I have been having a problem on one of my machines, and it seems
to be associated with medium/heavy IO loads.
After some period of time, usually an hour or two, the system will
appear to stop cold dead. A trace with DDB shows that the last
function is doreti. Above that is the DDB call stuff.
Once, the trace was simply doreti, other times it had the stack
of the ata and network drivers. Here are some values from one
that might be useful:
cpl = 6714ba (3, 7, 9, 10, 12, 14, 15 active, right?)
ipending = 401420 (nothing pending, right?)
astpending = 3
in_vm86call = 0
intr_nesting_level = 2
It "feels" like an endless loop in an interrupt handler, but I am not
sure where to start looking. One trace showed that my ATM driver was
interrupted while writing to a device register, but that was protected
by splimp, which should protect it from the driver interrupt, no?
Would it be worthwhile to connect a scope to the PCI interrupt lines
to see if anything is wedged?
Thanks,
-Richard
-------------------------------------------
Richard Hodges | Matriplex, inc.
Product Manager | 769 Basque Way
[EMAIL PROTECTED] | Carson City, NV 89706
775-886-6477 | www.matriplex.com
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
