From fe7de49f9d4e53f24ec9ef762a503f70b562341c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 20 Oct 2010 16:01:12 -0700 Subject: sched: Make sched_param argument static in sched_setscheduler() callers Andrew Morton pointed out almost all sched_setscheduler() callers are using fixed parameters and can be converted to static. It reduces runtime memory use a little. Signed-off-by: KOSAKI Motohiro Reported-by: Andrew Morton Acked-by: James Morris Cc: Ingo Molnar Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/sched.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index d42992bccdfa..51944e8c38a8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4701,7 +4701,7 @@ static bool check_same_owner(struct task_struct *p) } static int __sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param, bool user) + const struct sched_param *param, bool user) { int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; @@ -4856,7 +4856,7 @@ recheck: * NOTE that the task may be already dead. */ int sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param) + const struct sched_param *param) { return __sched_setscheduler(p, policy, param, true); } @@ -4874,7 +4874,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * but our caller might not have that capability. */ int sched_setscheduler_nocheck(struct task_struct *p, int policy, - struct sched_param *param) + const struct sched_param *param) { return __sched_setscheduler(p, policy, param, false); } -- cgit v1.2.3 From 48c5ccae88dcd989d9de507e8510313c6cbd352b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 13 Nov 2010 19:32:29 +0100 Subject: sched: Simplify cpu-hot-unplug task migration While discussing the need for sched_idle_next(), Oleg remarked that since try_to_wake_up() ensures sleeping tasks will end up running on a sane cpu, we can do away with migrate_live_tasks(). If we then extend the existing hack of migrating current from CPU_DYING to migrating the full rq worth of tasks from CPU_DYING, the need for the sched_idle_next() abomination disappears as well, since idle will be the only possible thread left after the migration thread stops. This greatly simplifies the hot-unplug task migration path, as can be seen from the resulting code reduction (and about half the new lines are comments). Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <1289851597.2109.547.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 - kernel/cpu.c | 16 ++-- kernel/sched.c | 206 +++++++++++++++----------------------------------- 3 files changed, 67 insertions(+), 158 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3cd70cf91fde..29d953abb5ad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1871,14 +1871,11 @@ extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #ifdef CONFIG_HOTPLUG_CPU -extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p); extern void idle_task_exit(void); #else static inline void idle_task_exit(void) {} #endif -extern void sched_idle_next(void); - #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) extern void wake_up_idle_cpu(int cpu); #else diff --git a/kernel/cpu.c b/kernel/cpu.c index f6e726f18491..8615aa65d927 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -189,7 +189,6 @@ static inline void check_for_tasks(int cpu) } struct take_cpu_down_param { - struct task_struct *caller; unsigned long mod; void *hcpu; }; @@ -208,11 +207,6 @@ static int __ref take_cpu_down(void *_param) cpu_notify(CPU_DYING | param->mod, param->hcpu); - if (task_cpu(param->caller) == cpu) - move_task_off_dead_cpu(cpu, param->caller); - /* Force idle task to run as soon as we yield: it should - immediately notice cpu is offline and die quickly. */ - sched_idle_next(); return 0; } @@ -223,7 +217,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct take_cpu_down_param tcd_param = { - .caller = current, .mod = mod, .hcpu = hcpu, }; @@ -253,9 +246,12 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) } BUG_ON(cpu_online(cpu)); - /* Wait for it to sleep (leaving idle task). */ - while (!idle_cpu(cpu)) - yield(); + /* + * The migration_call() CPU_DYING callback will have removed all + * runnable tasks from the cpu, there's only the idle task left now + * that the migration thread is done doing the stop_machine thing. + */ + BUG_ON(!idle_cpu(cpu)); /* This actually kills the CPU. */ __cpu_die(cpu); diff --git a/kernel/sched.c b/kernel/sched.c index 41f18695b730..b0d5f1b24a39 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2366,18 +2366,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p) return dest_cpu; /* No more Mr. Nice Guy. */ - if (unlikely(dest_cpu >= nr_cpu_ids)) { - dest_cpu = cpuset_cpus_allowed_fallback(p); - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, cpu); - } + dest_cpu = cpuset_cpus_allowed_fallback(p); + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); } return dest_cpu; @@ -5712,29 +5709,20 @@ static int migration_cpu_stop(void *data) } #ifdef CONFIG_HOTPLUG_CPU + /* - * Figure out where task on dead CPU should go, use force if necessary. + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. */ -void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) +void idle_task_exit(void) { - struct rq *rq = cpu_rq(dead_cpu); - int needs_cpu, uninitialized_var(dest_cpu); - unsigned long flags; + struct mm_struct *mm = current->active_mm; - local_irq_save(flags); + BUG_ON(cpu_online(smp_processor_id())); - raw_spin_lock(&rq->lock); - needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING); - if (needs_cpu) - dest_cpu = select_fallback_rq(dead_cpu, p); - raw_spin_unlock(&rq->lock); - /* - * It can only fail if we race with set_cpus_allowed(), - * in the racer should migrate the task anyway. - */ - if (needs_cpu) - __migrate_task(p, dead_cpu, dest_cpu); - local_irq_restore(flags); + if (mm != &init_mm) + switch_mm(mm, &init_mm, current); + mmdrop(mm); } /* @@ -5747,128 +5735,69 @@ void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) static void migrate_nr_uninterruptible(struct rq *rq_src) { struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); - unsigned long flags; - local_irq_save(flags); - double_rq_lock(rq_src, rq_dest); rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; rq_src->nr_uninterruptible = 0; - double_rq_unlock(rq_src, rq_dest); - local_irq_restore(flags); -} - -/* Run through task list and migrate tasks from the dead cpu. */ -static void migrate_live_tasks(int src_cpu) -{ - struct task_struct *p, *t; - - read_lock(&tasklist_lock); - - do_each_thread(t, p) { - if (p == current) - continue; - - if (task_cpu(p) == src_cpu) - move_task_off_dead_cpu(src_cpu, p); - } while_each_thread(t, p); - - read_unlock(&tasklist_lock); } /* - * Schedules idle task to be the next runnable task on current CPU. - * It does so by boosting its priority to highest possible. - * Used by CPU offline code. + * remove the tasks which were accounted by rq from calc_load_tasks. */ -void sched_idle_next(void) +static void calc_global_load_remove(struct rq *rq) { - int this_cpu = smp_processor_id(); - struct rq *rq = cpu_rq(this_cpu); - struct task_struct *p = rq->idle; - unsigned long flags; - - /* cpu has to be offline */ - BUG_ON(cpu_online(this_cpu)); - - /* - * Strictly not necessary since rest of the CPUs are stopped by now - * and interrupts disabled on the current cpu. - */ - raw_spin_lock_irqsave(&rq->lock, flags); - - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - - activate_task(rq, p, 0); - - raw_spin_unlock_irqrestore(&rq->lock, flags); + atomic_long_sub(rq->calc_load_active, &calc_load_tasks); + rq->calc_load_active = 0; } /* - * Ensures that the idle task is using init_mm right before its cpu goes - * offline. + * Migrate all tasks from the rq, sleeping tasks will be migrated by + * try_to_wake_up()->select_task_rq(). + * + * Called with rq->lock held even though we'er in stop_machine() and + * there's no concurrency possible, we hold the required locks anyway + * because of lock validation efforts. */ -void idle_task_exit(void) -{ - struct mm_struct *mm = current->active_mm; - - BUG_ON(cpu_online(smp_processor_id())); - - if (mm != &init_mm) - switch_mm(mm, &init_mm, current); - mmdrop(mm); -} - -/* called under rq->lock with disabled interrupts */ -static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) +static void migrate_tasks(unsigned int dead_cpu) { struct rq *rq = cpu_rq(dead_cpu); - - /* Must be exiting, otherwise would be on tasklist. */ - BUG_ON(!p->exit_state); - - /* Cannot have done final schedule yet: would have vanished. */ - BUG_ON(p->state == TASK_DEAD); - - get_task_struct(p); + struct task_struct *next, *stop = rq->stop; + int dest_cpu; /* - * Drop lock around migration; if someone else moves it, - * that's OK. No task can be added to this CPU, so iteration is - * fine. + * Fudge the rq selection such that the below task selection loop + * doesn't get stuck on the currently eligible stop task. + * + * We're currently inside stop_machine() and the rq is either stuck + * in the stop_machine_cpu_stop() loop, or we're executing this code, + * either way we should never end up calling schedule() until we're + * done here. */ - raw_spin_unlock_irq(&rq->lock); - move_task_off_dead_cpu(dead_cpu, p); - raw_spin_lock_irq(&rq->lock); - - put_task_struct(p); -} - -/* release_task() removes task from tasklist, so we won't find dead tasks. */ -static void migrate_dead_tasks(unsigned int dead_cpu) -{ - struct rq *rq = cpu_rq(dead_cpu); - struct task_struct *next; + rq->stop = NULL; for ( ; ; ) { - if (!rq->nr_running) + /* + * There's this thread running, bail when that's the only + * remaining thread. + */ + if (rq->nr_running == 1) break; + next = pick_next_task(rq); - if (!next) - break; + BUG_ON(!next); next->sched_class->put_prev_task(rq, next); - migrate_dead(dead_cpu, next); + /* Find suitable destination for @next, with force if needed. */ + dest_cpu = select_fallback_rq(dead_cpu, next); + raw_spin_unlock(&rq->lock); + + __migrate_task(next, dead_cpu, dest_cpu); + + raw_spin_lock(&rq->lock); } -} -/* - * remove the tasks which were accounted by rq from calc_load_tasks. - */ -static void calc_global_load_remove(struct rq *rq) -{ - atomic_long_sub(rq->calc_load_active, &calc_load_tasks); - rq->calc_load_active = 0; + rq->stop = stop; } + #endif /* CONFIG_HOTPLUG_CPU */ #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) @@ -6078,15 +6007,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) unsigned long flags; struct rq *rq = cpu_rq(cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: rq->calc_load_update = calc_load_update; break; case CPU_ONLINE: - case CPU_ONLINE_FROZEN: /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { @@ -6098,30 +6025,19 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_DEAD: - case CPU_DEAD_FROZEN: - migrate_live_tasks(cpu); - /* Idle task back to normal (off runqueue, low prio) */ - raw_spin_lock_irq(&rq->lock); - deactivate_task(rq, rq->idle, 0); - __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); - rq->idle->sched_class = &idle_sched_class; - migrate_dead_tasks(cpu); - raw_spin_unlock_irq(&rq->lock); - migrate_nr_uninterruptible(rq); - BUG_ON(rq->nr_running != 0); - calc_global_load_remove(rq); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); } + migrate_tasks(cpu); + BUG_ON(rq->nr_running != 1); /* the migration thread */ raw_spin_unlock_irqrestore(&rq->lock, flags); + + migrate_nr_uninterruptible(rq); + calc_global_load_remove(rq); break; #endif } -- cgit v1.2.3 From 2069dd75c7d0f49355939e5586daf5a9ab216db7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Nov 2010 15:47:00 -0800 Subject: sched: Rewrite tg_shares_up) By tracking a per-cpu load-avg for each cfs_rq and folding it into a global task_group load on each tick we can rework tg_shares_up to be strictly per-cpu. This should improve cpu-cgroup performance for smp systems significantly. [ Paul: changed to use queueing cfs_rq + bug fixes ] Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.580480400@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 - kernel/sched.c | 173 ++++++++++++------------------------------------ kernel/sched_debug.c | 15 +++-- kernel/sched_fair.c | 164 +++++++++++++++++++++++++++++---------------- kernel/sched_features.h | 2 - kernel/sysctl.c | 19 ------ 6 files changed, 162 insertions(+), 213 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29d953abb5ad..8abb8aa59664 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1885,8 +1885,6 @@ static inline void wake_up_idle_cpu(int cpu) { } extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; -extern unsigned int sysctl_sched_shares_ratelimit; -extern unsigned int sysctl_sched_shares_thresh; extern unsigned int sysctl_sched_child_runs_first; enum sched_tunable_scaling { diff --git a/kernel/sched.c b/kernel/sched.c index b0d5f1b24a39..e2f1a3024a99 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -253,6 +253,8 @@ struct task_group { /* runqueue "owned" by this group on each cpu */ struct cfs_rq **cfs_rq; unsigned long shares; + + atomic_t load_weight; #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -359,15 +361,11 @@ struct cfs_rq { */ unsigned long h_load; - /* - * this cpu's part of tg->shares - */ - unsigned long shares; + u64 load_avg; + u64 load_period; + u64 load_stamp; - /* - * load.weight at the time we set shares - */ - unsigned long rq_weight; + unsigned long load_contribution; #endif #endif }; @@ -806,20 +804,6 @@ late_initcall(sched_init_debug); */ const_debug unsigned int sysctl_sched_nr_migrate = 32; -/* - * ratelimit for updating the group shares. - * default: 0.25ms - */ -unsigned int sysctl_sched_shares_ratelimit = 250000; -unsigned int normalized_sysctl_sched_shares_ratelimit = 250000; - -/* - * Inject some fuzzyness into changing the per-cpu group shares - * this avoids remote rq-locks at the expense of fairness. - * default: 4 - */ -unsigned int sysctl_sched_shares_thresh = 4; - /* * period over which we average the RT time consumption, measured * in ms. @@ -1369,6 +1353,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec) lw->inv_weight = 0; } +static inline void update_load_set(struct load_weight *lw, unsigned long w) +{ + lw->weight = w; + lw->inv_weight = 0; +} + /* * To aid in avoiding the subversion of "niceness" due to uneven distribution * of tasks with abnormal "nice" values across CPUs the contribution that @@ -1557,97 +1547,44 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static __read_mostly unsigned long __percpu *update_shares_data; - -static void __set_se_shares(struct sched_entity *se, unsigned long shares); - -/* - * Calculate and set the cpu's group shares. - */ -static void update_group_shares_cpu(struct task_group *tg, int cpu, - unsigned long sd_shares, - unsigned long sd_rq_weight, - unsigned long *usd_rq_weight) -{ - unsigned long shares, rq_weight; - int boost = 0; - - rq_weight = usd_rq_weight[cpu]; - if (!rq_weight) { - boost = 1; - rq_weight = NICE_0_LOAD; - } - - /* - * \Sum_j shares_j * rq_weight_i - * shares_i = ----------------------------- - * \Sum_j rq_weight_j - */ - shares = (sd_shares * rq_weight) / sd_rq_weight; - shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); - - if (abs(shares - tg->se[cpu]->load.weight) > - sysctl_sched_shares_thresh) { - struct rq *rq = cpu_rq(cpu); - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight; - tg->cfs_rq[cpu]->shares = boost ? 0 : shares; - __set_se_shares(tg->se[cpu], shares); - raw_spin_unlock_irqrestore(&rq->lock, flags); - } -} +static void update_cfs_load(struct cfs_rq *cfs_rq); +static void update_cfs_shares(struct cfs_rq *cfs_rq); /* - * Re-compute the task group their per cpu shares over the given domain. - * This needs to be done in a bottom-up fashion because the rq weight of a - * parent group depends on the shares of its child groups. + * update tg->load_weight by folding this cpu's load_avg */ static int tg_shares_up(struct task_group *tg, void *data) { - unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0; - unsigned long *usd_rq_weight; - struct sched_domain *sd = data; + long load_avg; + struct cfs_rq *cfs_rq; unsigned long flags; - int i; + int cpu = (long)data; + struct rq *rq; - if (!tg->se[0]) + if (!tg->se[cpu]) return 0; - local_irq_save(flags); - usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id()); - - for_each_cpu(i, sched_domain_span(sd)) { - weight = tg->cfs_rq[i]->load.weight; - usd_rq_weight[i] = weight; - - rq_weight += weight; - /* - * If there are currently no tasks on the cpu pretend there - * is one of average load so that when a new task gets to - * run here it will not get delayed by group starvation. - */ - if (!weight) - weight = NICE_0_LOAD; + rq = cpu_rq(cpu); + cfs_rq = tg->cfs_rq[cpu]; - sum_weight += weight; - shares += tg->cfs_rq[i]->shares; - } + raw_spin_lock_irqsave(&rq->lock, flags); - if (!rq_weight) - rq_weight = sum_weight; + update_rq_clock(rq); + update_cfs_load(cfs_rq); - if ((!shares && rq_weight) || shares > tg->shares) - shares = tg->shares; + load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1); + load_avg -= cfs_rq->load_contribution; - if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) - shares = tg->shares; + atomic_add(load_avg, &tg->load_weight); + cfs_rq->load_contribution += load_avg; - for_each_cpu(i, sched_domain_span(sd)) - update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight); + /* + * We need to update shares after updating tg->load_weight in + * order to adjust the weight of groups with long running tasks. + */ + update_cfs_shares(cfs_rq); - local_irq_restore(flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); return 0; } @@ -1666,7 +1603,7 @@ static int tg_load_down(struct task_group *tg, void *data) load = cpu_rq(cpu)->load.weight; } else { load = tg->parent->cfs_rq[cpu]->h_load; - load *= tg->cfs_rq[cpu]->shares; + load *= tg->se[cpu]->load.weight; load /= tg->parent->cfs_rq[cpu]->load.weight + 1; } @@ -1675,21 +1612,16 @@ static int tg_load_down(struct task_group *tg, void *data) return 0; } -static void update_shares(struct sched_domain *sd) +static void update_shares(long cpu) { - s64 elapsed; - u64 now; - if (root_task_group_empty()) return; - now = local_clock(); - elapsed = now - sd->last_update; + /* + * XXX: replace with an on-demand list + */ - if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { - sd->last_update = now; - walk_tg_tree(tg_nop, tg_shares_up, sd); - } + walk_tg_tree(tg_nop, tg_shares_up, (void *)cpu); } static void update_h_load(long cpu) @@ -1699,7 +1631,7 @@ static void update_h_load(long cpu) #else -static inline void update_shares(struct sched_domain *sd) +static inline void update_shares(int cpu) { } @@ -1824,15 +1756,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) #endif -#ifdef CONFIG_FAIR_GROUP_SCHED -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) -{ -#ifdef CONFIG_SMP - cfs_rq->shares = shares; -#endif -} -#endif - static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); @@ -5551,7 +5474,6 @@ static void update_sysctl(void) SET_SYSCTL(sched_min_granularity); SET_SYSCTL(sched_latency); SET_SYSCTL(sched_wakeup_granularity); - SET_SYSCTL(sched_shares_ratelimit); #undef SET_SYSCTL } @@ -7787,8 +7709,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, se->cfs_rq = parent->my_q; se->my_q = cfs_rq; - se->load.weight = tg->shares; - se->load.inv_weight = 0; + update_load_set(&se->load, tg->shares); se->parent = parent; } #endif @@ -7881,10 +7802,6 @@ void __init sched_init(void) #endif /* CONFIG_CGROUP_SCHED */ -#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP - update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long), - __alignof__(unsigned long)); -#endif for_each_possible_cpu(i) { struct rq *rq; @@ -8452,8 +8369,7 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares) if (on_rq) dequeue_entity(cfs_rq, se, 0); - se->load.weight = shares; - se->load.inv_weight = 0; + update_load_set(&se->load, shares); if (on_rq) enqueue_entity(cfs_rq, se, 0); @@ -8510,7 +8426,6 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) /* * force a rebalance */ - cfs_rq_set_shares(tg->cfs_rq[i], 0); set_se_shares(tg->se[i], shares); } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 2e1b0d17dd9b..e6590e7312e8 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -202,15 +202,22 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) spread0 = min_vruntime - rq0_min_vruntime; SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0", SPLIT_NS(spread0)); - SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); - SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); - SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over", cfs_rq->nr_spread_over); + SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); + SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_avg", + SPLIT_NS(cfs_rq->load_avg)); + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_period", + SPLIT_NS(cfs_rq->load_period)); + SEQ_printf(m, " .