From owner-freebsd-bugs Mon Jun 15 08:44:13 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA01575 for freebsd-bugs-outgoing; Mon, 15 Jun 1998 08:44:13 -0700 (PDT) (envelope-from owner-freebsd-bugs@FreeBSD.ORG) Received: from sumatra.americantv.com (sumatra.americantv.com [207.170.17.37]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA01466 for ; Mon, 15 Jun 1998 08:44:03 -0700 (PDT) (envelope-from jlemon@americantv.com) Received: from right.PCS (right.PCS [148.105.10.31]) by sumatra.americantv.com (8.8.5/8.8.5) with ESMTP id KAA22535; Mon, 15 Jun 1998 10:43:57 -0500 (CDT) Received: (from jlemon@localhost) by right.PCS (8.6.13/8.6.4) id KAA04001; Mon, 15 Jun 1998 10:43:24 -0500 Message-ID: <19980615104323.11642@right.PCS> Date: Mon, 15 Jun 1998 10:43:23 -0500 From: Jonathan Lemon To: Matthew Dillon Cc: freebsd-bugs@FreeBSD.ORG Subject: Re: i386/6944: bug in i386/isa/icu_ipl.s - AST gets lost, causes extreme network slowdown when cpu-bound processes present, possibly other problems References: <199806150210.TAA17801@freefall.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.61.1 In-Reply-To: <199806150210.TAA17801@freefall.freebsd.org>; from Matthew Dillon on Jun 06, 1998 at 07:10:01PM -0700 Sender: owner-freebsd-bugs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Jun 06, 1998 at 07:10:01PM -0700, Matthew Dillon wrote: > The following reply was made to PR i386/6944; it has been noted by GNATS. > > From: Matthew Dillon > To: Bruce Evans > Cc: bde@zeta.org.au, dillon@backplane.com, FreeBSD-gnats-submit@FreeBSD.ORG > Subject: Re: i386/6944: bug in i386/isa/icu_ipl.s - AST gets lost, causes extreme network slowdown when cpu-bound processes present, possibly other problems > Date: Sun, 14 Jun 1998 19:00:43 -0700 (PDT) > > Fubar. I can't reproduce the xterm example on BEST's machines (running > 2.2.6). It's definitely reproduceable on my machine (3.0-current). > > I would like to track down what is causing the problem, so if anyone has > any suggestions on where the cpl can be checked for illegal values, > I'd appreciate it. I'll retest the VM86 removal to make sure that didn't > fix the problem and I'll test the AUTOEOI configs as well. > > As far as I can tell, the only two places where the bug can possibly be > are in the interface driver (pci/if_de.c) or the UDP/IP stack. > I recently observed something similar with doscmd/VM886. When running a cpu-bound process (rc5, for example), the cpl is not being reset to 0 when the doscmd process exits. Breaking to ddb and single-stepping across the iret instruction in doreti will sometimes `reset' the cpl. I'm pretty sure that this isn't a problem with the VM86 code, as I've seen this problem before (cf: doreti_stop in ipl.s), but this also happens even when not attempting to run in vm86 mode. -- Jonathan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-bugs" in the body of the message