就这第一章中断子系统和第二章时间子系统,我们进入tick中断处理函数tick_handle_periodic()
调度器分为核心调度器和周期性调度器:核心调度器是task调用schedule()主动让出cpu;而周期性调度器则是tick 时钟中断周期性调用的,调用周期为1个HZ(通常这个HZ设置为100);我们先讲核心调度器即schedule()开始。
核心调度器
来看schedule()函数 kernel/sched/core.c中
asmlinkage __visible void __sched schedule(void)
{
struct task_struct *tsk = current;
sched_submit_work(tsk);
do {
preempt_disable();
__schedule(false); /*正真的调度函数, 非抢占*/
sched_preempt_enable_no_resched();
} while (need_resched()); /*先执行一次调度,然后再检查需要调度否,检查task的flag的 TIF_NEED_RESCHED位*/
}
static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq_flags rf;
struct rq *rq;
int cpu;
cpu = smp_processor_id();
rq = cpu_rq(cpu); /*获取该cpu runqueue*/
prev = rq->curr; /*将当前的task 设置成上一个task*/
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
local_irq_disable();
rcu_note_context_switch(preempt);
/*
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up().
*
* The membarrier system call requires a full memory barrier
* after coming from user-space, before storing to rq->curr.
*/
rq_lock(rq, &rf);
smp_mb__after_spinlock();
/* Promote REQ to ACT */
rq->clock_update_flags <<= 1;
update_rq_clock(rq);
switch_count = &prev->nivcsw;
if (!preempt && prev->state) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} else {
deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
prev->on_rq = 0;
if (prev->in_iowait) {
atomic_inc(&rq->nr_iowait);
delayacct_blkio_start();
}
/*
* If a worker went to sleep, notify and ask workqueue
* whether it wants to wake up a task to maintain
* concurrency.
*/
if (prev->flags & PF_WQ_WORKER) {
struct task_struct *to_wakeup;
to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
try_to_wake_up_local(to_wakeup, &rf);
}
}
switch_count = &prev->nvcsw;
}
next = pick_next_task(rq, prev, &rf); /*选择下一个执行的task*/
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
if (likely(prev != next)) { /*这两个task不是同一个*/
rq->nr_switches++;
rq->curr = next; /*设置下一个task为runqueue的当前执行的task*/
/*
* The membarrier system call requires each architecture
* to have a full memory barrier after updating
* rq->curr, before returning to user-space.
*
* Here are the schemes providing that barrier on the
* various architectures:
* - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
* switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
* - finish_lock_switch() for weakly-ordered
* architectures where spin_unlock is a full barrier,
* - switch_to() for arm64 (weakly-ordered, spin_unlock
* is a RELEASE barrier),
*/
++*switch_count;
trace_sched_switch(preempt, prev, next);
/* Also unlocks the rq: */
rq = context_switch(rq, prev, next, &rf); /*切换上下文*/
} else {
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
rq_unlock_irq(rq, &rf);
}
balance_callback(rq);
}
我们重点来看pick_next_task()函数和context_switch();如何选择下一个task以及怎样切换上下文的;
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
const struct sched_class *class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in the fair class we can
* call that function directly, but only if the @prev task wasn't of a
* higher scheduling class, because otherwise those loose the
* opportunity to pull in more work from other CPUs.
