Messages in this thread | | | Date | Mon, 28 Jun 1999 07:46:49 +0200 | From | Andi Kleen <> | Subject | Re: FTP benchmark proposal |
| |
On Mon, Jun 28, 1999 at 12:11:21AM +0200, Marc Mutz wrote: > Andi Kleen wrote: > > > > The hard thing will be to simulate slow/timing out connections that occur over > > the internet. Just low-latency local networking with no lost packets is easy. > > > > So perhaps something like a NISTNET box is needed inbetween? > > > When benchmarking CGI on web servers, it is common to include a sleep(3) > or so call somewhere in the script. > Maybe this can most easily be done on the client side with a few lines > of perl (or C) like:
This does not help, because the client TCP/IP stack will still work asynchronously as long as the receive buffer does not fill up (and then it still acks the zero window probes), all rather unrealistic I would guess.
So if you want to test the stack, not the server user space hacks won't do.
-Andi -- This is like TV. I don't like TV.
- 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/
| |