lkml.org 
[lkml]   [2010]   [Sep]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
SubjectRe: [RFC patch 1/2] sched: dynamically adapt granularity with nr_running
From
Date
On Mon, 2010-09-13 at 14:53 +0200, Peter Zijlstra wrote:
> On Sun, 2010-09-12 at 16:37 -0400, Mathieu Desnoyers wrote:
> > The whole point of my patch is not to have to do this latency vs performance
> > tradeoff for low number of running threads. With your approach, lowering the
> > granularity even when there are few threads running will very likely hurt
> > performance, no ?
>
> But you presented it as a latency patch, not a throughput patch. And I'm
> not sure it will matter enough to offset the computational cost it
> introduces.


---
On Mon, 2010-09-13 at 14:53 +0200, Peter Zijlstra wrote:
On Sun, 2010-09-12 at 16:37 -0400, Mathieu Desnoyers wrote:
> > The whole point of my patch is not to have to do this latency vs performance
> > tradeoff for low number of running threads. With your approach, lowering the
> > granularity even when there are few threads running will very likely hurt
> > performance, no ?
> But you presented it as a latency patch, not a throughput patch. And I'm
> not sure it will matter enough to offset the computational cost it
> introduces.
>

One option is to simply get rid of that stuff in check_preempt_tick()
and instead do a wakeup-preempt check on the leftmost task instead.

The code as it stands today does that delta_exec < min_gran check to
ensure current gets some runtime before doing that second preemption
check, which compares vruntime with a wall-time measure.

Making that gran more complex doesn't really buy us much because for a
system with different weights in the gran and slice lengths don't match
up anyway.

---
Subject: sched: Simplify tick preemption
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Mon Jul 05 13:56:30 CEST 2010
Check the current slice, if not expired, see if the leftmost task
would otherwise have preempted current.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
kernel/sched_fair.c | 43 +++++++++++++++----------------------------
1 file changed, 15 insertions(+), 28 deletions(-)
Index: linux-2.6/kernel/sched_fair.c
===================================================================
--- linux-2.6.orig/kernel/sched_fair.c
+++ linux-2.6/kernel/sched_fair.c
@@ -838,44 +838,34 @@ dequeue_entity(struct cfs_rq *cfs_rq, st
se->vruntime -= cfs_rq->min_vruntime;
}

+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+
/*
* Preempt the current task with a newly woken task if needed:
*/
static void
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
- unsigned long ideal_runtime, delta_exec;
+ unsigned long slice = sched_slice(cfs_rq, curr);
+
+ if (curr->sum_exec_runtime - curr->prev_sum_exec_runtime < slice) {
+ struct sched_entity *pse = __pick_next_entity(cfs_rq);
+
+ if (pse && wakeup_preempt_entity(curr, pse) == 1)
+ goto preempt;

- ideal_runtime = sched_slice(cfs_rq, curr);
- delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime) {
- resched_task(rq_of(cfs_rq)->curr);
- /*
- * The current task ran long enough, ensure it doesn't get
- * re-elected due to buddy favours.
- */
- clear_buddies(cfs_rq, curr);
return;
}

/*
- * Ensure that a task that missed wakeup preemption by a
- * narrow margin doesn't have to wait for a full slice.
- * This also mitigates buddy induced latencies under load.
+ * The current task ran long enough, ensure it doesn't get
+ * re-elected due to buddy favours.
*/
- if (!sched_feat(WAKEUP_PREEMPT))
- return;
-
- if (delta_exec < sysctl_sched_min_granularity)
- return;
+ clear_buddies(cfs_rq, curr);

- if (cfs_rq->nr_running > 1) {
- struct sched_entity *se = __pick_next_entity(cfs_rq);
- s64 delta = curr->vruntime - se->vruntime;
-
- if (delta > ideal_runtime)
- resched_task(rq_of(cfs_rq)->curr);
- }
+preempt:
+ resched_task(rq_of(cfs_rq)->curr);
}

static void
@@ -908,9 +898,6 @@ set_next_entity(struct cfs_rq *cfs_rq, s
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}

-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
-
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = __pick_next_entity(cfs_rq);


\
 
 \ /
  Last update: 2010-09-13 15:19    [from the cache]
©2003-2014 Jasper Spaans. Advertise on this site