*/
if (likely((prev->sched_class == &idle_sched_class ||
prev->sched_class == &fair_sched_class) &&
rq->nr_running == rq->cfs.h_nr_running)) {
/*公平调度类的pick_next_task()函数*/
p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto again;
/* Assumes fair_sched_class->next == idle_sched_class */
/*空转调度类的pick_next_task()函数*/
if (unlikely(!p))
p = idle_sched_class.pick_next_task(rq, prev, rf);
return p;
}
again:
/*遍历每一个调度类;各调度类串成一个链表,优先级dl->rt->fair->idle*/
for_each_class(class) {
p = class->pick_next_task(rq, prev, rf);
if (p) {
if (unlikely(p == RETRY_TASK))
goto again;
return p;
}
}
/* The idle class should always have a runnable task: */
BUG();
}
我们看到,pick_next_task()其实是调用prev task的调度类的pick_next_task()函数;我们以公平调度类为例;
kernel/sched/fair.c
const struct sched_class fair_sched_class = {
.next = &idle_sched_class,
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
.yield_to_task = yield_to_task_fair,
.check_preempt_curr = check_preempt_wakeup,
.pick_next_task = pick_next_task_fair, /*pick_next_task 函数*/
.put_prev_task = put_prev_task_fair,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_fair,
.migrate_task_rq = migrate_task_rq_fair,
.rq_online = rq_online_fair,
.rq_offline = rq_offline_fair,
.task_dead = task_dead_fair,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
.set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
.switched_from = switched_from_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,
.update_curr = update_curr_fair,
#ifdef CONFIG_FAIR_GROUP_SCHED
.task_change_group = task_change_group_fair,
#endif
};
static struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct cfs_rq *cfs_rq = &rq->cfs; /*runqueue 的 cfs 队列*/
struct sched_entity *se;
struct task_struct *p;
int new_tasks;
again:
if (!cfs_rq->nr_running)
goto idle;
#ifdef CONFIG_FAIR_GROUP_SCHED
if (prev->sched_class != &fair_sched_class)
goto simple;
/*
* Because of the set_next_buddy() in dequeue_task_fair() it is rather
* likely that a next task is from the same cgroup as the current.
*
* Therefore attempt to avoid putting and setting the entire cgroup
* hierarchy, only change the part that actually changes.
*/
do {
struct sched_entity *curr = cfs_rq->curr;
/*
* Since we got here without doing put_prev_entity() we also
* have to consider cfs_rq->curr. If it is still a runnable
* entity, update_curr() will update its vruntime, otherwise
* forget we've ever seen it.
*/
if (curr) {
if (curr->on_rq)
update_curr(cfs_rq);
else
curr = NULL;
/*
* This call to check_cfs_rq_runtime() will do the
* throttle and dequeue its entity in the parent(s).
* Therefore the nr_running test will indeed
* be correct.
*/
if (unlikely(check_cfs_rq_runtime(cfs_rq))) {
cfs_rq = &rq->cfs;
if (!cfs_rq->nr_running)
goto idle;
goto simple;
}
}
se = pick_next_entity(cfs_rq, curr);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
/*
* Since we haven't yet done put_prev_entity and if the selected task
* is a different task than we started out with, try and touch the
* least amount of cfs_rqs.
*/
if (prev != p) {
struct sched_entity *pse = &prev->se;
while (!(cfs_rq = is_same_group(se, pse))) {
int se_depth = se->depth;
int pse_depth = pse->depth;
if (se_depth <= pse_depth) {
put_prev_entity(cfs_rq_of(pse), pse);
pse = parent_entity(pse);
}
if (se_depth >= pse_depth) {
set_next_entity(cfs_rq_of(se), se);
se = parent_entity(se);
}
}
put_prev_entity(cfs_rq, pse);
set_next_entity(cfs_rq, se);
}
goto done;
simple: /*我们来看simple方式*/
#endif
put_prev_task(rq, prev);
do {
se = pick_next_entity(cfs_rq, NULL);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
done: __maybe_unused;
#ifdef CONFIG_SMP
/*
* Move the next running task to the front of
* the list, so our cfs_tasks list becomes MRU
* one.
*/
list_move(&p->se.group_node, &rq->cfs_tasks);
#endif
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
return p;
idle:
new_tasks = idle_balance(rq, rf);
/*
* Because idle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
* must re-start the pick_next_entity() loop.
*/
if (new_tasks < 0)
return RETRY_TASK;
if (new_tasks > 0)
goto again;
return NULL;
}
pick_next_entity()函数;cfs里的task是用rbtree来管理的。
/*
* Pick the next process, keeping these things in mind, in this order:
* 1) keep things fair between processes/task groups
* 2) pick the "next" process, since someone really wants that to run
* 3) pick the "last" process, for cache locality
* 4) do not run the "skip" process, if something else is available
*/
static struct sched_entity *
pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
struct sched_entity *left = __pick_first_entity(cfs_rq); /*最左侧的实体*/
struct sched_entity *se;
/*
* If curr is set we have to see if its left of the leftmost entity
* still in the tree, provided there was anything in the tree at all.
