Scheduler patch recoding ...

[Rik van Riel]

On Thu, 20 Jan 2000, Davide Libenzi wrote:

> having a lot of requests about my scheduler patch which I've coded
> until 2.2.13 and 2.3.34, I've planned to recode it for 2.2.14 and
> 2.3.39 this weekend.

Where can we download your current code?

> After this step I need help from all of You that have a good
> testing console for a high switching rate environment ( IBM
> Volano, and I hope, many others ).

No you don't. This patch needs to be tested under a
realistic system load. An overloaded webserver or a
`make -j' is fine, but an artificial benchmark most
certainly is not.

> I've not spent enough time to develop my testing suite ( to say
> the truth it's very simple ), so I need one that can better
> simulate a __real__ high workload environments. My hope is that
> with this patch we can hiss pro M$ benchmarks dispatchers.

If benchmarking is the goal of your patch, I'll be
reading it for entertainment value only. OTOH, if
your patch is meant to make the scheduler more
scalable or better, then I'm willing to do something
more with it...

regards,

Rik
--
The Internet is not a network of computers. It is a network
of people. That is its real strength.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo en vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/