Re: Native preemption is the culprit [was Re: today's CURRENT lockups]
From: Thorsten Greiner (thorsten_at_tgreiner.net)
Date: 07/06/04
- Previous message: David Malone: "Re: recent libalias changes"
- In reply to: Robert Watson: "Re: Native preemption is the culprit [was Re: today's CURRENT lockups]"
- Next in thread: Michael L. Hostbaek: "Re: Native preemption is the culprit [was Re: today's CURRENT lockups]"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Tue, 6 Jul 2004 13:19:26 +0200 To: Robert Watson <rwatson@freebsd.org>
* Robert Watson <rwatson@freebsd.org> [2004-07-06 08:21]:
> The patch below appears to (brute force) eliminate the crash/hang I'm
> experiencing with SCHED_ULE in the post-preemption universe. However, I
> was experiencing it only in the SMP case, not UP, so it could be I'm just
> not triggering it timing-wise. This would be a temporary fix until jhb is
> online again post-USENIX to take a look, assuming this works around the
> problem for people other than me.
It does work here (as did backing out the native preemption stuff).
> Note that this is probably damaging to interrupt processing latency.
I have not observed anything unusual with this patch. There are
seemingly no increases of build times for my projects and I did not
experience any interactivity glitches (no jumpy mouse or the like).
Regards
-Thorsten
-- Those who in quarrels interpose, must often wipe a bloody nose. This message is digitally signed. To verify its integrity, download a copy of GnuPG for your operating system from http://www.gnupg.org .
- application/pgp-signature attachment: stored
- Previous message: David Malone: "Re: recent libalias changes"
- In reply to: Robert Watson: "Re: Native preemption is the culprit [was Re: today's CURRENT lockups]"
- Next in thread: Michael L. Hostbaek: "Re: Native preemption is the culprit [was Re: today's CURRENT lockups]"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Relevant Pages
|