- From: John Franks <john@math.nwu.edu>
- Date: Fri, 16 Dec 1994 16:05:33 -0600 (CST)
- To: Simon E Spero <ses@tipper.oit.unc.edu>
- Cc: john@math.nwu.edu, dmk@allegra.att.com, http-wg%cuckoo.hpl.hp.com@hplb.hpl.hp.com
According to Simon E Spero: > The perceived performance of Netscape is merely a function of their > rendering order. Netscape renders GIFS as they come in. THis is completely > independent of the protocol. I think the perceived performance of Netscape is a function of doing the layout and displaying the text *before* the images are downloaded. This is not completely independent of the protocol. It is also a function of being able to jump to a new link before all the downloads are finished (and hence abort all those downloads). > > The netscape approach of stealing other peoples bandwidth is > ultimately a negative sum game. If more and more people start using > this approach, not only will the netscape user not see any benefit, > but *EVERYBODY* will lose as more and more bandwidth becomes lost to > retransmission. > > If I wanted to get better performance by stealing bandwidth, I'd just > write my own transport protocol. Just run blast datagrams out as UDP > as fast as your interface can handle it, and ack every single > message. Hell, use a regenerative protocol and send everything > multiple times. You'll clear every TCP user off the routers in your > path and get the backbone for yourself. > I was, by chance, just looking a Eric Bina's home page where he discusses getting the FLAME OF THE MONTH award. I fear Simon may be in the competition this month. I am not sure what he means by "stealing other people's bandwidth." If I only use lynx and my viewing is slowed because I share the bandwidth with people who have a lot of images, are they stealing my bandwidth? John Franks
Received on Friday, 16 December 1994 14:07:15 UTC