From owner-freebsd-hackers Tue Oct 10 18:47:12 1995 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.6.12/8.6.6) id SAA16311 for hackers-outgoing; Tue, 10 Oct 1995 18:47:12 -0700 Received: from kryten.atinc.com (kryten.Atinc.COM [198.138.38.7]) by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id SAA16306 for ; Tue, 10 Oct 1995 18:47:06 -0700 Received: (jmb@localhost) by kryten.atinc.com (8.6.9/8.3) id VAA21309; Tue, 10 Oct 1995 21:34:45 -0400 Date: Tue, 10 Oct 1995 21:34:43 -0400 (EDT) From: "Jonathan M. Bresler" Subject: Re: VLB Disk Controllers To: Bruce Evans cc: chuckr@eng.umd.edu, se@ZPR.Uni-Koeln.DE, hackers@FreeBSD.org In-Reply-To: <199510100147.LAA32670@godzilla.zeta.org.au> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hackers@FreeBSD.org Precedence: bulk On Tue, 10 Oct 1995, Bruce Evans wrote: > Testing /dev/sd0 tests the buffer cache and shouldn't go anywhere near > the driver or the drive. There may be more variance because running > the program (not to mention other processes) disturbs the buffer cache. > /dev/sd0 is about twice as slow as /dev/zero here, but the "command" > overhead is about twice as small for /dev/sd0. i get /dev/zero nearly 3x slower than /dev/sd0 144 vs 50 /dev/rsd0 is much slower. ./disklatency /dev/zero Command overhead is 144 usec (time_4096 = 235, time_8192 = 326) transfer speed is 4.50987e+07 bytes/sec Aspen: {232} ^zero^sd0 ./disklatency /dev/sd0 Command overhead is 50 usec (time_4096 = 245, time_8192 = 441) transfer speed is 2.0966e+07 bytes/sec Aspen: {233} ^sd0^rsd0 ./disklatency /dev/rsd0 Command overhead is 1169 usec (time_4096 = 1696, time_8192 = 2222) transfer speed is 7.78268e+06 bytes/sec > > Bruce > Jonathan M. Bresler jmb@kryten.atinc.com | Analysis & Technology, Inc. FreeBSD Postmaster jmb@FreeBSD.Org | 2341 Jeff Davis Hwy play go. | Arlington, VA 22202 ride bike. hack FreeBSD.--ah the good life | 703-418-2800 x346