Date: Fri, 16 May 1997 17:02:13 -0400 (EDT) From: Ben Black <black@zen.cypher.net> To: Chuck Robey <chuckr@glue.umd.edu> Cc: Mark Tinguely <tinguely@plains.nodak.edu>, sthaug@nethelp.no, hackers@FreeBSD.ORG Subject: Re: Why use ATM, (was Cluster Computing in BSD) Message-ID: <Pine.LNX.3.91.970516165929.15056C-100000@zen.cypher.net> In-Reply-To: <Pine.BSF.3.91.970516171733.7298E-100000@Journey2.mat.net>
next in thread | previous in thread | raw e-mail | index | archive | help
you ignored part of what he said. PPP over SONET is the competition he refers to for ATM. it makes far better use of resources and is a lot less complex to use. the downside is that it is not cell-based so mixing all sorts of different traffic (voice, video, IP) is not as well supported, but i am guessing you can put ATM cells in SONET frames and pump them accross a SONET link even if it is also handling IP...current hardware may not support this and it may be more difficult than i suspect. b3n On Fri, 16 May 1997, Chuck Robey wrote: > On Fri, 16 May 1997, Mark Tinguely wrote: > > > Steinar Haug says: > > > I haven't seen any sign of inexpensive 155 Mbps ATM NICs, why do you > > > think inexpensive 622 Mbps ones are coming soon? > > > > they are coming down in price, but not nearly low enough to be mainstream. > > the cheapest cards are the ones that use host memory for packet segmentation > > and re-assembly. I wish I had a performance study to see how much speed > > is lost using host memory for SAR operations. > > > > Ben Black asks: > > > and why would you want to use something as inefficient as ATM for a > > > cluster interconnect? > > > > in-efficiency is not a concern problem IF the end result is faster than > > anything else on the market. ATM, lost that window of opportunity and today > > is not the fastest thing on the market because everone wants IP. I think even > > Sonet PPP/frame relay will upstage ATM. > > This confuses me somewhat. Let me detail what confuses me. > > You say that ATM is losing out to ip and (perhaps) to Sonet. This is > juggling the protocol levels badly in my mind, because SONET is a link > level protocol (so it isn't encapsulateable by anything), while ATM > isn't, it needs a link level protocol to ride on. What I'm saying, is I > don't think that ATM can be in competition with SONET; that's why your > statement confuses me. > > On top of that, I thought that ATM was being used as a way to link LANs, > so ip would be routed over ATM links, and again, not competitive. You > could conceivably have a SONET link that had an ATM constituent, which > was carrying an ip message inside it. That's the way I understood it, > and that example was (supposedly) fairly common, at least as common as > SONET itself is. > > Where am I wrong? > > > > > yeah, this prob. belongs in -chat or -atm. > > > > --mark. > > > > > > ----------------------------+----------------------------------------------- > Chuck Robey | Interests include any kind of voice or data > chuckr@eng.umd.edu | communications topic, C programming, and Unix. > 9120 Edmonston Ct #302 | > Greenbelt, MD 20770 | I run Journey2 and picnic, both FreeBSD > (301) 220-2114 | version 3.0 current -- and great FUN! > ----------------------------+----------------------------------------------- >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.LNX.3.91.970516165929.15056C-100000>