Re: PLEASE TEST: IPI deadlock avoidance patch
From: Lukas Ertl (le_at_FreeBSD.org)
Date: 08/24/04
- Previous message: Robert Watson: "Running the network stack without Giant -- change in default coming"
- In reply to: Robert Watson: "Re: PLEASE TEST: IPI deadlock avoidance patch"
- Next in thread: Jon Noack: "Re: PLEASE TEST: IPI deadlock avoidance patch"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Tue, 24 Aug 2004 16:36:28 +0200 (CEST) To: Robert Watson <rwatson@FreeBSD.org>
On Tue, 24 Aug 2004, Robert Watson wrote:
>
> On Tue, 24 Aug 2004, Lukas Ertl wrote:
>>
>> OK, it seems I shouted out too early. '-jX' buildworlds go fine, but my
>> news server (heavy disk and network traffic) still locks up within one
>> day of uptime. It's a Dual Xeon with HTT, SCHED_4BSD, ADAPTIVE_GIANT,
>> and no WITNESS or INVARIANTS.
>
> Using a serial break, are you able to get into the debugger on hang? If
> not, have you tried SW_WATCHDOG or MP_WATCHDOG?
Nope, NMI doesn't work. But I'll add MP_WATCHDOG and let the box run for
a while.
cheers,
le
-- Lukas Ertl http://homepage.univie.ac.at/l.ertl/ le@FreeBSD.org http://people.freebsd.org/~le/ _______________________________________________ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org"
- Previous message: Robert Watson: "Running the network stack without Giant -- change in default coming"
- In reply to: Robert Watson: "Re: PLEASE TEST: IPI deadlock avoidance patch"
- Next in thread: Jon Noack: "Re: PLEASE TEST: IPI deadlock avoidance patch"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Relevant Pages
|