Re: [PATCH v2] sched/pelt: Fix task util_est update filtering
On Mon, Mar 01, 2021 at 06:21:23PM +0100, Peter Zijlstra wrote: > On Mon, Mar 01, 2021 at 05:34:09PM +0100, Dietmar Eggemann wrote: > > On 26/02/2021 09:41, Peter Zijlstra wrote: > > > On Thu, Feb 25, 2021 at 04:58:20PM +, Vincent Donnefort wrote: > > >> +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) > > >> + > > >> /* > > >> - * Check if a (signed) value is within a specified (unsigned) margin, > > >> + * Check if a (signed) value is within the (unsigned) util_est margin, > > >> * based on the observation that: > > >> * > > >> * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) > > >> * > > >> - * NOTE: this only works when value + maring < INT_MAX. > > >> + * NOTE: this only works when value + UTIL_EST_MARGIN < INT_MAX. > > >> */ > > >> -static inline bool within_margin(int value, int margin) > > >> +static inline bool util_est_within_margin(int value) > > >> { > > >> -return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); > > >> +return ((unsigned int)(value + UTIL_EST_MARGIN - 1) < > > >> +(2 * UTIL_EST_MARGIN - 1)); > > >> } > > > > > >> -if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) > > >> +if (util_est_within_margin(last_ewma_diff)) { > > > > > > What was the purpose of this change? What was a generic helper is now > > > super specific. > > > > I guess because it was only ever used in util_est for last_ewma_diff. > > > > It's now used for last_ewma_diff and last_enqueued_diff, still only for > > util_est though and both times with the same margin > > (SCHED_CAPACITY_SCALE / 100)). > > > > Vincent D. should be back on Wed from hols. > > Fair enough; I've un-done it but kept the rest of the patch. Indeed I was off for couple of days. Apologies for the delay and thanks for applying the patch. -- Vincent
Re: [PATCH v2] sched/pelt: Fix task util_est update filtering
On Mon, Mar 01, 2021 at 05:34:09PM +0100, Dietmar Eggemann wrote: > On 26/02/2021 09:41, Peter Zijlstra wrote: > > On Thu, Feb 25, 2021 at 04:58:20PM +, Vincent Donnefort wrote: > >> +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) > >> + > >> /* > >> - * Check if a (signed) value is within a specified (unsigned) margin, > >> + * Check if a (signed) value is within the (unsigned) util_est margin, > >> * based on the observation that: > >> * > >> * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) > >> * > >> - * NOTE: this only works when value + maring < INT_MAX. > >> + * NOTE: this only works when value + UTIL_EST_MARGIN < INT_MAX. > >> */ > >> -static inline bool within_margin(int value, int margin) > >> +static inline bool util_est_within_margin(int value) > >> { > >> - return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); > >> + return ((unsigned int)(value + UTIL_EST_MARGIN - 1) < > >> + (2 * UTIL_EST_MARGIN - 1)); > >> } > > > >> - if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) > >> + if (util_est_within_margin(last_ewma_diff)) { > > > > What was the purpose of this change? What was a generic helper is now > > super specific. > > I guess because it was only ever used in util_est for last_ewma_diff. > > It's now used for last_ewma_diff and last_enqueued_diff, still only for > util_est though and both times with the same margin > (SCHED_CAPACITY_SCALE / 100)). > > Vincent D. should be back on Wed from hols. Fair enough; I've un-done it but kept the rest of the patch.
Re: [PATCH v2] sched/pelt: Fix task util_est update filtering
On 26/02/2021 09:41, Peter Zijlstra wrote: > On Thu, Feb 25, 2021 at 04:58:20PM +, Vincent Donnefort wrote: >> +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) >> + >> /* >> - * Check if a (signed) value is within a specified (unsigned) margin, >> + * Check if a (signed) value is within the (unsigned) util_est margin, >> * based on the observation that: >> * >> * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) >> * >> - * NOTE: this only works when value + maring < INT_MAX. >> + * NOTE: this only works when value + UTIL_EST_MARGIN < INT_MAX. >> */ >> -static inline bool within_margin(int value, int margin) >> +static inline bool util_est_within_margin(int value) >> { >> -return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); >> +return ((unsigned int)(value + UTIL_EST_MARGIN - 1) < >> +(2 * UTIL_EST_MARGIN - 1)); >> } > >> -if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) >> +if (util_est_within_margin(last_ewma_diff)) { > > What was the purpose of this change? What was a generic helper is now > super specific. I guess because it was only ever used in util_est for last_ewma_diff. It's now used for last_ewma_diff and last_enqueued_diff, still only for util_est though and both times with the same margin (SCHED_CAPACITY_SCALE / 100)). Vincent D. should be back on Wed from hols.
Re: [PATCH v2] sched/pelt: Fix task util_est update filtering
On Thu, Feb 25, 2021 at 04:58:20PM +, Vincent Donnefort wrote: > +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) > + > /* > - * Check if a (signed) value is within a specified (unsigned) margin, > + * Check if a (signed) value is within the (unsigned) util_est margin, > * based on the observation that: > * > * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) > * > - * NOTE: this only works when value + maring < INT_MAX. > + * NOTE: this only works when value + UTIL_EST_MARGIN < INT_MAX. > */ > -static inline bool within_margin(int value, int margin) > +static inline bool util_est_within_margin(int value) > { > - return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); > + return ((unsigned int)(value + UTIL_EST_MARGIN - 1) < > + (2 * UTIL_EST_MARGIN - 1)); > } > - if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) > + if (util_est_within_margin(last_ewma_diff)) { What was the purpose of this change? What was a generic helper is now super specific.
