libevent源码分析

libevent源码分析

结构体event_base

struct event_base {
	/** Function pointers and other data to describe this event_base's
	 * backend. */
	const struct eventop *evsel;
	/** Pointer to backend-specific data. */
	void *evbase;

	/** List of changes to tell backend about at next dispatch.  Only used
	 * by the O(1) backends. */
	struct event_changelist changelist;

	/** Function pointers used to describe the backend that this event_base
	 * uses for signals */
	const struct eventop *evsigsel;
	/** Data to implement the common signal handler code. */
	struct evsig_info sig;

	/** Number of virtual events */
	int virtual_event_count;
	/** Maximum number of virtual events active */
	int virtual_event_count_max;
	/** Number of total events added to this event_base */
	int event_count;
	/** Maximum number of total events added to this event_base */
	int event_count_max;
	/** Number of total events active in this event_base */
	int event_count_active;
	/** Maximum number of total events active in this event_base */
	int event_count_active_max;

	/** Set if we should terminate the loop once we're done processing
	 * events. */
	int event_gotterm;
	/** Set if we should terminate the loop immediately */
	int event_break;
	/** Set if we should start a new instance of the loop immediately. */
	int event_continue;

	/** The currently running priority of events */
	int event_running_priority;

	/** Set if we're running the event_base_loop function, to prevent
	 * reentrant invocation. */
	int running_loop;

	/** Set to the number of deferred_cbs we've made 'active' in the
	 * loop.  This is a hack to prevent starvation; it would be smarter
	 * to just use event_config_set_max_dispatch_interval's max_callbacks
	 * feature */
	int n_deferreds_queued;

	/* Active event management. */
	/** An array of nactivequeues queues for active event_callbacks (ones
	 * that have triggered, and whose callbacks need to be called).  Low
	 * priority numbers are more important, and stall higher ones.
	 */
	struct evcallback_list *activequeues;
	/** The length of the activequeues array */
	int nactivequeues;
	/** A list of event_callbacks that should become active the next time
	 * we process events, but not this time. */
	struct evcallback_list active_later_queue;

	/* common timeout logic */

	/** An array of common_timeout_list* for all of the common timeout
	 * values we know. */
	struct common_timeout_list **common_timeout_queues;
	/** The number of entries used in common_timeout_queues */
	int n_common_timeouts;
	/** The total size of common_timeout_queues. */
	int n_common_timeouts_allocated;

	/** Mapping from file descriptors to enabled (added) events */
	struct event_io_map io;

	/** Mapping from signal numbers to enabled (added) events. */
	struct event_signal_map sigmap;

	/** Priority queue of events with timeouts. */
	struct min_heap timeheap;

	/** Stored timeval: used to avoid calling gettimeofday/clock_gettime
	 * too often. */
	struct timeval tv_cache;

	struct evutil_monotonic_timer monotonic_timer;

	/** Difference between internal time (maybe from clock_gettime) and
	 * gettimeofday. */
	struct timeval tv_clock_diff;
	/** Second in which we last updated tv_clock_diff, in monotonic time. */
	time_t last_updated_clock_diff;

#ifndef EVENT__DISABLE_THREAD_SUPPORT
	/* threading support */
	/** The thread currently running the event_loop for this base */
	unsigned long th_owner_id;
	/** A lock to prevent conflicting accesses to this event_base */
	void *th_base_lock;
	/** A condition that gets signalled when we're done processing an
	 * event with waiters on it. */
	void *current_event_cond;
	/** Number of threads blocking on current_event_cond. */
	int current_event_waiters;
#endif
	/** The event whose callback is executing right now */
	struct event_callback *current_event;

#ifdef _WIN32
	/** IOCP support structure, if IOCP is enabled. */
	struct event_iocp_port *iocp;
#endif

	/** Flags that this base was configured with */
	enum event_base_config_flag flags;

	struct timeval max_dispatch_time;
	int max_dispatch_callbacks;
	int limit_callbacks_after_prio;