%-30s: %ld\n", "load_contrib", + cfs_rq->load_contribution); + SEQ_printf(m, " .%-30s: %d\n", "load_tg", + atomic_read(&tg->load_weight)); #endif + print_cfs_group_stats(m, cpu, cfs_rq->tg); #endif } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index f4f6a8326dd0..d86544b4151c 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -417,7 +417,6 @@ int sched_proc_update_handler(struct ctl_table *table, int write, WRT_SYSCTL(sched_min_granularity); WRT_SYSCTL(sched_latency); WRT_SYSCTL(sched_wakeup_granularity); - WRT_SYSCTL(sched_shares_ratelimit); #undef WRT_SYSCTL return 0; @@ -633,7 +632,6 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_add(&se->group_node, &cfs_rq->tasks); } cfs_rq->nr_running++; - se->on_rq = 1; } static void @@ -647,9 +645,89 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_del_init(&se->group_node); } cfs_rq->nr_running--; - se->on_rq = 0; } +#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED +static void update_cfs_load(struct cfs_rq *cfs_rq) +{ + u64 period = sched_avg_period(); + u64 now, delta; + + if (!cfs_rq) + return; + + now = rq_of(cfs_rq)->clock; + delta = now - cfs_rq->load_stamp; + + cfs_rq->load_stamp = now; + cfs_rq->load_period += delta; + cfs_rq->load_avg += delta * cfs_rq->load.weight; + + while (cfs_rq->load_period > period) { + /* + * Inline assembly required to prevent the compiler + * optimising this loop into a divmod call. + * See __iter_div_u64_rem() for another example of this. + */ + asm("" : "+rm" (cfs_rq->load_period)); + cfs_rq->load_period /= 2; + cfs_rq->load_avg /= 2; + } +} + +static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, + unsigned long weight) +{ + if (se->on_rq) + account_entity_dequeue(cfs_rq, se); + + update_load_set(&se->load, weight); + + if (se->on_rq) + account_entity_enqueue(cfs_rq, se); +} + +static void update_cfs_shares(struct cfs_rq *cfs_rq) +{ + struct task_group *tg; + struct sched_entity *se; + long load_weight, load, shares; + + if (!cfs_rq) + return; + + tg = cfs_rq->tg; + se = tg->se[cpu_of(rq_of(cfs_rq))]; + if (!se) + return; + + load = cfs_rq->load.weight; + + load_weight = atomic_read(&tg->load_weight); + load_weight -= cfs_rq->load_contribution; + load_weight += load; + + shares = (tg->shares * load); + if (load_weight) + shares /= load_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + if (shares > tg->shares) + shares = tg->shares; + + reweight_entity(cfs_rq_of(se), se, shares); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void update_cfs_load(struct cfs_rq *cfs_rq) +{ +} + +static inline void update_cfs_shares(struct cfs_rq *cfs_rq) +{ +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { #ifdef CONFIG_SCHEDSTATS @@ -771,7 +849,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); + update_cfs_load(cfs_rq); account_entity_enqueue(cfs_rq, se); + update_cfs_shares(cfs_rq); if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); @@ -782,6 +862,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) check_spread(cfs_rq, se); if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); + se->on_rq = 1; } static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -825,8 +906,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); + se->on_rq = 0; + update_cfs_load(cfs_rq); account_entity_dequeue(cfs_rq, se); update_min_vruntime(cfs_rq); + update_cfs_shares(cfs_rq); /* * Normalize the entity after updating the min_vruntime because the @@ -1055,6 +1139,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) flags = ENQUEUE_WAKEUP; } + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + update_cfs_load(cfs_rq); + update_cfs_shares(cfs_rq); + } + hrtick_update(rq); } @@ -1071,12 +1162,20 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); + /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) break; flags |= DEQUEUE_SLEEP; } + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + update_cfs_load(cfs_rq); + update_cfs_shares(cfs_rq); + } + hrtick_update(rq); } @@ -1143,51 +1242,20 @@ static void task_waking_fair(struct rq *rq, struct task_struct *p) * Adding load to a group doesn't make a group heavier, but can cause movement * of group shares between cpus. Assuming the shares were perfectly aligned one * can calculate the shift in shares. - * - * The problem is that perfectly aligning the shares is rather expensive, hence - * we try to avoid doing that too often - see update_shares(), which ratelimits - * this change. - * - * We compensate this by not only taking the current delta into account, but - * also considering the delta between when the shares were last adjusted and - * now. - * - * We still saw a performance dip, some tracing learned us that between - * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased - * significantly. Therefore try to bias the error in direction of failing - * the affine wakeup. - * */ -static long effective_load(struct task_group *tg, int cpu, - long wl, long wg) +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) { struct sched_entity *se = tg->se[cpu]; if (!tg->parent) return wl; - /* - * By not taking the decrease of shares on the other cpu into - * account our error leans towards reducing the affine wakeups. - */ - if (!wl && sched_feat(ASYM_EFF_LOAD)) - return wl; - for_each_sched_entity(se) { long S, rw, s, a, b; - long more_w; - - /* - * Instead of using this increment, also add the difference - * between when the shares were last updated and now. - */ - more_w = se->my_q->load.weight - se->my_q->rq_weight; - wl += more_w; - wg += more_w; S = se->my_q->tg->shares; - s = se->my_q->shares; - rw = se->my_q->rq_weight; + s = se->load.weight; + rw = se->my_q->load.weight; a = S*(rw + wl); b = S*rw + s*wg; @@ -1508,23 +1576,6 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ sd = tmp; } -#ifdef CONFIG_FAIR_GROUP_SCHED - if (sched_feat(LB_SHARES_UPDATE)) { - /* - * Pick the largest domain to update shares over - */ - tmp = sd; - if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight)) - tmp = affine_sd; - - if (tmp) { - raw_spin_unlock(&rq->lock); - update_shares(tmp); - raw_spin_lock(&rq->lock); - } - } -#endif - if (affine_sd) { if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) return select_idle_sibling(p, cpu); @@ -3014,7 +3065,6 @@ static int load_balance(int this_cpu, struct rq *this_rq, schedstat_inc(sd, lb_count[idle]); redo: - update_shares(sd); group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, cpus, balance); @@ -3156,8 +3206,6 @@ out_one_pinned: else ld_moved = 0; out: - if (ld_moved) - update_shares(sd); return ld_moved; } @@ -3549,6 +3597,8 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) int update_next_balance = 0; int need_serialize; + update_shares(cpu); + for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) continue; diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 185f920ec1a2..68e69acc29b9 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -52,8 +52,6 @@ SCHED_FEAT(ARCH_POWER, 0) SCHED_FEAT(HRTICK, 0) SCHED_FEAT(DOUBLE_TICK, 0) SCHED_FEAT(LB_BIAS, 1) -SCHED_FEAT(LB_SHARES_UPDATE, 1) -SCHED_FEAT(ASYM_EFF_LOAD, 1) /* * Spin-wait on mutex acquisition when the mutex owner is running on diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b65bf634035e..3132b25193db 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -259,8 +259,6 @@ static int min_wakeup_granularity_ns; /* 0 usecs */ static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; -static int min_sched_shares_ratelimit = 100000; /* 100 usec */ -static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */ #endif #ifdef CONFIG_COMPACTION @@ -304,15 +302,6 @@ static struct ctl_table kern_table[] = { .extra1 = &min_wakeup_granularity_ns, .extra2 = &max_wakeup_granularity_ns, }, - { - .procname = "sched_shares_ratelimit", - .data = &sysctl_sched_shares_ratelimit, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_proc_update_handler, - .extra1 = &min_sched_shares_ratelimit, - .extra2 = &max_sched_shares_ratelimit, - }, { .procname = "sched_tunable_scaling", .data = &sysctl_sched_tunable_scaling, @@ -322,14 +311,6 @@ static struct ctl_table kern_table[] = { .extra1 = &min_sched_tunable_scaling, .extra2 = &max_sched_tunable_scaling, }, - { - .procname = "sched_shares_thresh", - .data = &sysctl_sched_shares_thresh, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - }, { .procname = "sched_migration_cost", .data = &sysctl_sched_migration_cost, -- cgit v1.2.3 From 3d4b47b4b040c9d77dd68104cfc1055d89a55afd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Nov 2010 15:47:01 -0800 Subject: sched: Implement on-demand (active) cfs_rq list Make certain load-balance actions scale per number of active cgroups instead of the number of existing cgroups. This makes wakeup/sleep paths more expensive, but is a win for systems where the vast majority of existing cgroups are idle. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.666535048@google.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 105 ++++++++++++++-------------------------------------- kernel/sched_fair.c | 46 ++++++++++++++++++++--- kernel/sched_rt.c | 24 ++++++++++++ 3 files changed, 92 insertions(+), 83 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index e2f1a3024a99..22436dd2e19f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -274,9 +274,7 @@ struct task_group { #define root_task_group init_task_group -/* task_group_lock serializes add/remove of task groups and also changes to - * a task group's cpu shares. - */ +/* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); #ifdef CONFIG_FAIR_GROUP_SCHED @@ -344,6 +342,7 @@ struct cfs_rq { * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This * list is used during load balance. */ + int on_list; struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ @@ -1547,7 +1546,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static void update_cfs_load(struct cfs_rq *cfs_rq); +static void update_cfs_load(struct cfs_rq *cfs_rq, int lb); static void update_cfs_shares(struct cfs_rq *cfs_rq); /* @@ -1570,7 +1569,7 @@ static int tg_shares_up(struct task_group *tg, void *data) raw_spin_lock_irqsave(&rq->lock, flags); update_rq_clock(rq); - update_cfs_load(cfs_rq); + update_cfs_load(cfs_rq, 1); load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1); load_avg -= cfs_rq->load_contribution; @@ -7688,15 +7687,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) #ifdef CONFIG_FAIR_GROUP_SCHED static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, - struct sched_entity *se, int cpu, int add, + struct