Date: Wed, 30 Jul 1997 13:01:39 +0000 (GMT) From: Jason Young <doogie@forbidden-donut.anet-stl.com> To: john hood <cgull@smoke.marlboro.vt.us> Cc: Søren Schmidt <sos@sos.freebsd.dk>, freebsd-current@FreeBSD.ORG Subject: Re: code talks: announcing EIDE bus master patches Message-ID: <Pine.BSF.3.96.970730130024.28527E-100000@forbidden-donut.anet-stl.com> In-Reply-To: <199707301049.GAA03660@smoke.marlboro.vt.us>
next in thread | previous in thread | raw e-mail | index | archive | help
-----BEGIN PGP SIGNED MESSAGE----- On Wed, 30 Jul 1997, john hood wrote: > Jason Young writes: > > I'm not sure what this driver did to my 1GB Seagate, but all I have to say > > is buy this man a beer. :) The machine: AMD 5x86-133, 1GB seagate and > > 1.2GB WD EIDE drives, 32MB RAM. I ran these stats several times on an > > idle system without appreciable changes each time I ran them. > > well, i won't pass up a free beer, but my code didn't do it. :) > > you have a 486-class machine that doesn't have busmastering IDE. it's > not even a PCI bus machine. you just happened to turn on the > already-existing multi-block and 32-bit PIO flags in your latest > kernel upgrade. > > folks: performance with the default flags on the wd driver is > *terrible*, and the flags should always be configured for your > machine. see LINT for details. Yes it's 486-class, but it has a PCI bus. Otherwise I wouldn't have bothered with the code. Jason Young ANET Technical Staff -----BEGIN PGP SIGNATURE----- Version: 2.6.2 iQB1AwUBM987NKInE6ybC66VAQHk8gL/RSH6lWWQPohVgOcemrZzIxA7F2v8CeJx 4ZTMf6+REPc6ZFF/RjZGRQhfZQqCnVPOWRCgZ5P9uDLYoaNDRU77UGnGCvzutQyb kyjppH+XeYx/vaJGQWMBauVRuN7n1KbO =blN9 -----END PGP SIGNATURE-----
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.96.970730130024.28527E-100000>