[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <4850BFE1.7080603@freemail.hu>
Date: Thu, 12 Jun 2008 08:19:13 +0200
From: Németh Márton <nm127@...email.hu>
To: Ingo Molnar <mingo@...e.hu>
CC: Thomas Gleixner <tglx@...utronix.de>,
LKML <linux-kernel@...r.kernel.org>
Subject: Re: [regression][bisected] ~90,000 wakeups as of 2.6.26-rc3
Ingo Molnar wrote:
> * Németh Márton <nm127@...email.hu> wrote:
>
>> Hi,
>>
>> there is a problem in 2.6.26-rc3 which was not there in case of
>> 2.6.25: the CPU wakes up ~90,000 times per sec instead of ~60 per sec.
>>
>> I also "git bisected" the problem, the result is:
>>
>> 6e908947b4995bc0e551a8257c586d5c3e428201 is first bad commit
>> commit 6e908947b4995bc0e551a8257c586d5c3e428201
>> Author: Ingo Molnar <mingo@...e.hu>
>> Date: Fri Mar 21 14:32:36 2008 +0100
>>
>> x86: fix ioapic bug again
>
> thanks for tracking this down. Could you check whether the problem is
> also fixed in latest -tip? In particular the tip/x86/apic branch should
> properly solve this. You can pick up -tip via:
>
> http://people.redhat.com/mingo/tip.git/README
>
> but those tip/x86/apic fixes are too intrusive for v2.6.26, so i've
> queued up your revert into tip/x86/urgent, for v2.6.26 merging. Would be
> nice if you could check -tip though, to make sure we dont reintroduce
> the same problem again in v2.6.27.
I tested 2.6.26-rc5-00996-gb7d80d3 with the attached .config. I get ~50
wakeups per second which I guess is caused by the lack of hardware. I
also attached the full dmesg. Passed.
Márton Németh
View attachment ".config" of type "text/plain" (30248 bytes)
View attachment "dmesg-2.6.26-rc5-00996-gb7d80d3.txt" of type "text/plain" (32413 bytes)
Powered by blists - more mailing lists