sched_entity *se, int cpu, struct sched_entity *parent) { struct rq *rq = cpu_rq(cpu); tg->cfs_rq[cpu] = cfs_rq; init_cfs_rq(cfs_rq, rq); cfs_rq->tg = tg; - if (add) - list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list); tg->se[cpu] = se; /* se could be NULL for init_task_group */ @@ -7716,7 +7713,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, #ifdef CONFIG_RT_GROUP_SCHED static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, - struct sched_rt_entity *rt_se, int cpu, int add, + struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent) { struct rq *rq = cpu_rq(cpu); @@ -7725,8 +7722,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, init_rt_rq(rt_rq, rq); rt_rq->tg = tg; rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; - if (add) - list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list); tg->rt_se[cpu] = rt_se; if (!rt_se) @@ -7835,7 +7830,7 @@ void __init sched_init(void) * We achieve this by letting init_task_group's tasks sit * directly in rq->cfs (i.e init_task_group->se[] = NULL). */ - init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL); + init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, NULL); #endif #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -7843,7 +7838,7 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED INIT_LIST_HEAD(&rq->leaf_rt_rq_list); #ifdef CONFIG_CGROUP_SCHED - init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL); + init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, NULL); #endif #endif @@ -8119,7 +8114,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) if (!se) goto err_free_rq; - init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]); + init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); } return 1; @@ -8130,15 +8125,22 @@ err: return 0; } -static inline void register_fair_sched_group(struct task_group *tg, int cpu) -{ - list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list, - &cpu_rq(cpu)->leaf_cfs_rq_list); -} - static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { - list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list); + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + int i; + + /* + * Only empty task groups can be destroyed; so we can speculatively + * check on_list without danger of it being re-added. + */ + if (!tg->cfs_rq[cpu]->on_list) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); + list_del_leaf_cfs_rq(tg->cfs_rq[i]); + raw_spin_unlock_irqrestore(&rq->lock, flags); } #else /* !CONFG_FAIR_GROUP_SCHED */ static inline void free_fair_sched_group(struct task_group *tg) @@ -8151,10 +8153,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) return 1; } -static inline void register_fair_sched_group(struct task_group *tg, int cpu) -{ -} - static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { } @@ -8209,7 +8207,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) if (!rt_se) goto err_free_rq; - init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]); + init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); } return 1; @@ -8219,17 +8217,6 @@ err_free_rq: err: return 0; } - -static inline void register_rt_sched_group(struct task_group *tg, int cpu) -{ - list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list, - &cpu_rq(cpu)->leaf_rt_rq_list); -} - -static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) -{ - list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list); -} #else /* !CONFIG_RT_GROUP_SCHED */ static inline void free_rt_sched_group(struct task_group *tg) { @@ -8240,14 +8227,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) { return 1; } - -static inline void register_rt_sched_group(struct task_group *tg, int cpu) -{ -} - -static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) -{ -} #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CGROUP_SCHED @@ -8263,7 +8242,6 @@ struct task_group *sched_create_group(struct task_group *parent) { struct task_group *tg; unsigned long flags; - int i; tg = kzalloc(sizeof(*tg), GFP_KERNEL); if (!tg) @@ -8276,10 +8254,6 @@ struct task_group *sched_create_group(struct task_group *parent) goto err; spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) { - register_fair_sched_group(tg, i); - register_rt_sched_group(tg, i); - } list_add_rcu(&tg->list, &task_groups); WARN_ON(!parent); /* root should already exist */ @@ -8309,11 +8283,11 @@ void sched_destroy_group(struct task_group *tg) unsigned long flags; int i; - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) { + /* end participation in shares distribution */ + for_each_possible_cpu(i) unregister_fair_sched_group(tg, i); - unregister_rt_sched_group(tg, i); - } + + spin_lock_irqsave(&task_group_lock, flags); list_del_rcu(&tg->list); list_del_rcu(&tg->siblings); spin_unlock_irqrestore(&task_group_lock, flags); @@ -8391,7 +8365,6 @@ static DEFINE_MUTEX(shares_mutex); int sched_group_set_shares(struct task_group *tg, unsigned long shares) { int i; - unsigned long flags; /* * We can't change the weight of the root cgroup. @@ -8408,19 +8381,6 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) if (tg->shares == shares) goto done; - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) - unregister_fair_sched_group(tg, i); - list_del_rcu(&tg->siblings); - spin_unlock_irqrestore(&task_group_lock, flags); - - /* wait for any ongoing reference to this group to finish */ - synchronize_sched(); - - /* - * Now we are free to modify the group's share on each cpu - * w/o tripping rebalance_share or load_balance_fair. - */ tg->shares = shares; for_each_possible_cpu(i) { /* @@ -8429,15 +8389,6 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) set_se_shares(tg->se[i], shares); } - /* - * Enable load balance activity on this group, by inserting it back on - * each cpu's rq->leaf_cfs_rq_list. - */ - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) - register_fair_sched_group(tg, i); - list_add_rcu(&tg->siblings, &tg->parent->children); - spin_unlock_irqrestore(&task_group_lock, flags); done: mutex_unlock(&shares_mutex); return 0; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index d86544b4151c..0560e72bd732 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -143,6 +143,24 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) return cfs_rq->tg->cfs_rq[this_cpu]; } +static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (!cfs_rq->on_list) { + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq_of(cfs_rq)->leaf_cfs_rq_list); + + cfs_rq->on_list = 1; + } +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->on_list) { + list_del_rcu(&cfs_rq->leaf_cfs_rq_list); + cfs_rq->on_list = 0; + } +} + /* Iterate thr' all leaf cfs_rq's on a runqueue */ #define for_each_leaf_cfs_rq(rq, cfs_rq) \ list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) @@ -246,6 +264,14 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) return &cpu_rq(this_cpu)->cfs; } +static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + #define for_each_leaf_cfs_rq(rq, cfs_rq) \ for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) @@ -648,7 +674,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void update_cfs_load(struct cfs_rq *cfs_rq) +static void update_cfs_load(struct cfs_rq *cfs_rq, int lb) { u64 period = sched_avg_period(); u64 now, delta; @@ -673,6 +699,11 @@ static void update_cfs_load(struct cfs_rq *cfs_rq) cfs_rq->load_period /= 2; cfs_rq->load_avg /= 2; } + + if (lb && !cfs_rq->nr_running) { + if (cfs_rq->load_avg < (period / 8)) + list_del_leaf_cfs_rq(cfs_rq); + } } static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, @@ -719,7 +750,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq) reweight_entity(cfs_rq_of(se), se, shares); } #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_cfs_load(struct cfs_rq *cfs_rq) +static inline void update_cfs_load(struct cfs_rq *cfs_rq, int lb) { } @@ -849,7 +880,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); - update_cfs_load(cfs_rq); + update_cfs_load(cfs_rq, 0); account_entity_enqueue(cfs_rq, se); update_cfs_shares(cfs_rq); @@ -863,6 +894,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; + + if (cfs_rq->nr_running == 1) + list_add_leaf_cfs_rq(cfs_rq); } static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -907,7 +941,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); se->on_rq = 0; - update_cfs_load(cfs_rq); + update_cfs_load(cfs_rq, 0); account_entity_dequeue(cfs_rq, se); update_min_vruntime(cfs_rq); update_cfs_shares(cfs_rq); @@ -1142,7 +1176,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - update_cfs_load(cfs_rq); + update_cfs_load(cfs_rq, 0); update_cfs_shares(cfs_rq); } @@ -1172,7 +1206,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - update_cfs_load(cfs_rq); + update_cfs_load(cfs_rq, 0); update_cfs_shares(cfs_rq); } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index bea7d79f7e9c..c914ec747ca6 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -183,6 +183,17 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period); } +static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) +{ + list_add_rcu(&rt_rq->leaf_rt_rq_list, + &rq_of_rt_rq(rt_rq)->leaf_rt_rq_list); +} + +static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq) +{ + list_del_rcu(&rt_rq->leaf_rt_rq_list); +} + #define for_each_leaf_rt_rq(rt_rq, rq) \ list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list) @@ -276,6 +287,14 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) return ktime_to_ns(def_rt_bandwidth.rt_period); } +static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) +{ +} + +static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq) +{ +} + #define for_each_leaf_rt_rq(rt_rq, rq) \ for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL) @@ -825,6 +844,9 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) return; + if (!rt_rq->rt_nr_running) + list_add_leaf_rt_rq(rt_rq); + if (head) list_add(&rt_se->run_list, queue); else @@ -844,6 +866,8 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) __clear_bit(rt_se_prio(rt_se), array->bitmap); dec_rt_tasks(rt_se, rt_rq); + if (!rt_rq->rt_nr_running) + list_del_leaf_rt_rq(rt_rq); } /* -- cgit v1.2.3 From 9e3081ca61147b29f52fddb4f7c6b6b82ea5eb7a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Nov 2010 15:47:02 -0800 Subject: sched: Make tg_shares_up() walk on-demand Make tg_shares_up() use the active cgroup list, this means we cannot do a strict bottom-up walk of the hierarchy, but assuming its a very wide tree with a small number of active groups it should be a win. