Well i'm bringing this email back from the dead, original thread can be
found here https://lists.debian.org/debian-sparc/2013/01/msg00008.html
In a nutshell the qlogicpti driver isn't handling traffic demands very
well, the request queue will overflow and the system will panic. Just
letting a box idle for a few days will result in this issue popping up.
You can accelerate it by doing a large amount of disk I/O.
In particular, we are hitting this code in qlogicpti.c
toss_command:
printk(KERN_EMERG "qlogicpti%d: request queue overflow\n",
qpti->qpti_id);
/* Unfortunately, unless you use the new EH code, which
* we don't, the midlayer will ignore the return value,
* which is insane. We pick up the pieces like this.
*/
Cmnd->result = DID_BUS_BUSY;
done(Cmnd);
return 1;
}
Does anyone have any input on this? Fixing this would help stabilize a
ton of early sparc64 machines, almost everything with a scsi controller
around the US2 days use and isp1000 card.
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
