进程调度 : 决定哪个程序投入运行,何时运行以及运行多长时间。
多任务操作系统 : 能同时并发的交互执行多个进程的操作系统。
多任务系统可以分为 :非抢占式多任务(cooperation multitasking)和抢占式多任务(preemptive multitasking).
时间片(timeslice): 分配给每个可运行进程的处理器时间段。
进程主动挂起自己的操作称为让步(yielding).
1. 常用进程调度的算法有以下几种:
--- 先来先服务调度算法: 按进程就绪顺序来调度, 针对 SCHED_FIFO 类型的进程
--- 短进程优先调度算法: 按进程所需要运行时间长短来排序
--- 高优先级优先调度算法: 按进程优先级顺序
--- 时间片轮转算法: 按指定时间片轮转运行进程。 针对SCHED_RR任务
2. 调度器类 --- scheduler classes
Linux调度器以模块方式提供,它允许多种不同的调度算法并存,而且这些调度算法可以动态添加。
基本的调度器代码定义于 kernel/sched.c 中
2.1 CFS (Completely Fair Scheduling) --- 完全公平调度类
CFS 完全公平调度 是一个针对普通进程的调度类。
Linux系统中把普通进程是标志位 SCHED_NORMAL.
CFS 算法实现定义于 kernel/sched_fair.c中。
3. Linux进程调度的实现
3.1 调度器的实体结构 struct sched_entity
定义如下
struct sched_entity {
struct load_weight load; /* for load-balancing */
struct rb_node run_node;
struct list_head group_node;
unsigned int on_rq;
u64 exec_start; //开始运行时间
u64 sum_exec_runtime; //总共需运行多长时间
u64 vruntime;
u64 prev_sum_exec_runtime;
u64 nr_migrations;
#ifdef CONFIG_SCHEDSTATS
struct sched_statistics statistics;
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
struct sched_entity *parent;
/* rq on which this entity is (to be) queued: */
struct cfs_rq *cfs_rq;
/* rq "owned" by this entity/group: */
struct cfs_rq *my_q;
#endif
};
--- vruntime : 该变量存放进程的虚拟运行时间,以ns为单位。用来记录一个程序运行了多长时间,以及他应该再运行多久。
3.2 时间记账
所有的调度器,都必须对进程运行时间记账。
update_curr()函数 实现了该时间记账功能:
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
u64 now = rq_of(cfs_rq)->clock_task;
unsigned long delta_exec;
if (unlikely(!curr))
return;
/*
* Get the amount of time the current task was running
* since the last time we changed load (this cannot
* overflow on 32 bits):
*/
delta_exec = (unsigned long)(now - curr->exec_start);
if (!delta_exec)
return;
__update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
if (entity_is_task(curr)) {
struct task_struct *curtask = task_of(curr);
trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
cpuacct_charge(curtask, delta_exec);
account_group_exec_runtime(curtask, delta_exec);
}
}
__update_curr()根据当前可运行进程总数,对运行时间进行加权计算。
最终将上述权重值与当前运行进程的vruntime相加:
/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
*/
static inline void
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
unsigned long delta_exec)
{
unsigned long delta_exec_weighted;
schedstat_set(curr->statistics.exec_max,
max((u64)delta_exec, curr->statistics.exec_max));
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
delta_exec_weighted = calc_delta_fair(delta_exec, curr);
curr->vruntime += delta_exec_weighted;
update_min_vruntime(cfs_rq);
}
update_curr()是系统定时器周期性调用的,vruntime 可以准确的测量给定进程的运行时间。
3.3 进程选择
当CFS需要选择下一个进程时,它会挑一个具有最小 vruntime 的进程。
这就是CFS 调度算法的核心:挑选具有最小 vruntime 的任务。
CFS 使用红黑树(rbtree)来组织可运行进程队列,并利用其快速找到最小 vruntime 值的进程。
红黑树: rbtree, 是一个自平衡二叉搜索树。 这是一种以树节点形式存储的数据,这些数据都会对应一个键值。
我们可以通过这些键值来快速检索节点上的数据,重要的是,通过键值检索到对应节点的速度,与整个树的节点规模成指数比关系。
3.3.1 挑选下一个任务:
static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
if (!left)
return NULL;
return rb_entry(left, struct sched_entity, run_node);
}
3.3.2 向树中加入进程:
static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
/*
* Update the normalized vruntime before updating min_vruntime
* through callig update_curr().
*/
if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
se->vruntime += cfs_rq->min_vruntime;
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
account_entity_enqueue(cfs_rq, se);
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
enqueue_sleeper(cfs_rq, se);
}
update_stats_enqueue(cfs_rq, se);
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
}
/*
* Enqueue an entity into the rb-tree:
*/
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
struct rb_node *parent = NULL;
struct sched_entity *entry;
s64 key = entity_key(cfs_rq, se);
int leftmost = 1;
/*
* Find the right place in the rbtree:
*/
while (*link) {
parent = *link;
entry = rb_entry(parent, struct sched_entity, run_node);
/*
* We dont care about collisions. Nodes with
* the same key stay together.