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.754159484@google.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 67 ----------------------------------------------------- kernel/sched_fair.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+), 67 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 22436dd2e19f..6268d2dc9a91 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -279,13 +279,6 @@ static DEFINE_SPINLOCK(task_group_lock); #ifdef CONFIG_FAIR_GROUP_SCHED -#ifdef CONFIG_SMP -static int root_task_group_empty(void) -{ - return list_empty(&root_task_group.children); -} -#endif - # define INIT_TASK_GROUP_LOAD NICE_0_LOAD /* @@ -1546,48 +1539,6 @@ static unsigned long cpu_avg_load_per_task(int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED -static void update_cfs_load(struct cfs_rq *cfs_rq, int lb); -static void update_cfs_shares(struct cfs_rq *cfs_rq); - -/* - * update tg->load_weight by folding this cpu's load_avg - */ -static int tg_shares_up(struct task_group *tg, void *data) -{ - long load_avg; - struct cfs_rq *cfs_rq; - unsigned long flags; - int cpu = (long)data; - struct rq *rq; - - if (!tg->se[cpu]) - return 0; - - rq = cpu_rq(cpu); - cfs_rq = tg->cfs_rq[cpu]; - - raw_spin_lock_irqsave(&rq->lock, flags); - - update_rq_clock(rq); - update_cfs_load(cfs_rq, 1); - - load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1); - load_avg -= cfs_rq->load_contribution; - - atomic_add(load_avg, &tg->load_weight); - cfs_rq->load_contribution += load_avg; - - /* - * We need to update shares after updating tg->load_weight in - * order to adjust the weight of groups with long running tasks. - */ - update_cfs_shares(cfs_rq); - - raw_spin_unlock_irqrestore(&rq->lock, flags); - - return 0; -} - /* * Compute the cpu's hierarchical load factor for each task group. * This needs to be done in a top-down fashion because the load of a child @@ -1611,29 +1562,11 @@ static int tg_load_down(struct task_group *tg, void *data) return 0; } -static void update_shares(long cpu) -{ - if (root_task_group_empty()) - return; - - /* - * XXX: replace with an on-demand list - */ - - walk_tg_tree(tg_nop, tg_shares_up, (void *)cpu); -} - static void update_h_load(long cpu) { walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); } -#else - -static inline void update_shares(int cpu) -{ -} - #endif #ifdef CONFIG_PREEMPT diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 0560e72bd732..46ff6587dc16 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2004,6 +2004,60 @@ out: } #ifdef CONFIG_FAIR_GROUP_SCHED +/* + * update tg->load_weight by folding this cpu's load_avg + */ +static int tg_shares_up(struct task_group *tg, int cpu) +{ + struct cfs_rq *cfs_rq; + unsigned long flags; + struct rq *rq; + long load_avg; + + if (!tg->se[cpu]) + return 0; + + rq = cpu_rq(cpu); + cfs_rq = tg->cfs_rq[cpu]; + + raw_spin_lock_irqsave(&rq->lock, flags); + + update_rq_clock(rq); + update_cfs_load(cfs_rq, 1); + + load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1); + load_avg -= cfs_rq->load_contribution; + atomic_add(load_avg, &tg->load_weight); + cfs_rq->load_contribution += load_avg; + + /* + * We need to update shares after updating tg->load_weight in + * order to adjust the weight of groups with long running tasks. + */ + update_cfs_shares(cfs_rq); + + raw_spin_unlock_irqrestore(&rq->lock, flags); + + return 0; +} + +static void update_shares(int cpu) +{ + struct cfs_rq *cfs_rq; + struct rq *rq = cpu_rq(cpu); + + rcu_read_lock(); + for_each_leaf_cfs_rq(rq, cfs_rq) { + struct task_group *tg = cfs_rq->tg; + + do { + tg_shares_up(tg, cpu); + tg = tg->parent; + } while (tg); + } + rcu_read_unlock(); +} + static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, @@ -2051,6 +2105,10 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, return max_load_move - rem_load_move; } #else +static inline void update_shares(int cpu) +{ +} + static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, -- cgit v1.2.3 From e33078baa4d30ad1d0e46d1f62b9e5a63a3e6ee3 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 15 Nov 2010 15:47:04 -0800 Subject: sched: Fix update_cfs_load() synchronization Using cfs_rq->nr_running is not sufficient to synchronize update_cfs_load with the put path since nr_running accounting occurs at deactivation. It's also not safe to make the removal decision based on load_avg as this fails with both high periods and low shares. Resolve this by clipping history after 4 periods without activity. Note: the above will always occur from update_shares() since in the last-task-sleep-case that task will still be cfs_rq->curr when update_cfs_load is called. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.933428187@google.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- kernel/sched_fair.c | 33 +++++++++++++++++++++------------ 2 files changed, 22 insertions(+), 13 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 6268d2dc9a91..dadab4d13875 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -355,7 +355,7 @@ struct cfs_rq { u64 load_avg; u64 load_period; - u64 load_stamp; + u64 load_stamp, load_last; unsigned long load_contribution; #endif diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index d52b97a04e7a..a543a5b202a4 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -674,10 +674,11 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void update_cfs_load(struct cfs_rq *cfs_rq, int lb) +static void update_cfs_load(struct cfs_rq *cfs_rq) { u64 period = sched_avg_period(); u64 now, delta; + unsigned long load = cfs_rq->load.weight; if (!cfs_rq) return; @@ -685,9 +686,19 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int lb) now = rq_of(cfs_rq)->clock; delta = now - cfs_rq->load_stamp; + /* truncate load history at 4 idle periods */ + if (cfs_rq->load_stamp > cfs_rq->load_last && + now - cfs_rq->load_last > 4 * period) { + cfs_rq->load_period = 0; + cfs_rq->load_avg = 0; + } + cfs_rq->load_stamp = now; cfs_rq->load_period += delta; - cfs_rq->load_avg += delta * cfs_rq->load.weight; + if (load) { + cfs_rq->load_last = now; + cfs_rq->load_avg += delta * load; + } while (cfs_rq->load_period > period) { /* @@ -700,10 +711,8 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int lb) cfs_rq->load_avg /= 2; } - if (lb && !cfs_rq->nr_running) { - if (cfs_rq->load_avg < (period / 8)) - list_del_leaf_cfs_rq(cfs_rq); - } + if (!cfs_rq->curr && !cfs_rq->nr_running && !cfs_rq->load_avg) + list_del_leaf_cfs_rq(cfs_rq); } static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, @@ -750,7 +759,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta) reweight_entity(cfs_rq_of(se), se, shares); } #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_cfs_load(struct cfs_rq *cfs_rq, int lb) +static inline void update_cfs_load(struct cfs_rq *cfs_rq) { } @@ -880,7 +889,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); - update_cfs_load(cfs_rq, 0); + update_cfs_load(cfs_rq); update_cfs_shares(cfs_rq, se->load.weight); account_entity_enqueue(cfs_rq, se); @@ -941,7 +950,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); se->on_rq = 0; - update_cfs_load(cfs_rq, 0); + update_cfs_load(cfs_rq); account_entity_dequeue(cfs_rq, se); update_min_vruntime(cfs_rq); update_cfs_shares(cfs_rq, 0); @@ -1176,7 +1185,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - update_cfs_load(cfs_rq, 0); + update_cfs_load(cfs_rq); update_cfs_shares(cfs_rq, 0); } @@ -1206,7 +1215,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - update_cfs_load(cfs_rq, 0); + update_cfs_load(cfs_rq); update_cfs_shares(cfs_rq, 0); } @@ -2023,7 +2032,7 @@ static int tg_shares_up(struct task_group *tg, int cpu) raw_spin_lock_irqsave(&rq->lock, flags); update_rq_clock(rq); - update_cfs_load(cfs_rq, 1); + update_cfs_load(cfs_rq); load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1); load_avg -= cfs_rq->load_contribution; -- cgit v1.2.3 From 3b3d190ec3683d568fd2ebaead5e1ec7f97b6e37 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 15 Nov 2010 15:47:08 -0800 Subject: sched: Implement demand based update_cfs_load() When the system is busy, dilation of rq->next_balance makes lb->update_shares() insufficiently frequent for threads which don't sleep (no dequeue/enqueue updates). Adjust for this by making demand based updates based on the accumulation of execution time sufficient to wrap our averaging window. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234938.291159744@google.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 9 ++++++++- kernel/sched_fair.c | 12 ++++++++++++ 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index dadab4d13875..e914a716e1d4 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -353,9 +353,16 @@ struct cfs_rq { */ unsigned long h_load; + /* + * Maintaining per-cpu shares distribution for group scheduling + * + * load_stamp is the last time we updated the load average + * load_last is the last time we updated the load average and saw load + * load_unacc_exec_time is currently unaccounted execution time + */ u64 load_avg; u64 load_period; - u64 load_stamp, load_last; + u64 load_stamp, load_last, load_unacc_exec_time; unsigned long load_contribution; #endif diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 33f941dcf88c..e7e2f08e6d01 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -539,6 +539,9 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) return calc_delta_fair(sched_slice(cfs_rq, se), se); } +static void update_cfs_load(struct cfs_rq *cfs_rq); +static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta); + /* * Update the current task's runtime statistics. Skip current tasks that * are not in our scheduling class. @@ -558,6 +561,14 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, curr->vruntime += delta_exec_weighted; update_min_vruntime(cfs_rq); + +#ifdef CONFIG_FAIR_GROUP_SCHED + cfs_rq->load_unacc_exec_time += delta_exec; + if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) { + update_cfs_load(cfs_rq); + update_cfs_shares(cfs_rq, 0); + } +#endif } static void update_curr(struct cfs_rq *cfs_rq) @@ -713,6 +724,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq) } cfs_rq->load_stamp = now; + cfs_rq->load_unacc_exec_time = 0; cfs_rq->load_period += delta; if (load) { cfs_rq->load_last = now; -- cgit v1.2.3 From 9437178f623a19af5951808d880a8599f66ac150 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 15 Nov 2010 15:47:10 -0800 Subject: sched: Update tg->shares after cpu.shares write Formerly sched_group_set_shares would force a rebalance by overflowing domain share sums. Now that per-cpu averages are maintained we can set the true value by issuing an update_cfs_shares() following a tg->shares update. Also initialize tg se->load to 0 for consistency since we'll now set correct weights on enqueue. