From 50a323b73069b169385a8ac65633dee837a7d13f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:36 +0200 Subject: sched: define and use CPU_PRI_* enums for cpu notifier priorities Instead of hardcoding priority 10 and 20 in sched and perf, collect them into CPU_PRI_* enums. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Paul Mackerras Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo --- 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 f8b8996..552faf8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5801,7 +5801,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) */ static struct notifier_block __cpuinitdata migration_notifier = { .notifier_call = migration_call, - .priority = 10 + .priority = CPU_PRI_MIGRATION, }; static int __init migration_init(void) -- cgit v1.1 From 3a101d0548e925ab16ca6aaa8cf4f767d322ddb0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:36 +0200 Subject: sched: adjust when cpu_active and cpuset configurations are updated during cpu on/offlining Currently, when a cpu goes down, cpu_active is cleared before CPU_DOWN_PREPARE starts and cpuset configuration is updated from a default priority cpu notifier. When a cpu is coming up, it's set before CPU_ONLINE but cpuset configuration again is updated from the same cpu notifier. For cpu notifiers, this presents an inconsistent state. Threads which a CPU_DOWN_PREPARE notifier expects to be bound to the CPU can be migrated to other cpus because the cpu is no more inactive. Fix it by updating cpu_active in the highest priority cpu notifier and cpuset configuration in the second highest when a cpu is coming up. Down path is updated similarly. This guarantees that all other cpu notifiers see consistent cpu_active and cpuset configuration. cpuset_track_online_cpus() notifier is converted to cpuset_update_active_cpus() which just updates the configuration and now called from cpuset_cpu_[in]active() notifiers registered from sched_init_smp(). If cpuset is disabled, cpuset_update_active_cpus() degenerates into partition_sched_domains() making separate notifier for !CONFIG_CPUSETS unnecessary. This problem is triggered by cmwq. During CPU_DOWN_PREPARE, hotplug callback creates a kthread and kthread_bind()s it to the target cpu, and the thread is expected to run on that cpu. * Ingo's test discovered __cpuinit/exit markups were incorrect. Fixed. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar Cc: Paul Menage --- kernel/sched.c | 67 +++++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 50 insertions(+), 17 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 552faf8..2b942e4 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5804,17 +5804,46 @@ static struct notifier_block __cpuinitdata migration_notifier = { .priority = CPU_PRI_MIGRATION, }; +static int __cpuinit sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + static int __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; - /* Start one for the boot CPU: */ + /* Initialize migration for the boot CPU */ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + return 0; } early_initcall(migration_init); @@ -7273,29 +7302,35 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -#ifndef CONFIG_CPUSETS /* - * Add online and remove offline CPUs from the scheduler domains. - * When cpusets are enabled they take over this function. + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). */ -static int update_sched_domains(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) { - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - partition_sched_domains(1, NULL, NULL); + cpuset_update_active_cpus(); return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} +static int __cpuexit cpuset_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + cpuset_update_active_cpus(); + return NOTIFY_OK; default: return NOTIFY_DONE; } } -#endif static int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu) @@ -7341,10 +7376,8 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); put_online_cpus(); -#ifndef CONFIG_CPUSETS - /* XXX: Theoretical race here - CPU may be hotplugged now */ - hotcpu_notifier(update_sched_domains, 0); -#endif + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); /* RT runtime code needs to handle some hotplug events */ hotcpu_notifier(update_runtime, 0); -- cgit v1.1 From 9ed3811a6c0d6b66e6cd47a5d7b9136386dce743 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Dec 2009 15:08:03 +0900 Subject: sched: refactor try_to_wake_up() Factor ttwu_activate() and ttwu_woken_up() out of try_to_wake_up(). The factoring out doesn't affect try_to_wake_up() much code-generation-wise. Depending on configuration options, it ends up generating the same object code as before or slightly different one due to different register assignment. This is to help future implementation of try_to_wake_up_local(). Mike Galbraith suggested rename to ttwu_post_activation() from ttwu_woken_up() and comment update in try_to_wake_up(). Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Mike Galbraith Cc: Ingo Molnar --- kernel/sched.c | 83 ++++++++++++++++++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 34 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 2b942e4..96eafd5 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2267,11 +2267,52 @@ static void update_avg(u64 *avg, u64 sample) } #endif -/*** +static inline void ttwu_activate(struct task_struct *p, struct rq *rq, + bool is_sync, bool is_migrate, bool is_local, + unsigned long en_flags) +{ + schedstat_inc(p, se.statistics.nr_wakeups); + if (is_sync) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + if (is_migrate) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + if (is_local) + schedstat_inc(p, se.statistics.nr_wakeups_local); + else + schedstat_inc(p, se.statistics.nr_wakeups_remote); + + activate_task(rq, p, en_flags); +} + +static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, + int wake_flags, bool success) +{ + trace_sched_wakeup(p, success); + check_preempt_curr(rq, p, wake_flags); + + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } +#endif +} + +/** * try_to_wake_up - wake up a thread - * @p: the to-be-woken-up thread + * @p: the thread to be awakened * @state: the mask of task states that can be woken - * @sync: do a synchronous wakeup? + * @wake_flags: wake modifier flags (WF_*) * * Put it on the run-queue if it's not already there. The "current" * thread is always on the run-queue (except when the actual @@ -2279,7 +2320,8 @@ static void update_avg(u64 *avg, u64 sample) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * returns failure only if the task is already active. + * Returns %true if @p was woken up, %false if it was already running + * or @state didn't match @p's state. */ static int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) @@ -2359,38 +2401,11 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, out_activate: #endif /* CONFIG_SMP */ - schedstat_inc(p, se.statistics.nr_wakeups); - if (wake_flags & WF_SYNC) - schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (orig_cpu != cpu) - schedstat_inc(p, se.statistics.nr_wakeups_migrate); - if (cpu == this_cpu) - schedstat_inc(p, se.statistics.nr_wakeups_local); - else - schedstat_inc(p, se.statistics.nr_wakeups_remote); - activate_task(rq, p, en_flags); + ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, + cpu == this_cpu, en_flags); success = 1; - out_running: - trace_sched_wakeup(p, success); - check_preempt_curr(rq, p, wake_flags); - - p->state = TASK_RUNNING; -#ifdef CONFIG_SMP - if (p->sched_class->task_woken) - p->sched_class->task_woken(rq, p); - - if (unlikely(rq->idle_stamp)) { - u64 delta = rq->clock - rq->idle_stamp; - u64 max = 2*sysctl_sched_migration_cost; - - if (delta > max) - rq->avg_idle = max; - else - update_avg(&rq->avg_idle, delta); - rq->idle_stamp = 0; - } -#endif + ttwu_post_activation(p, rq, wake_flags, success); out: task_rq_unlock(rq, &flags); put_cpu(); -- cgit v1.1 From 21aa9af03d06cb1d19a3738e5cf12acff984e69b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:37 +0200 Subject: sched: add hooks for workqueue Concurrency managed workqueue needs to know when workers are going to sleep and waking up. Using these two hooks, cmwq keeps track of the current concurrency level and throttles execution of new works if it's too high and wakes up another worker from the sleep hook if it becomes too low. This patch introduces PF_WQ_WORKER to identify workqueue workers and adds the following two hooks. * wq_worker_waking_up(): called when a worker is woken up. * wq_worker_sleeping(): called when a worker is going to sleep and may return a pointer to a local task which should be woken up. The returned task is woken up using try_to_wake_up_local() which is simplified ttwu which is called under rq lock and can only wake up local tasks. Both hooks are currently defined as noop in kernel/workqueue_sched.h. Later cmwq implementation will replace them with proper implementation. These hooks are hard coded as they'll always be enabled. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Mike Galbraith Cc: Ingo Molnar --- kernel/sched.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 51 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 96eafd5..edd5a54 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -77,6 +77,7 @@ #include #include "sched_cpupri.h" +#include "workqueue_sched.h" #define CREATE_TRACE_POINTS #include @@ -2306,6 +2307,9 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, rq->idle_stamp = 0; } #endif + /* if a worker is waking up, notify workqueue */ + if ((p->flags & PF_WQ_WORKER) && success) + wq_worker_waking_up(p, cpu_of(rq)); } /** @@ -2414,6 +2418,37 @@ out: } /** + * try_to_wake_up_local - try to wake up a local task with rq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not alredy there. The caller must + * ensure that this_rq() is locked, @p is bound to this_rq() and not + * the current task. this_rq() stays locked over invocation. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + bool success = false; + + BUG_ON(rq != this_rq()); + BUG_ON(p == current); + lockdep_assert_held(&rq->lock); + + if (!(p->state & TASK_NORMAL)) + return; + + if (!p->se.on_rq) { + if (likely(!task_running(rq, p))) { + schedstat_inc(rq, ttwu_count); + schedstat_inc(rq, ttwu_local); + } + ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); + success = true; + } + ttwu_post_activation(p, rq, 0, success); +} + +/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -3618,10 +3653,24 @@ need_resched_nonpreemptible: clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely(signal_pending_state(prev->state, prev))) + if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; - else + } else { + /* + * If a worker is going to sleep, notify and + * ask workqueue whether it wants to wake up a + * task to maintain concurrency. If so, wake + * up the task. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); + if (to_wakeup) + try_to_wake_up_local(to_wakeup); + } deactivate_task(rq, prev, DEQUEUE_SLEEP); + } switch_count = &prev->nvcsw; } -- cgit v1.1 From c676329abb2b8359d9a5d734dec0c81779823fd6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 May 2010 10:48:51 +0200 Subject: sched_clock: Add local_clock() API and improve documentation For people who otherwise get to write: cpu_clock(smp_processor_id()), there is now: local_clock(). Also, as per suggestion from Andrew, provide some documentation on the various clock interfaces, and minimize the unsigned long long vs u64 mess. Signed-off-by: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Cc: Jens Axboe LKML-Reference: <1275052414.1645.52.camel@laptop> 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 8f351c5..3abd8f7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1647,7 +1647,7 @@ static void update_shares(struct sched_domain *sd) if (root_task_group_empty()) return; - now = cpu_clock(raw_smp_processor_id()); + now = local_clock(); elapsed = now - sd->last_update; if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { -- cgit v1.1 From 246d86b51845063e4b06b27579990492dc5fa317 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 19 May 2010 14:57:11 +0200 Subject: sched: Simplify the reacquire_kernel_lock() logic - Contrary to what 6d558c3a says, there is no need to reload prev = rq->curr after the context switch. You always schedule back to where you came from, prev must be equal to current even if cpu/rq was changed. - This also means reacquire_kernel_lock() can use prev instead of current. - No need to reassign switch_count if reacquire_kernel_lock() reports need_resched(), we can just move the initial assignment down, under the "need_resched_nonpreemptible:" label. - Try to update the comment after context_switch(). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100519125711.GA30199@redhat.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 3abd8f7..f37a961 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3636,7 +3636,6 @@ need_resched: rq = cpu_rq(cpu); rcu_note_context_switch(cpu); prev = rq->curr; - switch_count = &prev->nivcsw; release_kernel_lock(prev); need_resched_nonpreemptible: @@ -3649,6 +3648,7 @@ need_resched_nonpreemptible: raw_spin_lock_irq(&rq->lock); clear_tsk_need_resched(prev); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; @@ -3689,8 +3689,10 @@ need_resched_nonpreemptible: context_switch(rq, prev, next); /* unlocks the rq */ /* - * the context switch might have flipped the stack from under - * us, hence refresh the local variables. + * The context switch have flipped the stack from under us + * and restored the local variables which were saved when + * this task called schedule() in the past. prev == current + * is still correct, but it can be moved to another cpu/rq. */ cpu = smp_processor_id(); rq = cpu_rq(cpu); @@ -3699,11 +3701,8 @@ need_resched_nonpreemptible: post_schedule(rq); - if (unlikely(reacquire_kernel_lock(current) < 0)) { - prev = rq->curr; - switch_count = &prev->nivcsw; + if (unlikely(reacquire_kernel_lock(prev))) goto need_resched_nonpreemptible; - } preempt_enable_no_resched(); if (need_resched()) -- cgit v1.1 From fdf3e95d3916f18bf8703fb065499fdbc4dfe34c Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Mon, 17 May 2010 18:14:43 -0700 Subject: sched: Avoid side-effect of tickless idle on update_cpu_load tickless idle has a negative side effect on update_cpu_load(), which in turn can affect load balancing behavior. update_cpu_load() is supposed to be called every tick, to keep track of various load indicies. With tickless idle, there are no scheduler ticks called on the idle CPUs. Idle CPUs may still do load balancing (with idle_load_balance CPU) using the stale cpu_load. It