内核源码分析之进程调度机制（基于3.16-rc4）

进程调度所使用到的数据结构：

1.就绪队列

内核为每一个cpu创建一个进程就绪队列，该队列上的进程均由该cpu执行，代码如下（kernel/sched/core.c）。

1 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

定义了一个struct rq结构体数组，每个数组元素是一个就绪队列，对应一个cpu。下面看下struct rq结构体（kernel/sched/sched.h）：

  1 struct rq {
  2     /* runqueue lock: */
  3     raw_spinlock_t lock;
  4 
  5     /*
  6      * nr_running and cpu_load should be in the same cacheline because
  7      * remote CPUs use both these fields when doing load calculation.
  8      */
  9     unsigned int nr_running;
 10 #ifdef CONFIG_NUMA_BALANCING
 11     unsigned int nr_numa_running;
 12     unsigned int nr_preferred_running;
 13 #endif
 14     #define CPU_LOAD_IDX_MAX 5
 15     unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 16     unsigned long last_load_update_tick;
 17 #ifdef CONFIG_NO_HZ_COMMON
 18     u64 nohz_stamp;
 19     unsigned long nohz_flags;
 20 #endif
 21 #ifdef CONFIG_NO_HZ_FULL
 22     unsigned long last_sched_tick;
 23 #endif
 24     int skip_clock_update;
 25 
 26     /* capture load from *all* tasks on this cpu: */
 27     struct load_weight load;
 28     unsigned long nr_load_updates;
 29     u64 nr_switches;
 30 
 31     struct cfs_rq cfs;
 32     struct rt_rq rt;
 33     struct dl_rq dl;
 34 
 35 #ifdef CONFIG_FAIR_GROUP_SCHED
 36     /* list of leaf cfs_rq on this cpu: */
 37     struct list_head leaf_cfs_rq_list;
 38 
 39     struct sched_avg avg;
 40 #endif /* CONFIG_FAIR_GROUP_SCHED */
 41 
 42     /*
 43      * This is part of a global counter where only the total sum
 44      * over all CPUs matters. A task can increase this counter on
 45      * one CPU and if it got migrated afterwards it may decrease
 46      * it on another CPU. Always updated under the runqueue lock:
 47      */
 48     unsigned long nr_uninterruptible;
 49 
 50     struct task_struct *curr, *idle, *stop;
 51     unsigned long next_balance;
 52     struct mm_struct *prev_mm;
 53 
 54     u64 clock;
 55     u64 clock_task;
 56 
 57     atomic_t nr_iowait;
 58 
 59 #ifdef CONFIG_SMP
 60     struct root_domain *rd;
 61     struct sched_domain *sd;
 62 
 63     unsigned long cpu_capacity;
 64 
 65     unsigned char idle_balance;
 66     /* For active balancing */
 67     int post_schedule;
 68     int active_balance;
 69     int push_cpu;
 70     struct cpu_stop_work active_balance_work;
 71     /* cpu of this runqueue: */
 72     int cpu;
 73     int online;
 74 
 75     struct list_head cfs_tasks;
 76 
 77     u64 rt_avg;
 78     u64 age_stamp;
 79     u64 idle_stamp;
 80     u64 avg_idle;
 81 
 82     /* This is used to determine avg_idle's max value */
 83     u64 max_idle_balance_cost;
 84 #endif
 85 
 86 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 87     u64 prev_irq_time;
 88 #endif
 89 #ifdef CONFIG_PARAVIRT
 90     u64 prev_steal_time;
 91 #endif
 92 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 93     u64 prev_steal_time_rq;
 94 #endif
 95 
 96     /* calc_load related fields */
 97     unsigned long calc_load_update;
 98     long calc_load_active;
 99 
100 #ifdef CONFIG_SCHED_HRTICK
101 #ifdef CONFIG_SMP
102     int hrtick_csd_pending;
103     struct call_single_data hrtick_csd;
104 #endif
105     struct hrtimer hrtick_timer;
106 #endif
107 
108 #ifdef CONFIG_SCHEDSTATS
109     /* latency stats */
110     struct sched_info rq_sched_info;
111     unsigned long long rq_cpu_time;
112     /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
113 
114     /* sys_sched_yield() stats */
115     unsigned int yld_count;
116 
117     /* schedule() stats */
118     unsigned int sched_count;
119     unsigned int sched_goidle;
120 
121     /* try_to_wake_up() stats */
122     unsigned int ttwu_count;
123     unsigned int ttwu_local;
124 #endif
125 
126 #ifdef CONFIG_SMP
127     struct llist_head wake_list;
128 #endif
129 };

struct rq