Messages in this thread |  | | | Date | Mon, 6 Oct 2008 08:59:25 +0200 (CEST) | | From | Thomas Gleixner <> | | Subject | Re: aim7 47% regression with 2.6.27-rc8 | |
On Mon, 6 Oct 2008, Zhang, Yanmin wrote:
> Comparing with 2.6.27-rc8, aim7 result has about 47% regression with 2.6.27-rc8 on
> my 16-core tigerton and 8 core+HyperThreading x86_64 machine.
>
> I bisected it down to patch:
>
> 302745699c1b675b5d2a1af87271de10e4d96b6a is first bad commit
> commit 302745699c1b675b5d2a1af87271de10e4d96b6a
> Author: Thomas Gleixner <tglx@linutronix.de>
> Date: Mon Sep 22 19:02:25 2008 +0200
>
> clockevents: check broadcast device not tick device
>
> Impact: Possible hang on CPU online observed on AMD C1E machines.
>
> The broadcast setup code looks at the mode of the tick device to
> determine whether it needs to be shut down or setup. This is wrong
> when the broadcast mode is set to one shot already. This can happen
> when a CPU is brought online as it goes through the periodic setup
> first.
>
> The problem went unnoticed as sane systems do not call into that code
> before the switch to one shot for the clock event device happens.
> The AMD C1E idle routine switches over immediately and thereby shuts
> down the just setup device before the first interrupt happens.
>
>
> After I reverted the patch against 2.6.27-rc8, the regression disappears.
> It's interesting that the regression doesn't exist on 8-core stoakley.
There is a fixup patch for this one after rc8. 07454bfff151d2465ada809bbaddf3548cc1097c
Can you check with this one applied please ?
Thanks,
tglx
|  |