From 58e2d4ca581167c2a079f4ee02be2f0bc52e8729 Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Fri, 25 Jan 2008 21:08:00 +0100 Subject: [PATCH] sched: group scheduling, change how cpu load is calculated This patch changes how the cpu load exerted by fair_sched_class tasks is calculated. Load exerted by fair_sched_class tasks on a cpu is now a summation of the group weights, rather than summation of task weights. Weight exerted by a group on a cpu is dependent on the shares allocated to it. This version of patch has a minor impact on code size, but should have no runtime/functional impact for !CONFIG_FAIR_GROUP_SCHED. Signed-off-by: Srivatsa Vaddagiri Signed-off-by: Ingo Molnar --- kernel/sched.c | 27 +++++++++++---------------- kernel/sched_fair.c | 31 +++++++++++++++++++++++++++---- kernel/sched_rt.c | 2 ++ 3 files changed, 40 insertions(+), 20 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index cfa695819252..c915f3e6e593 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -886,6 +886,16 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime); static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} #endif +static inline void inc_cpu_load(struct rq *rq, unsigned long load) +{ + update_load_add(&rq->load, load); +} + +static inline void dec_cpu_load(struct rq *rq, unsigned long load) +{ + update_load_sub(&rq->load, load); +} + #include "sched_stats.h" #include "sched_idletask.c" #include "sched_fair.c" @@ -896,26 +906,14 @@ static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} #define sched_class_highest (&rt_sched_class) -static inline void inc_load(struct rq *rq, const struct task_struct *p) -{ - update_load_add(&rq->load, p->se.load.weight); -} - -static inline void dec_load(struct rq *rq, const struct task_struct *p) -{ - update_load_sub(&rq->load, p->se.load.weight); -} - static void inc_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running++; - inc_load(rq, p); } static void dec_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running--; - dec_load(rq, p); } static void set_load_weight(struct task_struct *p) @@ -4087,10 +4085,8 @@ void set_user_nice(struct task_struct *p, long nice) goto out_unlock; } on_rq = p->se.on_rq; - if (on_rq) { + if (on_rq) dequeue_task(rq, p, 0); - dec_load(rq, p); - } p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p); @@ -4100,7 +4096,6 @@ void set_user_nice(struct task_struct *p, long nice) if (on_rq) { enqueue_task(rq, p, 0); - inc_load(rq, p); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 0c5fdce67228..30ae9c2a2861 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -760,15 +760,26 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se) static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup) { struct cfs_rq *cfs_rq; - struct sched_entity *se = &p->se; + struct sched_entity *se = &p->se, + *topse = NULL; /* Highest schedulable entity */ + int incload = 1; for_each_sched_entity(se) { - if (se->on_rq) + topse = se; + if (se->on_rq) { + incload = 0; break; + } cfs_rq = cfs_rq_of(se); enqueue_entity(cfs_rq, se, wakeup); wakeup = 1; } + /* Increment cpu load if we just enqueued the first task of a group on + * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs + * at the highest grouping level. + */ + if (incload) + inc_cpu_load(rq, topse->load.weight); } /* @@ -779,16 +790,28 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup) static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) { struct cfs_rq *cfs_rq; - struct sched_entity *se = &p->se; + struct sched_entity *se = &p->se, + *topse = NULL; /* Highest schedulable entity */ + int decload = 1; for_each_sched_entity(se) { + topse = se; cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, sleep); /* Don't dequeue parent if it has other entities besides us */ - if (cfs_rq->load.weight) + if (cfs_rq->load.weight) { + if (parent_entity(se)) + decload = 0; break; + } sleep = 1; } + /* Decrement cpu load if we just dequeued the last task of a group on + * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs + * at the highest grouping level. + */ + if (decload) + dec_cpu_load(rq, topse->load.weight); } /* diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 9ba3daa03475..cefcd5105146 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -32,6 +32,7 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) list_add_tail(&p->run_list, array->queue + p->prio); __set_bit(p->prio, array->bitmap); + inc_cpu_load(rq, p->se.load.weight); } /* @@ -46,6 +47,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) list_del(&p->run_list); if (list_empty(array->queue + p->prio)) __clear_bit(p->prio, array->bitmap); + dec_cpu_load(rq, p->se.load.weight); } /*