	/* Notify main thread to wake up break, etc. */
	/** True if the base already has a pending notify, and we don't need
	 * to add any more. */
	int is_notify_pending;
	/** A socketpair used by some th_notify functions to wake up the main
	 * thread. */
	evutil_socket_t th_notify_fd[2];
	/** An event used by some th_notify functions to wake up the main
	 * thread. */
	struct event th_notify;
	/** A function used to wake up the main thread from another thread. */
	int (*th_notify_fn)(struct event_base *base);

	/** Saved seed for weak random number generator. Some backends use
	 * this to produce fairness among sockets. Protected by th_base_lock. */
	struct evutil_weakrand_state weakrand_seed;

	/** List of event_onces that have not yet fired. */
	LIST_HEAD(once_event_list, event_once) once_events;

};

eventop结构体

/** Structure to define the backend of a given event_base. */
struct eventop {
	/** The name of this backend. */
	const char *name;
	/** Function to set up an event_base to use this backend.  It should
	 * create a new structure holding whatever information is needed to
	 * run the backend, and return it.  The returned pointer will get
	 * stored by event_init into the event_base.evbase field.  On failure,
	 * this function should return NULL. */
	void *(*init)(struct event_base *);
	/** Enable reading/writing on a given fd or signal.  'events' will be
	 * the events that we're trying to enable: one or more of EV_READ,
	 * EV_WRITE, EV_SIGNAL, and EV_ET.  'old' will be those events that
	 * were enabled on this fd previously.  'fdinfo' will be a structure
	 * associated with the fd by the evmap; its size is defined by the
	 * fdinfo field below.  It will be set to 0 the first time the fd is
	 * added.  The function should return 0 on success and -1 on error.
	 */
	int (*add)(struct event_base *, evutil_socket_t fd, short old, short events, void *fdinfo);
	/** As "add", except 'events' contains the events we mean to disable. */
	int (*del)(struct event_base *, evutil_socket_t fd, short old, short events, void *fdinfo);
	/** Function to implement the core of an event loop.  It must see which
	    added events are ready, and cause event_active to be called for each
	    active event (usually via event_io_active or such).  It should
	    return 0 on success and -1 on error.
	 */
	int (*dispatch)(struct event_base *, struct timeval *);
	/** Function to clean up and free our data from the event_base. */
	void (*dealloc)(struct event_base *);
	/** Flag: set if we need to reinitialize the event base after we fork.
	 */
	int need_reinit;
	/** Bit-array of supported event_method_features that this backend can
	 * provide. */
	enum event_method_feature features;
	/** Length of the extra information we should record for each fd that
	    has one or more active events.  This information is recorded
	    as part of the evmap entry for each fd, and passed as an argument
	    to the add and del functions above.
	 */
	size_t fdinfo_len;
};

结构体event

struct event {
	struct event_callback ev_evcallback;

	/* for managing timeouts */
	union {
		TAILQ_ENTRY(event) ev_next_with_common_timeout;
		int min_heap_idx;
	} ev_timeout_pos;
	evutil_socket_t ev_fd;

	struct event_base *ev_base;

	union {
		/* used for io events */
		struct {
			LIST_ENTRY (event) ev_io_next;
			struct timeval ev_timeout;
		} ev_io;

		/* used by signal events */
		struct {
			LIST_ENTRY (event) ev_signal_next;
			short ev_ncalls;
			/* Allows deletes in callback */
			short *ev_pncalls;
		} ev_signal;
	} ev_;

	short ev_events;
	short ev_res;		/* result passed to event callback */
	struct timeval ev_timeout;
};

1、初始化event_init

struct event_base *event_init(void)
{
	struct event_base *base = event_base_new_with_config(NULL);

	if (base == NULL) {
		event_errx(1, "%s: Unable to construct event_base", __func__);
		return NULL;
	}

	current_base = base;

	return (base);
}

event_init 就是初始化一个event_base对象并返回给我们使用

struct event_base *event_base_new_with_config(const struct event_config *cfg)
{
	int i;
	struct event_base *base;
	int should_check_environment;

#ifndef EVENT__DISABLE_DEBUG_MODE
	event_debug_mode_too_late = 1;
#endif

    //为event_base分配动态内存 后面需要释放
	if ((base = mm_calloc(1, sizeof(struct event_base))) == NULL) {
		event_warn("%s: calloc", __func__);
		return NULL;
	}

	if (cfg)
		base->flags = cfg->flags;

