From owner-freebsd-hardware@FreeBSD.ORG Mon Mar 8 15:00:19 2010 Return-Path: Delivered-To: freebsd-hardware@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A3C701065676 for ; Mon, 8 Mar 2010 15:00:19 +0000 (UTC) (envelope-from andrew.hood@lynchpin.com) Received: from zebedee.abp.lypn.net (zebedee.abp.lypn.net [212.11.77.147]) by mx1.freebsd.org (Postfix) with ESMTP id 013748FC19 for ; Mon, 8 Mar 2010 15:00:18 +0000 (UTC) Received: (qmail 79823 invoked by uid 98); 8 Mar 2010 14:33:35 -0000 Received: from 192.168.13.65 by zebedee.abp.lypn.net (envelope-from , uid 82) with qmail-scanner-2.01 (clamdscan: 0.95.2/9703. spamassassin: 3.2.5. Clear:RC:1(192.168.13.65):. Processed in 0.019069 secs); 08 Mar 2010 14:33:35 -0000 Received: from unknown (HELO ?192.168.13.65?) (192.168.13.65) by mail.lypn.net with CAMELLIA256-SHA encrypted SMTP; 8 Mar 2010 14:33:35 -0000 Message-ID: <4B950ABF.2050403@lynchpin.com> Date: Mon, 08 Mar 2010 14:33:35 +0000 From: Andrew Hood User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.1.8) Gecko/20100227 Thunderbird/3.0.3 MIME-Version: 1.0 To: freebsd-hardware@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: amr lockup on 8.0-RELEASE X-BeenThere: freebsd-hardware@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: General discussion of FreeBSD hardware List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 08 Mar 2010 15:00:19 -0000 Hi, Recently upgraded to 8.0-RELEASE-p2 (amd64) on a dual-processor Opteron system with a LSI MegaRAID SCSI 320-1. Since then, am getting a complete lock-up of the disk subsystem under heavy write load. It copes fine with a kernel build, but an attempt to rsync 150GB or so of data from the machine it is supposed to be replacing routinely hangs. I can systematically (and pretty immediately) recreate the issue using /usr/ports/sysutils/stress with one hdd hog (stress -d 1). When the hang occurs, the load average gradually moves up to 0.99 with the following CPU states shown in top: CPU: 0.0% user, 0.0% nice, 0.0% system, 25.0% interrupt, 75.0% idle I'm guessing 25% is expressed as a proportion of 4 processor cores (2 x dual cores)? If I run top -S, I can see one interrupt handler (?) at 100% 12 root 20 -60 - 0K 320K WAIT 0 0:08 100.00% intr From that point, the machine will happily do anything that doesn't involve reading or writing to disk. Anything attempting to access the disk subsystem will just hang indefinitely. Killing the process that was attempting to access this disk does not restore things. No errors at all in syslog or on the console. Machine had previously been running quite happily on 6.2-RELEASE as a PostgreSQL server without any issues; but equally may not have been as heavily loaded. Not quite sure where to look next in terms of further diagnosis, wondered if anyone had experienced anything similar? Thanks, Andrew -- Andrew Hood Managing Director Lynchpin Analytics t: 0845 838 1136 f: 0845 838 1137 e: andrew.hood@lynchpin.com Lynchpin Analytics Limited is registered in Scotland No. SC279857 Registered Office: 5th Floor, 7 Castle Street, Edinburgh, EH2 3AH From owner-freebsd-hardware@FreeBSD.ORG Tue Mar 9 05:09:41 2010 Return-Path: Delivered-To: freebsd-hardware@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 11229106566C for ; Tue, 9 Mar 2010 05:09:41 +0000 (UTC) (envelope-from freebsd@sopwith.solgatos.com) Received: from sopwith.solgatos.com (pool-98-108-131-15.ptldor.fios.verizon.net [98.108.131.15]) by mx1.freebsd.org (Postfix) with ESMTP id 28F8B8FC15 for ; Tue, 9 Mar 2010 05:09:39 +0000 (UTC) Received: by sopwith.solgatos.com (Postfix, from userid 66) id 381FFB64F; Mon, 8 Mar 2010 21:09:14 -0800 (PST) Received: from localhost by sopwith.solgatos.com (8.8.8/6.24) id CAA13697; Tue, 9 Mar 2010 02:37:07 GMT Message-Id: <201003090237.CAA13697@sopwith.solgatos.com> To: freebsd-hardware@freebsd.org Date: Mon, 08 Mar 2010 18:37:07 PST From: Dieter Subject: siis(4) questions X-BeenThere: freebsd-hardware@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: freebsd@sopwith.solgatos.com List-Id: General discussion of FreeBSD hardware List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 09 Mar 2010 05:09:41 -0000 The siis(4) man page promises a ada(4) man page, but I can't find it. Even tried the online man page tool. dmesg says: ada0 at siisch0 bus 0 target 0 lun 0 ada0: ATA/ATAPI-8 SATA 2.x device ada0: 300.000MB/s transfers ada0: 953869MB (1953525168 512 byte sectors: 16H 63S/T 16383C) ada0: Native Command Queueing enabled but camcontrol says: # camcontrol inquiry ada0 -R 150.000MB/s transfers # camcontrol identify ada0 [ ... ] Feature Support Enable Value Vendor write cache yes no read ahead yes yes Native Command Queuing (NCQ) yes 31/0x1F So camcontrol disagrees with dmesg about the transfer speed. And camcontrol doesn't even fill in whether NCQ is enabled or not. The readcap and modepage stuff doesn't work at all: # camcontrol readcap ada0 (pass0:siisch0:0:0:0): READ CAPACITY(10). CDB: 25 0 0 0 0 0 0 0 0 0 (pass0:siisch0:0:0:0): CAM Status: SCSI Status Error (pass0:siisch0:0:0:0): SCSI Status: Check Condition # camcontrol modepage ada0 -l camcontrol: error sending mode sense command # camcontrol modepage ada0 -m 0 camcontrol: error sending mode sense command # camcontrol modepage ada0 -m 1 camcontrol: error sending mode sense command # camcontrol modepage ada0 -m 2 camcontrol: error sending mode sense command # camcontrol modepage ada1 -m 2 camcontrol: error sending mode sense command I get the same problems with Seagate disks, so it isn't just Hitachi. I suspect that the dmesg info is correct. I'm not sure whether to believe *any* of the stuff camcontrol prints out? Like whether the write cache is on or not. And with the modepage stuff not working, how do I turn the write cache on and off?