Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On 2005-11-25T14:29:13, Philipp Reisner <philipp.reisner at linbit.com> wrote:
Thanks for the forward...
> you are right. It looks like CONFIG_4KSTACKS has gone away. I think this was
> introduced in 2.6.12 or 2.6.13 but the SUSE guys have backported a lot of
> current kernel "things".
Yes, but certainly not the 4KSTACKS limitation; the stack in SLES9 is at
least 8kb (or two pages). Did you compile the kernel yourself?
> After several tests I think my problem was caused by the SUSE-default
> IO-sheduler (cfq). Switching to the vanilla default (as) fixed the problem.
This is rather unlikely; we've never observed anything like this. To the
higher levels, the schedulers look identical except for slightly
different performance characteristics.
> But I think it has something to do with my hardware-setup because we never
> had this problem before!
This is more likely.
Sincerely,
Lars Marowsky-Brée <lmb at suse.de>
--
High Availability & Clustering
SUSE Labs, Research and Development
SUSE LINUX Products GmbH - A Novell Business -- Charles Darwin
"Ignorance more frequently begets confidence than does knowledge"