There is an interesting paper at
http://www.cs.rice.edu/CS/Systems/Web-measurement/ where the authors
atempt to more correctly measure web servers. I think some of their
methods would directly apply to attempting to simulate client latency on a
proxy also.
Justin
On Tue, 9 Dec 1997, James R Grinter wrote:
> On Wed 10 Dec, 1997, Dancer <dancer@brisnet.org.au> wrote:
> >Alex Rousskov wrote:
> >> Without going into numerous obvious details, how important/useful/urgent
> >> the development of such a test suite is?
> >
> >I would say that it's important, useful and steadily becoming more urgent :)
>
> But very difficult to get right.
>
> It is absolutely essential to also be able to simulate client latency (we can't
> easily simulate client broken TCP behaviour, but we'll have to live with that).
>
> I did find, long ago, some references to papers on a sort of network "sandbox"
> implementation, but I never found it again when I actually wanted it (I think
> it was some work at MIT, but I can't remember what papers I was reading at the
> time)
>
> James.
>
>
Received on Tue Dec 16 1997 - 22:47:32 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:37:58 MST