*/
if (!left || (curr && entity_before(curr, left)))
left = curr;
se = left; /* ideally we run the leftmost entity */
/*
* Avoid running the skip buddy, if running something else can
* be done without getting too unfair.
*/
if (cfs_rq->skip == se) {
struct sched_entity *second;
if (se == curr) {
second = __pick_first_entity(cfs_rq); /*红黑树中查找*/
} else {
second = __pick_next_entity(se);
if (!second || (curr && entity_before(curr, second)))
second = curr;
}
if (second && wakeup_preempt_entity(second, left) < 1)
se = second;
}
/*
* Prefer last buddy, try to return the CPU to a preempted task.
*/
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
/*
* Someone really wants this to run. If it's not unfair, run it.
*/
if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
se = cfs_rq->next;
clear_buddies(cfs_rq, se);
return se;
}
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return grp->my_q;
}
pick_next_task_fair()的simple方式,如果这个调度实例的组队列my_q不为空,就继续找下一个,直到找到group_cfs_rq为空的sched entity。
来看看这个my_q是在何处设置?sched entity是何时创建并加入rbtree的?
init_tg_cfs_entry()函数
void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent)
{
struct rq *rq = cpu_rq(cpu);
cfs_rq->tg = tg; /*关联 cfs 和 任务组*/
cfs_rq->rq = rq;
init_cfs_rq_runtime(cfs_rq);
tg->cfs_rq[cpu] = cfs_rq; /*关联 cfs 和 任务组*/
tg->se[cpu] = se; /*关联 cfs 和 sched entity的头指针*/
/* se could be NULL for root_task_group */
if (!se)
return;
if (!parent) {
se->cfs_rq = &rq->cfs;
se->depth = 0;
} else {
se->cfs_rq = parent->my_q;
se->depth = parent->depth + 1;
}
se->my_q = cfs_rq; /*设置调度实例的调度队列runqueue*/
/* guarantee group entities always have weight */
update_load_set(&se->load, NICE_0_LOAD);
se->parent = parent;
}
init_tg_cfs_entry()被sched_init() 和 alloc_fair_sched_group()调用; sched_init()则是在start_kernel()中调用的。那我们来看看调度器的初始化。
void __init sched_init(void)
{
int i, j;
unsigned long alloc_size = 0, ptr;
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
/*分配实例入口sched_entity和 runqueue 的指针*/
#ifdef CONFIG_FAIR_GROUP_SCHED
/*root 调度组*/
root_task_group.se = (struct sched_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.cfs_rq = (struct cfs_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.rt_rq = (struct rt_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_RT_GROUP_SCHED */
}
#ifdef CONFIG_CPUMASK_OFFSTACK
for_each_possible_cpu(i) {
per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
cpumask_size(), GFP_KERNEL, cpu_to_node(i));
per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node(
cpumask_size(), GFP_KERNEL, cpu_to_node(i));
}
#endif /* CONFIG_CPUMASK_OFFSTACK */
/*初始化事实调度的bandwidth*/
init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_CGROUP_SCHED
task_group_cache = KMEM_CACHE(task_group, 0);
list_add(&root_task_group.list, &task_groups);
INIT_LIST_HEAD(&root_task_group.children);
INIT_LIST_HEAD(&root_task_group.siblings);
autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */
for_each_possible_cpu(i) {
struct rq *rq;
rq = cpu_rq(i); /*获取每个cpu 的runqueue*/
raw_spin_lock_init(&rq->lock);
rq->nr_running = 0;
rq->calc_load_active = 0;
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs); /*初始化runque的cfs,公平调度器*/
init_rt_rq(&rq->rt); /*初始化runque的rt,实时调度器*/
init_dl_rq(&rq->dl); /*初始化runque的dl,deadline调度器*/
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
* How much CPU bandwidth does root_task_group get?
*
* In case of task-groups formed thr' the cgroup filesystem, it
* gets 100% of the CPU resources in the system. This overall
* system CPU resource is divided among the tasks of
* root_task_group and its child task-groups in a fair manner,
* based on each entity's (task or task-group's) weight
* (se->load.weight).
