From owner-freebsd-stable@FreeBSD.ORG Fri Jun 23 04:15:09 2006 Return-Path: X-Original-To: freebsd-stable@freebsd.org 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 5994E16A481 for ; Fri, 23 Jun 2006 04:15:09 +0000 (UTC) (envelope-from dan@dan.emsphone.com) Received: from dan.emsphone.com (dan.emsphone.com [199.67.51.101]) by mx1.FreeBSD.org (Postfix) with ESMTP id EDF1C43D48 for ; Fri, 23 Jun 2006 04:15:08 +0000 (GMT) (envelope-from dan@dan.emsphone.com) Received: (from dan@localhost) by dan.emsphone.com (8.13.1/8.13.4) id k5N4F84w011672; Thu, 22 Jun 2006 23:15:08 -0500 (CDT) (envelope-from dan) Date: Thu, 22 Jun 2006 23:15:08 -0500 From: Dan Nelson To: "Marc G. Fournier" Message-ID: <20060623041508.GC95588@dan.emsphone.com> References: <20060622170836.Q1114@ganymede.hub.org> <20060623032231.GE5115@deviant.kiev.zoral.com.ua> <20060623004037.T1114@ganymede.hub.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20060623004037.T1114@ganymede.hub.org> X-OS: FreeBSD 5.5-PRERELEASE X-message-flag: Outlook Error User-Agent: Mutt/1.5.11 Cc: Konstantin Belousov , freebsd-stable@freebsd.org Subject: Re: FreeBSD 6-STABLE freezing up ... X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Jun 2006 04:15:09 -0000 In the last episode (Jun 23), Marc G. Fournier said: > On Fri, 23 Jun 2006, Konstantin Belousov wrote: > >What exactly happens ? Are you sure that the _system_ freezes ? > >Could it be that only your application has some troubles ? > > Nothing works ... I can ping the server, and that is about it ... the > last time it happened, I had a vmstat process running in an xterm, to > see, and I suspect that there is a process (or two) starting up > hitting the hard drive extra hard, as the drives go from an ~5 busy, > to 45 busy, and stays like that ... the fun part is figuring out what > is killing the drives ;( Hit "m" in top to switch to I/O mode, and enter "ototal" to sort by I/O instead of CPU. As long as whatever's doing the I/O lasts longer than top's refresh interval it should show up. -- Dan Nelson dnelson@allantgroup.com