will also cause problems when all CPUs go idle for a while and become active again. In this case loads would not degrade as expected. This is how rq->nr_load_updates change looks like under different conditions: All CPUS idle for 10 seconds (HZ=1000) 0 1621 10 496 11 139 12 875 13 1672 14 12 15 21 1 1472 2 2426 3 1161 4 2108 5 1525 6 701 7 249 8 766 9 1967 One CPU busy rest idle for 10 seconds 0 10003 10 601 11 95 12 966 13 1597 14 114 15 98 1 3457 2 93 3 6679 4 1425 5 1479 6 595 7 193 8 633 9 1687 All CPUs busy for 10 seconds 0 10026 10 10026 11 10026 12 10026 13 10025 14 10025 15 10025 1 10026 2 10026 3 10026 4 10026 5 10026 6 10026 7 10026 8 10026 9 10026 That is update_cpu_load works properly only when all CPUs are busy. If all are idle, all the CPUs get way lower updates. And when few CPUs are busy and rest are idle, only busy and ilb CPU does proper updates and rest of the idle CPUs will do lower updates. The patch keeps track of when a last update was done and fixes up the load avg based on current time. On one of my test system SPECjbb with warehouse 1..numcpus, patch improves throughput numbers by ~1% (average of 6 runs). On another test system (with different domain hierarchy) there is no noticable change in perf. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Peter Zijlstra Cc: Thomas Gleixner LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 100 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 95 insertions(+), 5 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index f37a961..a757f6b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -457,6 +457,7 @@ struct rq { unsigned long nr_running; #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned long last_load_update_tick; #ifdef CONFIG_NO_HZ u64 nohz_stamp; unsigned char in_nohz_recently; @@ -1803,6 +1804,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); +static void update_cpu_load(struct rq *this_rq); static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { @@ -3050,23 +3052,102 @@ static void calc_load_account_active(struct rq *this_rq) } /* + * The exact cpuload at various idx values, calculated at every tick would be + * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load + * + * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called + * on nth tick when cpu may be busy, then we have: + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load + * + * decay_load_missed() below does efficient calculation of + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load + * + * The calculation is approximated on a 128 point scale. + * degrade_zero_ticks is the number of ticks after which load at any + * particular idx is approximated to be zero. + * degrade_factor is a precomputed table, a row for each load idx. + * Each column corresponds to degradation factor for a power of two ticks, + * based on 128 point scale. + * Example: + * row 2, col 3 (=12) says that the degradation at load idx 2 after + * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). + * + * With this power of 2 load factors, we can degrade the load n times + * by looking at 1 bits in n and doing as many mult/shift instead of + * n mult/shifts needed by the exact degradation. + */ +#define DEGRADE_SHIFT 7 +static const unsigned char + degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const unsigned char + degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + {0, 0, 0, 0, 0, 0, 0, 0}, + {64, 32, 8, 0, 0, 0, 0, 0}, + {96, 72, 40, 12, 1, 0, 0}, + {112, 98, 75, 43, 15, 1, 0}, + {120, 112, 98, 76, 45, 16, 2} }; + +/* + * Update cpu_load for any missed ticks, due to tickless idle. The backlog + * would be when CPU is idle and so we just decay the old load without + * adding any new load. + */ +static unsigned long +decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) +{ + int j = 0; + + if (!missed_updates) + return load; + + if (missed_updates >= degrade_zero_ticks[idx]) + return 0; + + if (idx == 1) + return load >> missed_updates; + + while (missed_updates) { + if (missed_updates % 2) + load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; + + missed_updates >>= 1; + j++; + } + return load; +} + +/* * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). + * scheduler tick (TICK_NSEC). With tickless idle this will not be called + * every tick. We fix it up based on jiffies. */ static void update_cpu_load(struct rq *this_rq) { unsigned long this_load = this_rq->load.weight; + unsigned long curr_jiffies = jiffies; + unsigned long pending_updates; int i, scale; this_rq->nr_load_updates++; + /* Avoid repeated calls on same jiffy, when moving in and out of idle */ + if (curr_jiffies == this_rq->last_load_update_tick) + return; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; + /* Update our load: */ - for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ + for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { unsigned long