    //此处的值为1
	should_check_environment = !(cfg && (cfg->flags & EVENT_BASE_FLAG_IGNORE_ENV));

	{
		struct timeval tmp;
		int precise_time = cfg && (cfg->flags & EVENT_BASE_FLAG_PRECISE_TIMER);   //值为0
		int flags;
		if (should_check_environment && !precise_time) {
		    //evutil_getenv 如果没有setuid、setgid 就直接返回EVENT_PRECISE_TIMER的环境变量的值
		    //此处如果是都没有设置 就返回环境变量的值  此处precise_time的值为1
			precise_time = evutil_getenv_("EVENT_PRECISE_TIMER") != NULL;
			if (precise_time) {
				base->flags |= EVENT_BASE_FLAG_PRECISE_TIMER;
			}
		}
		flags = precise_time ? EV_MONOT_PRECISE : 0;
		//设置base->monotonic_timer为CLOCK_MONOTONIC
		//从系统启动这一刻起开始计时,不受系统时间被用户改变的影响
		evutil_configure_monotonic_time_(&base->monotonic_timer, flags);
        //根据base中的信息给tmp赋值
		gettime(base, &tmp);
	}
    //小根堆的构造
	min_heap_ctor_(&base->timeheap);

	base->sig.ev_signal_pair[0] = -1;
	base->sig.ev_signal_pair[1] = -1;
	base->th_notify_fd[0] = -1;
	base->th_notify_fd[1] = -1;

	TAILQ_INIT(&base->active_later_queue);

	evmap_io_initmap_(&base->io);
	evmap_signal_initmap_(&base->sigmap);
	event_changelist_init_(&base->changelist);

	base->evbase = NULL;

	if (cfg) {
		memcpy(&base->max_dispatch_time,
		    &cfg->max_dispatch_interval, sizeof(struct timeval));
		base->limit_callbacks_after_prio =
		    cfg->limit_callbacks_after_prio;
	} else {
		base->max_dispatch_time.tv_sec = -1;
		base->limit_callbacks_after_prio = 1;
	}
	if (cfg && cfg->max_dispatch_callbacks >= 0) {
		base->max_dispatch_callbacks = cfg->max_dispatch_callbacks;
	} else {
		base->max_dispatch_callbacks = INT_MAX;
	}
	if (base->max_dispatch_callbacks == INT_MAX &&
	    base->max_dispatch_time.tv_sec == -1)
		base->limit_callbacks_after_prio = INT_MAX;

	for (i = 0; eventops[i] && !base->evbase; i++) {
		if (cfg != NULL) {
			/* determine if this backend should be avoided */
			if (event_config_is_avoided_method(cfg,
				eventops[i]->name))
				continue;
			if ((eventops[i]->features & cfg->require_features)
			    != cfg->require_features)
				continue;
		}

		/* also obey the environment variables */
		if (should_check_environment &&
		    event_is_method_disabled(eventops[i]->name))
			continue;

		base->evsel = eventops[i];

		base->evbase = base->evsel->init(base);
	}

	if (base->evbase == NULL) {
		event_warnx("%s: no event mechanism available",
		    __func__);
		base->evsel = NULL;
		event_base_free(base);
		return NULL;
	}

	if (evutil_getenv_("EVENT_SHOW_METHOD"))
		event_msgx("libevent using: %s", base->evsel->name);

	/* allocate a single active event queue */
	if (event_base_priority_init(base, 1) < 0) {
		event_base_free(base);
		return NULL;
	}

	/* prepare for threading */

#if !defined(EVENT__DISABLE_THREAD_SUPPORT) && !defined(EVENT__DISABLE_DEBUG_MODE)
	event_debug_created_threadable_ctx_ = 1;
#endif

#ifndef EVENT__DISABLE_THREAD_SUPPORT
	if (EVTHREAD_LOCKING_ENABLED() &&
	    (!cfg || !(cfg->flags & EVENT_BASE_FLAG_NOLOCK))) {
		int r;
		EVTHREAD_ALLOC_LOCK(base->th_base_lock, 0);
		EVTHREAD_ALLOC_COND(base->current_event_cond);
		r = evthread_make_base_notifiable(base);
		if (r<0) {
			event_warnx("%s: Unable to make base notifiable.", __func__);
			event_base_free(base);
			return NULL;
		}
	}
#endif

