From owner-freebsd-hackers Wed Mar 4 14:53:35 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA12178 for freebsd-hackers-outgoing; Wed, 4 Mar 1998 14:53:35 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from uni4nn.gn.iaf.nl (osmium.gn.iaf.nl [193.67.144.12]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id OAA12072 for ; Wed, 4 Mar 1998 14:53:15 -0800 (PST) (envelope-from wilko@yedi.iaf.nl) Received: by uni4nn.gn.iaf.nl with UUCP id AA32002 (5.67b/IDA-1.5 for hackers@FreeBSD.ORG); Wed, 4 Mar 1998 23:52:52 +0100 Received: (from wilko@localhost) by yedi.iaf.nl (8.8.7/8.6.12) id XAA04270; Wed, 4 Mar 1998 23:11:26 +0100 (MET) From: Wilko Bulte Message-Id: <199803042211.XAA04270@yedi.iaf.nl> Subject: Re: SCSI Bus redundancy... In-Reply-To: from Simon Shapiro at "Mar 4, 98 12:18:31 pm" To: shimon@simon-shapiro.org Date: Wed, 4 Mar 1998 23:11:26 +0100 (MET) 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 X-Organisation: Private FreeBSD site - Arnhem, The Netherlands X-Pgp-Info: PGP public key at 'finger wilko@freefall.freebsd.org' X-Mailer: ELM [version 2.4ME+ PL32 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG As Simon Shapiro wrote... > > 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. Or a FibreChannel array. Will be playing with that for the rest of the week. I'm pretty curious to see how that behaves. > > 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 don't know if DPT will be part of our product offering. I play with what they throw at me ;-) The FC array is cute so I don't complain. > > 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. Somebody/something locking resources? But that is definetely worth investigating for SMP users. Wilko (who has plenty of CPUs, but all in the own mainboard/box) _ ______________________________________________________________________ | / o / / _ Bulte email: wilko @ yedi.iaf.nl http://www.tcja.nl/~wilko |/|/ / / /( (_) Arnhem, The Netherlands - Do, or do not. There is no 'try' --------------- Support your local daemons: run [Free,Net,Open]BSD Unix -- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message