Re: OR/U's versus Pipeline 75 (fwd)

Jake Messinger (jake@ams.com)
Wed, 21 May 1997 07:37:09 -0500 (CDT)

On Tue, 20 May 1997, MegaZone wrote:

> Once upon a time Al Hopper shaped the electrons to say...
> >OK I just don't get it! Lets say you get an average of 2:1 compression
>
> You won't in the real world.

HTML code compresses great!

> >using compression on a TCP/IP connection. Why would you _not_ want 2:1
> >compression on a T-1 link? Whats the alternative - get another T1
>
> Compression introduces latency. The more data you try to compress, the
> worse it will get.

It would be better to have 24 small compressed channels than 1 large
uncompressed channel dont you think?
>
> You will also eventually overwhelm the CPU. It is widely accepted that
> trying to compress a full T1 is a *bad* idea.
>
> It doesn't work the same way on a line that is highly utilized. There are
> know statistics on dialin usage, etc. You design for those. Trying to
> deal with a full T1 that is stuffed full of data is different from dealing
> with 23 B channels all being used by dialin users.

Right. If the data is streaming, when do you tell the router to stop, make
a compressed packet, then continue? Especially if the data is already
random, or compressed as in the case of mpeg. The compression would slow
things down.

> It would raise the HW costs significantly to give it the kind of horsepower
> needed. And it would introduce latency - which is the bane of any
> interactive application. Latency is the number one problem for gaming for
> instance.

Im latent for work! Gotta go!

~*-,._.,-*~'`^`'~*-,._.,-*~'`^`'~*-,._.,-*~'`^`'~*-,._.,-*~'`^`'~*-,._.,-*~
Jake Messinger 713-772-6690 jake@ams.com
Advanced Medical Systems, Inc. jake@uh.edu
9919 S. Gessner #201
Houston, Texas 77071 http://www.ams.com/~jake
~*-,._.,-*~'`^`'~*-,._.,-*~'`^`'~*-,._.,-*~'`^`'~*-,._.,-*~'`^`'~*-,._.,-*~