2.1 進(jìn)程優(yōu)先級(jí)

1. 進(jìn)程分類

1）硬實(shí)時(shí)進(jìn)程: 有嚴(yán)格時(shí)間限制
2）軟實(shí)時(shí)進(jìn)程，
3）普通進(jìn)程：大多數(shù)進(jìn)程

2.2 進(jìn)程生命周期

進(jìn)程的生命周期可歸結(jié)為以下三個(gè)狀態(tài)：

1. 運(yùn)行：進(jìn)程正在執(zhí)行；
2. 睡眠：進(jìn)程正在睡眠，不能執(zhí)行，它在等待一個(gè)外部事件；
3. 等待：進(jìn)程可以運(yùn)行，但是需要等到下一任務(wù)切換時(shí)執(zhí)行。
   更細(xì)致的，從task_struct中state中得到具體狀態(tài)：
   1）運(yùn)行時(shí)狀態(tài)：
   TASK_RUNNING：進(jìn)程處于可運(yùn)行狀態(tài)，但并不意味著已實(shí)際分配了CPU，而是進(jìn)程可以無(wú)需等待外部條件執(zhí)行；
   TASK_INTERRUPTIBLE：進(jìn)程處于睡眠狀態(tài)，可由外部信號(hào)喚醒；
   TASK_UNINTERRUPTIBLE：睡眠狀態(tài)，但不能有外部信號(hào)喚醒，例如IO等待，這種狀態(tài)主要是為了保持強(qiáng)一致性，例如讀取磁盤(pán)時(shí)若外部信號(hào)能中斷，那么磁盤(pán)讀取則會(huì)處理不完整狀態(tài)，影響正常使用。
   __TASK_STOPPED：進(jìn)程特意停止運(yùn)行，如由調(diào)試器暫停；
   __TASK_TRACED：ptrace跟蹤用，在調(diào)試時(shí)區(qū)分常規(guī)進(jìn)程；
   2）退出時(shí)狀態(tài)：exit_state
   EXIT_ZOMBIE: 進(jìn)程處于僵尸狀態(tài)。當(dāng)進(jìn)程被另一個(gè)進(jìn)程或用戶殺死的同時(shí)，父進(jìn)程在該子進(jìn)程終止時(shí)，未調(diào)用wait函數(shù)，則會(huì)出現(xiàn)僵尸進(jìn)程。
   EXIT_DEAD：指父進(jìn)程已發(fā)出wait調(diào)用，但進(jìn)程還未完全從系統(tǒng)中移除之前的狀態(tài)

2.3 進(jìn)程表示

進(jìn)程的表示主要通過(guò)task_struct結(jié)構(gòu)：

struct task_struct {
    volatile long state;    /* -1 unrunnable, 0 runnable, >0 stopped */
    void *stack;
    atomic_t usage;
    unsigned int flags; /* per process flags, defined below */
    unsigned int ptrace;

    int lock_depth;     /* BKL lock depth */

#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
    int oncpu;
#endif
#endif

    int prio, static_prio, normal_prio;
    unsigned int rt_priority;
    const struct sched_class *sched_class;
    struct sched_entity se;
    struct sched_rt_entity rt;

#ifdef CONFIG_PREEMPT_NOTIFIERS
    /* list of struct preempt_notifier: */
    struct hlist_head preempt_notifiers;
#endif

    /*
     * fpu_counter contains the number of consecutive context switches
     * that the FPU is used. If this is over a threshold, the lazy fpu
     * saving becomes unlazy to save the trap. This is an unsigned char
     * so that after 256 times the counter wraps and the behavior turns
     * lazy again; this to deal with bursty apps that only use FPU for
     * a short time
     */
    unsigned char fpu_counter;
#ifdef CONFIG_BLK_DEV_IO_TRACE
    unsigned int btrace_seq;
#endif

    unsigned int policy;
    cpumask_t cpus_allowed;

#ifdef CONFIG_PREEMPT_RCU
    int rcu_read_lock_nesting;
    char rcu_read_unlock_special;
    struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
    struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
    struct rt_mutex *rcu_boost_mutex;
#endif /* #ifdef CONFIG_RCU_BOOST */

