From owner-freebsd-current@FreeBSD.ORG Tue Dec 12 10:55:09 2006 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 633E616A47C for ; Tue, 12 Dec 2006 10:55:09 +0000 (UTC) (envelope-from caelian@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.172]) by mx1.FreeBSD.org (Postfix) with ESMTP id CE86343CCC for ; Tue, 12 Dec 2006 10:53:20 +0000 (GMT) (envelope-from caelian@gmail.com) Received: by ug-out-1314.google.com with SMTP id o2so1469107uge for ; Tue, 12 Dec 2006 02:54:40 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=KNYTKDz3Q5/0TLjB+OJmh1MW35EdXcmmvjocS2/Gho99PdKfvctl2hQk5bR08BsaldjSBsH74xTLuO4XP62wRaWBXrtIchr812AO9dNaG8oDSgbzmrW0xPdpDC0ySuj3OUXEDDV4yLosIDfd9OTny4odQX+AwD3HDyMnI8Sg4oc= Received: by 10.78.50.5 with SMTP id x5mr2462581hux.1165920880622; Tue, 12 Dec 2006 02:54:40 -0800 (PST) Received: by 10.78.145.16 with HTTP; Tue, 12 Dec 2006 02:54:40 -0800 (PST) Message-ID: Date: Tue, 12 Dec 2006 11:54:40 +0100 From: "Pascal Hofstee" To: "FreeBSD Current" MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Subject: umass intermittently "stalling" ... processes seemingly stuck in "wdrain" state 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, 12 Dec 2006 10:55:09 -0000 I recently bought an USB Mass Storage unit (about 300GB) and a 4+1 slot PCI USB2.0 card (since it's an old box that didn't have USB 2 on board yet), and i have noticed that intermittently the device "stalls" any operations that try to access it: - copying data onto the disk - reading data from the disk - running an ls while inside a directory on the disk's mount point Today while trying to scp a fairly large set of files from my office system to my umass disk at home i noticed the similar stalling behaviour and decided to check ps output on my home system. There i noticed that every single time to scp session would begin stalling (lasting up to about 30-40s per stall) ... the scp process on my home-system would have dropped into a wdrain state. As soon as the scp process (after about 30 or more seconds) would finally get out of this wdrain state (usually into an sbwait state) the scp process on my work system would start picking up transfer speed again until the next slip into wdrain. I haven't been able to test this on a non-CURRENT system yet so i am not sure wether or not this is a CURRENT only issue or a more generic problem, but if somebody could give some pointers on where to start looking on fixing this ... i am open for suggestions. -- Pascal