rw_i = {2, 4, 1, 0} s_i = {2/7, 4/7, 1/7, 0} wakeup on cpu0, weight=1 rw'_i = {3, 4, 1, 0} s'_i = {3/8, 4/8, 1/8, 0} s_0 = S * rw_0 / \Sum rw_j -> \Sum rw_j = S*rw_0/s_0 = 1*2*7/2 = 7 (correct) s'_0 = S * (rw_0 + 1) / (\Sum rw_j + 1) = 1 * (2+1) / (7+1) = 3/8 (correct so we find that adding 1 to cpu0 gains 5/56 in weight if say the other cpu were, cpu1, we'd also have to calculate its 4/56 loss Signed-off-by: Peter Zijlstra --- kernel/sched_fair.c | 48 ++++++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 22 deletions(-) Index: linux-2.6/kernel/sched_fair.c =================================================================== --- linux-2.6.orig/kernel/sched_fair.c +++ linux-2.6/kernel/sched_fair.c @@ -1074,10 +1074,10 @@ static inline int wake_idle(int cpu, str static const struct sched_class fair_sched_class; #ifdef CONFIG_FAIR_GROUP_SCHED -static unsigned long effective_load(struct task_group *tg, long wl, int cpu) +static unsigned long effective_load(struct task_group *tg, int cpu, + unsigned long wl, unsigned long wg) { struct sched_entity *se = tg->se[cpu]; - long wg = wl; for_each_sched_entity(se) { #define D(n) (likely(n) ? (n) : 1) @@ -1092,6 +1092,13 @@ static unsigned long effective_load(stru b = S*rw + s*wg; wl = s*(a-b)/D(b); + /* + * Assume the group is already running and will + * thus already be accounted for in the weight. + * + * That is, moving shares between CPUs, does not + * alter the group weight. + */ wg = 0; #undef D } @@ -1099,26 +1106,12 @@ static unsigned long effective_load(stru return wl; } -static unsigned long task_load_sub(struct task_struct *p) -{ - return effective_load(task_group(p), -(long)p->se.load.weight, task_cpu(p)); -} - -static unsigned long task_load_add(struct task_struct *p, int cpu) -{ - return effective_load(task_group(p), p->se.load.weight, cpu); -} - #else -static unsigned long task_load_sub(struct task_struct *p) +static inline unsigned long effective_load(struct task_group *tg, int cpu, + unsigned long wl, unsigned long wg) { - return -p->se.load.weight; -} - -static unsigned long task_load_add(struct task_struct *p, int cpu) -{ - return p->se.load.weight; + return wl; } #endif @@ -1130,8 +1123,10 @@ wake_affine(struct rq *rq, struct sched_ unsigned int imbalance) { struct task_struct *curr = this_rq->curr; + struct task_group *tg; unsigned long tl = this_load; unsigned long tl_per_task; + unsigned long weight; int balanced; if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) @@ -1142,10 +1137,19 @@ wake_affine(struct rq *rq, struct sched_ * effect of the currently running task from the load * of the current CPU: */ - if (sync) - tl += task_load_sub(current); + if (sync) { + tg = task_group(current); + weight = current->se.load.weight; + + tl += effective_load(tg, this_cpu, -weight, -weight); + load += effective_load(tg, prev_cpu, 0, -weight); + } + + tg = task_group(p); + weight = p->se.load.weight; - balanced = 100*(tl + task_load_add(p, this_cpu)) <= imbalance*load; + balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <= + imbalance*(load + effective_load(tg, prev_cpu, 0, weight)); /* * If the currently running task will sleep within Index: linux-2.6/kernel/sched.c =================================================================== --- linux-2.6.orig/kernel/sched.c +++ linux-2.6/kernel/sched.c @@ -363,6 +363,10 @@ static inline void set_task_rq(struct ta #else static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} #endif /* CONFIG_GROUP_SCHED */ -- -- 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/