From owner-freebsd-stable Wed Jul 3 12: 5: 2 2002 Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 28EEC37B401 for ; Wed, 3 Jul 2002 12:04:57 -0700 (PDT) Received: from tinker.exit.com (tinker.exit.com [206.223.0.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5607443E42 for ; Wed, 3 Jul 2002 12:04:56 -0700 (PDT) (envelope-from frank@exit.com) Received: from realtime.exit.com (realtime [206.223.0.5]) by tinker.exit.com (8.12.3/8.12.3) with ESMTP id g63J4q48046210; Wed, 3 Jul 2002 12:04:52 -0700 (PDT) (envelope-from frank@exit.com) Received: from realtime.exit.com (localhost [127.0.0.1]) by realtime.exit.com (8.12.3/8.12.2) with ESMTP id g63J4qDb073914; Wed, 3 Jul 2002 12:04:52 -0700 (PDT) (envelope-from frank@realtime.exit.com) Received: (from frank@localhost) by realtime.exit.com (8.12.3/8.12.3/Submit) id g63J4qqB073913; Wed, 3 Jul 2002 12:04:52 -0700 (PDT) From: Frank Mayhar Message-Id: <200207031904.g63J4qqB073913@realtime.exit.com> Subject: Re: Status of fxp / smp problem? In-Reply-To: <035a01c222c3$f35fe3b0$fd01a8c0@getlost> To: Shadow Date: Wed, 3 Jul 2002 12:04:52 -0700 (PDT) Cc: frank@exit.com, stable@FreeBSD.ORG Reply-To: frank@exit.com X-Copyright0: Copyright 2002 Frank Mayhar. All Rights Reserved. X-Copyright1: Permission granted for electronic reproduction as Usenet News or email only. X-Mailer: ELM [version 2.4ME+ PL99 (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG Shadow wrote: > Frank Mayhar wrote: > > I have been one of the people suffering from the "intermittent-hang" > > problem, with occasional hard freezes requiring a reset. Well, it > > appears that the problem has disappeared. With a June 17 kernel > > (although the installed /kernel says June 23, so it's _somewhere_ in > > there) the problems, intermittent hangs and hard freezes, are gone > > completely. I've reinstalled dnetc and will be rerunning it, but as > > I've been banging the CPUs heavily with video processing, I don't > > expect a problem. > Anybody have any info on this? Have a production 4.6 with the bug (also > appearing on xl driver) and would like to kludge the changes manually w/o > having to cvsup. > > What was the problem fineally traced to? Anyone? Reinstalling dnetc and rerunning it (on one or both CPUs) reintroduced the "intermittent-hang" problem. After reflection, I realized that the difference between the video processing and the dnetc processing is that the former spends quite a lot of time in the kernel (from a tenth to up to half of the CPU time is 'system'), whereas the dnetc processing is entirely is in userland. What this indicates to me is that there may well be an end-of-quantum context-switch problem with respect to interrupts. So the problem is still extant; I'm just managing to avoid it for the most part. I've had no hard hangs requiring a reboot in over ten days, now. -- Frank Mayhar frank@exit.com http://www.exit.com/ Exit Consulting http://www.gpsclock.com/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message