From: Peter Zijlstra <peterz@infradead.org> It turns out that a few workloads (easyWave, fio) have a fairly low success rate on newidle balance, but still benefit greatly from having it anyway. Luckliky these workloads have a faily low newidle rate, so the cost if doing the newidle is relatively low, even if unsuccessfull. Add a simple rate based part to the newidle ratio compute, such that low rate newidle will still have a high newidle ratio. This cures the easyWave and fio workloads while not affecting the schbench numbers either (which have a very high newidle rate). Reported-by: Mario Roy <marioeroy@gmail.com> Reported-by: "Mohamed Abuelfotoh, Hazem" <abuehaze@amazon.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Mario Roy <marioeroy@gmail.com> Tested-by: "Mohamed Abuelfotoh, Hazem" <abuehaze@amazon.com> Link: https://patch.msgid.link/20260127151748.GA1079264@noisy.programming.kicks-as... Signed-off-by: Luo Gengkun <luogengkun2@huawei.com> --- include/linux/sched/topology.h | 1 + kernel/sched/fair.c | 27 +++++++++++++++++++++++++-- kernel/sched/features.h | 3 ++- kernel/sched/topology.c | 3 +++ 4 files changed, 31 insertions(+), 3 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index ab45a04061fb..d66e6c6c2cdf 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -134,6 +134,7 @@ struct sched_domain { unsigned int newidle_call; unsigned int newidle_success; unsigned int newidle_ratio; + u64 newidle_stamp; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 31a1f7734332..ec40e79802bd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11846,7 +11846,30 @@ static inline void update_newidle_stats(struct sched_domain *sd, unsigned int su sd->newidle_success += success; if (sd->newidle_call >= 1024) { - sd->newidle_ratio = sd->newidle_success; + u64 now = sched_clock(); + s64 delta = now - sd->newidle_stamp; + sd->newidle_stamp = now; + int ratio = 0; + + if (delta < 0) + delta = 0; + + if (sched_feat(NI_RATE)) { + /* + * ratio delta freq + * + * 1024 - 4 s - 128 Hz + * 512 - 2 s - 256 Hz + * 256 - 1 s - 512 Hz + * 128 - .5 s - 1024 Hz + * 64 - .25 s - 2048 Hz + */ + ratio = delta >> 22; + } + + ratio += sd->newidle_success; + + sd->newidle_ratio = min(1024, ratio); sd->newidle_call /= 2; sd->newidle_success /= 2; } @@ -12544,7 +12567,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) if (sd->flags & SD_BALANCE_NEWIDLE) { unsigned int weight = 1; - if (sched_feat(NI_RANDOM)) { + if (sched_feat(NI_RANDOM) && sd->newidle_ratio < 1024) { /* * Throw a 1k sided dice; and only run * newidle_balance according to the success diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 0198f4e97d24..9a8b6f41f4cb 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -121,4 +121,5 @@ SCHED_FEAT(TEST_STEAL_PLUS_IDLE, false) /* * Do newidle balancing proportional to its success rate using randomization. */ -SCHED_FEAT(NI_RANDOM, true) \ No newline at end of file +SCHED_FEAT(NI_RANDOM, true) +SCHED_FEAT(NI_RATE, true) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index cb82bbc4fb41..ac198e940978 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -4,6 +4,7 @@ */ #include "sched.h" #include "sparsemask.h" +#include <linux/sched/clock.h> DEFINE_MUTEX(sched_domains_mutex); @@ -1783,6 +1784,7 @@ sd_init(struct sched_domain_topology_level *tl, struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); int sd_id, sd_weight, sd_flags = 0; struct cpumask *sd_span; + u64 now = sched_clock(); #ifdef CONFIG_NUMA /* @@ -1827,6 +1829,7 @@ sd_init(struct sched_domain_topology_level *tl, .newidle_call = 512, .newidle_success = 256, .newidle_ratio = 512, + .newidle_stamp = now, .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, -- 2.34.1