Re: 2.6.14-rt1

[Carlos Antunes]

On 11/1/05, Steven Rostedt <rostedt@xxxxxxxxxxx> wrote:
> On Tue, 2005-11-01 at 21:55 -0500, Carlos Antunes wrote:
>
> >
> > Fernando,
> >
> > I'm also having some when using SCHED_FIFO and SCHED_RR. When running
> > several hundred threads, each sleeping on a loop for 20ms, SCHED_OTHER
> > performs ok with latencies of less than 10ms while with SCHED_FIFO or
> > SCHED_RR, I see latencies exceeding 1 full second!
>
> Are you saying that you have several hundred threads in SCHED_FIFO or
> SCHED_RR? Or is just Jack as that.
>

It's a simple program I put together to test wakeup latency. Each
thread basically sleeps for 20ms, wakes up and executes a couple of
instructions and goes back to sleep for another 20ms. Multiply this by
a thousand. What I found out is that, inthis situation, and using
realtime-preempt, SCHED_OTHER offers 3 orders of magnitude less
latency than SCHED_FIFO or SCHED_RR. Which suggests to me there is
something fishy going on.

Carlos


--
"We hold [...] that all men are created equal; that they are
endowed [...] with certain inalienable rights; that among
these are life, liberty, and the pursuit of happiness"
        -- Thomas Jefferson
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/