Re: [PATCH] scheduler patch, faster still
Richard Gooch (rgooch@atnf.csiro.au)
Mon, 28 Sep 1998 09:52:52 +1000
Rik van Riel writes:
> Hi Richard, Larry,
>
> Here is a second version of my scheduler patch. It
> should improve RT latency a little bit and remove
> overhead with programs waiting very shortly on things
> like IPC or buffer cache locks...
>
> I don't know whether I should have bothered with the
> RT piece; a second 'runqueue' for RT processes (not
> a full-blown queue, but one with almost the same
> structure as the bottom_half queues) would be better
> still... (avoiding the add_to_runqueue altogether
> and replacing it with something more appropriate)
I agree: the dominant effect would be having a separate run queue. The
RT "fastpath" would only make a very small difference, rather than a
factor of two.
Regards,
Richard....
-
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/