zijlstra
2015-06-25 13:47 ` Paul E. McKenney
2015-06-25 14:20 ` Peter Zijlstra
2015-06-25 14:51 ` Paul E. McKenney
2015-06-26 12:32 ` Peter Zijlstra
2015-06-26 16:14 ` Paul E. McKenney
2015-06-29 7:56 ` Peter Zijlstra
2015-06-30 21:32 ` Paul E. McKenney
2015-07-01 11:56 ` Peter Zijlstra
2015-07-01 15:56 ` Paul E. McKenney
2015-07-01 16:16 ` Peter Zijlstra
2015-07-01 18:45 ` Paul E. McKenney
2015-06-23 14:39 ` Paul E. McKenney
2015-06-23 16:20 ` Oleg Nesterov
2015-06-23 17:24 ` Oleg Nesterov
2015-06-25 19:18 ` Peter Zijlstra
2015-06-22 12:16 ` [RFC][PATCH 13/13] locking: " Peter Zijlstra
2015-06-22 12:36 ` [RFC][PATCH 00/13] percpu rwsem -v2 Peter Zijlstra
2015-06-22 18:11 ` Daniel Wagner
2015-06-22 19:05 ` Peter Zijlstra
2015-06-23 9:35 ` Daniel Wagner
2015-06-23 10:00 ` Ingo Molnar
2015-06-23 14:34 ` Peter Zijlstra
2015-06-23 14:56 ` Daniel Wagner [this message]
2015-06-23 17:50 ` Peter Zijlstra
2015-06-23 19:36 ` Peter Zijlstra
2015-06-24 8:46 ` Ingo Molnar
2015-06-24 9:01 ` Peter Zijlstra
2015-06-24 9:18 ` Daniel Wagner
2015-07-01 5:57 ` Daniel Wagner
2015-07-01 21:54 ` Linus Torvalds
2015-07-02 9:41 ` Peter Zijlstra
2015-07-20 5:53 ` Daniel Wagner
2015-07-20 18:44 ` Linus Torvalds
2015-06-22 20:06 ` Linus Torvalds
2015-06-23 16:10 ` Davidlohr Bueso
2015-06-23 16:21 ` 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=558973A7.6010407@bmw-carit.de \
--to=daniel.wagner@bmw-carit.de \
--cc=dave@stgolabs.net \
--cc=der.herr@hofr.at \
--cc=jlayton@poochiereds.net \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=tj@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=viro@ZenIV.linux.org.uk \
/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
Powered by JetHome