From owner-freebsd-questions@FreeBSD.ORG Thu Sep 4 00:43:56 2003 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 797A316A4BF for ; Thu, 4 Sep 2003 00:43:56 -0700 (PDT) Received: from linda-2.paradise.net.nz (bm-2a.paradise.net.nz [202.0.58.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5CA4E43F3F for ; Thu, 4 Sep 2003 00:43:55 -0700 (PDT) (envelope-from markir@paradise.net.nz) Received: from smtp-3.paradise.net.nz (smtp-3b.paradise.net.nz [202.0.32.212]) by linda-2.paradise.net.nz (Paradise.net.nz) with ESMTP id <0HKO00C8AIT5IJ@linda-2.paradise.net.nz> for questions@freebsd.org; Thu, 04 Sep 2003 19:43:54 +1200 (NZST) Received: from paradise.net.nz (202-0-44-31.adsl.paradise.net.nz [202.0.44.31]) by smtp-3.paradise.net.nz (Postfix) with ESMTP id 9BBB0ADF99 for ; Thu, 04 Sep 2003 19:43:53 +1200 (NZST) Date: Thu, 04 Sep 2003 19:39:25 +1200 From: Mark Kirkwood In-reply-to: <3F50335D.1030807@paradise.net.nz> To: questions@freebsd.org Message-id: <3F56EC2D.1050508@paradise.net.nz> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=us-ascii Content-transfer-encoding: 7bit X-Accept-Language: en-us, en User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.4) Gecko/20030630 References: <3F50335D.1030807@paradise.net.nz> Subject: Re: IO To IDE Blocking In 5.1 X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 04 Sep 2003 07:43:56 -0000 Poor form to anwser my own question but .... I removed and inspected the IDE cables... found one with some damage - I suspect this is the cause. Happend to get a Promise TX2000 raid card yesterday , so I reinstalled (+ new cables). Retesting the scenario finds that iostat is not blocked. regards Mark P.s : Still seeing loss of 2 processor scaling where *any* io is involved, but I will study this some more and post to smp if cant understand it (I wonder if its something to do with running 2 copies of the *same* binary). Mark Kirkwood wrote: > ..... > iostat blocks until the process is completed. If I start iostat > *first*, then it does not block, and > I can see the io activity generated by the process when it starts. > > I am running the SMP kernel, but can reproduce this using GENERIC. > > Any ideas ?