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
    struct sched_info sched_info;
#endif

    struct list_head tasks;
#ifdef CONFIG_SMP
    struct plist_node pushable_tasks;
#endif

    struct mm_struct *mm, *active_mm;
#ifdef CONFIG_COMPAT_BRK
    unsigned brk_randomized:1;
#endif
#if defined(SPLIT_RSS_COUNTING)
    struct task_rss_stat    rss_stat;
#endif
/* task state */
    int exit_state;
    int exit_code, exit_signal;
    int pdeath_signal;  /*  The signal sent when the parent dies  */
    /* ??? */
    unsigned int personality;
    unsigned did_exec:1;
    unsigned in_execve:1;   /* Tell the LSMs that the process is doing an
                 * execve */
    unsigned in_iowait:1;


    /* Revert to default priority/policy when forking */
    unsigned sched_reset_on_fork:1;

    pid_t pid;
    pid_t tgid;

#ifdef CONFIG_CC_STACKPROTECTOR
    /* Canary value for the -fstack-protector gcc feature */
    unsigned long stack_canary;
#endif

    /* 
     * pointers to (original) parent process, youngest child, younger sibling,
     * older sibling, respectively.  (p->father can be replaced with 
     * p->real_parent->pid)
     */
    struct task_struct *real_parent; /* real parent process */
    struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
    /*
     * children/sibling forms the list of my natural children
     */
    struct list_head children;  /* list of my children */
    struct list_head sibling;   /* linkage in my parent's children list */
    struct task_struct *group_leader;   /* threadgroup leader */

    /*
     * ptraced is the list of tasks this task is using ptrace on.
     * This includes both natural children and PTRACE_ATTACH targets.
     * p->ptrace_entry is p's link on the p->parent->ptraced list.
     */
    struct list_head ptraced;
    struct list_head ptrace_entry;

    /* PID/PID hash table linkage. */
    struct pid_link pids[PIDTYPE_MAX];
    struct list_head thread_group;

    struct completion *vfork_done;      /* for vfork() */
    int __user *set_child_tid;      /* CLONE_CHILD_SETTID */
    int __user *clear_child_tid;        /* CLONE_CHILD_CLEARTID */

    cputime_t utime, stime, utimescaled, stimescaled;
    cputime_t gtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
    cputime_t prev_utime, prev_stime;
#endif
    unsigned long nvcsw, nivcsw; /* context switch counts */
    struct timespec start_time;         /* monotonic time */
    struct timespec real_start_time;    /* boot based time */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
    unsigned long min_flt, maj_flt;

    struct task_cputime cputime_expires;
    struct list_head cpu_timers[3];

/* process credentials */
    const struct cred __rcu *real_cred; /* objective and real subjective task
                     * credentials (COW) */
    const struct cred __rcu *cred;  /* effective (overridable) subjective task
                     * credentials (COW) */
    struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */

    char comm[TASK_COMM_LEN]; /* executable name excluding path
                     - access with [gs]et_task_comm (which lock
                       it with task_lock())
                     - initialized normally by setup_new_exec */
/* file system info */
    int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
    struct sysv_sem sysvsem;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
    unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
    struct thread_struct thread;
/* filesystem information */
    struct fs_struct *fs;
/* open file information */
    struct files_struct *files;
/* namespaces */
    struct nsproxy *nsproxy;
/* signal handlers */
    struct signal_struct *signal;
    struct sighand_struct *sighand;

    sigset_t blocked, real_blocked;
    sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */
    struct sigpending pending;

    unsigned long sas_ss_sp;
    size_t sas_ss_size;
    int (*notifier)(void *priv);
    void *notifier_data;
    sigset_t *notifier_mask;
    struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
    uid_t loginuid;
    unsigned int sessionid;
#endif
    seccomp_t seccomp;

/* Thread group tracking */
    u32 parent_exec_id;
    u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
    spinlock_t alloc_lock;

#ifdef CONFIG_GENERIC_HARDIRQS
    /* IRQ handler threads */
    struct irqaction *irqaction;
#endif

    /* Protection of the PI data structures: */
    raw_spinlock_t pi_lock;

