lkml.org 
[lkml]   [2004]   [Aug]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [patch] voluntary-preempt-2.6.8.1-P0
From
Date
On Sun, 2004-08-15 at 13:56 +0200, Ingo Molnar wrote:
> i've uploaded the -P0 patch:
>
> http://redhat.com/~mingo/voluntary-preempt/voluntary-preempt-2.6.8.1-P0
>
> those who had APIC (and USB, under SMP) problems under previous
> versions, are the problems still present in -P0?
>
> Changes:
>
> - make redirected softirqs and hardirqs preemptible by default. I
> reviewed a number of softirq users and it appears to be safe.
> Process-level enable/disable_bh still disables preemption, but the
> handlers themselves run in a preemptible way. This preemptability
> should fix e.g. the IDE latencies. It could also fix some of the
> /dev/random related latencies.
>
> - fixed a bug in hardirq redirection - we didnt re-disable interrupts
>
> - updated the IO-APIC changes - hopefully it's more robust now
>
> Ingo

Hi Ingo,

It still locks up hard for me when voluntary-preempt=3, however it does
finish the boot; dmesg attached. The lockup occurs several minutes into
use; usually by by the time I've started X, launched evolution and
selected my first imap folder the machine's dead.

If you need more information or want me to try some patches, just let me
know.

BTW, do you intent on keeping the preempt-smp patch alive?

--
Peter Zijlstra <a.p.zijlstra@chello.nl>
[unhandled content-type:application/x-gzip]
\
 
 \ /
  Last update: 2005-03-22 14:05    [W:0.926 / U:0.056 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site