From owner-freebsd-hardware Sat Aug 15 21:08:46 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id VAA27390 for freebsd-hardware-outgoing; Sat, 15 Aug 1998 21:08:46 -0700 (PDT) (envelope-from owner-freebsd-hardware@FreeBSD.ORG) Received: from mindcrime.termfrost.org (mindcrime.termfrost.org [208.141.2.81]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id VAA27376 for ; Sat, 15 Aug 1998 21:08:42 -0700 (PDT) (envelope-from mandrews@termfrost.org) Received: from localhost (mandrews@localhost) by mindcrime.termfrost.org (8.9.1/8.9.1/mindcrime-19980706) with SMTP id AAA24586; Sun, 16 Aug 1998 00:07:57 -0400 (EDT) (envelope-from mandrews@termfrost.org) Date: Sun, 16 Aug 1998 00:07:57 -0400 (EDT) From: Mike Andrews To: "Christopher R. Bowman" cc: freebsd-hardware@FreeBSD.ORG Subject: Re: DEC Tulip sluggishness on a 486 In-Reply-To: <199808160503.AAA08701@quark.ChrisBowman.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hardware@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sat, 15 Aug 1998, Christopher R. Bowman wrote: > At 08:04 PM 8/15/98 , Mike Andrews wrote: > >Here's a weird one... > > > >I've been using an old 386SX for a few years to route my home network, > >using two SMC Ultras and a full-length Wavelan with no problems. Today I > >decided to add 100baseTX to the mix, so I pulled out an old 486 PCI board > >(SiS 85c496 + 85c497 chipset), pulled all the guts out of the 386SX, added > >a DEC Tulip 21140-AB card and fired it up. > > > >I'm getting really *horrible* performance out of this. Pinging between > >machines on the same segment sometimes gives over 1000 ms ping times, 30% > >packet loss, and sometimes doesn't talk at all -- ifconfig shows the > >OACTIVE flag set, and it usually takes a few tries of "ifconfig de0 down; > >ifconfig de0 up" to wake it up. Sometimes plugging/unplugging the cable > >helps too. [snip] > > Is this a duplex negotiation problem? Try manually configing the dec > adaptor into the propper duplexing mode. Let me know how this works. It's running half duplex. I've got "media 100baseTX" in rc.conf just to make sure it doesn't drop to 10. (It's a cheapo Linksys 5 port 100baseTX hub, which doesn't do full duplex.) Actually, I lied earlier about having tried turning the cache off. (I meant to send the message after I'd really tried it. :) I'm running with both L1 and L2 caches turned off and it's now behaving itself (though now the machine is of course dog slow :) I'll try turning L1 back on tomorrow to see if it breaks again. But my current theory is that the SiS 486 PCI chipset on this board is screwed up and can't cope with the traffic coming off the card or something... Mike Andrews (MA12) icq 6602506 -------------- mandrews@dcr.net Senior Systems/Network Administrator --- mandrews@termfrost.org Digital Crescent, Frankfort, KY ----- http://www.termfrost.org/ "If Barbie is so popular, why do you have to buy her friends?..." To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message