*
* In other words, if root_task_group has 10 tasks of weight
* 1024) and two child groups A0 and A1 (of weight 1024 each),
* then A0's share of the CPU resource is:
*
* A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
*
* We achieve this by letting root_task_group's tasks sit
* directly in rq->cfs (i.e root_task_group->se[] = NULL).
*/
init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); /*加入task group,只关联cfs和 root_task_group; 未创建调度实例*/
#endif /* CONFIG_FAIR_GROUP_SCHED */
rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
rq->cpu_load[j] = 0;
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
rq->balance_callback = NULL;
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
rq->cpu = i;
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->cfs_tasks);
rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ_COMMON
rq->last_load_update_tick = jiffies;
rq->last_blocked_load_update_tick = jiffies;
atomic_set(&rq->nohz_flags, 0);
#endif
#endif /* CONFIG_SMP */
hrtick_rq_init(rq);
atomic_set(&rq->nr_iowait, 0);
}
set_load_weight(&init_task, false); /*设置init 任务的调度优先级 weight*/
/*
* The boot idle thread does lazy MMU switching as well:
*/
mmgrab(&init_mm);
enter_lazy_tlb(&init_mm, current);
/*
* Make us the idle thread. Technically, schedule() should not be
* called from this thread, however somewhere below it might be,
* but because we are the idle thread, we just pick up running again
* when this runqueue becomes "idle".
*/
init_idle(current, smp_processor_id());
calc_load_update = jiffies + LOAD_FREQ;
#ifdef CONFIG_SMP
idle_thread_set_boot_cpu();
#endif
init_sched_fair_class();
init_schedstats();
scheduler_running = 1;
}
先来看看 init_rt_bandwidth() kernel/sched/rt.c 中是做什么的?
void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
{
rt_b->rt_period = ns_to_ktime(period);
rt_b->rt_runtime = runtime;
raw_spin_lock_init(&rt_b->rt_runtime_lock);
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
/*初始化一个hrtimer*/
rt_b->rt_period_timer.function = sched_rt_period_timer;
/*sched_rt_period_timer,实时调度类hrimer 的handler*/
}
sched_rt_period_timer();实施调度类的hrtimer 定时做了什么?这个我们后面再分析。
sched_init()中的init_tg_rt_entry(),只将root_task_group和该cpu的rq->cfs所关联起来;那调度实例,sched entity是在何处建立的呢?接着看alloc_fair_sched_group()函数。
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
struct sched_entity *se;
struct cfs_rq *cfs_rq;
int i;
tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL);
/*二维指针数组,每个cpu对应一个index*/
if (!tg->cfs_rq)
goto err;
tg->se = kcalloc(nr_cpu_ids, sizeof(se), GFP_KERNEL);
if (!tg->se)
goto err;
tg->shares = NICE_0_LOAD;
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
/*分配cfs_rq*/
if (!cfs_rq)
goto err;
se = kzalloc_node(sizeof(struct sched_entity),
GFP_KERNEL, cpu_to_node(i));
/*分配调度实例*/
if (!se)
goto err_free_rq;
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
/*关联 task_group; cfs_rq; 和调度实例sched entity*/
init_entity_runnable_average(se);
}
return 1;
err_free_rq:
kfree(cfs_rq);
err:
return 0;
}
alloc_fair_sched_group()在何处调用?
cpu_cgroup_css_alloc()
->sched_create_group()
->-> alloc_fair_sched_group()
cpu_cgroup_css_alloc() 是cpu 的cgroup的一个成员函数;关于cgroup 子系统的知识后面再学。css:cgroup sched subsystem。
kernel/sched/core.c中
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
.css_online = cpu_cgroup_css_online,
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.css_extra_stat_show = cpu_extra_stat_show,
.fork = cpu_cgroup_fork,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.legacy_cftypes = cpu_legacy_files,
.dfl_cftypes = cpu_files,
.early_init = true,
.threaded = true,
};
这个是cpu子系统的cgroup。<linux/cgroup_subsys.h>中,这个我们不再深究下一节学习 cgroup。
再回到__schedule()函数,context_switch()中的上下文转换函数__switch_to函数是架构相关的,arch/arm/kernel/entry_v7m.S的汇编代码:
/*
* Register switch for ARMv7-M processors.
