> From [email protected] Thu Feb 18 11:00:58 1999
> From: [email protected]
> To: [email protected]
> Cc: [email protected]
> Subject: Re: HTTP performance issues
> Date: 22 Jan 1999 08:42:46 -0500
> Lines: 30
>
> [email protected] writes:
>
> > Hi ,
> >
> > We are now in the process of rolling-out web based applications to a number of
> > remote VSAT connected sites. With the tests we did, I have to conclude that the
> > performance of HTTP is rather poor. Now one factor that might have an impact is
> > that we use Transaction reservation on the VSAT inroutes. (TR give round trip
> > times of about 1500msec). We don't have any choice, we cannot use Stream for all
> > remote sites. Is there a way to improve the performance, we know for example the
> > product Venturi (from Fourelle) but that product turns the HTTP protocol into
> > something proprietary protocol. What I'm trying to find out is : are there
> > tunings possible to the existing standard HTTP protocol ?
> >
> > Many Thanks,
> > Guy Raymakers
> >
> >
>
> Unless you use http 1.1 and use the persistent TCP connections (forgot
> the real name, sorry) that do not open a TCP connection for each HTTP
> request then you are pretty much out of luck. With 1.5 sec RTT, you
> will get awful performance for HTTP traffic (on the order of
> 8Kbytes/sec or so). Your best bet is to use one of the available TCP
> spoofing/proxy boxes and break the end-2-end semantics.
Why? 1.1 and persistent connections doesn't require the spoofing stuff...
Joe
This archive was generated by hypermail 2b29 : Mon Feb 14 2000 - 16:14:53 EST