home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!usc!isi.edu!finn
- From: finn@isi.edu (Greg Finn)
- Newsgroups: comp.dcom.cell-relay
- Subject: Re: Curious attitude ...
- Message-ID: <22075@venera.isi.edu>
- Date: 29 Jul 92 21:42:31 GMT
- References: <1992Jul29.164110.1@research.ptt.nl>
- Sender: news@isi.edu
- Reply-To: finn@dalek.isi.edu (Greg Finn)
- Organization: USC-Information Sciences Institute
- Lines: 21
-
- In article <1992Jul29.164110.1@research.ptt.nl> walvdrk@research.ptt.nl (Kees van der Wal +31 70 332 6295) writes:
-
- >Well, compression helps ... but also takes some time. If there's delay in the
- >transmitting coding, propagation delay and decoding delay, there's not much to
- >spend on queueing delay in the network if the "target" of 50-100ms is to be
- >reached.
-
- I asked. The current system's transcontinental round-trip
- end-to-end ping packets during teleconferencing return in about 60ms.
- One way, the compressed video packets have a delay of about 50ms.
- Compression is done by hardware and I would assumed is pipelined.
-
- This points out what can be done with prototype teleconference
- systems already over a 1.34 Mb/s IP based data network. I wouldn't
- claim that it is a commercial system. We don't build those. We do
- research. Our concerns are technology development and demonstration.
- We use vanilla SPARC IPC routers the size of a Webster's Collegiate
- and commercial T1 DSU/CSUs.
- --
- Gregory Finn (310) 822-1511
- Information Sciences Institute, Marina Del Rey, CA 90292
-