* r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info
* previous and next are guaranteed not to be the same.
*/
ENTRY(__switch_to)
.fnstart
.cantunwind
add ip, r1, #TI_CPU_SAVE
stmia ip!, {r4 - r11} @ Store most regs on stack
str sp, [ip], #4
str lr, [ip], #4
mov r5, r0
add r4, r2, #TI_CPU_SAVE
ldr r0, =thread_notify_head
mov r1, #THREAD_NOTIFY_SWITCH
bl atomic_notifier_call_chain
mov ip, r4
mov r0, r5
ldmia ip!, {r4 - r11} @ Load all regs saved previously
ldr sp, [ip]
ldr pc, [ip, #4]!
.fnend
ENDPROC(__switch_to)
周期性调度schedule_tick()
tick 时钟中断函数入手
tick_handle_periodic()
->tick_periodic()
->update_process_times()
->scheduler_tick()
curr->sched_class->task_tick(rq, curr, 0);
scheduler_tick()函数
void scheduler_tick(void)
{
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
struct task_struct *curr = rq->curr;
struct rq_flags rf;
sched_clock_tick();
rq_lock(rq, &rf);
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
cpu_load_update_active(rq);
calc_global_load_tick(rq);
rq_unlock(rq, &rf);
perf_event_task_tick();
#ifdef CONFIG_SMP
rq->idle_balance = idle_cpu(cpu);
trigger_load_balance(rq);
#endif
}
调用当前task的调度类的task_tick函数。
- 当前task的调度类是在何处设置?
- 各调度类的task_tick是什么?以fair为例。
下来回答第二个问题,fair 调度类的task_tick函数是task_tick_fair();
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &curr->se; /*当前task 的调度实例?*/
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
entity_tick(cfs_rq, se, queued); /*实例调度*/
}
if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
}
static void
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq); /*更新当前任务的运行时间,公平调度类的调度策略是,运行时间少的task 排在rbtree的左侧*/
/*
* Ensure that runnable average is periodically updated.
*/
update_load_avg(cfs_rq, curr, UPDATE_TG); /*更新权重*/
update_cfs_group(curr);
#ifdef CONFIG_SCHED_HRTICK
/*
* queued ticks are scheduled to match the slice, so don't bother
* validating it and just reschedule.
*/
if (queued) {
resched_curr(rq_of(cfs_rq)); /*置位flag,触发延时调度*/
return;
}
/*
* don't let the period tick interfere with the hrtick preemption
*/
if (!sched_feat(DOUBLE_TICK) &&
hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
return;
#endif
if (cfs_rq->nr_running > 1)
check_preempt_tick(cfs_rq, curr);
}
关于公平调度类,该博客讲的比较详细
https://blog.csdn.net/sunshineywz/article/details/104889806
task_tick_fair只是更新时间并没有真正进行调度。只是设置了task的flag为TIF_NEED_RESCHED;待schedule() 调用时才真正发生上下文切换。
void resched_curr(struct rq *rq)
{
struct task_struct *curr = rq->curr;
int cpu;
lockdep_assert_held(&rq->lock);
if (test_tsk_need_resched(curr))
return;
cpu = cpu_of(rq);
if (cpu == smp_processor_id()) {
set_tsk_need_resched(curr); /*设置当前task 的flag 为need sched;触发延时调度*/
set_preempt_need_resched();
return;
}
if (set_nr_and_not_polling(curr))
smp_send_reschedule(cpu);
else
trace_sched_wake_idle_without_ipi(cpu);
}
完全公平队列中的进程, 首先根据当前就绪队列中的进程数算出一个延迟时间间隔,大概每个进程分配2ms时间,然后按照该进程在队列中的总权重中占得比例,算出它该执行的时间X,如果该进程执行物理时间超过了X,则激发延迟调度;如果没有超过X,但是红黑树就绪队列中下一个进程优先级更高,即curr->vruntime-leftmost->vruntime > X,也将延迟调度
延迟调度的真正调度过程在:schedule中实现,会按照调度类顺序和优先级挑选出一个最高优先级的进程执行
如果当前进程是实时调度类中的进程:则如果该进程是SCHED_RR,则递减时间片[为HZ/10],到期,插入到队列尾部,并激发延迟调度,如果是SCHED_FIFO,则什么也不做,直到该进程执行完成。
出自
https://blog.csdn.net/gatieme/article/details/51872561
那task的sched class是如何设置的呢?且是在何时和一个sched entity绑定起来的呢?