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234938.465521344@google.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 42 +++++++++++------------------------------- 1 file changed, 11 insertions(+), 31 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index e914a716e1d4..550cf3a02377 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7646,7 +7646,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, se->cfs_rq = parent->my_q; se->my_q = cfs_rq; - update_load_set(&se->load, tg->shares); + update_load_set(&se->load, 0); se->parent = parent; } #endif @@ -8274,37 +8274,12 @@ void sched_move_task(struct task_struct *tsk) #endif /* CONFIG_CGROUP_SCHED */ #ifdef CONFIG_FAIR_GROUP_SCHED -static void __set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - int on_rq; - - on_rq = se->on_rq; - if (on_rq) - dequeue_entity(cfs_rq, se, 0); - - update_load_set(&se->load, shares); - - if (on_rq) - enqueue_entity(cfs_rq, se, 0); -} - -static void set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - struct rq *rq = cfs_rq->rq; - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - __set_se_shares(se, shares); - raw_spin_unlock_irqrestore(&rq->lock, flags); -} - static DEFINE_MUTEX(shares_mutex); int sched_group_set_shares(struct task_group *tg, unsigned long shares) { int i; + unsigned long flags; /* * We can't change the weight of the root cgroup. @@ -8323,10 +8298,15 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) tg->shares = shares; for_each_possible_cpu(i) { - /* - * force a rebalance - */ - set_se_shares(tg->se[i], shares); + struct rq *rq = cpu_rq(i); + struct sched_entity *se; + + se = tg->se[i]; + /* Propagate contribution to hierarchy */ + raw_spin_lock_irqsave(&rq->lock, flags); + for_each_sched_entity(se) + update_cfs_shares(group_cfs_rq(se), 0); + raw_spin_unlock_irqrestore(&rq->lock, flags); } done: -- cgit v1.2.3 From 28d0686cf7b14e30243096bd874d3f80591ed392 Mon Sep 17 00:00:00 2001 From: Erik Gilling Date: Fri, 19 Nov 2010 18:08:51 -0800 Subject: sched: Make task dump print all 15 chars of proc comm Signed-off-by: Erik Gilling Signed-off-by: John Stultz Signed-off-by: Peter Zijlstra LKML-Reference: <1290218934-8544-3-git-send-email-john.stultz@linaro.org> Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 550cf3a02377..324afce0e223 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5249,7 +5249,7 @@ void sched_show_task(struct task_struct *p) unsigned state; state = p->state ? __ffs(p->state) + 1 : 0; - printk(KERN_INFO "%-13.13s %c", p->comm, + printk(KERN_INFO "%-15.15s %c", p->comm, state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); #if BITS_PER_LONG == 32 if (state == TASK_RUNNING) -- cgit v1.2.3 From 335d7afbfb71faac833734a94240c1e07cf0ead8 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 22 Nov 2010 15:47:36 +0100 Subject: mutexes, sched: Introduce arch_mutex_cpu_relax() The spinning mutex implementation uses cpu_relax() in busy loops as a compiler barrier. Depending on the architecture, cpu_relax() may do more than needed in this specific mutex spin loops. On System z we also give up the time slice of the virtual cpu in cpu_relax(), which prevents effective spinning on the mutex. This patch replaces cpu_relax() in the spinning mutex code with arch_mutex_cpu_relax(), which can be defined by each architecture that selects HAVE_ARCH_MUTEX_CPU_RELAX. The default is still cpu_relax(), so this patch should not affect other architectures than System z for now. Signed-off-by: Gerald Schaefer Signed-off-by: Peter Zijlstra LKML-Reference: <1290437256.7455.4.camel@thinkpad> Signed-off-by: Ingo Molnar --- arch/Kconfig | 3 +++ arch/s390/Kconfig | 1 + arch/s390/include/asm/mutex.h | 2 ++ include/linux/mutex.h | 4 ++++ kernel/mutex.c | 2 +- kernel/sched.c | 3 ++- 6 files changed, 13 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/arch/Kconfig b/arch/Kconfig index 8bf0fa652eb6..f78c2be4242b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -175,4 +175,7 @@ config HAVE_PERF_EVENTS_NMI config HAVE_ARCH_JUMP_LABEL bool +config HAVE_ARCH_MUTEX_CPU_RELAX + bool + source "kernel/gcov/Kconfig" diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e0b98e71ff47..6c6d7b339aae 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -99,6 +99,7 @@ config S390 select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO select HAVE_GET_USER_PAGES_FAST + select HAVE_ARCH_MUTEX_CPU_RELAX select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h index 458c1f7fbc18..688271f5f2e4 100644 --- a/arch/s390/include/asm/mutex.h +++ b/arch/s390/include/asm/mutex.h @@ -7,3 +7,5 @@ */ #include + +#define arch_mutex_cpu_relax() barrier() diff --git a/include/linux/mutex.h b/include/linux/mutex.h index f363bc8fdc74..94b48bd40dd7 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -160,4 +160,8 @@ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX +#define arch_mutex_cpu_relax() cpu_relax() +#endif + #endif diff --git a/kernel/mutex.c b/kernel/mutex.c index 200407c1502f..a5889fb28ecf 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -199,7 +199,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - cpu_relax(); + arch_mutex_cpu_relax(); } #endif spin_lock_mutex(&lock->wait_lock, flags); diff --git a/kernel/sched.c b/kernel/sched.c index 3e8a7db951a6..abe7aec55763 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -75,6 +75,7 @@ #include #include +#include #include "sched_cpupri.h" #include "workqueue_sched.h" @@ -3888,7 +3889,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) if (task_thread_info(rq->curr) != owner || need_resched()) return 0; - cpu_relax(); + arch_mutex_cpu_relax(); } return 1; -- cgit v1.2.3 From b7a2b39d9b7703ccf068f549c8dc3465fc41d015 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Fri, 26 Nov 2010 12:37:09 +0530 Subject: sched: Remove unused argument dest_cpu to migrate_task() Remove unused argument, 'dest_cpu' of migrate_task(), and pass runqueue, as it is always known at the call site. Signed-off-by: Nikanth Karthikesan Signed-off-by: Peter Zijlstra LKML-Reference: <201011261237.09187.knikanth@suse.de> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index abe7aec55763..35a6373f1265 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2061,10 +2061,8 @@ static int migration_cpu_stop(void *data); * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static bool migrate_task(struct task_struct *p, int dest_cpu) +static bool migrate_task(struct task_struct *p, struct rq *rq) { - struct rq *rq = task_rq(p); - /* * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. @@ -3224,7 +3222,7 @@ void sched_exec(void) * select_task_rq() can race against ->cpus_allowed */ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) { + likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { struct migration_arg arg = { p, dest_cpu }; task_rq_unlock(rq, &flags); @@ -5504,7 +5502,7 @@ again: goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (migrate_task(p, dest_cpu)) { + if (migrate_task(p, rq)) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ task_rq_unlock(rq, &flags); -- cgit v1.2.3 From 822bc180a7f7a7bc5fcaaea195f41b487cc8cae8 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 29 Nov 2010 16:55:40 -0800 Subject: sched: Fix unregister_fair_sched_group() In the flipping and flopping between calling unregister_fair_sched_group() on a per-cpu versus per-group basis we ended up in a bad state. Remove from the list for the passed cpu as opposed to some arbitrary index. ( This fixes explosions w/ autogroup as well as a group creation/destruction stress test. ) Reported-by: Stephen Rothwell Signed-off-by: Paul Turner Cc: Peter Zijlstra Cc: Mike Galbraith LKML-Reference: <20101130005740.080828123@google.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 35a6373f1265..66ef5790d932 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8085,7 +8085,6 @@ static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long flags; - int i; /* * Only empty task groups can be destroyed; so we can speculatively @@ -8095,7 +8094,7 @@ static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) return; raw_spin_lock_irqsave(&rq->lock, flags); - list_del_leaf_cfs_rq(tg->cfs_rq[i]); + list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); raw_spin_unlock_irqrestore(&rq->lock, flags); } #else /* !CONFG_FAIR_GROUP_SCHED */ -- cgit v1.2.3 From 5091faa449ee0b7d73bc296a93bca9540fc51d0a Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 30 Nov 2010 14:18:03 +0100 Subject: sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc//autogroup Displays the task's group and the group's nice level. echo > /proc//autogroup Sets the task group's shares to the weight of nice task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith Acked-by: Linus Torvalds Acked-by: Peter Zijlstra Cc: Markus Trippelsdorf Cc: Mathieu Desnoyers Cc: Paul Turner Cc: Oleg Nesterov [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar --- Documentation/kernel-parameters.txt | 2 + fs/proc/base.c | 79 +++++++++++++ include/linux/sched.h | 23 ++++ init/Kconfig | 13 ++ kernel/fork.c | 5 +- kernel/sched.c | 13 +- kernel/sched_autogroup.c | 229 ++++++++++++++++++++++++++++++++++++ kernel/sched_autogroup.h | 32 +++++ kernel/sched_debug.c | 47 +------- kernel/sys.c | 4 +- kernel/sysctl.c | 11 ++ 11 files changed, 409 insertions(+), 49 deletions(-) create mode 100644 kernel/sched_autogroup.c create mode 100644 kernel/sched_autogroup.h (limited to 'kernel/sched.c') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 92e83e53148f..86820a727b0b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1622,6 +1622,8 @@ and is between 256 and 4096 characters. It is defined in the file noapic [SMP,APIC] Tells the kernel to not make use of any IOAPICs that may be present in the system. + noautogroup Disable scheduler automatic task group creation. + nobats [PPC] Do not use BATs for mapping kernel lowmem on "Classic" PPC cores. diff --git a/fs/proc/base.c b/fs/proc/base.c index f3d02ca461ec..2fa0ce29b6dc 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1407,6 +1407,82 @@ static const struct file_operations proc_pid_sched_operations = { #endif +#ifdef CONFIG_SCHED_AUTOGROUP +/* + * Print