mrm@sceard.UUCP (M.R.Murphy) (08/22/88)
In article <1677@spdcc.COM> eli@spdcc.COM (Steve Elias) writes: >In <1988Aug15.170727.24258@utzoo.uucp> henry@utzoo.uucp (Henry Spencer) writes: [Some comments deleted...] > > how do you propose to network large groups of buildings > or factories??? not with 802.3 -- the maximum cable length > limitation can't be ignored. > Repeaters, bridges, routers, and gateways can reasonably be used. > do you contend that the 802 standards were made by marketeers ? Widespread use of r,b,r and g should certainly increase revenue of some companies enough to please their marketeers:-) -- Mike Murphy Sceard Systems, Inc. 544 South Pacific St. San Marcos, CA 92069 ARPA: sceard!mrm@nosc.MIL BITNET: MURPHY@UCLACH UUCP: ucsd!sceard!mrm INTERNET: mrm%sceard.UUCP@ucsd.ucsd.edu
wsmith@umn-cs.cs.umn.edu (Warren Smith [Randy]) (08/24/88)
<In article <1988Aug22.170009.4743@utzoo.uucp> henry@utzoo.uucp (Henry Spencer) writes: <>In article <20447@watmath.waterloo.edu> egisin@watmath.waterloo.edu (Eric Gisin) writes: <>>> ... the 802.3 <>>> distance constraints shrink if you raise the bit rate, meaning that it's <>>> not going to work well at FDDI speeds. <>> <>>Is this true? I thought you could either decrease the physical length <>>OR increase the minimum packet size when increasing the bit rate. <> <>That's correct; as I recall it, the constraint is basically that the time <>needed to transmit the shortest possible packet must exceed the worst-case <>round-trip time of the network. The underlying requirement is that a <>collision must be a network-wide phenomenon that all nodes involved with <>a packet will agree on. ... Partially correct. However, you must remember that the increased propagation delay results in an increased likelihood of collisions due to the enlarged time window between the time a transmission is started and before it is heard by all other stations on the network. Here the actual distribution of stations along the network begins to play a part. -- Randy Smith wsmith@umn-csw.cs.umn.edu ...!rutgers!umn-cs!wsmith
morgan@Jessica.stanford.edu (RL "Bob" Morgan) (08/24/88)
I heartily urge everyone who is interested in Ethernet performance and characterization to read the recently released paper "Measured Capacity of an Ethernet: Myths and Reality" by David R. Boggs, Jeffrey C. Mogul, and Christopher A. Kent which was delivered at last week's ACM SIGComm symposium [consider this yet another plug to join the ACM!]. The work was done at DEC's Western Research Lab; I imagine the paper may be available at some point as a technical report from them. Also, I believe the symposium proceedings will come out as an issue of the SIGComm newsletter, which should be at your favorite university library. Quoting from the introduction [by permission of ACM, copyright ACM 1988]: "We first summarize the theoretical studies relevant to Ethernet, and attempt to extract the important lessons from them. Then, based on measurements of actual implementations, we show that for a wide class of applications, Ethernet is capable of carrying its nominal bandwidth of useful traffic, and allocates the bandwidth fairly. We then discuss how implementations can achieve this performance, describe some problems that have arisen in existing implementations, and suggest ways to avoid future problems." Basically, you can get as close as you want to 10 Mbps, and the exponential backoff algorithm really works to keep collisions low and maximum delay reasonable, even on a maximum-length net. - RL "Bob" Morgan Networking Systems Stanford