From owner-freebsd-hackers Wed Mar 22 12:19:17 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id MAA13671 for hackers-outgoing; Wed, 22 Mar 1995 12:19:17 -0800 Received: from efn.efn.org (root@efn.org [198.68.17.1]) by freefall.cdrom.com (8.6.10/8.6.6) with SMTP id MAA13665; Wed, 22 Mar 1995 12:19:15 -0800 Received: from haus.efn.org.efn.org by efn.efn.org (4.1/smail2.5/05-07-92) id AA07824; Wed, 22 Mar 95 12:18:06 PST Received: by haus.efn.org.efn.org (4.1/SMI-4.1) id AA15851; Wed, 22 Mar 95 12:18:24 PST Date: Wed, 22 Mar 1995 12:18:24 -0800 (PST) From: John-Mark Gurney To: Poul-Henning Kamp Cc: hackers@FreeBSD.org, faq@FreeBSD.org Subject: Re: Why IDE is bad In-Reply-To: <199503220841.AAA04565@ref.tfs.com> Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: hackers-owner@FreeBSD.org Precedence: bulk On Wed, 22 Mar 1995, Poul-Henning Kamp wrote: > I just made a simple test, this shows why IDE is inferior to SCSI for > FreeBSD: here is my test of IDE using an EIDE disk on a VL/EIDE controler with dual channel... and using the patches submitted a while ago to use 32-bit data transfer of the vl/eide card... > 540868608 bytes transferred in 240 secs (2253619 bytes/sec) > > Here is what "systat" tells me: > 2.0%Sys 82.0%Intr 0.5%User 0.0%Nice 15.6%Idle > | | | | | | | | | | > =+++++++++++++++++++++++++++++++++++++++++ ok... mine was using a Conner CFA-850a (if I remeber right) only 540868608 bytes transferred in 336 secs (1609728 bytes/sec) but on a 486/33DX running at 40... I never passed 14% on system... I don't have intr as I only am using 2.0... and I might add this was under a multiuser system... and the adverage was about 5% sys... it was generating about 3000 inters a second and near then end jumped up to 4000... > > Quantum Empire 2100 SCSI-II disk on VL-buslogic controller: > ------------------------------------------------------------- > dd if=/dev/rsd0d of=/dev/null bs=64k count=8253 > 8253+0 records in > 8253+0 records out > 540868608 bytes transferred in 110 secs (4916987 bytes/sec) > > Here is what "systat" tells me: > 5.6%Sys 20.6%Intr 0.2%User 0.0%Nice 73.6%Idle > | | | | | | | | | | > ===++++++++++ > > CONCLUSION: > ----------- > The SCSI-controller transfers twice as much data in the same time, and > uses only 25% of the CPU resources the IDE-controller needs. was the IDE isa? or using the same footing as the vl/bus SCSI? not to flame or anything... John-Mark Gurney gurney_j@efn.org -or- gurney_j@4j.lane.edu -or- Fido: John-Mark Gurney @ 1:152/56.2