From owner-freebsd-stable@FreeBSD.ORG Fri Jul 6 17:19:40 2012 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 4CB89106566B for ; Fri, 6 Jul 2012 17:19:40 +0000 (UTC) (envelope-from gmx@ross.cx) Received: from www81.your-server.de (www81.your-server.de [213.133.104.81]) by mx1.freebsd.org (Postfix) with ESMTP id 0874E8FC0A for ; Fri, 6 Jul 2012 17:19:40 +0000 (UTC) Received: from [92.76.69.32] (helo=michael-think) by www81.your-server.de with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.74) (envelope-from ) id 1SnCBu-0007mK-Lr for freebsd-stable@freebsd.org; Fri, 06 Jul 2012 19:19:38 +0200 Content-Type: text/plain; charset=iso-8859-15; format=flowed; delsp=yes To: freebsd-stable@freebsd.org Date: Fri, 06 Jul 2012 19:19:30 +0200 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: "Michael Ross" Message-ID: User-Agent: Opera Mail/12.00 (Win32) X-Authenticated-Sender: gmx@ross.cx X-Virus-Scanned: Clear (ClamAV 0.97.3/15115/Fri Jul 6 15:58:34 2012) Subject: Trouble with gmirror and device ada 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, 06 Jul 2012 17:19:40 -0000 Hello, I rented a new machine a couple of days ago, and it happens: Test: Transfer some 5GB of files to the machine Works fine as long as I use one of the drives individually. If I gmirror the drives gmirror label gm0 ada0 gmirror insert gm0 ada1 ...wait for rebuild the machine reliably locks up on the file transfer, with a frozen systat screen showing both drives at 100% busy: 10 users Load 0,41 0,44 0,20 6 Jul 18:47 Mem:KB REAL VIRTUAL VN PAGER SWAP PAGER Tot Share Tot Share Free in out in out Act 23496 6036 600772 12252 1361840 count All 71680 6632 1074428k 28264 pages Proc: Interrupts r p d s w Csw Trp Sys Int Sof Flt cow 121 total 28 199 2 121 4 67 zfod atkbd0 1 ozfod 4 re0 16 0,4%Sys 0,0%Intr 0,0%User 0,0%Nice 99,6%Idle %ozfod atapci0 20 | | | | | | | | | | | daefr 94 cpu0:timer prcfr 23 cpu1:timer 1333 dtbuf 4 totfr Namei Name-cache Dir-cache 111358 desvn react Calls hits % hits % 1009 numvn pdwak 3 3 100 32 frevn pdpgs intrn Disks ada0 ada1 pass0 pass1 302680 wire KB/t 16,00 16,00 0,00 0,00 14716 act tps 1 1 0 0 334260 inact MB/s 0,02 0,02 0,00 0,00 cache %busy 100 100 0 0 1361840 free 217488 buf While the network stays responsive, i. e. I can ping the machine and _connect_ via ssh, I can't actually log in (or, in already open shell, execute anything). System requires a hardware reset. Nothing in the logs whatsoever (no surprise here). I have no KVM access to this system. OS is generic 9.0 stable from two days ago. I run 8.2-R on an identical machine without trouble. I run 9.0 stable as of May 4th on an similiar (other CPU and NIC) machine without trouble. On both machines, the drives are recognized as ``ad''. (Why btw? ``man ada'' says ``device ada'', but there is no such option in the GENERIC config. Do I get ``ada'' with ``device ATA_CAM ''? I'm going to try this next, kick ata_cam from the kernel, see if drives are ``ad'' and system doesn't crash.) I'd appreciate suggestions on what I could do. Thanks, Michael