#ifdef CONFIG_RT_MUTEXES
    /* PI waiters blocked on a rt_mutex held by this task */
    struct plist_head pi_waiters;
    /* Deadlock detection and priority inheritance handling */
    struct rt_mutex_waiter *pi_blocked_on;
#endif

#ifdef CONFIG_DEBUG_MUTEXES
    /* mutex deadlock detection */
    struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
    unsigned int irq_events;
    unsigned long hardirq_enable_ip;
    unsigned long hardirq_disable_ip;
    unsigned int hardirq_enable_event;
    unsigned int hardirq_disable_event;
    int hardirqs_enabled;
    int hardirq_context;
    unsigned long softirq_disable_ip;
    unsigned long softirq_enable_ip;
    unsigned int softirq_disable_event;
    unsigned int softirq_enable_event;
    int softirqs_enabled;
    int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
    u64 curr_chain_key;
    int lockdep_depth;
    unsigned int lockdep_recursion;
    struct held_lock held_locks[MAX_LOCK_DEPTH];
    gfp_t lockdep_reclaim_gfp;
#endif

/* journalling filesystem info */
    void *journal_info;

/* stacked block device info */
    struct bio_list *bio_list;

#ifdef CONFIG_BLOCK
/* stack plugging */
    struct blk_plug *plug;
#endif

/* VM state */
    struct reclaim_state *reclaim_state;

    struct backing_dev_info *backing_dev_info;

    struct io_context *io_context;

    unsigned long ptrace_message;
    siginfo_t *last_siginfo; /* For ptrace use.  */
    struct task_io_accounting ioac;
#if defined(CONFIG_TASK_XACCT)
    u64 acct_rss_mem1;  /* accumulated rss usage */
    u64 acct_vm_mem1;   /* accumulated virtual memory usage */
    cputime_t acct_timexpd; /* stime + utime since last update */
#endif
#ifdef CONFIG_CPUSETS
    nodemask_t mems_allowed;    /* Protected by alloc_lock */
    int mems_allowed_change_disable;
    int cpuset_mem_spread_rotor;
    int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
    /* Control Group info protected by css_set_lock */
    struct css_set __rcu *cgroups;
    /* cg_list protected by css_set_lock and tsk->alloc_lock */
    struct list_head cg_list;
#endif
#ifdef CONFIG_FUTEX
    struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
    struct compat_robust_list_head __user *compat_robust_list;
#endif
    struct list_head pi_state_list;
    struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTS
    struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
    struct mutex perf_event_mutex;
    struct list_head perf_event_list;
#endif
#ifdef CONFIG_NUMA
    struct mempolicy *mempolicy;    /* Protected by alloc_lock */
    short il_next;
    short pref_node_fork;
#endif
    atomic_t fs_excl;   /* holding fs exclusive resources */
    struct rcu_head rcu;

    /*
     * cache last used pipe for splice
     */
    struct pipe_inode_info *splice_pipe;
#ifdef  CONFIG_TASK_DELAY_ACCT
    struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
    int make_it_fail;
#endif
    struct prop_local_single dirties;
#ifdef CONFIG_LATENCYTOP
    int latency_record_count;
    struct latency_record latency_record[LT_SAVECOUNT];
#endif
    /*
     * time slack values; these are used to round up poll() and
     * select() etc timeout values. These are in nanoseconds.
     */
    unsigned long timer_slack_ns;
    unsigned long default_timer_slack_ns;

    struct list_head    *scm_work_list;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
    /* Index of current stored address in ret_stack */
    int curr_ret_stack;
    /* Stack of return addresses for return function tracing */
    struct ftrace_ret_stack *ret_stack;
    /* time stamp for last schedule */
    unsigned long long ftrace_timestamp;
    /*
     * Number of functions that haven't been traced
     * because of depth overrun.
     */
    atomic_t trace_overrun;
    /* Pause for the tracing */
    atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
    /* state flags for use by tracers */
    unsigned long trace;
    /* bitmask of trace recursion */
    unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
    struct memcg_batch_info {
        int do_batch;   /* incremented when batch uncharge started */
        struct mem_cgroup *memcg; /* target memcg of uncharge */
        unsigned long nr_pages; /* uncharged usage */
        unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
    } memcg_batch;
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
    atomic_t ptrace_bp_refcnt;
#endif
};

