Re: Improving traffic condition@inet

_Betreff : Re: Improve the traffic condition on the Internet
_Arrival : 21-03-1996 01:17:06
(Benjamin Franz S@N)
S@N> On Wed, 20 Mar 1996, Gao Hong wrote:
S@N> >
S@N> > I have an idea about improving the traffic condition on the Internet.  W
S@N> > I mean we define a compress standard using on the internet.  [...]
S@N> The fundamental idea is sound - but the reality is that the vast majority 
S@N> traffic *is* already compressed. Additional attempts at compression are
S@N> simply not going to provide much improvment in the current situation.
S@N> At (serving tens of thousands of web pages by a few
S@N> thousand different people), yesterday's traffic top three byte count
S@N> categories (from a total of files transfered of 640,628
S@N> and total bytes transfered of 6,083,382,508) were:
S@N> Hits    Bytes         File type
S@N> ======  ==========    =================
S@N> 207994  2483328017    jpg graphic files
S@N> 184952  1399457986    html files
S@N> 181799  1248240540    gif graphic files
and that's only a part of the whole internet byte-chaos.
The only we might be able to do is to compress ALL html-pages.
(As You know there are text-only.)
But that would be a new standard. (html 4 pro? :-) )
S@N> Neither the jpg nor gif files can be ... compressed [...]
I suggest that the gif files have to been compressed, too.
The quality doesn't decrease very much... but the quantity does.
S@N> are already, so that pretty much leaves the html files. Assuming a 75%
S@N> compression of the html files on the average (a not too unreasonable figur
S@N> for English text - does anyone have average compression figures for the JI
S@N> family of text encoding?), the *net* savings would be only around 20% of t
S@N> total byte count. This is because html files only represent about 1/4 of t
S@N> traffic right now.
and: "step by step"
and: all is bet...
S@N> The fact is that page authors are in fact making *excellent* use of
S@N> compression in general and files are being kept quite small individually.
S@N> The average size of a jpg in the sample was only 11.9 Kbytes, the average
S@N> size of gif files was 6.8 Kbytes, the average size of an html file was
S@N> 7.5 Kbytes.
S@N> Finally, at the rate of growth of the net today, a savings of 20% in
S@N> total traffic would just be 'setting back the clock' by about two
S@N> or three months. It is a stopgap, not a solution to the fundamental
S@N> scaling problem of everyone accessing resources directly.
S@N> A much more effective approach would be the widespread deployment of
S@N> hierarchial proxy servers and large scale trans-continental mirroring of
S@N> sites to keep most accesses relatively local. Not that it would help that
S@N> much with the recent (non) performance of MCI and Sprint in the SF Bay Are
S@N> I often can't reach places less than 6 hops and 10 miles away...
That's right.
| |
|                   | pgp-able mail-transfer
|                  |

Received on Thursday, 21 March 1996 14:24:37 UTC