kenw@noah.arc.CDN (Ken Wallewein) (10/13/88)
I keep hearing about people saying LocalTalk is slow. Frankly, I'm
skeptical.
Think about it. LocalTalk is rated at about 230 Kbps -- about the same as a
floppy disk drive, but without seek and skew latency delays. It works out to
about 28 Kbytes per second.
Even at 50% of optimum throughput, a person should be a able to launch an
application via LocalTalk in about a third of the time it seems to take from a
floppy disk.
I've been doing a little checking, comparing different kinds of sources.
Here are informal, approximate times to launch MacWrite. Note: these are
_approximate_ times only!
15 Floppy disk drive (800 K on Mac Plus)
20 Corvus Omnidrive (note: has 38 Kbaud bottleneck)
30 Pacer Via Kinetics Fastpath 3 to MicroVax II
~10 Mac Se <==(Localtalk)==> Mac II
<==(Northern Telecom's Meridian Lanstar @ 2Mb/sec)==> ?Server
I haven't yet timed AlisaTalk, Tops, a Mac-based Appleshare server, or
anything using Ethernet.
However, the figures I have so far seem to indicate that _nobody_ saturates
LocalTalk, and that the bottleneck may well be in the gateway. There are
rumours that Kinetics KFPS-4s are somewhat faster.
I'd be most interested in hearing other people's test results.
/kenw
A L B E R T A
Ken Wallewein R E S E A R C H
kenw@noah.arc.cdn C O U N C I Lminshall@kinetics.UUCP (Greg Minshall) (10/22/88)
From article <964*kenw@noah.arc.cdn>, by kenw@noah.arc.CDN (Ken Wallewein): > > I keep hearing about people saying LocalTalk is slow. Frankly, I'm > skeptical. ... > I've been doing a little checking, comparing different kinds of sources. > Here are informal, approximate times to launch MacWrite. Note: these are > _approximate_ times only! > > 15 Floppy disk drive (800 K on Mac Plus) > 20 Corvus Omnidrive (note: has 38 Kbaud bottleneck) > 30 Pacer Via Kinetics Fastpath 3 to MicroVax II > ~10 Mac Se <==(Localtalk)==> Mac II > <==(Northern Telecom's Meridian Lanstar @ 2Mb/sec)==> ?Server ... > However, the figures I have so far seem to indicate that _nobody_ saturates > LocalTalk, and that the bottleneck may well be in the gateway. There are > rumours that Kinetics KFPS-4s are somewhat faster. I've seen LocalTalk (thru a FastPath) run up to 18 Kbytes/second (of "useful" data). Needless to say, there is more to performance than just the speed of the wire. For example, block size, window size, etc., all have a large effect. I just tried launching MacWrite: ~10 MacII via Kinetics Fastpath 4 to MacII server. ~5 MacII via Ethernet to MacII server. Possibly your Pacer connection is a bit slow as a result of process switches on the MicroVax II? Greg Minshall
paul@unisoft.UUCP (n) (10/26/88)
In article <639@kinetics.UUCP> minshall@kinetics.UUCP (Greg Minshall) writes: >From article <964*kenw@noah.arc.cdn>, by kenw@noah.arc.CDN (Ken Wallewein): >> >> I keep hearing about people saying LocalTalk is slow. Frankly, I'm >> skeptical. > > I've seen LocalTalk (thru a FastPath) run up to 18 Kbytes/second >(of "useful" data). Needless to say, there is more to performance than just >the speed of the wire. For example, block size, window size, etc., all >have a large effect. I run UUCP over LocalTalk (don't ask why :-) .... it runs on top of ATP, it's a relatively noise-free net so retries are at a minimum. I sometimes see data rates over 100k. The main reason for this is that I can do 8 (large) packet writes across the net (I also have hardware that will buffer upto 25 Localtalk packets so I can do disk IO at the same time as transmission and reception, and the Unix buffer cache etc that does delayed writes and read ahead for me). The main reason for posting this is to point out that it is possible to claim a large part of the LocalTalk bandwidth without really trying hard (in fact I spent some time thinking about ways to detect when the net was getting full so UUCP could throttle itself down a bit - it doesn't really care about real-time response - anyone got any ideas - I thought of collecting collision rate information and averaging over time). Paul PS: if anyone else is crazy enough to want to run UUCP over AppleTalk, I'm willing to give away my sources (at least the parts that don't belong to AT&T - ie the ones for the protocol) just so we don't end up with multiple protocols for doing the same thing -- Paul Campbell, UniSoft Corp. 6121 Hollis, Emeryville, Ca ..ucbvax!unisoft!paul Nothing here represents the opinions of UniSoft or its employees (except me) "Where was George?" - Nudge, nudge say no more
spector@vx2.NYU.EDU (David HM Spector) (10/26/88)
Yes!! Please post the sources!!!
_DHMS
-------------------------------------------------------------------------------
David HM Spector New York University
Senior Systems Programmer Stern School of Business
ARPAnet: SPECTOR@GBA.NYU.EDU Academic Computing Center
USEnet:...!{allegra,rocky,harvard}!cmcl2!spector 90 Trinity Place, Rm C-4
HamRadio: N2BCA MCIMail: DSpector New York, New York 10006
AppleLink: D1161 CompuServe: 71260,1410 (212) 285-6080
"Capital punishment is our society's recognition of the sanctity of human life"
- Senator Orrin Hatchcrum@lipari.usc.edu (Gary L. Crum) (10/29/88)
Has anyone out there used DaynaTalk yet? I want to know if it works with gateways such as the KFPS and Gatorbox products. I also want to know about throughput and if the transfer rate between a sending node with DaynaTalk and a receiving node without DaynaTalk is affected (i.e., does buying one for only the server or gateway and not all LocalTalk nodes help any?). DaynaTalk is a LocalTalk hardware enhancement that, acording to the Byte review of MacExpo (Byte, Nov 1988, p140), speeds up LocalTalk data transmission rate, to 850Kbps for Macintosh nodes and 1.7Mbps for PC nodes. I haven't communicated with Dayna yet. Dayna Communications, Inc. 50 South Main St., Fifth Floor Salt Lake City, UT 84144 /* Ski Utah! */ (801)531-0203 Gary crum@cse.usc.edu