Subj : Re: A multithreading benchmark
To   : comp.programming.threads
From : David Schwartz
Date : Mon Jun 06 2005 11:59 pm


"chris noonan" <usenet@leapheap.co.uk> wrote in message 
news:1118080460.562281.177610@o13g2000cwo.googlegroups.com...

> 2. The program will take the server role of a
> client-server system, and will run on a
> thread-per-connection basis.

    Since this architecture is almost never used by programmers looking for 
performance, why use it as a benchmark?

> Is there some way of simulating a number of
> clients without the complication of having
> multiple machines and real network connections?

    Not really, I'm afraid. The Internet is a strange place filled with 
lossy connections, re-ordering links, broken TCP/IP stacks, and so on. All 
of this stuff affects performance significantly.

    You are taking on an extremely hard problem. You would do well to 
research all the mistakes that have already been made rather than deciding 
to repeat them. ;)

    DS

.