| Message ID | 1421316570-23097-6-git-send-email-vincent.guittot@linaro.org |
|---|---|
| State | New |
| Headers | show |
On 19 February 2015 at 18:18, Morten Rasmussen <morten.rasmussen@arm.com> wrote: > On Thu, Feb 19, 2015 at 04:52:41PM +0000, Peter Zijlstra wrote: >> On Thu, Jan 15, 2015 at 11:09:25AM +0100, Vincent Guittot wrote: >> > The average running time of RT tasks is used to estimate the remaining compute >> > capacity for CFS tasks. This remaining capacity is the original capacity scaled >> > down by a factor (aka scale_rt_capacity). This estimation of available capacity >> > must also be invariant with frequency scaling. >> > >> > A frequency scaling factor is applied on the running time of the RT tasks for >> > computing scale_rt_capacity. >> > >> > In sched_rt_avg_update, we scale the RT execution time like below: >> > rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT >> > >> > Then, scale_rt_capacity can be summarized by: >> > scale_rt_capacity = SCHED_CAPACITY_SCALE - >> > ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / period) >> > >> > We can optimize by removing right and left shift in the computation of rq->rt_avg >> > and scale_rt_capacity >> >> So far so good.. >> >> > The call to arch_scale_frequency_capacity in the rt scheduling path might be >> > a concern for RT folks because I'm not sure whether we can rely on >> > arch_scale_freq_capacity to be short and efficient ? >> >> No, that is, arch_scale_frequency_capacity() _must_ be short and >> efficient, event for the fair class, its called in very hot paths. > > ... and very frequently too. > >> I think we've talked about this before; this function should basically >> only return a cached value, which is periodically updated through some >> means. > > Agreed. I think it is reasonable to assume that the arch code > implementing arch_scale_freq_capacity() does it's best to make it fast > for the particular architecture. Since the scaling factor to be returned > by the function may be obtained in different ways for different > architectures the caching should be done on the arch side. > >> But lets see, I've yet to see an actual implementation of it; and its >> got that sd argument, curious what you're going to do with that. > > So we do have an RFC implementation for ARM already which I posted in > December and is also included in the rather large RFC posting I did some > weeks ago. That one basically reads two atomic variables and returns the > ratio between the two. I have yet to benchmark how horribly expensive it > is though. The sd argument is ignored. We might actually not need it at > all? For consistency across all arch_scale_xx_capacity, i would prefer to keep the same prototype interface (struct sched_domain *sd, int cpu) even if it's not used ofr now > -- > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a5039da..b37c27b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5785,7 +5785,7 @@ unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); - u64 total, available, age_stamp, avg; + u64 total, used, age_stamp, avg; s64 delta; /* @@ -5801,19 +5801,12 @@ static unsigned long scale_rt_capacity(int cpu) total = sched_avg_period() + delta; - if (unlikely(total < avg)) { - /* Ensures that capacity won't end up being negative */ - available = 0; - } else { - available = total - avg; - } + used = div_u64(avg, total); - if (unlikely((s64)total < SCHED_CAPACITY_SCALE)) - total = SCHED_CAPACITY_SCALE; + if (likely(used < SCHED_CAPACITY_SCALE)) + return SCHED_CAPACITY_SCALE - used; - total >>= SCHED_CAPACITY_SHIFT; - - return div_u64(available, total); + return 1; } static void update_cpu_capacity(struct sched_domain *sd, int cpu) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c34bd11..fc5b152 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1312,9 +1312,11 @@ static inline int hrtick_enabled(struct rq *rq) #ifdef CONFIG_SMP extern void sched_avg_update(struct rq *rq); +extern unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu); + static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { - rq->rt_avg += rt_delta; + rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); sched_avg_update(rq); } #else
The average running time of RT tasks is used to estimate the remaining compute capacity for CFS tasks. This remaining capacity is the original capacity scaled down by a factor (aka scale_rt_capacity). This estimation of available capacity must also be invariant with frequency scaling. A frequency scaling factor is applied on the running time of the RT tasks for computing scale_rt_capacity. In sched_rt_avg_update, we scale the RT execution time like below: rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT Then, scale_rt_capacity can be summarized by: scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / period) We can optimize by removing right and left shift in the computation of rq->rt_avg and scale_rt_capacity The call to arch_scale_frequency_capacity in the rt scheduling path might be a concern for RT folks because I'm not sure whether we can rely on arch_scale_freq_capacity to be short and efficient ? Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> --- kernel/sched/fair.c | 17 +++++------------ kernel/sched/sched.h | 4 +++- 2 files changed, 8 insertions(+), 13 deletions(-)