From owner-freebsd-geom@FreeBSD.ORG Mon Nov 6 19:12:56 2006 Return-Path: X-Original-To: freebsd-geom@freebsd.org Delivered-To: freebsd-geom@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8807616A40F; Mon, 6 Nov 2006 19:12:56 +0000 (UTC) (envelope-from don_oles@able.com.ua) Received: from able.com.ua (able.com.ua [80.91.162.66]) by mx1.FreeBSD.org (Postfix) with ESMTP id D6F9943D8C; Mon, 6 Nov 2006 19:12:48 +0000 (GMT) (envelope-from don_oles@able.com.ua) Received: from able.com.ua (localhost [127.0.0.1]) by able.com.ua (Postfix) with ESMTP id D2DAA44C13; Mon, 6 Nov 2006 21:12:36 +0200 (EET) Received: from vanta.oles.net (ip.85.202.111.30.dyn.sub-1.broadband.voliacable.com [85.202.111.30]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by able.com.ua (Postfix) with ESMTP id 718D944C11; Mon, 6 Nov 2006 21:12:33 +0200 (EET) Date: Mon, 6 Nov 2006 21:12:34 +0200 From: Oles Hnatkevych X-Mailer: The Bat! (v3.71.01) Professional X-Priority: 3 (Normal) Message-ID: <512766008.20061106211234@able.com.ua> To: Oliver Fromme In-Reply-To: <200611061204.kA6C4FXt079703@lurza.secnetix.de> References: <961295086.20061105000919@able.com.ua> <200611061204.kA6C4FXt079703@lurza.secnetix.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV using ClamSMTP at ABLE Cc: freebsd-perfomance@freebsd.org, pjd@freebsd.org Subject: Re[2]: geom stripe perfomance question X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Oles Hnatkevych List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 06 Nov 2006 19:12:56 -0000 Hello, All It turns out that it was a hardware/controller problem. The benchmarks with 'dd bs=1m' gave the following results. Two disks Samsung SP2514N, stripe size 65kb The controller ICH2 (ATA100), Celeron 800: ad(x): ~72 Mb/sec ad1 & ad2 in parallel: ~33 Mb/sec each (disks on separate ATA channels) stripe: ~65-68 Mb/sec The controller VIA 82xxxx (ATA133), Athlon 1700+ ad(x): 72-74 Mb/sec ad1 & ad2 in parallel (same ATA channel): ~26Mb/sec each! ad1 & ad2 in parallel (different ATA channels): same as one disk! stripe (different ATA channels): ~144 Mb/sec (even without kern.geom.stripe.fast option). What really is surprising that disks on the same ATA channel on VIA controller behave much worse than half of their full speed. Yet on a different ATA channels they perform flawlessly. Seems like the gmirror(8) man page should contain a separate paragraph telling about peculiarities using old ATA controllers or using disks on the same ATA channel. ;-) -- Oles Hnatkevych mailto:don_oles@able.com.ua