lkml.org 
[lkml]   [2010]   [Sep]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: 2.6.35.*: horrible (exponential? >linear) slowdown to unusability (ACPI idle?)
> > I think this is related to what has been discussed in this thread:
> > http://lkml.org/lkml/2010/7/14/11

* Nix <nix@esperi.org.uk> [2010-09-06 21:27]:
> Quite possibly :/ though I'm on x86-64, not x86, and certainly don't
> have kmemleak turne don.

Yes, at first we were talking about x86 and kmemleak but leter on, the
problem seemed more related to x86-64 and the config_no_bootmem option.

> > So if you can reproduce it quite easily, I guess bisection (even
> > painful) will be the best way to get (hopefuly) an idea of where the
> > problem might come from...

> 'Quite easily' is not quite true. It does not show up in qemu -kernel.
> It does not show up if you boot straight to an emergency boot shell
> in the initramfs (I was trying to avoid activating the RAID arrays).

> So I guess it's a full-blown boot each time, which is made pointlessly
> difficult by the fact that the rpc.mountd on my NFS server is acting up,
> giving me -ESTALE half the time for an initial mount (??!!!) and thus
> totally buggering up my client system whenever I reboot. So I may have
> to debug *that* first. What fun.

Yes, but you seem to get it at each boot and immediately, which was
never my case (don't know about Zeno). With 2.6.35.3 I got it only once
in several days of uptimes and boots.

I hope your specific situation will help isolate the problem...

--
Damien Wyart


\
 
 \ /
  Last update: 2010-09-07 07:39    [W:0.098 / U:0.316 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site