Re: Re: 2.6 Kernel Userspace Daemon 0.1-0602131225 (Hopefully attached)

Hi Matt,

On 23:20 Sat 25 Feb     , Matt Rechenburg wrote:
> Sadly migrating processes back home caused a kernel panic on the remote node.
> Could this be fixed already by the patch from Ansgar ?

I've tried to reproduce this but couldn't provoke a kernel panic. The
best (or better: worst) I can do with the current kernel patch is to
provoke a segfault at migration home. This does only (and repeatable)
occur when the process is currently performing some system call when
migration back home is triggered.

When running processes that do few system calls and are in general CPU
bound, migration works perfectly alright for me (with the current git
version, no matter if using 2.6.15, 2.6.14, 2.6.13 or 2.6.12) and
AFAICS no segfaults or similar happen at all.

How is it in your case? Could you give some more infos on the
processes you're migrating? Have you tried very simple, single minded
test programs?

Regards
-Andreas


-------------------------------------------------------
This SF.Net email is sponsored by xPML, a groundbreaking scripting language
that extends applications into web and mobile media. Attend the live webcast
and join the prime developer group breaking into this new coding territory!
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=110944&bid=241720&dat=121642