#ifdef _WIN32
	if (cfg && (cfg->flags & EVENT_BASE_FLAG_STARTUP_IOCP))
		event_base_start_iocp_(base, cfg->n_cpus_hint);
#endif

	return (base);
}

setuid：用户以可执行文件owner的权限来运行这个可执行文件。
setgid：用户以可执行文件groupr的权限来运行这个可执行文件。

2、event_add

int event_add(struct event *ev, const struct timeval *tv)
{
	int res;

	if (EVUTIL_FAILURE_CHECK(!ev->ev_base)) {
		event_warnx("%s: event has no event_base set.", __func__);
		return -1;
	}

	EVBASE_ACQUIRE_LOCK(ev->ev_base, th_base_lock);

	res = event_add_nolock_(ev, tv, 0);

	EVBASE_RELEASE_LOCK(ev->ev_base, th_base_lock);

	return (res);
}

其中最主要的函数是event_add_nolock_

/* 用于添加事件的实现函数。就像event_add一样工作，
除了：1）它要求我们有锁。2） 如果设置了tv_is_absolute，我们将tv视为绝对时间，而不是添加到当前时间的间隔 */
int event_add_nolock_(struct event *ev, const struct timeval *tv, int tv_is_absolute)
{
	struct event_base *base = ev->ev_base;
	int res = 0;
	int notify = 0;

	EVENT_BASE_ASSERT_LOCKED(base);
	event_debug_assert_is_setup_(ev);

	event_debug((
		 "event_add: event: %p (fd "EV_SOCK_FMT"), %s%s%s%scall %p",
		 ev,
		 EV_SOCK_ARG(ev->ev_fd),
		 ev->ev_events & EV_READ ? "EV_READ " : " ",
		 ev->ev_events & EV_WRITE ? "EV_WRITE " : " ",
		 ev->ev_events & EV_CLOSED ? "EV_CLOSED " : " ",
		 tv ? "EV_TIMEOUT " : " ",
		 ev->ev_callback));

	EVUTIL_ASSERT(!(ev->ev_flags & ~EVLIST_ALL));

	if (ev->ev_flags & EVLIST_FINALIZING) {
		/* XXXX debug */
		return (-1);
	}

	/*该函数很简单，n表示堆的元素的个数(第二个参数 n)，首先判断元素a（堆总大小）是否小于n，如果小于，表示堆的空间不够用了，需要分配新的空间，通过realloc分配更大的空间，当原来堆为空时，默认分配8个元素的空间；当原来堆不为空，分配原来两倍的空间。*/
	if (tv != NULL && !(ev->ev_flags & EVLIST_TIMEOUT)) {
		if (min_heap_reserve_(&base->timeheap,
			1 + min_heap_size_(&base->timeheap)) == -1)
			return (-1);  /* ENOMEM == errno */
	}

	/* If the main thread is currently executing a signal event's
	 * callback, and we are not the main thread, then we want to wait
	 * until the callback is done before we mess with the event, or else
	 * we can race on ev_ncalls and ev_pncalls below. */
#ifndef EVENT__DISABLE_THREAD_SUPPORT
	if (base->current_event == event_to_event_callback(ev) &&
	    (ev->ev_events & EV_SIGNAL)
	    && !EVBASE_IN_THREAD(base)) {
		++base->current_event_waiters;
		EVTHREAD_COND_WAIT(base->current_event_cond, base->th_base_lock);
	}
#endif

	if ((ev->ev_events & (EV_READ|EV_WRITE|EV_CLOSED|EV_SIGNAL)) &&
	    !(ev->ev_flags & (EVLIST_INSERTED|EVLIST_ACTIVE|EVLIST_ACTIVE_LATER))) {
		if (ev->ev_events & (EV_READ|EV_WRITE|EV_CLOSED))
			res = evmap_io_add_(base, ev->ev_fd, ev);
		else if (ev->ev_events & EV_SIGNAL)
			res = evmap_signal_add_(base, (int)ev->ev_fd, ev);
		if (res != -1)
			event_queue_insert_inserted(base, ev);
		if (res == 1) {
			/* evmap says we need to notify the main thread. */
			notify = 1;
			res = 0;
		}
	}