old_load, new_load; /* scale is effectively 1 << i now, and >> i divides by scale */ old_load = this_rq->cpu_load[i]; + old_load = decay_load_missed(old_load, pending_updates - 1, i); new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -3074,9 +3155,15 @@ static void update_cpu_load(struct rq *this_rq) * example. */ if (new_load > old_load) - new_load += scale-1; - this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; + new_load += scale - 1; + + this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; } +} + +static void update_cpu_load_active(struct rq *this_rq) +{ + update_cpu_load(this_rq); calc_load_account_active(this_rq); } @@ -3464,7 +3551,7 @@ void scheduler_tick(void) raw_spin_lock(&rq->lock); update_rq_clock(rq); - update_cpu_load(rq); + update_cpu_load_active(rq); curr->sched_class->task_tick(rq, curr, 0); raw_spin_unlock(&rq->lock); @@ -7688,6 +7775,9 @@ void __init sched_init(void) for (j = 0; j < CPU_LOAD_IDX_MAX; j++) rq->cpu_load[j] = 0; + + rq->last_load_update_tick = jiffies; + #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; -- cgit v1.1 From 83cd4fe27ad8446619b2e030b171b858501de87d Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Fri, 21 May 2010 17:09:41 -0700 Subject: sched: Change nohz idle load balancing logic to push model In the new push model, all idle CPUs indeed go into nohz mode. There is still the concept of idle load balancer (performing the load balancing on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz balancer when any of the nohz CPUs need idle load balancing. The kickee CPU does the idle load balancing on behalf of all idle CPUs instead of the normal idle balance. This addresses the below two problems with the current nohz ilb logic: * the idle load balancer continued to have periodic ticks during idle and wokeup frequently, even though it did not have any rebalancing to do on behalf of any of the idle CPUs. * On x86 and CPUs that have APIC timer stoppage on idle CPUs, this periodic wakeup can result in a periodic additional interrupt on a CPU doing the timer broadcast. Also currently we are migrating the unpinned timers from an idle to the cpu doing idle load balancing (when all the cpus in the system are idle, there is no idle load balancing cpu and timers get added to the same idle cpu where the request was made. So the existing optimization works only on semi idle system). And In semi idle system, we no longer have periodic ticks on the idle load balancer CPU. Using that cpu will add more delays to the timers than intended (as that cpu's timer base may not be uptodate wrt jiffies etc). This was causing mysterious slowdowns during boot etc. For now, in the semi idle case, use the nearest busy cpu for migrating timers from an idle cpu. This is good for power-savings anyway. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: Peter Zijlstra Cc: Thomas Gleixner LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 34 +++++++++++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index a757f6b..132950b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -460,7 +460,7 @@ struct rq { unsigned long last_load_update_tick; #ifdef CONFIG_NO_HZ u64 nohz_stamp; - unsigned char in_nohz_recently; + unsigned char nohz_balance_kick; #endif unsigned int skip_clock_update; @@ -1195,6 +1195,27 @@ static void resched_cpu(int cpu) #ifdef CONFIG_NO_HZ /* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(void) +{ + int cpu = smp_processor_id(); + int i; + struct sched_domain *sd; + + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) + if (!idle_cpu(i)) + return i; + } + return cpu; +} +/* * When add_timer_on() enqueues a timer into the timer wheel of an * idle CPU then this timer might expire before the next timer event * which is scheduled to wake up that CPU. In case of a completely @@ -7791,6 +7812,10 @@ void __init sched_init(void) rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; rq_attach_root(rq, &def_root_domain); +#ifdef CONFIG_NO_HZ + rq->nohz_balance_kick = 0; + init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i)); +#endif #endif init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); @@ -7835,8 +7860,11 @@ void __init sched_init(void) zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ - zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); - alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); + alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT); + atomic_set(&nohz.load_balancer, nr_cpu_ids); + atomic_set(&nohz.first_pick_cpu, nr_cpu_ids); + atomic_set(&nohz.second_pick_cpu, nr_cpu_ids); #endif /* May be allocated at isolcpus cmdline parse time */ if (cpu_isolated_map == NULL) -- cgit v1.1 From a44702e8858a071aa0f2365113ea4a2e51c8b575 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 11 Jun 2010 01:09:44 +0200 Subject: sched: __sched_setscheduler: Read the RLIMIT_RTPRIO value lockless __sched_setscheduler() takes lock_task_sighand() to access task->signal. This is not needed since ea6d290c, ->signal can't go away. