Hi,
I am running a stock 2.2.16 kernel + Software RAID patch on an ASUS P2B-D2
SMP motherboard with dual PIII 550 CPU's and 512 MB RAM. The MB has a
built-in Adaptec AIC-7890 Ultra2, with three 18 GB IBM drives attached,
part of it is configured in one sofware-raid5 slice, the rest is ordinary
diskspace.
There is a bios option that says 'MPS 1.4 Support', enable or disable. If I
enable it, the machine does hard lockups after about 10-15 minutes in
Linux. Unplug one of the CPU's - stable as a rock. Disable the MPS
'feature' in the BIOS, and the machine seems to be stable with both CPU's
plugged in. Looking at older posts regarding MPS and USB, this seems to be
a typical case of a broken BIOS, right?
I have the latest official version installed (bios revision 1011.A), so
I'll just have to run the beast in MPS 1.1 mode. Is this a performance hit?
But, running in MPS 1.1 mode, I did get an 'unexpected IRQ vector 208 on
CPU#0', after 'gzip -d'-ing a 270 MB file that expanded to a 1GB file. This
message seemed to occur at the moment the gzip was finished and deleted the
.gz file. I was not doing this on the software-raid partition.
Looking through dmesg, I found the same message for CPU#1, just once. I
don't know what caused that - it must have been last night. The machine has
been up for almost a day and a half, happily numbercrunching, so it seems
to be stable.
Apart from cluttering up the console, this doesn't seem to do much harm,
though, the machine is still humming along happily - but I thought I'd just
let you know.
I found one occurence of this 'unexpected IRQ vector' thing in the archives
of this list, but that was an unanswered post of more than a year ago
concerning 2.2.5 on SMP.
Bye for now,
Ward Vandewege.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Jun 15 2000 - 21:00:31 EST