X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id A53309DC88C for ; Wed, 1 Feb 2006 13:57:50 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 97675-09 for ; Wed, 1 Feb 2006 13:57:49 -0400 (AST) X-Greylist: domain auto-whitelisted by SQLgrey- Received: from uproxy.gmail.com (uproxy.gmail.com [66.249.92.192]) by postgresql.org (Postfix) with ESMTP id 21C309DC85F for ; Wed, 1 Feb 2006 13:57:47 -0400 (AST) Received: by uproxy.gmail.com with SMTP id j40so45829ugd for ; Wed, 01 Feb 2006 09:57:48 -0800 (PST) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=pinxwUwh3WJBiktAorOCTFsjmhxea1ksyZIk8GyG1WgCtkJxU1RXoe3vI8AMvX+fSwWYUB0M1a3Vwbfr4RonRGNAhTyYLYcSeJsALAvl9lfAAl86M28qMI7nTsJYyxB65SMyrgNk3jyW7cyBMvzMOtdjYKuWjULdGhZtt449R44= Received: by 10.49.92.10 with SMTP id u10mr1193714nfl; Wed, 01 Feb 2006 09:57:47 -0800 (PST) Received: by 10.49.15.20 with HTTP; Wed, 1 Feb 2006 09:57:47 -0800 (PST) Message-ID: Date: Wed, 1 Feb 2006 17:57:47 +0000 From: Mike Rylander To: Luke Lonergan Subject: Re: Huge Data sets, simple queries Cc: PFC , "Jeffrey W. Baker" , pgsql-performance@postgresql.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=1.062 required=5 tests=[AWL=-0.270, RCVD_IN_BL_SPAMCOP_NET=1.332] X-Spam-Score: 1.062 X-Spam-Level: * X-Archive-Number: 200602/18 X-Sequence-Number: 17004 On 2/1/06, Luke Lonergan wrote: [snip] > This is actually interesting overall - I think what this might be showing= is > that the Linux SW RAID1 is alternating I/Os to the mirror disks from > different processes (LWP or HWP both maybe?), but not within one process. I can confirm this behavior after looking at my multipathed fibre channel SAN. To the best of my knowledge, the multipathing code uses the same underlying I/O code as the Linux SW RAID logic. -- Mike Rylander mrylander@gmail.com GPLS -- PINES Development Database Developer http://open-ils.org