進(jìn)程管理中需要注意的一些重要成員：
1、state: 見(jiàn)上文；
2、資源管理rlim數(shù)組，見(jiàn)signal_struct中:

struct rlimit rlim[RLIM_NLIMITS];

rlimit定義如下：

struct rlmit {
  unsigned long rlim_cur;  // 進(jìn)程當(dāng)前的資源限制，叫軟限制
  unsigned long rlim_max; // 進(jìn)程最大容許值，叫硬限制 
}

rlim數(shù)組的索引標(biāo)識(shí)類型，資源限制可通過(guò)查看limits文件得知：

cat /proc/pid/limits

2.3.1 進(jìn)程類型

1、新進(jìn)程是通過(guò)fork、exec系統(tǒng)調(diào)用產(chǎn)生的；
2、clone也可以產(chǎn)生新進(jìn)程，但是clone主要用于實(shí)現(xiàn)線程，它和fork的主要不同點(diǎn)在于父子進(jìn)程共享的資源不同，本質(zhì)上是沒(méi)有任務(wù)區(qū)別的。

2.3.2 命名空間

作用

不同于KVM或VMWare，Linux的命名空間只使用一個(gè)內(nèi)核在一臺(tái)物理計(jì)算機(jī)上運(yùn)作，只需要很少的資源，便可虛擬化出多臺(tái)計(jì)算機(jī)。namespace主要做資源的隔離，正如目前很熱門(mén)的Docker技術(shù)也是使用類似的原理。

創(chuàng)建方式

創(chuàng)建方式有三種：
1、clone() – 實(shí)現(xiàn)線程的系統(tǒng)調(diào)用，用來(lái)創(chuàng)建一個(gè)新的進(jìn)程，并可以通過(guò)設(shè)計(jì)參數(shù)達(dá)到各類資源的隔離。
2、unshare() – 使某進(jìn)程脫離某個(gè)namespace
3、setns() – 把某進(jìn)程加入到某個(gè)namespace

實(shí)現(xiàn)方式

namespace的實(shí)現(xiàn)主要由nsproxy結(jié)構(gòu)：

struct nsproxy {
    atomic_t count;  // 引用計(jì)數(shù)，
    struct uts_namespace *uts_ns; // UTS命名空間，包括內(nèi)核名稱版本等信息
    struct ipc_namespace *ipc_ns; // 進(jìn)程間通信相關(guān)信息
    struct mnt_namespace *mnt_ns;  // 文件系統(tǒng)掛載信息
        struct user_namespace *user_ns; // 用于保存限制每個(gè)用戶資源使用的信息
    struct pid_namespace *pid_ns;  // 進(jìn)程ID相關(guān)信息
    struct net       *net_ns;  // 網(wǎng)絡(luò)相關(guān)命名空間信息
};

具體可參考：DOCKER基礎(chǔ)技術(shù)：LINUX NAMESPACE（上）

2.3.2 進(jìn)程ID號(hào)

pid.png

上圖很好的闡述了進(jìn)程ID的結(jié)構(gòu)信息
首先從task_struct開(kāi)始：

struct task_struct {
  ...
  struct pid_link pids[PIDTYPE_MAX];
  ...
}

其中pids數(shù)組是一個(gè)將task_struct關(guān)聯(lián)到pid的散列表。

struct pid_link {
    struct hlist_node node;  用作散列表元素
    struct pid *pid;
}

struct upid {
    /* Try to keep pid_chain in the same cacheline as nr for find_vpid */
    int nr;  // ID數(shù)值
    struct pid_namespace *ns;  // 關(guān)聯(lián)到pid_namespace的指針
    struct hlist_node pid_chain;
};