Re: [PATCH v2] sched/pelt: Fix task util_est update filtering
On Thu, 25 Feb 2021 at 17:58, Vincent Donnefort wrote: > > Being called for each dequeue, util_est reduces the number of its updates > by filtering out when the EWMA signal is different from the task util_avg > by less than 1%. It is a problem for a sudden util_avg ramp-up. Due to the > decay from a previous high util_avg, EWMA might now be close enough to > the new util_avg. No update would then happen while it would leave > ue.enqueued with an out-of-date value. > > Taking into consideration the two util_est members, EWMA and enqueued for > the filtering, ensures, for both, an up-to-date value. > > This is for now an issue only for the trace probe that might return the > stale value. Functional-wise, it isn't a problem, as the value is always > accessed through max(enqueued, ewma). > > This problem has been observed using LISA's UtilConvergence:test_means on > the sd845c board. > > No regression observed with Hackbench on sd845c and Perf-bench sched pipe > on hikey/hikey960. > > Signed-off-by: Vincent Donnefort > Reviewed-by: Dietmar Eggemann Reviewed-by: Vincent Guittot > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index 9e4104ae39ae..214e02862994 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -3966,24 +3966,27 @@ static inline void util_est_dequeue(struct cfs_rq > *cfs_rq, > trace_sched_util_est_cfs_tp(cfs_rq); > } > > +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) > + > /* > - * Check if a (signed) value is within a specified (unsigned) margin, > + * Check if a (signed) value is within the (unsigned) util_est margin, > * based on the observation that: > * > * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) > * > - * NOTE: this only works when value + maring < INT_MAX. > + * NOTE: this only works when value + UTIL_EST_MARGIN < INT_MAX. > */ > -static inline bool within_margin(int value, int margin) > +static inline bool util_est_within_margin(int value) > { > - return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); > + return ((unsigned int)(value + UTIL_EST_MARGIN - 1) < > + (2 * UTIL_EST_MARGIN - 1)); > } > > static inline void util_est_update(struct cfs_rq *cfs_rq, >struct task_struct *p, >bool task_sleep) > { > - long last_ewma_diff; > + long last_ewma_diff, last_enqueued_diff; > struct util_est ue; > > if (!sched_feat(UTIL_EST)) > @@ -4004,6 +4007,8 @@ static inline void util_est_update(struct cfs_rq > *cfs_rq, > if (ue.enqueued & UTIL_AVG_UNCHANGED) > return; > > + last_enqueued_diff = ue.enqueued; > + > /* > * Reset EWMA on utilization increases, the moving average is used > only > * to smooth utilization decreases. > @@ -4017,12 +4022,17 @@ static inline void util_est_update(struct cfs_rq > *cfs_rq, > } > > /* > -* Skip update of task's estimated utilization when its EWMA is > +* Skip update of task's estimated utilization when its members are > * already ~1% close to its last activation value. > */ > last_ewma_diff = ue.enqueued - ue.ewma; > - if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) > + last_enqueued_diff -= ue.enqueued; > + if (util_est_within_margin(last_ewma_diff)) { > + if (!util_est_within_margin(last_enqueued_diff)) > + goto done; > + > return; > + } > > /* > * To avoid overestimation of actual task utilization, skip updates if > -- > 2.25.1 >
[PATCH v2] sched/pelt: Fix task util_est update filtering
Being called for each dequeue, util_est reduces the number of its updates by filtering out when the EWMA signal is different from the task util_avg by less than 1%. It is a problem for a sudden util_avg ramp-up. Due to the decay from a previous high util_avg, EWMA might now be close enough to the new util_avg. No update would then happen while it would leave ue.enqueued with an out-of-date value. Taking into consideration the two util_est members, EWMA and enqueued for the filtering, ensures, for both, an up-to-date value. This is for now an issue only for the trace probe that might return the stale value. Functional-wise, it isn't a problem, as the value is always accessed through max(enqueued, ewma). This problem has been observed using LISA's UtilConvergence:test_means on the sd845c board. No regression observed with Hackbench on sd845c and Perf-bench sched pipe on hikey/hikey960. Signed-off-by: Vincent Donnefort Reviewed-by: Dietmar Eggemann diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9e4104ae39ae..214e02862994 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3966,24 +3966,27 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq, trace_sched_util_est_cfs_tp(cfs_rq); } +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) + /* - * Check if a (signed) value is within a specified (unsigned) margin, + * Check if a (signed) value is within the (unsigned) util_est margin, * based on the observation that: * * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) * - * NOTE: this only works when value + maring < INT_MAX. + * NOTE: this only works when value + UTIL_EST_MARGIN < INT_MAX. */ -static inline bool within_margin(int value, int margin) +static inline bool util_est_within_margin(int value) { - return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); + return ((unsigned int)(value + UTIL_EST_MARGIN - 1) < + (2 * UTIL_EST_MARGIN - 1)); } static inline void util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) { - long last_ewma_diff; + long last_ewma_diff, last_enqueued_diff; struct util_est ue; if (!sched_feat(UTIL_EST)) @@ -4004,6 +4007,8 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, if (ue.enqueued & UTIL_AVG_UNCHANGED) return; + last_enqueued_diff = ue.enqueued; + /* * Reset EWMA on utilization increases, the moving average is used only * to smooth utilization decreases. @@ -4017,12 +4022,17 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, } /* -* Skip update of task's estimated utilization when its EWMA is +* Skip update of task's estimated utilization when its members are * already ~1% close to its last activation value. */ last_ewma_diff = ue.enqueued - ue.ewma; - if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) + last_enqueued_diff -= ue.enqueued; + if (util_est_within_margin(last_ewma_diff)) { + if (!util_est_within_margin(last_enqueued_diff)) + goto done; + return; + } /* * To avoid overestimation of actual task utilization, skip updates if -- 2.25.1