emulating netbench

Andrew Tridgell (tridge@samba.org)
Sun, 16 May 1999 15:36:49 +1000

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Alex K.: "PATCH: checksum optimization on semi-686's"
Previous message: Manfred Spraul: "Re: [PATCH][2.3.0] Read-write locks instead semaphores on UTS structures"

Some of you may have seen the recent benchmark results that show
problems with the throughput of Linux/Samba when running the netbench
benchmark on a large server. While the way that benchmark was
conducted leaves a lot to be desired and the results were not exactly
accurate they did serve to point out areas that need improving.

The problem with tuning for netbench is that you need _very_ deep
pockets to setup a full lab that can run the test. To overcome this
I've written a couple of tools that allow you to reproduce the results
with only one or two machines.

Please have a look at ftp://samba.org/pub/tridge/dbench/README if you
are interested in trying these tools and helping to optimise
Linux/Samba.

Cheers, Tridge

-
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/

Next message: Alex K.: "PATCH: checksum optimization on semi-686's"
Previous message: Manfred Spraul: "Re: [PATCH][2.3.0] Read-write locks instead semaphores on UTS structures"