lkml.org 
[lkml]   [1998]   [Sep]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: my broken TCP is faster on broken networks
    On Sat, 12 Sep 1998, Martin Mares wrote:

    > > It is another vendors attempt to make their browser look "faster" than
    > > others. Netscape always opens up 4 connections in parallel by default
    > > and uses persistant transactions over each one. You can configure it
    > > to use only one open connection.
    >
    > It seems people from Netscape should read the RFC's...

    The people from Netscape don't use HTTP/1.1 in Navigator.

    And there are valid issues with page layout in the current world meaning
    that the optimal way to transfer files with the goal of getting all the
    content across as quickly as possible is not the same as the optimal way
    of getting something that the user wants to look at as quickly as
    possible, even if the full transfer isn't complete.

    This goes off into a huge number of areas including the problems with
    HTML, possible compression of documents, both streaming and
    pre-compressed, the ways to allow easier rendering, the benefits of
    multiplexing requests over a single connection, HTTP-NG, where the heck
    the W3C thinks it is going into an fantasy world of objects, etc.

    But that is very off topic and has been discussed to death.

    What it boils down to is that no one has shown any valid, documented
    support for breaking congestion control in Linux, nor have they shown that
    magical improvements will do anything except accomplish their goal of
    "making _my_ page load faster!". Some of the suggestions I have seen here
    "well hey, it doens't work very well IMHO now anyway so we may as well
    just trash the whole concept of congestion control and let everyone fight
    it out however they want" are beyond crazy.

    Any such changes would require the proper research, presentation, and
    discussion in the appropriate forums before deployment would make any
    sense. The appropriate forum isn't here.


    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.rutgers.edu
    Please read the FAQ at http://www.tux.org/lkml/faq.html

    \
     
     \ /
      Last update: 2005-03-22 13:44    [W:4.012 / U:0.236 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site