struct pid
{
    atomic_t count;   // 引用計(jì)數(shù)
    unsigned int level;  // 層級(jí)，子命名空間的level為父命名空間level+1
    /* lists of tasks that use this pid */
    struct hlist_head tasks[PIDTYPE_MAX];  // 一個(gè)HASH數(shù)組，每一項(xiàng)都是一個(gè)鏈表頭。分別是PID鏈表頭，進(jìn)程組ID表頭，會(huì)話ID表頭；
    struct rcu_head rcu;
    struct upid numbers[1]; // 是一個(gè)UPID數(shù)組，記錄對(duì)應(yīng)層級(jí)的命名空間中的UPID，所以可以想到，該P(yáng)ID處于第幾層，那么這個(gè)數(shù)組應(yīng)該有幾項(xiàng)（當(dāng)然都是從0開(kāi)始）。
};

enum pid_type
{
    PIDTYPE_PID,   // 進(jìn)程PID
    PIDTYPE_PGID,  // 進(jìn)程組PID
    PIDTYPE_SID,   // 會(huì)話PID
    PIDTYPE_MAX
};

這里沒(méi)加上TGID的原因是線程組也是一種PID：線程組長(zhǎng)PID，再單獨(dú)定義一個(gè)id沒(méi)有必要。
upid中關(guān)聯(lián)到pid_namespace，再看看pid_namespace定義：

struct pid_namespace {
    struct kref kref;  
    struct pidmap pidmap[PIDMAP_ENTRIES];
    int last_pid;
    struct task_struct *child_reaper;
    struct kmem_cache *pid_cachep;
    unsigned int level;
    struct pid_namespace *parent;
#ifdef CONFIG_PROC_FS
    struct vfsmount *proc_mnt;
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
    struct bsd_acct_struct *bacct;
#endif
};

在這里只關(guān)注child_reaper指針、level和parent指針。
其中child_reaper作用類似于fork函數(shù)中父進(jìn)程調(diào)用wait系列函數(shù)，用于托管進(jìn)程：就是當(dāng)父進(jìn)程先于子進(jìn)程結(jié)束的時(shí)候，就把子進(jìn)程的父進(jìn)程更新為child_reaper。
level即為命名空間的層級(jí)關(guān)系；
parent：父pid命名空間指針。
參考文章：Pid NameSpace淺分析

生成唯一PID

唯一pid的生成其實(shí)是通過(guò)一個(gè)大的bitmap生成，bitmap有高效、節(jié)省空間的作用，本質(zhì)即是尋找bitmap中第一個(gè)為0的比特用于分配新pid。該bitmap可見(jiàn)pid_namespace:

struct pid_namespace {
    ...
    struct pidmap pidmap[PIDMAP_ENTRIES];
    ...
}

#define PIDMAP_ENTRIES         ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8);
#define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \
    (sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT));

alloc_pidmap函數(shù)用于分配一個(gè)PID，而free_pidmap用于地方一個(gè)PID，具體見(jiàn)kernel/pid.c

2.3 進(jìn)程管理相關(guān)的系統(tǒng)調(diào)用

2.3.1 進(jìn)程復(fù)制

進(jìn)程復(fù)制主要有三個(gè)api:
1、fork(): 重量級(jí)調(diào)用，建立一個(gè)父進(jìn)程的完整副本，然后作為子進(jìn)程執(zhí)行。
2、vfork()：類似fork()，不同在于vfork中父子進(jìn)程共享數(shù)據(jù)，同時(shí)子進(jìn)程在創(chuàng)建后，父進(jìn)程會(huì)一直等到子進(jìn)程執(zhí)行完成；
3、clone()：用于線程實(shí)現(xiàn)，通過(guò)設(shè)定不同的flag來(lái)控制父子進(jìn)程的共享項(xiàng)。

1、寫(xiě)時(shí)復(fù)制

寫(xiě)時(shí)復(fù)制主要解決子進(jìn)程生成時(shí)復(fù)制大量數(shù)據(jù)從而耗費(fèi)資源的問(wèn)題，資源耗費(fèi)主要有兩方面：1是使用了大量?jī)?nèi)存，2是復(fù)制操作耗費(fèi)大量時(shí)間。寫(xiě)時(shí)復(fù)制實(shí)現(xiàn)的主要依據(jù)是進(jìn)程通常只需要內(nèi)存頁(yè)的一小部分，同時(shí)大部分子進(jìn)程在創(chuàng)建后會(huì)立即執(zhí)行。寫(xiě)時(shí)復(fù)制實(shí)現(xiàn)中，當(dāng)一個(gè)進(jìn)程師徒向復(fù)制的內(nèi)存頁(yè)寫(xiě)入數(shù)據(jù)時(shí)，處理器會(huì)立即報(bào)告缺頁(yè)異常，這時(shí)內(nèi)核會(huì)檢查內(nèi)存頁(yè)面是否只讀，若是只讀，則報(bào)告段錯(cuò)誤，否則執(zhí)行復(fù)制操作。

