From owner-freebsd-current Wed Mar 4 20:00:50 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id UAA18449 for freebsd-current-outgoing; Wed, 4 Mar 1998 20:00:50 -0800 (PST) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from dingo.cdrom.com (dingo.cdrom.com [204.216.28.145]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id UAA18432 for ; Wed, 4 Mar 1998 20:00:39 -0800 (PST) (envelope-from mike@dingo.cdrom.com) Received: from dingo.cdrom.com (localhost [127.0.0.1]) by dingo.cdrom.com (8.8.8/8.8.5) with ESMTP id TAA24001; Wed, 4 Mar 1998 19:57:40 -0800 (PST) Message-Id: <199803050357.TAA24001@dingo.cdrom.com> X-Mailer: exmh version 2.0zeta 7/24/97 To: Stephen McKay cc: Simon Shapiro , current@FreeBSD.ORG Subject: Re: silo overflows (Was Re: 3.0-RELEASE?) In-reply-to: Your message of "Thu, 05 Mar 1998 13:41:44 +1000." <199803050341.NAA08541@troll.dtir.qld.gov.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 04 Mar 1998 19:57:39 -0800 From: Mike Smith Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > Do you have a Matrox Millennium? I borrowed a Matrox Millennium II for > a while and put it in my Pentium 133 box. Suddenly I got silo overflows > when there was simultaneous incoming serial data and X activity (like > scrolling a 60 line xterm window). When I returned the Millennium and > put my Trio64V+ card back in, all serial problems disappeared. At the time, > I was running the serial port at only 38400, but now run it at 115200 with > no problems. > > I didn't do enough investigation to even guess at the cause. I looked in > the XFree86 server code for interrupt disabling but found nothing interesting. Does the server disable interrupts for extended periods of time? > I was wondering though if any PCI experts knew if a PCI video card could > starve the PCI-ISA bridge of cycles. Any experts out there? It's quite possible; it would depend on the PCI latency timer settings, but generally the latency provided for there is only of the order of a few microseconds. I would be more interested in knowing whether the X server did interrupt-related things specific to the Matrox driver... -- \\ Sometimes you're ahead, \\ Mike Smith \\ sometimes you're behind. \\ mike@smith.net.au \\ The race is long, and in the \\ msmith@freebsd.org \\ end it's only with yourself. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message