Home » Mailing list archives » linux-kernel » 2007 » September » 18

Re: Scheduler benchmarks - a follow-up

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
[view in full thread]
From: Rob Hussey <robjhussey@...>
To: Ingo Molnar <mingo@...>
Cc: <linux-kernel@...>, <ck@...>
Subject: Re: Scheduler benchmarks - a follow-up
Date: Tuesday, September 18, 2007 - 12:30 am

On 9/17/07, Ingo Molnar <mingo@elte.hu> wrote:

I reverted the patch from before since it didn't seem to help. Do you
think it may have to do with my system having Hyper-Threading enabled?
I should have pointed out before that I don't really have a dual-core
system, just a P4 with Hyper-Threading (I loosely used core to refer
to processor).

Some new numbers for 2.6.23-rc6-cfs-devel (!CONFIG_PREEMPT and bound
to single processor)

lat_ctx:

15  2.73
16  2.74
17  2.81
18  2.74
19  2.74
20  2.73
21  2.60
22  2.74
23  2.72
24  2.74
25  2.74

hackbench:

80 11.578
81 11.991
82 11.914
83 12.026
84 12.226
85 12.347
86 12.552
87 12.655
88 13.011
89 12.941
90 13.237

pipe-test:

1  9.58
2  9.58
3  9.58
4  9.58
5  9.58
6  9.58
7  9.58
8  9.58
9  9.58
10 9.58

The obligatory graphs:
http://www.healthcarelinen.com/misc/benchmarks/BOUND_NOPREEMPT_lat_ctx_benchmark.png
http://www.healthcarelinen.com/misc/benchmarks/BOUND_NOPREEMPT_hackbench_benchmark.png
http://www.healthcarelinen.com/misc/benchmarks/BOUND_NOPREEMPT_pipe-test_benchmark.png

A cursory glance suggests that performance wrt lat_ctx and hackbench
has increased (lower numbers), but degraded quite a lot for pipe-test.
The numbers for  pipe-test are extremely stable though, while the
numbers for hackbench are more erratic (which isn't saying much since
the original numbers gave nearly a straight line). I'm still willing
to try out any more ideas.

Regards,
Rob
-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
Messages in current thread:
Scheduler benchmarks - a follow-up, Rob Hussey, (Mon Sep 17, 5:21 am)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Mon Sep 17, 9:05 am)
Re: Scheduler benchmarks - a follow-up, Rob Hussey, (Mon Sep 17, 9:44 pm)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Mon Sep 17, 4:36 pm)
Re: Scheduler benchmarks - a follow-up, Rob Hussey, (Tue Sep 18, 12:30 am)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Tue Sep 18, 4:48 am)
Re: Scheduler benchmarks - a follow-up, Rob Hussey, (Tue Sep 18, 5:45 am)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Tue Sep 18, 5:48 am)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Tue Sep 18, 2:40 am)
Re: Scheduler benchmarks - a follow-up, Rob Hussey, (Tue Sep 18, 4:23 am)
Re: Scheduler benchmarks - a follow-up, Willy Tarreau, (Tue Sep 18, 12:53 am)
Re: Scheduler benchmarks - a follow-up, Rob Hussey, (Tue Sep 18, 12:58 am)
Re: [ck] Re: Scheduler benchmarks - a follow-up, Jos Poortvliet, (Mon Sep 17, 10:01 am)
Re: [ck] Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Mon Sep 17, 10:12 am)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Mon Sep 17, 7:27 am)
Re: Scheduler benchmarks - a follow-up, Ed Tomlinson, (Mon Sep 17, 7:12 am)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Mon Sep 17, 4:22 pm)
Re: Scheduler benchmarks - a follow-up, Ingo Molnar, (Mon Sep 17, 7:47 am)