From owner-freebsd-hackers Sat Mar 25 18:32:43 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id SAA23471 for hackers-outgoing; Sat, 25 Mar 1995 18:32:43 -0800 Received: from ref.tfs.com (ref.tfs.com [140.145.254.251]) by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id SAA23465 for ; Sat, 25 Mar 1995 18:32:42 -0800 Received: (from phk@localhost) by ref.tfs.com (8.6.8/8.6.6) id SAA19879; Sat, 25 Mar 1995 18:32:30 -0800 From: Poul-Henning Kamp Message-Id: <199503260232.SAA19879@ref.tfs.com> Subject: Re: Why IDE is bad To: rgrimes@gndrsh.aac.dev.com (Rodney W. Grimes) Date: Sat, 25 Mar 1995 18:32:30 -0800 (PST) Cc: teren@lyria.stanford.edu, freebsd-hackers@FreeBSD.org In-Reply-To: <199503260223.SAA08801@gndrsh.aac.dev.com> from "Rodney W. Grimes" at Mar 25, 95 06:23:12 pm Content-Type: text Content-Length: 815 Sender: hackers-owner@FreeBSD.org Precedence: bulk > This last one is the move towards what mainframe systems do. A IBM > I/O channel is only 3MB/sec, but you have many channels in a > typical system. One channel to each DASD controller, often you only > put 1 or 2 drives on a controller (so you don't saturate the channel). > > You often see 8 or 16 channels just for DASD use. I recently tested some performance issues of a VERY big mainframe. Each disk could only do about 2 Mb/sec writes, but they could run "around 50 disks per application" in parallel, they weren't quite sure what the number was or where the limitation was, they had never had a problem with it so far... -- Poul-Henning Kamp -- TRW Financial Systems, Inc. 'All relevant people are pertinent' && 'All rude people are impertinent' => 'no rude people are relevant'