From owner-freebsd-hackers Sun Nov 21 17:26:54 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from etinc.com (et-gw.etinc.com [207.252.1.2]) by hub.freebsd.org (Postfix) with ESMTP id 88F7114F53 for ; Sun, 21 Nov 1999 17:26:52 -0800 (PST) (envelope-from dennis@etinc.com) Received: from workstation.etinc.com (port51.netsvr1.cst.vastnet.net [207.252.73.51]) by etinc.com (8.9.3/8.9.3) with SMTP id UAA28430; Sun, 21 Nov 1999 20:27:00 -0500 (EST) Message-Id: <199911220127.UAA28430@etinc.com> X-Sender: dennis@mail.etinc.com X-Mailer: QUALCOMM Windows Eudora Pro Version 4.0 Date: Mon, 22 Nov 1999 08:47:28 -0500 To: Mike Smith From: Dennis Subject: Re: PCI DMA lockups in 3.2 (3.3 maybe?) Cc: hackers@freebsd.org In-Reply-To: <199911212021.MAA03537@dingo.cdrom.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG At 12:21 PM 11/21/99 -0800, you wrote: >> At 09:15 PM 11/20/99 -0800, Mike Smith wrote: >> >> I'll test this in 3.3 shortly...has anything been done in this area? It >> >> seems to happen on passive backplace systems (although its more likely the >> >> chipsets used on SBCs)...my acer MB doesnt lock up with the same test. This >> >> problem has been duplicated on more than 1 system with completely different >> >> hardware. >> >> >> >> Any ideas? >> > >> >Nope. You haven't given anything like enough information to even guess >> >at the nature of the problem. >> >> And what additional info, short of putting a scope on the bus, may I >> provide you? > >Anything that might help locating the nature of the "lockup". A scope >on the bus would be helpful, sure. Some idea where in the kernel the >CPU was executing would be good. The values of cpl and ipending are >always informative. > >Basically though, you're saying "I have a problem with an old version of >freebsd on some sorts of hardware. Is it fixed?". There's no possible >way for anyone else to answer such a totally vague question. Its a late 3.2-STABLE. so its not that old. Surely someone knows if something in this area was fixed or not? Since its a DMA lockup, how would you suggest that the informatoin about what instruction was executing be obtained? The nightmare of instability of 3.x continues whilst the braintrust flogs away at 4.x. Its really a damn shame. And why is 3.x so much slower than 2.2.8? Will 4.0 be slower yet? DB To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message