out autogroup related information: + */ +static int sched_autogroup_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_autogroup_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_autogroup_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct task_struct *p; + char buffer[PROC_NUMBUF]; + long nice; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + + err = strict_strtol(strstrip(buffer), 0, &nice); + if (err) + return -EINVAL; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + err = nice; + err = proc_sched_autogroup_set_nice(p, &err); + if (err) + count = err; + + put_task_struct(p); + + return count; +} + +static int sched_autogroup_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = single_open(filp, sched_autogroup_show, NULL); + if (!ret) { + struct seq_file *m = filp->private_data; + + m->private = inode; + } + return ret; +} + +static const struct file_operations proc_pid_sched_autogroup_operations = { + .open = sched_autogroup_open, + .read = seq_read, + .write = sched_autogroup_write, + .llseek = seq_lseek, + .release = single_release, +}; + +#endif /* CONFIG_SCHED_AUTOGROUP */ + static ssize_t comm_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { @@ -2732,6 +2808,9 @@ static const struct pid_entry tgid_base_stuff[] = { INF("limits", S_IRUGO, proc_pid_limits), #ifdef CONFIG_SCHED_DEBUG REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), +#endif +#ifdef CONFIG_SCHED_AUTOGROUP + REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), #endif REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), #ifdef CONFIG_HAVE_ARCH_TRACEHOOK diff --git a/include/linux/sched.h b/include/linux/sched.h index a5b92c70c737..9c2d46da486e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -509,6 +509,8 @@ struct thread_group_cputimer { spinlock_t lock; }; +struct autogroup; + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -576,6 +578,9 @@ struct signal_struct { struct tty_struct *tty; /* NULL if no tty */ +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. @@ -1927,6 +1932,24 @@ int sched_rt_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_compat_yield; +#ifdef CONFIG_SCHED_AUTOGROUP +extern unsigned int sysctl_sched_autogroup_enabled; + +extern void sched_autogroup_create_attach(struct task_struct *p); +extern void sched_autogroup_detach(struct task_struct *p); +extern void sched_autogroup_fork(struct signal_struct *sig); +extern void sched_autogroup_exit(struct signal_struct *sig); +#ifdef CONFIG_PROC_FS +extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +#endif +#else +static inline void sched_autogroup_create_attach(struct task_struct *p) { } +static inline void sched_autogroup_detach(struct task_struct *p) { } +static inline void sched_autogroup_fork(struct signal_struct *sig) { } +static inline void sched_autogroup_exit(struct signal_struct *sig) { } +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); diff --git a/init/Kconfig b/init/Kconfig index 88c10468db46..f1bba0a1b051 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -728,6 +728,19 @@ config NET_NS endif # NAMESPACES +config SCHED_AUTOGROUP + bool "Automatic process group scheduling" + select EVENTFD + select CGROUPS + select CGROUP_SCHED + select FAIR_GROUP_SCHED + help + This option optimizes the scheduler for common desktop workloads by + automatically creating and populating task groups. This separation + of workloads isolates aggressive CPU burners (like build jobs) from + desktop applications. Task group autogeneration is currently based + upon task session. + config MM_OWNER bool diff --git a/kernel/fork.c b/kernel/fork.c index 3b159c5991b7..b6f2475f1e83 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -174,8 +174,10 @@ static inline void free_signal_struct(struct signal_struct *sig) static inline void put_signal_struct(struct signal_struct *sig) { - if (atomic_dec_and_test(&sig->sigcnt)) + if (atomic_dec_and_test(&sig->sigcnt)) { + sched_autogroup_exit(sig); free_signal_struct(sig); + } } void __put_task_struct(struct task_struct *tsk) @@ -904,6 +906,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) posix_cpu_timers_init_group(sig); tty_audit_fork(sig); + sched_autogroup_fork(sig); sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; diff --git a/kernel/sched.c b/kernel/sched.c index 66ef5790d932..b646dad4a40e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -79,6 +79,7 @@ #include "sched_cpupri.h" #include "workqueue_sched.h" +#include "sched_autogroup.h" #define CREATE_TRACE_POINTS #include @@ -271,6 +272,10 @@ struct task_group { struct task_group *parent; struct list_head siblings; struct list_head children; + +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif }; #define root_task_group init_task_group @@ -603,11 +608,14 @@ static inline int cpu_of(struct rq *rq) */ static inline struct task_group *task_group(struct task_struct *p) { + struct task_group *tg; struct cgroup_subsys_state *css; css = task_subsys_state_check(p, cpu_cgroup_subsys_id, lockdep_is_held(&task_rq(p)->lock)); - return container_of(css, struct task_group, css); + tg = container_of(css, struct task_group, css); + + return autogroup_task_group(p, tg); } /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ @@ -1869,6 +1877,7 @@ static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { } #include "sched_idletask.c" #include "sched_fair.c" #include "sched_rt.c" +#include "sched_autogroup.c" #include "sched_stoptask.c" #ifdef CONFIG_SCHED_DEBUG # include "sched_debug.c" @@ -7750,7 +7759,7 @@ void __init sched_init(void) #ifdef CONFIG_CGROUP_SCHED list_add(&init_task_group.list, &task_groups); INIT_LIST_HEAD(&init_task_group.children); - + autogroup_init(&init_task); #endif /* CONFIG_CGROUP_SCHED */ for_each_possible_cpu(i) { diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c new file mode 100644 index 000000000000..57a7ac286a02 --- /dev/null +++ b/kernel/sched_autogroup.c @@ -0,0 +1,229 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +#include +#include +#include +#include + +unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; +static struct autogroup autogroup_default; +static atomic_t autogroup_seq_nr; + +static void autogroup_init(struct task_struct *init_task) +{ + autogroup_default.tg = &init_task_group; + init_task_group.autogroup = &autogroup_default; + kref_init(&autogroup_default.kref); + init_rwsem(&autogroup_default.lock); + init_task->signal->autogroup = &autogroup_default; +} + +static inline void autogroup_free(struct task_group *tg) +{ + kfree(tg->autogroup); +} + +static inline void autogroup_destroy(struct kref *kref) +{ + struct autogroup *ag = container_of(kref, struct autogroup, kref); + + sched_destroy_group(ag->tg); +} + +static inline void autogroup_kref_put(struct autogroup *ag) +{ + kref_put(&ag->kref, autogroup_destroy); +} + +static inline struct autogroup *autogroup_kref_get(struct autogroup *ag) +{ + kref_get(&ag->kref); + return ag; +} + +static inline struct autogroup *autogroup_create(void) +{ + struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL); + struct task_group *tg; + + if (!ag) + goto out_fail; + + tg = sched_create_group(&init_task_group); + + if (IS_ERR(tg)) + goto out_free; + + kref_init(&ag->kref); + init_rwsem(&ag->lock); + ag->id = atomic_inc_return(&autogroup_seq_nr); + ag->tg = tg; + tg->autogroup = ag; + + return ag; + +out_free: + kfree(ag); +out_fail: + if (printk_ratelimit()) { + printk(KERN_WARNING "autogroup_create: %s failure.\n", + ag ? "sched_create_group()" : "kmalloc()"); + } + + return autogroup_kref_get(&autogroup_default); +} + +static inline bool +task_wants_autogroup(struct task_struct *p, struct task_group *tg) +{ + if (tg != &root_task_group) + return false; + + if (p->sched_class != &fair_sched_class) + return false; + + /* + * We can only assume the task group can't go away on us if + * autogroup_move_group() can see us on ->thread_group list. + */ + if (p->flags & PF_EXITING) + return false; + + return true; +} + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled); + + if (enabled && task_wants_autogroup(p, tg)) + return p->signal->autogroup->tg; + + return tg; +} + +static void +autogroup_move_group(struct task_struct *p, struct autogroup *ag) +{ + struct autogroup *prev; + struct task_struct *t; + unsigned long flags; + + BUG_ON(!lock_task_sighand(p, &flags)); + + prev = p->signal->autogroup; + if (prev == ag) { + unlock_task_sighand(p, &flags); + return; + } + + p->signal->autogroup = autogroup_kref_get(ag); + + t = p; + do { + sched_move_task(t); + } while_each_thread(p, t); + + unlock_task_sighand(p, &flags); + autogroup_kref_put(prev); +} + +/* Allocates GFP_KERNEL, cannot be called under any spinlock */ +void sched_autogroup_create_attach(struct task_struct *p) +{ + struct autogroup *ag = autogroup_create(); + + autogroup_move_group(p, ag); + /* drop extra refrence added by autogroup_create() */ + autogroup_kref_put(ag); +} +EXPORT_SYMBOL(sched_autogroup_create_attach); + +/* Cannot be called under siglock. Currently has no users */ +void sched_autogroup_detach(struct task_struct *p) +{ + autogroup_move_group(p, &autogroup_default); +} +EXPORT_SYMBOL(sched_autogroup_detach); + +void sched_autogroup_fork(struct signal_struct *sig) +{ + struct task_struct *p = current; + + spin_lock_irq(&p->sighand->siglock); + sig->autogroup = autogroup_kref_get(p->signal->autogroup); + spin_unlock_irq(&p->sighand->siglock); +} + +void sched_autogroup_exit(struct signal_struct *sig) +{ + autogroup_kref_put(sig->autogroup); +} + +static int __init setup_autogroup(char *str) +{ + sysctl_sched_autogroup_enabled = 0; + + return 1; +} + +__setup("noautogroup", setup_autogroup); + +#ifdef CONFIG_PROC_FS + +/* Called with siglock held. */ +int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) +{ + static unsigned long next = INITIAL_JIFFIES; + struct autogroup *ag; + int err; + + if (*nice < -20 || *nice > 19) + return -EINVAL; + + err = security_task_setnice(current, *nice); + if (err) + return err; + + if (*nice < 0 && !can_nice(current, *nice)) + return -EPERM; + + /* this is a heavy operation taking global locks.. */ + if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next)) + return -EAGAIN; + + next = HZ / 10 + jiffies; + ag = autogroup_kref_get(p->signal->autogroup); + + down_write(&ag->lock); + err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]); + if (!err) + ag->nice = *nice; + up_write(&ag->lock); + + autogroup_kref_put(ag); + + return