From owner-freebsd-hackers Wed Mar 4 12:11:54 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id MAA13333 for freebsd-hackers-outgoing; Wed, 4 Mar 1998 12:11:54 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from sendero.simon-shapiro.org (sendero-fxp0.Simon-Shapiro.ORG [206.190.148.34]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id MAA13318 for ; Wed, 4 Mar 1998 12:11:41 -0800 (PST) (envelope-from shimon@sendero-fxp0.simon-shapiro.org) Received: (qmail 9708 invoked by uid 1000); 4 Mar 1998 20:18:31 -0000 Message-ID: X-Mailer: XFMail 1.3-alpha-021598 [p0] on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <199803041805.TAA01136@yedi.iaf.nl> Date: Wed, 04 Mar 1998 12:18:31 -0800 (PST) Reply-To: shimon@simon-shapiro.org Organization: The Simon Shapiro Foundation From: Simon Shapiro To: Wilko Bulte Subject: Re: SCSI Bus redundancy... Cc: grog@lemis.com, hackers@FreeBSD.ORG, blkirk@float.eli.net, jdn@acp.qiv.com, tlambert@primenet.com, sbabkin@dcn.att.com, karl@mcs.net Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On 04-Mar-98 Wilko Bulte wrote: ... >> The difficulty is in having FreeBSD capable of producing this traffic on >> small blocks (dd if=/dev/zero of=/dev/something bs=64k is NOT typical >> application). > > Build a datawarehouse and do full-table reads etc. For dataprocessing etc > you will never come near. Sure. These you make with 256KB stripes or larger, and turn read-ahead on. BTW, these applications should enjoy Super-Ultra-Wide-ExtraWide SCSI. > We've seen host adapters becoming saturated before the RAIDbox. This is > of course using an artificial benchmark that produces 100% cache hits on > the RAIDbox' cache. Yup. I think you will enjoy the new generation DPT controllers. Even as a passthrough to your RAID box. >> > I could run two host channels on this thing across two RAID sets into >> > two >> > Adaptec adapters. That might be a big win. > > That could be possible, highly depends on the adapter & driver. But for > single stream a well written driver & good card will probably not be the > bottleneck. The bottleneck is not in the driver, but most likely in the SCSI sequencer. I suspect something in the kernel is also holding things down. A clue can be had in the drop in I/O rate when you switch from UP to SMP. I dropped the ball on tracking these down but will pick it up soon. SMP is twice as slow as UP in these tests. ---------- Sincerely Yours, Simon Shapiro Shimon@Simon-Shapiro.ORG Voice: 503.799.2313 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message