From: Ingo Molnar <mingo@kernel.org> mainline inclusion from mainline-v7.0-rc1 commit 4ff674fa986c27ec8a0542479258c92d361a2566 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/8903 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The ::avg_load field is a long-standing misnomer: it says it's an 'average load', but in reality it's the momentary sum of the load of all currently runnable tasks. We'd have to also perform a division by nr_running (or use time-decay) to arrive at any sort of average value. This is clear from comments about the math of fair scheduling: * \Sum w_i := cfs_rq->avg_load The sum of all weights is ... the sum of all weights, not the average of all weights. To make it doubly confusing, there's also an ::avg_load in the load-balancing struct sg_lb_stats, which *is* a true average. The second part of the field's name is a minor misnomer as well: it says 'load', and it is indeed a load_weight structure as it shares code with the load-balancer - but it's only in an SMP load-balancing context where load = weight, in the fair scheduling context the primary purpose is the weighting of different nice levels. So rename the field to ::sum_weight instead, which makes the terminology of the EEVDF math match up with our implementation of it: * \Sum w_i := cfs_rq->sum_weight Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://patch.msgid.link/20251201064647.1851919-6-mingo@kernel.org Conflicts: kernel/sched/sched.h [Context difference.] Signed-off-by: Zicheng Qu <quzicheng@huawei.com> --- kernel/sched/fair.c | 16 ++++++++-------- kernel/sched/sched.h | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ad30bb800961..7706902e904d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -818,7 +818,7 @@ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) * * v0 := cfs_rq->zero_vruntime * \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime - * \Sum w_i := cfs_rq->avg_load + * \Sum w_i := cfs_rq->sum_weight * * Since zero_vruntime closely tracks the per-task service, these * deltas: (v_i - v), will be in the order of the maximal (virtual) lag @@ -835,7 +835,7 @@ avg_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se) s64 key = entity_key(cfs_rq, se); cfs_rq->avg_vruntime += key * weight; - cfs_rq->avg_load += weight; + cfs_rq->sum_weight += weight; } static void @@ -845,16 +845,16 @@ avg_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se) s64 key = entity_key(cfs_rq, se); cfs_rq->avg_vruntime -= key * weight; - cfs_rq->avg_load -= weight; + cfs_rq->sum_weight -= weight; } static inline void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta) { /* - * v' = v + d ==> avg_vruntime' = avg_runtime - d*avg_load + * v' = v + d ==> avg_vruntime' = avg_runtime - d*sum_weight */ - cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta; + cfs_rq->avg_vruntime -= cfs_rq->sum_weight * delta; } /* @@ -865,7 +865,7 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; s64 avg = cfs_rq->avg_vruntime; - long load = cfs_rq->avg_load; + long load = cfs_rq->sum_weight; if (curr && curr->on_rq) { unsigned long weight = scale_load_down(curr->load.weight); @@ -938,7 +938,7 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) { struct sched_entity *curr = cfs_rq->curr; s64 avg = cfs_rq->avg_vruntime; - long load = cfs_rq->avg_load; + long load = cfs_rq->sum_weight; if (curr && curr->on_rq) { unsigned long weight = scale_load_down(curr->load.weight); @@ -5419,7 +5419,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * * vl_i = (W + w_i)*vl'_i / W */ - load = cfs_rq->avg_load; + load = cfs_rq->sum_weight; if (curr && curr->on_rq) load += scale_load_down(curr->load.weight); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2cbbf75a3e92..718dbdd18434 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -669,7 +669,7 @@ struct cfs_rq { unsigned int idle_h_nr_running; /* SCHED_IDLE */ s64 avg_vruntime; - u64 avg_load; + u64 sum_weight; u64 exec_clock; KABI_REPLACE(u64 min_vruntime, u64 zero_vruntime) -- 2.34.1