2、執(zhí)行系統(tǒng)調(diào)用

fork()，vfork()，clone()最終都會(huì)調(diào)用do_fork()函數(shù)。三種實(shí)現(xiàn)只有微小的差別。

3、do_fork()實(shí)現(xiàn)

do_fork.png

2.5 調(diào)度器實(shí)現(xiàn)

在2.6之后，調(diào)度器策略進(jìn)行了改變，從O(1)調(diào)度器到完全公平隊(duì)列調(diào)度，有了質(zhì)的改變，完全公平調(diào)度不再依賴時(shí)間片的概念，摒棄了舊版本調(diào)度存在的不足。
調(diào)度操作起點(diǎn)是kernel/sched.c中的schedule函數(shù)。

2.5.2 數(shù)據(jù)結(jié)構(gòu)

schedule.png

整體的調(diào)度框架如上圖所示，可有兩種方法激活調(diào)度：
1、直接方式
例如進(jìn)程打算睡眠或出于其他原因放棄cpu；
2、周期性
固定頻率運(yùn)行，檢查是否需要進(jìn)程切換。
具體的，有以下幾個(gè)調(diào)度時(shí)機(jī)：
1）調(diào)用cond_resched()時(shí)
2）顯式調(diào)用schedule()時(shí)
3）從系統(tǒng)調(diào)用或者異常中斷返回用戶空間時(shí)
4）從中斷上下文返回用戶空間時(shí)
　　當(dāng)開(kāi)啟內(nèi)核搶占(默認(rèn)開(kāi)啟)時(shí)，會(huì)多出幾個(gè)調(diào)度時(shí)機(jī)，如下
1）在系統(tǒng)調(diào)用或者異常中斷上下文中調(diào)用preempt_enable()時(shí)(多次調(diào)用preempt_enable()時(shí)，系統(tǒng)只會(huì)在最后一次調(diào)用時(shí)會(huì)調(diào)度)
2）在中斷上下文中，從中斷處理函數(shù)返回到可搶占的上下文時(shí)(這里是中斷下半部，中斷上半部實(shí)際上會(huì)關(guān)中斷，而新的中斷只會(huì)被登記，由于上半部處理很快，上半部處理完成后才會(huì)執(zhí)行新的中斷信號(hào)，這樣就形成了中斷可重入)

task_struct結(jié)構(gòu)中相關(guān)成員：

struct task_struct {
  // prio和normal_prio為動(dòng)態(tài)優(yōu)先級(jí)，static_prio為靜態(tài)優(yōu)先級(jí)
// 靜態(tài)優(yōu)先級(jí)是進(jìn)程啟動(dòng)時(shí)分配的優(yōu)先級(jí)，可用nice或sched_setscheduler系統(tǒng)調(diào)用修改
// normal_prio基于進(jìn)程的靜態(tài)優(yōu)先級(jí)和調(diào)度策略計(jì)算出來(lái)的優(yōu)先級(jí)
// fork時(shí)，子進(jìn)程的prio來(lái)自父進(jìn)程的普通優(yōu)先級(jí)，static_prio來(lái)自父進(jìn)程的靜態(tài)優(yōu)先級(jí)
  int prio, static_prio, normal_prio;
    // 表示實(shí)時(shí)進(jìn)程的優(yōu)先級(jí)，范圍為[0, 99]，值越大優(yōu)先級(jí)越高
    unsigned int rt_priority;
    // 進(jìn)程所屬調(diào)度器類
    const struct sched_class *sched_class;
    // 調(diào)度實(shí)體，調(diào)度器操作的對(duì)象
    struct sched_entity se;
    // 調(diào)度策略，包括SCHED_NORMAL（普通進(jìn)程）,SCHED_RR, SCHED_FIFO(軟實(shí)時(shí)進(jìn)程)
    unsigned int policy;
    // 用于限制進(jìn)程可以在哪些CPU上運(yùn)行，CPU親和力
    cpumask_t cups_allowed;
    // run_list是一個(gè)表頭，維護(hù)包含各進(jìn)程的一個(gè)運(yùn)行表，time_slice指定進(jìn)程可以使用cpu的剩余時(shí)間
    struct list_head run_list;
    unsigned int time_slice;
}

