Strange scheduling behavoir in SMP (kernel 2.2.14)

[Stephen C. Tweedie]

Hi,

On Fri, 28 Jan 2000 18:41:36 +0100, Michael Schulz
<michael_schulz en public.uni-hamburg.de> said:

> But the point is: where have processes been scheduled the first
> time. Let's say X started on cpu0 and has a strong tendency to stay there.
> Somehow xosview made it to the same cpu0 after a wile. That could be
> the outcome because the benchmark tends to be more active and xosview
> more sleepy. Or whatever other constraints could influence process
> migration and scheduling.

We're talking about a real life situation, not a "what if".  The real
life situation is that both X and xosview spend most of their time
asleep and so binding them to a given CPU simply doesn't enter the
picture; and that when they wake up, the scheduler is *required* to
schedule them both as soon as possible (that's an unbreakable, hard
requirement for interactive tasks).  If they are both awake at some
point in time --- let's say, xosview has logged more data and has sent
it to X for display --- then the scheduler is required to run them both
in preference to any background computation.  

Sorry, but in this case you just don't have the option of leaving your
background task running and scheduling only one of the two runnable
interactive tasks.

--Stephen

-
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/