我们从系统调用fork()开始追朔
long _do_fork(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr,
unsigned long tls)
{
struct completion vfork;
struct pid *pid;
struct task_struct *p;
int trace = 0;
long nr;
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (!(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
add_latent_entropy();
if (IS_ERR(p))
return PTR_ERR(p);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
trace_sched_process_fork(current, p);
pid = get_task_pid(p, PIDTYPE_PID);
nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
put_pid(pid);
return nr;
}
_do_fork()
->copy_process()
->->sched_fork() kernel/sched/core.c
来看看sched_fork()函数
int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
__sched_fork(clone_flags, p);
/*
* We mark the process as NEW here. This guarantees that
* nobody will actually run it, and a signal or other external
* event cannot wake it up and insert it on the runqueue either.
*/
p->state = TASK_NEW;
/*
* Make sure we do not leak PI boosting priority to the child.
*/
p->prio = current->normal_prio;
/*
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->policy = SCHED_NORMAL;
p->static_prio = NICE_TO_PRIO(0);
p->rt_priority = 0;
} else if (PRIO_TO_NICE(p->static_prio) < 0)
p->static_prio = NICE_TO_PRIO(0);
p->prio = p->normal_prio = __normal_prio(p);
set_load_weight(p, false);
/*
* We don't need the reset flag anymore after the fork. It has
* fulfilled its duty:
*/
p->sched_reset_on_fork = 0;
}
if (dl_prio(p->prio))
return -EAGAIN;
else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class; /*设置调度类*/
init_entity_runnable_average(&p->se); /*初始化调度实例*/
/*
* The child is not yet in the pid-hash so no cgroup attach races,
* and the cgroup is pinned to this child due to cgroup_fork()
* is ran before sched_fork().
*
* Silence PROVE_RCU.
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
/*
* We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
*/
__set_task_cpu(p, smp_processor_id());
if (p->sched_class->task_fork)
p->sched_class->task_fork(p); /*调用调度类的task_fork*/
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
#ifdef CONFIG_SCHED_INFO
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP)
p->on_cpu = 0;
#endif
init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
return 0;
}
我们来看cfs的task_fork()函数
static void task_fork_fair(struct task_struct *p)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se, *curr;
struct rq *rq = this_rq();
struct rq_flags rf;
rq_lock(rq, &rf);
update_rq_clock(rq);
cfs_rq = task_cfs_rq(current);
curr = cfs_rq->curr;
if (curr) {
update_curr(cfs_rq);
se->vruntime = curr->vruntime; /*虚拟时间*/
}
place_entity(cfs_rq, se, 1);
if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
resched_curr(rq);
}
se->vruntime -= cfs_rq->min_vruntime;
rq_unlock(rq, &rf);
}
sched entity何时入rbtree?
fair的enqueue_task()用来入队列。
调用关系
_do_fork()
->wake_up_new_task()
->activate_task()
->enqueue_task()
p->sched_class->enqueue_task() 完成入队列。
linux调度策略:
SCHED_NORMAL和SCHED_BATCH调度普通的非实时进程
SCHED_FIFO和SCHED_RR和SCHED_DEADLINE则采用不同的调度策略调度实时进程
SCHED_IDLE则在系统空闲时调用idle进程.
核心调度器的调度时机?
周期性调度器scheduler_tick() 只新task的信息,cfs调度类中curr的vruntime,而不做真正的调度;正真的进程调度切换是在schedule()中进行的。而发生进程切换的时机:
1.中断处理过程中和中断返回时
2.从内核态返回用户态时;判断need_resched,task_struct的flag的对应位
3.内核线程只有内核态,所以自己可以调用schedule(),主动调度让出cpu,内核线程既可以主动调度,也可以被动调度
4.用户进程只能被动调度