On Thursday 08 November 2007 15:37, Gregory Haskins wrote:
> Peter Zijlstra wrote:
> > Bah, missed a hunk
> >
> > ---
> > Subject: sched: avoid large irq-latencies in smp-balancing
> >
> > SMP balancing is done with IRQs disabled and can iterate the full rq.
> > When rqs are large this can cause la
Peter Zijlstra infradead.org> writes:
> @@ -2237,7 +2243,7 @@ balance_tasks(struct rq *this_rq, int th
> enum cpu_idle_type idle, int *all_pinned,
> int *this_best_prio, struct rq_iterator *iterator)
> {
> - int pulled = 0, pinned = 0, skip_for_load;
> + int loops
Peter Zijlstra wrote:
> Bah, missed a hunk
>
> ---
> Subject: sched: avoid large irq-latencies in smp-balancing
>
> SMP balancing is done with IRQs disabled and can iterate the full rq. When rqs
> are large this can cause large irq-latencies. Limit the nr of iterations on
> each run.
>
> Signed-
On Wed, 2007-11-07 at 17:10 -0500, Steven Rostedt wrote:
> >
> > It would be nice if sched_nr_migrate didn't exist, really. It's hard to
> > imagine anyone wanting to tweak it, apart from developers.
>
> I'm not so sure about that. It is a tunable for RT. That is we can tweak
> this value to be
On Wed, Nov 07, 2007 at 10:27:25AM -0800, Andrew Morton wrote:
> > On Wed, 07 Nov 2007 13:17:00 +0100 Peter Zijlstra <[EMAIL PROTECTED]> wrote:
> > + {
> > + .ctl_name = CTL_UNNUMBERED,
> > + .procname = "sched_nr_migrate",
> > + .data = &sysctl
On Wed, 2007-11-07 at 10:27 -0800, Andrew Morton wrote:
> > On Wed, 07 Nov 2007 13:17:00 +0100 Peter Zijlstra <[EMAIL PROTECTED]> wrote:
> > + {
> > + .ctl_name = CTL_UNNUMBERED,
> > + .procname = "sched_nr_migrate",
> > + .data = &sysctl_sched_
> On Wed, 07 Nov 2007 13:17:00 +0100 Peter Zijlstra <[EMAIL PROTECTED]> wrote:
> + {
> + .ctl_name = CTL_UNNUMBERED,
> + .procname = "sched_nr_migrate",
> + .data = &sysctl_sched_nr_migrate,
> + .maxlen = sizeof(unsig
Bah, missed a hunk
---
Subject: sched: avoid large irq-latencies in smp-balancing
SMP balancing is done with IRQs disabled and can iterate the full rq. When rqs
are large this can cause large irq-latencies. Limit the nr of iterations on
each run.
Signed-off-by: Peter Zijlstra <[EMAIL PROTECTED]>
Subject: sched: avoid large irq-latencies in smp-balancing
SMP balancing is done with IRQs disabled and can iterate the full rq. When rqs
are large this can cause large irq-latencies. Limit the nr of iterations on
each run.
Signed-off-by: Peter Zijlstra <[EMAIL PROTECTED]>
CC: Peter Williams <[EM
9 matches
Mail list logo
