From owner-freebsd-scsi@FreeBSD.ORG Thu Dec 11 02:45:59 2003 Return-Path: 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 9376216A4CE; Thu, 11 Dec 2003 02:45:59 -0800 (PST) Received: from sockar.homeip.net (tourist.net1.nerim.net [62.212.109.212]) by mx1.FreeBSD.org (Postfix) with ESMTP id 88E6943D1D; Thu, 11 Dec 2003 02:45:57 -0800 (PST) (envelope-from amon@sockar.homeip.net) Received: from sockar.homeip.net (localhost [127.0.0.1]) by sockar.homeip.net (8.12.9p2/8.12.9) with ESMTP id hBBAlNpd018080; Thu, 11 Dec 2003 11:47:23 +0100 (CET) (envelope-from amon@sockar.homeip.net) Received: (from amon@localhost) by sockar.homeip.net (8.12.9p2/8.12.9/Submit) id hBBAlNfn018079; Thu, 11 Dec 2003 11:47:23 +0100 (CET) (envelope-from amon) Date: Thu, 11 Dec 2003 11:47:23 +0100 From: amon@sockar.homeip.net To: Scott Long Message-ID: <20031211114723.D206@ra.aabs> References: <20031210173002.B206@ra.aabs> <20031210094420.D6877@pooker.samsco.home> <20031210201056.C206@ra.aabs> <20031210135055.T6877@pooker.samsco.home> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit User-Agent: Mutt/1.2.5.1i In-Reply-To: <20031210135055.T6877@pooker.samsco.home>; from scottl@freebsd.org on Wed, Dec 10, 2003 at 01:54:37PM -0700 cc: freebsd-scsi@freebsd.org Subject: Re: Performance problem with adaptec 2120S X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 11 Dec 2003 10:45:59 -0000 Le 10/12/2003 à 13:54, Scott Long a écrit: > > Some hardware architecture choices were made that influence this. Better > choices were made with the 2200S so it should be faster, especially in a > 64/66 PCI slot. I see. > Are you talking about the write cache on the drives or on the array? You > should never enable the write cache on the drives unless you are certain > that you will never ever have a power failure. FOr the arrays, the > optimal cache configuration is to have the read cache turned off and the > write cache turned on. If this is not the case for you, I'd like to see > the diagnostic output from the card. I only enabled the write cache of the array and aaccli now shows : AAC0> COMMAND: container show cache 0 Executing: container show cache 0 Global Container Read Cache Size : 475136 Global Container Write Cache Size : 40140800 Read Cache Setting : DISABLE Write Cache Setting : ENABLE ALWAYS Write Cache Status : Active, not protected, battery not present The complete 'diag dump text' output is there : http://khonshou.hst.nerim.net/aac-diag Are all those NMI_SECONDARY_ATU_ERROR in the history buffer normal ? -- Herve Boulouis - EFREI Promo 2003 - Equipe systeme Unix