*/
if (key < entity_key(cfs_rq, entry)) {
link = &parent->rb_left;
} else {
link = &parent->rb_right;
leftmost = 0;
}
}
/*
* Maintain a cache of leftmost tree entries (it is frequently
* used):
*/
if (leftmost)
cfs_rq->rb_leftmost = &se->run_node;
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}
3.3.3 从树中删除进程
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
update_stats_dequeue(cfs_rq, se);
if (flags & DEQUEUE_SLEEP) {
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
if (tsk->state & TASK_INTERRUPTIBLE)
se->statistics.sleep_start = rq_of(cfs_rq)->clock;
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->statistics.block_start = rq_of(cfs_rq)->clock;
}
#endif
}
clear_buddies(cfs_rq, se);
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
/*
* Normalize the entity after updating the min_vruntime because the
* update can refer to the ->curr item and we need to reflect this
* movement in our normalized position.
*/
if (!(flags & DEQUEUE_SLEEP))
se->vruntime -= cfs_rq->min_vruntime;
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (cfs_rq->rb_leftmost == &se->run_node) {
struct rb_node *next_node;
next_node = rb_next(&se->run_node);
cfs_rq->rb_leftmost = next_node;
}
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
4. 调度器入口 --- schedule()
schedule() 是内核其他部分调用调度器的入口。
/*
* schedule() is the main scheduler function.
*/
asmlinkage void __sched schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_note_context_switch(cpu);
prev = rq->curr;
release_kernel_lock(prev);
need_resched_nonpreemptible:
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} 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;
}
pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
put_prev_task(rq, prev);
next = pick_next_task(rq);
clear_tsk_need_resched(prev);
rq->skip_clock_update = 0;
if (likely(prev != next)) {
sched_info_switch(prev, next);
perf_event_task_sched_out(prev, next);
rq->nr_switches++;
rq->curr = next;
++*switch_count;
context_switch(rq, prev, next); /* unlocks the rq */
/*
* 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);
} else
raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
if (unlikely(reacquire_kernel_lock(prev)))
goto need_resched_nonpreemptible;
preempt_enable_no_resched();
if (need_resched())
goto need_resched;
}
EXPORT_SYMBOL(schedule);
runqueue --- 就是上面 的 struct rq, 每个CPU 都具备的一个runqueue data structure, 表示准备运行的进程。
定义如下:
/*
* This is the main, per-CPU runqueue data structure.
*
* Locking rule: those places that want to lock multiple runqueues
* (such as the load balancing or the thread migration code), lock
* acquire operations must be ordered by ascending &runqueue.
*/
struct rq {
/* runqueue lock: */
raw_spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
* remote CPUs use both these fields when doing load calculation.
*/
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 nohz_balance_kick;
#endif
unsigned int skip_clock_update;
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
struct cfs_rq cfs;
struct rt_rq rt;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
struct list_head leaf_rt_rq_list;
#endif
/*
* This is part of a global counter where only the total sum
* over all CPUs matters. A task can increase this counter on
* one CPU and if it got migrated afterwards it may decrease
* it on another CPU. Always updated under the runqueue lock:
*/
unsigned long nr_uninterruptible;
struct task_struct *curr, *idle, *stop;
unsigned long next_balance;
struct mm_struct *prev_mm;
u64 clock;
u64 clock_task;
atomic_t nr_iowait;
#ifdef CONFIG_SMP
struct root_domain *rd;
struct sched_domain *sd;
unsigned long cpu_power;
unsigned char idle_at_tick;
/* For active balancing */
int post_schedule;
int active_balance;
int push_cpu;
struct cpu_stop_work active_balance_work;
/* cpu of this runqueue: */
int cpu;
int online;
unsigned long avg_load_per_task;
u64 rt_avg;
u64 age_stamp;
u64 idle_stamp;
u64 avg_idle;
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
u64 prev_irq_time;
#endif
/* calc_load related fields */
unsigned long calc_load_update;
long calc_load_active;
#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
int hrtick_csd_pending;
struct call_single_data hrtick_csd;
#endif
struct hrtimer hrtick_timer;
#endif
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
unsigned long long rq_cpu_time;
/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
unsigned int yld_count;
/* schedule() stats */
unsigned int sched_switch;
unsigned int sched_count;
unsigned int sched_goidle;
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
/* BKL stats */
unsigned int bkl_count;
#endif
};
schdule() 中会运行 pick_next_task(rq) 来选择运行下一个进程:
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
pick_next_task(struct rq *rq)
{
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:
*/
if (likely(rq->nr_running == rq->cfs.nr_running)) {
p = fair_sched_class.pick_next_task(rq);
if (likely(p))
return p;
}
for_each_class(class) {
p = class->pick_next_task(rq);
if (p)
return p;
}
BUG(); /* the idle class will always have a runnable task */
}