From owner-freebsd-hackers Thu May 29 23:55:19 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id XAA02593 for hackers-outgoing; Thu, 29 May 1997 23:55:19 -0700 (PDT) Received: from misery.sdf.com (misery.sdf.com [204.244.210.193]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id XAA02588 for ; Thu, 29 May 1997 23:55:16 -0700 (PDT) Received: from localhost (tom@localhost) by misery.sdf.com (8.8.5/8.8.5) with SMTP id XAA11839; Thu, 29 May 1997 23:55:02 -0700 (PDT) X-Authentication-Warning: misery.sdf.com: tom owned process doing -bs Date: Thu, 29 May 1997 23:55:01 -0700 (PDT) From: Tom Samplonius To: jbryant@tfs.net cc: freebsd-hackers@FreeBSD.ORG Subject: Re: ahc0 In-Reply-To: <199705300424.XAA01480@argus.nuke.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Thu, 29 May 1997, Jim Bryant wrote: > just another observation... > > iozone shows drastic reductions in throughput on a SCSI-2 2G > barracuda... i was getting approximately 5.5-6.5 M/S on both read and > write under 2.1-R... > > now i get approximately 2.5 M/S write and 4.5-5.5 M/S read... > > options AHC_TAGENABLE # experimental > > is the 2.1-R config and gives the above results... > > options AHC_ALLOW_MEMIO > > seems to give no improvement... > > currently running 2.2.2-R If you are sure the hardware is the same, it it likely the newfs options you used. You probably shouldn't use any. I get easy 6 to 7MB with a Barracuda 4LP 2GB drive on large sequential writes to a test file using dd, under 2.2.2. My impressions are that 2.2.2 has nice performance improvements over 2.1.x > jim > -- > All opinions expressed are mine, if you | "I will not be pushed, stamped, > think otherwise, then go jump into turbid | briefed, debriefed, indexed, or > radioactive waters and yell WAHOO !!! | numbered!" - #1, "The Prisoner" > jbryant@tfs.net - KC5VDJ 2M, 70cm, KPC-3+ - kc5vdj@wv0t.#neks.ks.usa.noam > > Tom