From owner-freebsd-hackers Tue Dec 16 17:14:24 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id RAA19148 for hackers-outgoing; Tue, 16 Dec 1997 17:14:24 -0800 (PST) (envelope-from owner-freebsd-hackers) Received: from freebie.lemis.com (gregl1.lnk.telstra.net [139.130.136.133]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id RAA18589 for ; Tue, 16 Dec 1997 17:08:30 -0800 (PST) (envelope-from grog@lemis.com) Received: (from grog@localhost) by freebie.lemis.com (8.8.8/8.8.7) id LAA27601; Wed, 17 Dec 1997 11:38:01 +1030 (CST) (envelope-from grog) Message-ID: <19971217113801.53802@lemis.com> Date: Wed, 17 Dec 1997 11:38:01 +1030 From: Greg Lehey To: Mike Smith Cc: John Kelly , FreeBSD Hackers Subject: Re: 3com 3c509 card References: <34974fcb.31632460@mail.cetlink.net> <199712162352.KAA00272@word.smith.net.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.84e In-Reply-To: <199712162352.KAA00272@word.smith.net.au>; from Mike Smith on Wed, Dec 17, 1997 at 10:22:42AM +1030 Organisation: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 WWW-Home-Page: http://www.lemis.com/~grog Sender: owner-freebsd-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Wed, Dec 17, 1997 at 10:22:42AM +1030, Mike Smith wrote: >> On Tue, 16 Dec 1997 19:10:50 +1030, Mike Smith >> wrote: >> >>>> I replaced an NE2000 clone with a SMC Ultra 16, thinking shared memory >>>> would consume far less CPU than PIO with an NE2000. But it seems to >>>> be about the same. >>> >>> About half. Please don't confuse anecdotal evidence with measured >>> results. >>> >> >> I tested with an FTP transfer and consumed about 45% CPU in both >> cases. >> >> I wonder if I'm doing something wrong. > > Well, for starters you aren't disclosing your measurement technique. > It sounds to me as though it's not measuring the relative CPU consumed > per bytes/datagrams transferred by the driver though. > > All you have established is that a known ~50% improvement in the CPU > utilisation of the driver has not affected the amount of CPU used for > your FTP transfer. This should tell you something about how efficient > the driver is in the first place, especially compared with the other > operations involved in the transfer. > > First thing anyone should learn; how to measure things. Whether you're > talking engineering, physics, chemistry or computing; if you don't know > what you're measuring, the numbers mean nothing. It's easy to say that sort of thing. Now how about explaining what he should be looking for? I've been doing some experiments with ftps on my local network, but the results have been puzzling, and until I know what's going on, I'm not going to go into too much detail. But I've noticed that I'm getting very high interrupt times on a P5/133 (up to over 50%) when receiving large files (40 MB). I've also noticed that the transfer starts at about 1 MB/s, but after about 10 MB there are problems, and the final transfer rate is often less than 500 kB/s. This is not what I measured on the same systems about a year ago. I may follow up on this if I find time. Greg