From owner-freebsd-hardware Tue Oct 21 20:19:00 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id UAA00575 for hardware-outgoing; Tue, 21 Oct 1997 20:19:00 -0700 (PDT) (envelope-from owner-freebsd-hardware) Received: from fly.HiWAAY.net (root@fly.HiWAAY.net [208.147.154.56]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id UAA00566 for ; Tue, 21 Oct 1997 20:18:56 -0700 (PDT) (envelope-from dkelly@nospam.hiwaay.net) Received: from nospam.hiwaay.net (max4-120.HiWAAY.net [208.147.145.120]) by fly.HiWAAY.net (8.8.7/8.8.6) with ESMTP id WAA04715; Tue, 21 Oct 1997 22:18:48 -0500 (CDT) Received: from localhost (localhost [127.0.0.1]) by nospam.hiwaay.net (8.8.7/8.8.4) with ESMTP id WAA18942; Tue, 21 Oct 1997 22:18:46 -0500 (CDT) Message-Id: <199710220318.WAA18942@nospam.hiwaay.net> X-Mailer: exmh version 2.0zeta 7/24/97 To: Joe McGuckin cc: hardware@FreeBSD.ORG From: dkelly@hiwaay.net Subject: Re: PCI device numbering ? In-reply-to: Message from Joe McGuckin of "Tue, 21 Oct 1997 19:00:50 PDT." <199710220200.TAA29845@monk.via.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 21 Oct 1997 22:18:45 -0500 Sender: owner-freebsd-hardware@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > If I've got multiple PCI cards of the same type installed, > how do I know which is de0, de1, de2, etc. > > Does the numbering begin from one side of the board? On my Asus P6NP5 FreeBSD favors those cards closest to the power supply connector. YMMV. Its documented in the Asus manual. I still got it exactly wrong the first time and had to move some cards. Of a similar note, is there any advantage/disadvantage to sharing IRQ's on PCI? Was initially concerned that my new 9.1G UW IBM HD on an Asus SC875 all by itself wasn't much of a match for an old non-Ultra 7200 RPM 2.1G Seagate Barracuda on an early Adaptec 2940 (AIC-7870). Watched dmesg closely and BIOS boot messages and found my video, SC875 and 2940 were all assigned IRQ 9. Moved one of the SCSI cards to IRQ 11. No improvement in SCSI performance. Then I figured out how to enable write caching on the IBM. Much better! But still the IRQ question lingers. -- David Kelly N4HHE, dkelly@hiwaay.net ===================================================================== The human mind ordinarily operates at only ten percent of its capacity -- the rest is overhead for the operating system.