From owner-freebsd-questions@FreeBSD.ORG Tue Oct 27 23:37:01 2009 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 630E6106568D for ; Tue, 27 Oct 2009 23:37:01 +0000 (UTC) (envelope-from phantomcircuit@covertinferno.org) Received: from mail.covertinferno.org (adsl-99-33-24-145.dsl.pltn13.sbcglobal.net [99.33.24.145]) by mx1.freebsd.org (Postfix) with ESMTP id 3DD2C8FC15 for ; Tue, 27 Oct 2009 23:37:00 +0000 (UTC) Received: from [192.168.1.121] (unknown [192.168.1.1]) by mail.covertinferno.org (Postfix) with ESMTPSA id C4D6D12CD29 for ; Tue, 27 Oct 2009 23:36:54 +0000 (UTC) Message-ID: <4AE7841B.4080408@covertinferno.org> Date: Tue, 27 Oct 2009 16:36:59 -0700 From: phantomcircuit User-Agent: Thunderbird 2.0.0.23 (X11/20090817) MIME-Version: 1.0 To: freebsd-questions@freebsd.org References: <4AE774BC.8080006@daemonfun.com> In-Reply-To: <4AE774BC.8080006@daemonfun.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: What causes random disk access slow down X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Oct 2009 23:37:01 -0000 How full are the disks? Jin Guojun wrote: > A 6-7 years old Xeon dual 2.4MHz CPU machine runs FreeBSD 6.4-Release > suddenly becomes > slow on some tasks requiring disk access. Typical things like ls, > objdump etc. Be more specific, a couple of minutes objdump became a > several hours job. > A several seconds "ls -RC" became a 15-minute task (see output below). > > It sounds like a hard drive problem, but run sequential disk test on > all drives, their throughput > meet the original disk spec and disks run very quite, at random disk > access, disks generate > some rigid noise, so it looks like a random disk access problem. > This machine has two IDE PATA drives (ignore da0 -- a USB stick), but > No error message has > been recorded in dmesg for any dirve a couple of weeks after the > problem happened. > > Machine has been rebooted a few times after slowness occurred, but it > won't help. > Is there anyway/any tool to find out what is going wrong in the system? > > -Jin > > [165] bsd-ms: ls -RC > Dir > 3.756u 19.402s 15:29.37 2.4% 30+2938k 49120+76io 0pf+0w > > monitored from the other terms -- > [138] bsd-ms: ll ~/Dir > -rw-r--r-- 1 src wheel 6152192 Oct 27 14:53 /home/users/src/Dir > [139] bsd-ms: ll ~/Dir > -rw-r--r-- 1 src wheel 8019968 Oct 27 14:56 /home/users/src/Dir > [140] bsd-ms: ll ~/Dir > -rw-r--r-- 1 src wheel 9915957 Oct 27 14:58 /home/users/src/Dir > > tty ad0 ad1 da0 > cpu > tin tout KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy > in id > 9 365 9.14 6 0.05 12.08 6 0.07 121.91 0 0.00 2 0 1 > 0 97 > 0 1020 11.75 87 0.99 17.82 7 0.13 0.00 0 0.00 76 0 14 > 0 10 > 0 1005 8.54 262 2.19 52.94 23 1.21 0.00 0 0.00 61 0 29 > 1 9 > 0 893 7.54 184 1.36 85.76 34 2.82 0.00 0 0.00 53 0 32 > 1 14 > 0 551 3.35 265 0.87 9.38 4 0.04 0.00 0 0.00 47 0 33 > 1 19 > 0 594 6.81 201 1.33 37.82 4 0.14 0.00 0 0.00 54 0 16 > 0 30 > 0 1106 3.54 252 0.87 55.19 17 0.93 0.00 0 0.00 39 0 33 > 1 27 > 0 393 2.88 223 0.63 11.43 2 0.03 0.00 0 0.00 67 0 31 > 1 1 > 0 644 4.81 165 0.77 16.00 0 0.01 0.00 0 0.00 87 0 12 > 1 1 > 27 339 10.39 180 1.82 15.18 11 0.17 0.00 0 0.00 86 0 13 > 0 0 > 32 130 5.06 146 0.72 23.40 46 1.04 0.00 0 0.00 86 0 8 > 1 5 > 32 267 8.39 138 1.13 61.09 4 0.22 0.00 0 0.00 73 0 26 > 1 0 > 33 340 8.75 222 1.90 61.54 4 0.26 0.00 0 0.00 78 0 21 > 1 0 > 32 595 5.85 154 0.88 12.20 3 0.04 0.00 0 0.00 87 0 12 > 1 0 > 32 288 5.28 147 0.76 6.00 1 0.01 0.00 0 0.00 86 0 13 > 1 0 > > _______________________________________________ > freebsd-questions@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-questions > To unsubscribe, send any mail to > "freebsd-questions-unsubscribe@freebsd.org"