Re: [RFC][PATCH] Improving directed yield scalability for PLEhandler
From: Andrew Theurer
Date: Mon Sep 10 2012 - 16:13:15 EST
On Mon, 2012-09-10 at 19:12 +0200, Peter Zijlstra wrote:
> On Mon, 2012-09-10 at 22:26 +0530, Srikar Dronamraju wrote:
> > > +static bool __yield_to_candidate(struct task_struct *curr, struct task_struct *p)
> > > +{
> > > + if (!curr->sched_class->yield_to_task)
> > > + return false;
> > > +
> > > + if (curr->sched_class != p->sched_class)
> > > + return false;
> >
> >
> > Peter,
> >
> > Should we also add a check if the runq has a skip buddy (as pointed out
> > by Raghu) and return if the skip buddy is already set.
>
> Oh right, I missed that suggestion.. the performance improvement went
> from 81% to 139% using this, right?
>
> It might make more sense to keep that separate, outside of this
> function, since its not a strict prerequisite.
>
> > >
> > > + if (task_running(p_rq, p) || p->state)
> > > + return false;
> > > +
> > > + return true;
> > > +}
>
>
> > > @@ -4323,6 +4340,10 @@ bool __sched yield_to(struct task_struct *p,
> > bool preempt)
> > > rq = this_rq();
> > >
> > > again:
> > > + /* optimistic test to avoid taking locks */
> > > + if (!__yield_to_candidate(curr, p))
> > > + goto out_irq;
> > > +
>
> So add something like:
>
> /* Optimistic, if we 'raced' with another yield_to(), don't bother */
> if (p_rq->cfs_rq->skip)
> goto out_irq;
> >
> >
> > > p_rq = task_rq(p);
> > > double_rq_lock(rq, p_rq);
> >
> >
> But I do have a question on this optimization though,.. Why do we check
> p_rq->cfs_rq->skip and not rq->cfs_rq->skip ?
>
> That is, I'd like to see this thing explained a little better.
>
> Does it go something like: p_rq is the runqueue of the task we'd like to
> yield to, rq is our own, they might be the same. If we have a ->skip,
> there's nothing we can do about it, OTOH p_rq having a ->skip and
> failing the yield_to() simply means us picking the next VCPU thread,
> which might be running on an entirely different cpu (rq) and could
> succeed?
Here's two new versions, both include a __yield_to_candidate(): "v3"
uses the check for p_rq->curr in guest mode, and "v4" uses the cfs_rq
skip check. Raghu, I am not sure if this is exactly what you want
implemented in v4.
Results:
> ple on: 2552 +/- .70%
> ple on: w/fixv1: 4621 +/- 2.12% (81% improvement)
> ple on: w/fixv2: 6115 (139% improvement)
v3: 5735 (124% improvement)
v4: 4524 ( 3% regression)
Both patches included below
-Andrew
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fbf1fd0..0d98a67 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4820,6 +4820,23 @@ void __sched yield(void)
}
EXPORT_SYMBOL(yield);
+/*
+ * Tests preconditions required for sched_class::yield_to().
+ */
+static bool __yield_to_candidate(struct task_struct *curr, struct task_struct *p, struct rq *p_rq)
+{
+ if (!curr->sched_class->yield_to_task)
+ return false;
+
+ if (curr->sched_class != p->sched_class)
+ return false;
+
+ if (task_running(p_rq, p) || p->state)
+ return false;
+
+ return true;
+}
+
/**
* yield_to - yield the current processor to another thread in
* your thread group, or accelerate that thread toward the
@@ -4844,20 +4861,27 @@ bool __sched yield_to(struct task_struct *p, bool preempt)
again:
p_rq = task_rq(p);
+
+ /* optimistic test to avoid taking locks */
+ if (!__yield_to_candidate(curr, p, p_rq))
+ goto out_irq;
+
+ /*
+ * if the target task is not running, then only yield if the
+ * current task is in guest mode
+ */
+ if (!(p_rq->curr->flags & PF_VCPU))
+ goto out_irq;
+
double_rq_lock(rq, p_rq);
while (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
- if (!curr->sched_class->yield_to_task)
- goto out;
-
- if (curr->sched_class != p->sched_class)
- goto out;
-
- if (task_running(p_rq, p) || p->state)
- goto out;
+ /* validate state, holding p_rq ensures p's state cannot change */
+ if (!__yield_to_candidate(curr, p, p_rq))
+ goto out_unlock;
yielded = curr->sched_class->yield_to_task(rq, p, preempt);
if (yielded) {
@@ -4877,8 +4901,9 @@ again:
rq->skip_clock_update = 0;
}
-out:
+out_unlock:
double_rq_unlock(rq, p_rq);
+out_irq:
local_irq_restore(flags);
if (yielded)
****************
v4:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fbf1fd0..2bec2ed 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4820,6 +4820,23 @@ void __sched yield(void)
}
EXPORT_SYMBOL(yield);
+/*
+ * Tests preconditions required for sched_class::yield_to().
+ */
+static bool __yield_to_candidate(struct task_struct *curr, struct task_struct *p, struct rq *p_rq)
+{
+ if (!curr->sched_class->yield_to_task)
+ return false;
+
+ if (curr->sched_class != p->sched_class)
+ return false;
+
+ if (task_running(p_rq, p) || p->state)
+ return false;
+
+ return true;
+}
+
/**
* yield_to - yield the current processor to another thread in
* your thread group, or accelerate that thread toward the
@@ -4844,20 +4861,24 @@ bool __sched yield_to(struct task_struct *p, bool preempt)
again:
p_rq = task_rq(p);
+
+ /* optimistic test to avoid taking locks */
+ if (!__yield_to_candidate(curr, p, p_rq))
+ goto out_irq;
+
+ /* if a yield is in progress, skip */
+ if (p_rq->cfs.skip)
+ goto out_irq;
+
double_rq_lock(rq, p_rq);
while (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
- if (!curr->sched_class->yield_to_task)
- goto out;
-
- if (curr->sched_class != p->sched_class)
- goto out;
-
- if (task_running(p_rq, p) || p->state)
- goto out;
+ /* validate state, holding p_rq ensures p's state cannot change */
+ if (!__yield_to_candidate(curr, p, p_rq))
+ goto out_unlock;
yielded = curr->sched_class->yield_to_task(rq, p, preempt);
if (yielded) {
@@ -4877,8 +4898,9 @@ again:
rq->skip_clock_update = 0;
}
-out:
+out_unlock:
double_rq_unlock(rq, p_rq);
+out_irq:
local_irq_restore(flags);
if (yielded)
--
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/