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100610230944.GA25903@redhat.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 132950b..b4427cc 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4600,12 +4600,8 @@ recheck: */ if (user && !capable(CAP_SYS_NICE)) { if (rt_policy(policy)) { - unsigned long rlim_rtprio; - - if (!lock_task_sighand(p, &flags)) - return -ESRCH; - rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); - unlock_task_sighand(p, &flags); + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); /* can't set/change the rt policy */ if (policy != p->policy && !rlim_rtprio) -- cgit v1.1 From 0b2e918aa99fe6c3b8f163aa323a275ad8577828 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 21 Jun 2010 23:53:31 +0200 Subject: sched, cpuset: Drop __cpuexit from cpu hotplug callbacks Commit 3a101d05 (sched: adjust when cpu_active and cpuset configurations are updated during cpu on/offlining) added hotplug notifiers marked with __cpuexit; however, ia64 drops text in __cpuexit during link unlike x86. This means that functions which are referenced during init but used only for cpu hot unplugging afterwards shouldn't be marked with __cpuexit. Drop __cpuexit from those functions. Reported-by: Tony Luck Signed-off-by: Tejun Heo Acked-by: Tony Luck Cc: Peter Zijlstra LKML-Reference: <4C1FDF5B.1040301@kernel.org> Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index b4427cc..9064e7d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7477,8 +7477,8 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) * disabled, cpuset_update_active_cpus() becomes a simple wrapper * around partition_sched_domains(). */ -static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: @@ -7490,8 +7490,8 @@ static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb, } } -static int __cpuexit cpuset_cpu_inactive(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, + void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: -- cgit v1.1 From 396e894d289d69bacf5acd983c97cd6e21a14c08 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 9 Jul 2010 15:12:27 +0200 Subject: sched: Revert nohz_ratelimit() for now Norbert reported that nohz_ratelimit() causes his laptop to burn about 4W (40%) extra. For now back out the change and see if we can adjust the power management code to make better decisions. Reported-by: Norbert Preining Signed-off-by: Peter Zijlstra Acked-by: Mike Galbraith Cc: Arjan van de Ven LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index f52a880..63b4a14 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1232,16 +1232,6 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } -int nohz_ratelimit(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - u64 diff = rq->clock - rq->nohz_stamp; - - rq->nohz_stamp = rq->clock; - - return diff < (NSEC_PER_SEC / HZ) >> 1; -} - #endif /* CONFIG_NO_HZ */ static u64 sched_avg_period(void) -- cgit v1.1 From 68c38fc3cb4e5a60f502ee9c45f3dfe70e5165ad Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Thu, 15 Jul 2010 23:18:22 +0300 Subject: sched: No need for bootmem special cases As of commit dcce284 ("mm: Extend gfp masking to the page allocator") and commit 7e85ee0 ("slab,slub: don't enable interrupts during early boot"), the slab allocator makes sure we don't attempt to sleep during boot. Therefore, remove bootmem special cases from the scheduler and use plain GFP_KERNEL instead. Signed-off-by: Pekka Enberg Cc: Peter Zijlstra LKML-Reference: <1279225102-2572-1-git-send-email-penberg@cs.helsinki.fi> Signed-off-by: Ingo Molnar --- kernel/sched.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 9064e7d..7b443ee 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6248,23 +6248,18 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) free_rootdomain(old_rd); } -static int init_rootdomain(struct root_domain *rd, bool bootmem) +static int init_rootdomain(struct root_domain *rd) { - gfp_t gfp = GFP_KERNEL; - memset(rd, 0, sizeof(*rd)); - if (bootmem) - gfp = GFP_NOWAIT; - - if (!alloc_cpumask_var(&rd->span, gfp)) + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) goto out; - if (!alloc_cpumask_var(&rd->online, gfp)) + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, gfp)) + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) goto free_online; - if (cpupri_init(&rd->cpupri, bootmem) != 0) + if (cpupri_init(&rd->cpupri) != 0) goto free_rto_mask; return 0; @@ -6280,7 +6275,7 @@ out: static void init_defrootdomain(void) { - init_rootdomain(&def_root_domain, true); + init_rootdomain(&def_root_domain); atomic_set(&def_root_domain.refcount, 1); } @@ -6293,7 +6288,7 @@ static struct root_domain *alloc_rootdomain(void) if (!rd) return NULL; - if (init_rootdomain(rd, false) != 0) { + if (init_rootdomain(rd) != 0) { kfree(rd); return NULL; } -- cgit v1.1