From owner-freebsd-questions@FreeBSD.ORG Thu Jun 9 06:30:02 2011 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 4C47A106564A for ; Thu, 9 Jun 2011 06:30:02 +0000 (UTC) (envelope-from rendaw@zarbosoft.com) Received: from mout.perfora.net (mout.perfora.net [74.208.4.195]) by mx1.freebsd.org (Postfix) with ESMTP id E24138FC0A for ; Thu, 9 Jun 2011 06:30:01 +0000 (UTC) Received: from [192.168.1.64] (rrcs-74-87-85-100.west.biz.rr.com [74.87.85.100]) by mrelay.perfora.net (node=mrus4) with ESMTP (Nemesis) id 0M864P-1PZihp0Vgf-00vhI9; Thu, 09 Jun 2011 02:17:25 -0400 Message-ID: <4DF06569.9070900@zarbosoft.com> Date: Thu, 09 Jun 2011 01:17:13 -0500 From: rendaw User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.7) Gecko/20100720 Lanikai/3.1.1 MIME-Version: 1.0 To: freebsd-questions@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Provags-ID: V02:K0:K6U2tM7y0fJbRW/RU+PidiWbh8GU353PUDTQX88sghc s3YYch12is8fUZr6eCKBQcO6/tEQ36HYtCEBiBz9CtVQ+t6uNy BTyqev237B87syfzR6LqavPWN3V4wgAcZKbLksM4bNdsJCwmEe aCo6uiulmOex5+kpL0N3eMUmZAbWk06TjJP9t2UA3E5P18K7MJ cI7KfPAzyRnsKvF1lozhIBk1doyeyUj8AbvqFIw+OQ= Subject: Re: Intermittent pauses copying from one usb drive to another 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: Thu, 09 Jun 2011 06:30:02 -0000 Referencing http://lists.freebsd.org/pipermail/freebsd-usb/2011-February/009950.html I'm not sure the best way to go about referencing old threads, but I hope this is acceptable. I'm having the same issue with two 3.5" drives in USB 2.0 enclosures operating in USB 1 mode. Like the OP, I see write activity for 1-5 seconds followed by 1-2 minutes of no activity (I get the same vmstat output). Unlike the OP, I get no error messages in /var/log/messages. I get the same behavior copying files from a local server both scp'ing and tar-over-ssh'ing. Doing tcpdump shows the network traffic completely stop for those pause periods as well (other than some dns or arp or something chatter every once and a while). I did try it on a linux box (just because it was handy) and I got full 1 mb/s speeds with dd (dd if=/dev/whatever of=/dev/null). I get around 800kb/s on FreeBSD doing the same test on either drive. I have the two drives in a ZFS raidz setup, but "top" says I have around 400 of 512mb ram free and the about 2.0 ghz processor is more or less completely unloaded. I tried the same scp to the linux box's internal drive and got no pausing, so I don't think it's an scp/server issue. Assuming this isn't caused by drive message incompatibility, is there some other configuration that could be wrong? Are there some other diagnostics I could try? Thank you very much, Andrew Baxter