調(diào)度器類

struct sched_class {
    const struct sched_class *next; // 鏈表連接
    // 向就緒隊(duì)列添加新進(jìn)程
    void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
        // 從就緒隊(duì)列去掉進(jìn)程
    void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
    void (*yield_task) (struct rq *rq); // 放棄處理器控制權(quán)
    bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
        // 使用新喚醒的進(jìn)程搶占當(dāng)前進(jìn)程
    void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
        // 選擇下一個(gè)將要運(yùn)行的進(jìn)程
    struct task_struct * (*pick_next_task) (struct rq *rq);
    void (*put_prev_task) (struct rq *rq, struct task_struct *p);

#ifdef CONFIG_SMP
    int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
                   int sd_flag, int flags);

    void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
    void (*post_schedule) (struct rq *this_rq);
    void (*task_waking) (struct rq *this_rq, struct task_struct *task);
    void (*task_woken) (struct rq *this_rq, struct task_struct *task);

    void (*set_cpus_allowed)(struct task_struct *p,
                 const struct cpumask *newmask);

    void (*rq_online)(struct rq *rq);
    void (*rq_offline)(struct rq *rq);
#endif

    void (*set_curr_task) (struct rq *rq);
    void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
    void (*task_fork) (struct task_struct *p);

    void (*switched_from) (struct rq *this_rq, struct task_struct *task);
    void (*switched_to) (struct rq *this_rq, struct task_struct *task);
    void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
                 int oldprio);

    unsigned int (*get_rr_interval) (struct rq *rq,
                     struct task_struct *task);

#ifdef CONFIG_FAIR_GROUP_SCHED
    void (*task_move_group) (struct task_struct *p, int on_rq);
#endif
};

在進(jìn)程注冊(cè)到就緒隊(duì)列時(shí)，sched_entity實(shí)例的on_rq設(shè)置為1，否則為0

就緒隊(duì)列

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;  // 隊(duì)列上可運(yùn)行進(jìn)程的數(shù)目
    #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; // 就緒隊(duì)列當(dāng)前負(fù)荷的度量
    unsigned long nr_load_updates;
    u64 nr_switches;

    struct cfs_rq cfs;  // 子就緒隊(duì)列，用于完全公平調(diào)度器
    struct rt_rq rt;  // 子就緒隊(duì)列，用于實(shí)時(shí)調(diào)度器
        // 分別是當(dāng)前task_struct實(shí)例，idle進(jìn)程實(shí)例，
    struct task_struct *curr, *idle;
    //  就緒隊(duì)列自身時(shí)鐘，每次調(diào)用周期性調(diào)度器時(shí)，都會(huì)更新clock值
    u64 clock;
    u64 clock_task;
};

系統(tǒng)的所有就緒隊(duì)列都在runqueues數(shù)組中，該數(shù)組的每個(gè)元素分別對(duì)應(yīng)于系統(tǒng)中的一個(gè)CPU。

調(diào)度實(shí)體

struct sched_entity {
    struct load_weight load; // 權(quán)重，決定各個(gè)實(shí)體占隊(duì)列總負(fù)荷的比例
    struct rb_node run_node; // 樹(shù)節(jié)點(diǎn)，實(shí)體在紅黑樹(shù)上排序
    unsigned int on_rq;  // 當(dāng)前實(shí)體是否在就緒隊(duì)列上接受調(diào)度
    u64 exec_start; // 當(dāng)前時(shí)間
    u64 sum_exec_runtime; // 消耗的CPU時(shí)間
    u64 vruntime; // 虛擬時(shí)鐘上流逝的時(shí)間數(shù)量
    u64 prev_sum_exec_runtime; // 保存sum_exec_runtime
}