Date: Wed, 29 Jan 1997 09:31:49 -0600 (CST) From: jpt@msc.edu (Joseph Thomas) To: dg@root.com Cc: jpt@msc.edu, danny@panda.hilink.com.au, shovey@buffnet.net, robert@nanguo.chalmers.com.au, freebsd-isp@freebsd.org, hackers@freebsd.org Subject: Re: RFC 1323 default settings (was Re: progress report on connection problems) Message-ID: <199701291531.JAA11228@ww.msc.edu> In-Reply-To: <199701290030.QAA17983@root.com> from "David Greenman" at Jan 28, 97 04:30:11 pm
next in thread | previous in thread | raw e-mail | index | archive | help
> > > As a data point - running a local-area ATM with "out of the box" > >parameters (for 2.2 this looks to be 16K windows with no-scaling), I get > >60 KB/s out of the box vs 3.0-3.5 MB/s into the box, [notice the really > > Yikes, that's really awful. What kind of round-trip times are you seeing? > > -DG > > David Greenman > Core-team/Principal Architect, The FreeBSD Project > Transmitter: - 133 MHz Pentium, 32 MB RAM - FreeBSD 2.2-960801-SNAP - FORE PCA200E OC3c adapter - HARP ATM software (http://www.msci.magic.net) - <3C507 R1> ethernet Receiver: - SGI Challenge XL - IRIX64 6.2 03131016 - 2 150 MHZ IP19 Processors - 128 MB RAM, 2-way interleaved - FORE VMA200E OC3c adapter - FORE Systems Release: irix62_A_ForeThought_4.0.2 (1.13) - Integral Ethernet controller: et0 (IO4 card) - Initial packet (Max.) includes ARP time and call setup for ATM ATM: - both parties connected to FORE ASX-200BX - UNI 3.0 - AAL5 - LLC SNAP encapsulation - MSS 9140 (9180 MTU) With ARP and call setup: --- 198.207.143.4 ping statistics --- 101 packets transmitted, 101 packets received, 0% packet loss round-trip min/avg/max = 0.782/1.041/16.027 ms Without ARP and call setup: --- 198.207.143.4 ping statistics --- 101 packets transmitted, 101 packets received, 0% packet loss round-trip min/avg/max = 0.801/0.898/1.349 ms ETHERNET: - parties connected to different 10BaseT hubs - same subnet, no routing - MSS 1460 (1500 MTU) --- 137.66.176.4 ping statistics --- 101 packets transmitted, 101 packets received, 0% packet loss round-trip min/avg/max = 0.939/0.972/2.041 ms Now, that being said, I'm not ready to start pointing fingers at anything yet. It should be noted that using TTCP with window scaling and going to large socket buffers, I've seen 68.58 Mbits out of the machine, and 96.97 Mbits into the machine. I have not run the simple ftp test over ethernet, nor have I looked into why the ATM transmit is so slow. [We're gennerally pretty good at figuring this stuff out, we do it alot over wide-area ATM, including links with satellites.] I really need to do some more investigation of the ATM software, as well as repeat the tests using ethernet. [I should be receiving another pentium machine in the near future. I'm trying to arrange for a second ATM card, as well as some 100Mbit ethernet cards.] My point in the post was only to provide a data point that perhaps we (being the FreeBSD community) ought to think and ask more questions before taking the easy road of "turn it off." [Not that this might not be the correct answer.] It would be more work to go back later and say "opps, we solved the wrong problem and need to turn extensions back on as the default." Anyways... like I said, just a data point for consideration... -- Joseph Thomas E/Mail: jpt@msc.edu Minnesota Supercomputer Center, Inc. jpt@magic.net 1200 Washington Ave So. Tel: +1 612 337 3558 Minneapolis, MN 55415-1227 FAX: +1 612 337 3400 You cannot see what I see because you see what you see. You cannot know what I know because you know what you know. "Mostly Harmless" - Douglas Adams
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199701291531.JAA11228>