On Mon, 2005-06-27 at 17:16 +0000, Ferris McCormick wrote: > On Mon, 2005-06-27 at 00:33 -0400, David S. Miller wrote: > > [ CC:'ing Josh Grebe, he could reproduce these SMP hangs on > > his box quite reliably ] > > > > I'm not squash, but I have an update. System=U60(2x450), 2 disks > installed. > > Kernel=2.6.12_rc6 > > Patch installs without any issues; however, system up time was about > 4 hours; died under heavy disk activity (trying to do reverse dependency > check for package rebuilds). The failure looked like it always looks: > everything stops, system responds only to the reset switch. >
OK, here's a better update. Kernel is from gentoo-sources, sync'ed to
2.6.12.1. Patch installs without incident. And, status:
U2(2x400) --- comes up fine, not running long enough for status.
However 2.6.12 generally has done pretty well on this system.
U60(2x450) --- Does much better than other 2.6.xx kernels have, but
squash's crashme.sh script does crash it. (Hard failure on pass 3;
system was NOT otherwise idle, and before the crash I had done a
'umount -a -t nfs' to unmount one file system completely independent of
the crashme playgrounds.) For this test, crashme is 'cp -R'-ing from a
file system on /dev/sdb4 --> /dev/sda6.
SB1000(2x900) --- With patch, under heavy load up time is measured in
minutes (as under 10 minutes) consistently. Same kernel, but without
patch, system seems stable.
Hope this helps, although it's not what anyone wanted to hear. We're
all awaiting squash's netra results for the *real truth*.
{For those who don't know: crashme is a do-forever shell script which:
cp -R <directory-with-lots-of-files> <someplace>; tar cf someplace.tar
someplace; rm -rf someplace; tar xf someplace.tar; rm -rf someplace
someplace.tar}
Regards,
Ferris
--
Ferris McCormick (P44646, MI) <[EMAIL PROTECTED]>
Developer, Gentoo Linux (Sparc, Devrel)
signature.asc
Description: This is a digitally signed message part