err; +} + +void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) +{ + struct autogroup *ag = autogroup_kref_get(p->signal->autogroup); + + down_read(&ag->lock); + seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice); + up_read(&ag->lock); + + autogroup_kref_put(ag); +} +#endif /* CONFIG_PROC_FS */ + +#ifdef CONFIG_SCHED_DEBUG +static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); +} +#endif /* CONFIG_SCHED_DEBUG */ + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h new file mode 100644 index 000000000000..5358e241cb20 --- /dev/null +++ b/kernel/sched_autogroup.h @@ -0,0 +1,32 @@ +#ifdef CONFIG_SCHED_AUTOGROUP + +struct autogroup { + struct kref kref; + struct task_group *tg; + struct rw_semaphore lock; + unsigned long id; + int nice; +}; + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg); + +#else /* !CONFIG_SCHED_AUTOGROUP */ + +static inline void autogroup_init(struct task_struct *init_task) { } +static inline void autogroup_free(struct task_group *tg) { } + +static inline struct task_group * +autogroup_task_group(struct task_struct *p, struct task_group *tg) +{ + return tg; +} + +#ifdef CONFIG_SCHED_DEBUG +static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) +{ + return 0; +} +#endif + +#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index e95b77414a99..1dfae3d014b5 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -54,8 +54,7 @@ static unsigned long nsec_low(unsigned long long nsec) #define SPLIT_NS(x) nsec_high(x), nsec_low(x) #ifdef CONFIG_FAIR_GROUP_SCHED -static void print_cfs_group_stats(struct seq_file *m, int cpu, - struct task_group *tg) +static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) { struct sched_entity *se = tg->se[cpu]; if (!se) @@ -110,16 +109,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); #endif -#ifdef CONFIG_CGROUP_SCHED - { - char path[64]; - - rcu_read_lock(); - cgroup_path(task_group(p)->css.cgroup, path, sizeof(path)); - rcu_read_unlock(); - SEQ_printf(m, " %s", path); - } -#endif SEQ_printf(m, "\n"); } @@ -147,19 +136,6 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_unlock_irqrestore(&tasklist_lock, flags); } -#if defined(CONFIG_CGROUP_SCHED) && \ - (defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED)) -static void task_group_path(struct task_group *tg, char *buf, int buflen) -{ - /* may be NULL if the underlying cgroup isn't fully-created yet */ - if (!tg->css.cgroup) { - buf[0] = '\0'; - return; - } - cgroup_path(tg->css.cgroup, buf, buflen); -} -#endif - void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) { s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1, @@ -168,16 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) struct sched_entity *last; unsigned long flags; -#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) - char path[128]; - struct task_group *tg = cfs_rq->tg; - - task_group_path(tg, path, sizeof(path)); - - SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); -#else SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); -#endif SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", SPLIT_NS(cfs_rq->exec_clock)); @@ -215,7 +182,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %ld\n", "load_contrib", cfs_rq->load_contribution); SEQ_printf(m, " .%-30s: %d\n", "load_tg", - atomic_read(&tg->load_weight)); + atomic_read(&cfs_rq->tg->load_weight)); #endif print_cfs_group_stats(m, cpu, cfs_rq->tg); @@ -224,17 +191,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) { -#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED) - char path[128]; - struct task_group *tg = rt_rq->tg; - - task_group_path(tg, path, sizeof(path)); - - SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path); -#else SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); -#endif - #define P(x) \ SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) diff --git a/kernel/sys.c b/kernel/sys.c index 7f5a0cd296a9..2745dcdb6c6c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1080,8 +1080,10 @@ SYSCALL_DEFINE0(setsid) err = session; out: write_unlock_irq(&tasklist_lock); - if (err > 0) + if (err > 0) { proc_sid_connector(group_leader); + sched_autogroup_create_attach(group_leader); + } return err; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a00fdefd24ce..121e4fff03d1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -370,6 +370,17 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_SCHED_AUTOGROUP + { + .procname = "sched_autogroup_enabled", + .data = &sysctl_sched_autogroup_enabled, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &one, + }, +#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", -- cgit v1.2.3 From 806c09a7db457be3758e14b1f152761135d89af5 Mon Sep 17 00:00:00 2001 From: Dario Faggioli Date: Tue, 30 Nov 2010 19:51:33 +0100 Subject: sched: Make pushable_tasks CONFIG_SMP dependant As noted by Peter Zijlstra at https://lkml.org/lkml/2010/11/10/391 (while reviewing other stuff, though), tracking pushable tasks only makes sense on SMP systems. Signed-off-by: Dario Faggioli Acked-by: Steven Rostedt Acked-by: Gregory Haskins Signed-off-by: Peter Zijlstra LKML-Reference: <1291143093.2697.298.camel@Palantir> Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 9 ++++++++- include/linux/sched.h | 2 ++ kernel/sched.c | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel/sched.c') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1f8c06ce0fa6..6ed8812bfe2d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -12,6 +12,13 @@ #include #include +#ifdef CONFIG_SMP +# define INIT_PUSHABLE_TASKS(tsk) \ + .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), +#else +# define INIT_PUSHABLE_TASKS(tsk) +#endif + extern struct files_struct init_files; extern struct fs_struct init_fs; @@ -137,7 +144,7 @@ extern struct cred init_cred; .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ - .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \ + INIT_PUSHABLE_TASKS(tsk) \ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \ .real_parent = &tsk, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c2d46da486e..4f92a239c14d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1240,7 +1240,9 @@ struct task_struct { #endif struct list_head tasks; +#ifdef CONFIG_SMP struct plist_node pushable_tasks; +#endif struct mm_struct *mm, *active_mm; #if defined(SPLIT_RSS_COUNTING) diff --git a/kernel/sched.c b/kernel/sched.c index b646dad4a40e..3925a1bbf5dd 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2595,7 +2595,9 @@ void sched_fork(struct task_struct *p, int clone_flags) /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif +#ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); +#endif put_cpu(); } -- cgit v1.2.3 From 6706125e291bd3dddd269e043323a6ab93ccd5fb Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Fri, 31 Dec 2010 21:58:58 +0800 Subject: sched: Remove redundant CONFIG_CGROUP_SCHED ifdef CONFIG_[FAIR|RT]_GROUP_SCHED always means CONFIG_CGROUP_SCHED Signed-off-by: Yong Zhang Cc: Peter Zijlstra LKML-Reference: <1293803938-8157-1-git-send-email-yong.zhang0@gmail.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 3925a1bbf5dd..9f9dd8dda53c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7777,7 +7777,6 @@ void __init sched_init(void) #ifdef CONFIG_FAIR_GROUP_SCHED init_task_group.shares = init_task_group_load; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); -#ifdef CONFIG_CGROUP_SCHED /* * How much cpu bandwidth does init_task_group get? * @@ -7798,15 +7797,12 @@ void __init sched_init(void) * directly in rq->cfs (i.e init_task_group->se[] = NULL). */ init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, NULL); -#endif #endif /* CONFIG_FAIR_GROUP_SCHED */ rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; #ifdef CONFIG_RT_GROUP_SCHED INIT_LIST_HEAD(&rq->leaf_rt_rq_list); -#ifdef CONFIG_CGROUP_SCHED init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, NULL); -#endif #endif for (j = 0; j < CPU_LOAD_IDX_MAX; j++) -- cgit v1.2.3 From 6bf4123760a5aece6e4829ce90b70b6ffd751d65 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 5 Jan 2011 12:50:16 +1100 Subject: sched: Change wait_for_completion_*_timeout() to return a signed long wait_for_completion_*_timeout() can return: 0: if the wait timed out -ve: if the wait was interrupted +ve: if the completion was completed. As they currently return an 'unsigned long', the last two cases are not easily distinguished which can easily result in buggy code, as is the case for the recently added wait_for_completion_interruptible_timeout() call in net/sunrpc/cache.c So change them both to return 'long'. As MAX_SCHEDULE_TIMEOUT is LONG_MAX, a large +ve return value should never overflow. Signed-off-by: NeilBrown Cc: Peter Zijlstra Cc: J. Bruce Fields Cc: Andrew Morton Cc: Linus Torvalds LKML-Reference: <20110105125016.64ccab0e@notabene.brown> Signed-off-by: Ingo Molnar --- include/linux/completion.h | 8 ++++---- kernel/sched.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/completion.h b/include/linux/completion.h index 36d57f74cd01..51494e6b5548 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -81,10 +81,10 @@ extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); -extern unsigned long wait_for_completion_interruptible_timeout( - struct completion *x, unsigned long timeout); -extern unsigned long wait_for_completion_killable_timeout( - struct completion *x, unsigned long timeout); +extern long wait_for_completion_interruptible_timeout( + struct completion *x, unsigned long timeout); +extern long wait_for_completion_killable_timeout( + struct completion *x, unsigned long timeout); extern bool try_wait_for_completion(struct completion *x); extern bool completion_done(struct completion *x); diff --git a/kernel/sched.c b/kernel/sched.c index f2f914e0c47c..114a0deb2b01 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4395,7 +4395,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible); * This waits for either a completion of a specific task to be signaled or for a * specified timeout to expire. It is interruptible. The timeout is in jiffies. */ -unsigned long __sched +long __sched wait_for_completion_interruptible_timeout(struct completion *x, unsigned long timeout) { @@ -4428,7 +4428,7 @@ EXPORT_SYMBOL(wait_for_completion_killable); * signaled or for a specified timeout to expire. It can be * interrupted by a kill signal. The timeout is in jiffies. */ -unsigned long __sched +long __sched wait_for_completion_killable_timeout(struct completion *x, unsigned long timeout) { -- cgit v1.2.3