From owner-freebsd-scsi@FreeBSD.ORG Sat Jun 24 18:40:34 2006 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1476816A494 for ; Sat, 24 Jun 2006 18:40:34 +0000 (UTC) (envelope-from materribile@yahoo.com) Received: from web33508.mail.mud.yahoo.com (web33508.mail.mud.yahoo.com [68.142.206.157]) by mx1.FreeBSD.org (Postfix) with SMTP id 1575943D6B for ; Sat, 24 Jun 2006 18:40:33 +0000 (GMT) (envelope-from materribile@yahoo.com) Received: (qmail 41217 invoked by uid 60001); 24 Jun 2006 18:40:32 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=McpBi8xfUG6YBA+uqCOA1jlBHNNjlYi8Wma0Ohx4IFbsPuzXy5J6JiKeaMb8O6HE+divcLbLQqOh/vZIT5OuaOil755nNx662d5w5wag+PtayvNV3zueFbzilxUc1TZdiD1eAUUqnU1eWpmrdlCSTZmnLyvknwRYbI4wedVD478= ; Message-ID: <20060624184032.41215.qmail@web33508.mail.mud.yahoo.com> Received: from [67.84.118.3] by web33508.mail.mud.yahoo.com via HTTP; Sat, 24 Jun 2006 11:40:32 PDT Date: Sat, 24 Jun 2006 11:40:32 -0700 (PDT) From: Mark Terribile To: freebsd-scsi@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Subject: e: ahd(4) poor performance X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 24 Jun 2006 18:40:34 -0000 On Fri, 23 Jun 2006, Tom Samplonius wrote: >On Fri, 23 Jun 2006, Matthew D. Fuller wrote: > >> On Sat, Jun 24, 2006 at 12:25:06AM +0300 I heard the voice of >> Volodymyr Kostyrko, and lo! it spake thus: >>> >>> Script: >>> >>> dd if=/dev/zero of=/dev/da0s1b count=20480& >>> dd if=/dev/zero of=/dev/da0s1b count=20480& >> [...] >> >> This seems like it would be a record-shattering worst possible case >> for the disk. ... > I agree with that, but it happens to be an almost best case scenario >for a write-back cache. ... > But in write-through (no write cache), it is definitely a nice way to >thrash the disk. You would get one write per block, per dd process. > >> --- >> Matthew Fuller (MF4839) | fullermd@over-yonder.net >> Systems/Network Administrator | http://www.over-yonder.net/~fullermd/ >> On the Internet, nobody can hear you scream. > >Tom Some years ago I ran some scripts like this to see what we could expect from our disks. When I piled operations like this up, I found that the sequences of operations tended to synchronize. It appeared that whenever two operations in sequence found themselves on the same cylinder, they would be serviced very quickly together (rotation, no seek). Once synchronized, they stayed synchronized and so unless the dd's were started with a very large time lag, they would all end at about the same time. Mark Terribile __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com