From owner-cvs-all Mon Mar 5 7:56:34 2001 Delivered-To: cvs-all@freebsd.org Received: from salmon.maths.tcd.ie (salmon.maths.tcd.ie [134.226.81.11]) by hub.freebsd.org (Postfix) with SMTP id 5005637B71A; Mon, 5 Mar 2001 07:56:22 -0800 (PST) (envelope-from dwmalone@maths.tcd.ie) Received: from walton.maths.tcd.ie by salmon.maths.tcd.ie with SMTP id ; 5 Mar 2001 15:56:21 +0000 (GMT) Date: Mon, 5 Mar 2001 15:56:21 +0000 From: David Malone To: John Baldwin Cc: Dag-Erling Smorgrav , cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/i386/isa apic_vector.s icu_vector.s Message-ID: <20010305155621.A97107@walton.maths.tcd.ie> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5i In-Reply-To: ; from jhb@FreeBSD.org on Mon, Mar 05, 2001 at 07:48:43AM -0800 Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Mon, Mar 05, 2001 at 07:48:43AM -0800, John Baldwin wrote: > On 05-Mar-01 Dag-Erling Smorgrav wrote: > > John Baldwin writes: > >> This fixed some hard hangs that David was seeing on his machine under heavy > >> load. > > > > I've been seeing solid hangs too with recent kernels (always under > > heavy I/O load). They seemed to go away when I regressed to a > > 2001-02-23 kernel. Haven't tried this patch yet. > > Heavy load could generate enough interrupts to overflow the stack and trash th > pcb, so this very well might fix that. I think I may have been seeing this. I have a machine which keeps dieing during heavy IO and when I try to get a back trace I found the stack is so messed up that machine just page faults again. It actually seems pretty easy to reproduce at home - I haven't been able to buildworld for a few weeks. David. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message