From owner-freebsd-current@FreeBSD.ORG Tue Jun 7 15:33:23 2005 Return-Path: X-Original-To: freebsd-current@FreeBSD.org Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 27D7616A41C for ; Tue, 7 Jun 2005 15:33:23 +0000 (GMT) (envelope-from oberman@es.net) Received: from postal2.es.net (postal2.es.net [198.128.3.206]) by mx1.FreeBSD.org (Postfix) with ESMTP id 01BA943D53 for ; Tue, 7 Jun 2005 15:33:22 +0000 (GMT) (envelope-from oberman@es.net) Received: from ptavv.es.net ([198.128.4.29]) by postal2.es.net (Postal Node 2) with ESMTP (SSL) id IBA74465; Tue, 07 Jun 2005 08:33:22 -0700 Received: from ptavv (localhost [127.0.0.1]) by ptavv.es.net (Tachyon Server) with ESMTP id 208B85D07; Tue, 7 Jun 2005 08:33:22 -0700 (PDT) To: "Daniel Eriksson" In-reply-to: Your message of "Tue, 07 Jun 2005 02:40:02 +0200." Date: Tue, 07 Jun 2005 08:33:22 -0700 From: "Kevin Oberman" Message-Id: <20050607153322.208B85D07@ptavv.es.net> Cc: freebsd-current@FreeBSD.org Subject: Re: Livelock seen on current with threaded processes X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 07 Jun 2005 15:33:23 -0000 > From: "Daniel Eriksson" > Date: Tue, 7 Jun 2005 02:40:02 +0200 > > Kevin Oberman wrote: > > > I run transcode on a video file to convert it to divx4 using the xvid4 > > library. I do this with nice set to 10 and top confirms that it is set > > to 10. At various times, the system starts locking up. Windows won't > > refresh. Shell commands never execute (nor do keys echo) in > > some windows > > including syscons vtys. If my gkrellm is still alive (and it usually > > is), I see the system at 97% CPU and nothing else busy. There > > is a bit a > > disk I/O but not much. > > This sounds a lot like the problems I described in the thread "Serious I/O > problems (bad performance and live-lock)" from a few weeks ago. It seems > that when the VM subsystem is put under pressure the machine comes to a > grinding halt. In my case I could trigger this with a simple 'dd' (on a > filesystem, not on a raw device). Yes, it does sound similar. I was hoping that your thread would lead to a resolution of my problem. I can certainly believe that the problem is VM related. Unfortunately, I believe the work-around was to set debug.mpsafevm to 1, but that didn't seem to help at my case at all. Am I remembering correctly? -- R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634