From owner-freebsd-current Mon Aug 17 04:14:05 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id EAA23592 for freebsd-current-outgoing; Mon, 17 Aug 1998 04:14:05 -0700 (PDT) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from alushta.NL.net (alushta.NL.net [193.78.240.22]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id EAA23587 for ; Mon, 17 Aug 1998 04:14:02 -0700 (PDT) (envelope-from paulz@trantor.stuyts.nl) Received: from stuyts by alushta.NL.net with UUCP id <4329-4659>; Mon, 17 Aug 1998 13:13:09 +0200 Received: from trantor.stuyts.nl (uucp@localhost) by terminus.stuyts.nl (8.9.1/8.8.8) with UUCP id NAA17846 for current@FreeBSD.ORG; Mon, 17 Aug 1998 13:10:31 +0200 (MET DST) (envelope-from paulz@trantor.stuyts.nl) Received: from trantor.stuyts.nl (localhost [127.0.0.1]) by trantor.stuyts.nl (8.9.1/8.8.5) with ESMTP id NAA23662 for ; Mon, 17 Aug 1998 13:04:54 +0200 (MET DST) Message-Id: <199808171104.NAA23662@trantor.stuyts.nl> X-Mailer: exmh version 2.0.2 2/24/98 To: current@FreeBSD.ORG Subject: Cards sharing irq's on PCI bus Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 17 Aug 1998 13:04:53 +0200 From: Paul van der Zwan Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG I am running very low on available irq's and I noticed that the bios put both my SMC 8432BT and my Adaptec 2740 on irq 9. Network performance was terrible, iozone on NFS only 300kB/s. After disabling my IDE controller (only need that when running Solaris) the Adaptrec was put on irq 14 (where the IDE used to be) and my network performance was back ( more than 900kB/s). Is it allowed to put have more than one PCI card use the same irq ??? It sort of worked. No errors or so, just lousy performance ?? Maybe someone can shed some light on this ?? Paul -- Paul van der Zwan paulz @ trantor.stuyts.nl "I think I'll move to theory, everything works in theory..." To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message