	/*
	 * we should change the timeout state only if the previous event
	 * addition succeeded.
	 */
	if (res != -1 && tv != NULL) {
		struct timeval now;
		int common_timeout;
#ifdef USE_REINSERT_TIMEOUT
		int was_common;
		int old_timeout_idx;
#endif

		/*
		 * for persistent timeout events, we remember the
		 * timeout value and re-add the event.
		 *
		 * If tv_is_absolute, this was already set.
		 */
		if (ev->ev_closure == EV_CLOSURE_EVENT_PERSIST && !tv_is_absolute)
			ev->ev_io_timeout = *tv;

#ifndef USE_REINSERT_TIMEOUT
		if (ev->ev_flags & EVLIST_TIMEOUT) {
			event_queue_remove_timeout(base, ev);
		}
#endif

		/* Check if it is active due to a timeout.  Rescheduling
		 * this timeout before the callback can be executed
		 * removes it from the active list. */
		if ((ev->ev_flags & EVLIST_ACTIVE) &&
		    (ev->ev_res & EV_TIMEOUT)) {
			if (ev->ev_events & EV_SIGNAL) {
				/* See if we are just active executing
				 * this event in a loop
				 */
				if (ev->ev_ncalls && ev->ev_pncalls) {
					/* Abort loop */
					*ev->ev_pncalls = 0;
				}
			}

			event_queue_remove_active(base, event_to_event_callback(ev));
		}

		gettime(base, &now);

		common_timeout = is_common_timeout(tv, base);
#ifdef USE_REINSERT_TIMEOUT
		was_common = is_common_timeout(&ev->ev_timeout, base);
		old_timeout_idx = COMMON_TIMEOUT_IDX(&ev->ev_timeout);
#endif

		if (tv_is_absolute) {
			ev->ev_timeout = *tv;
		} else if (common_timeout) {
			struct timeval tmp = *tv;
			tmp.tv_usec &= MICROSECONDS_MASK;
			evutil_timeradd(&now, &tmp, &ev->ev_timeout);
			ev->ev_timeout.tv_usec |=
			    (tv->tv_usec & ~MICROSECONDS_MASK);
		} else {
			evutil_timeradd(&now, tv, &ev->ev_timeout);
		}

		event_debug((
			 "event_add: event %p, timeout in %d seconds %d useconds, call %p",
			 ev, (int)tv->tv_sec, (int)tv->tv_usec, ev->ev_callback));

#ifdef USE_REINSERT_TIMEOUT
		event_queue_reinsert_timeout(base, ev, was_common, common_timeout, old_timeout_idx);
#else
		event_queue_insert_timeout(base, ev);
#endif

		if (common_timeout) {
			struct common_timeout_list *ctl =
			    get_common_timeout_list(base, &ev->ev_timeout);
			if (ev == TAILQ_FIRST(&ctl->events)) {
				common_timeout_schedule(ctl, &now, ev);
			}
		} else {
			struct event* top = NULL;
			/* See if the earliest timeout is now earlier than it
			 * was before: if so, we will need to tell the main
			 * thread to wake up earlier than it would otherwise.
			 * We double check the timeout of the top element to
			 * handle time distortions due to system suspension.
			 */
			if (min_heap_elt_is_top_(ev))
				notify = 1;
			else if ((top = min_heap_top_(&base->timeheap)) != NULL &&
					 evutil_timercmp(&top->ev_timeout, &now, <))
				notify = 1;
		}
	}

	/* if we are not in the right thread, we need to wake up the loop */
	if (res != -1 && notify && EVBASE_NEED_NOTIFY(base))
		evthread_notify_base(base);

	event_debug_note_add_(ev);

	return (res);
}

上述函数中，主要函数是以下函数

/* return -1 on error, 0 on success if nothing changed in the event backend,
 * and 1 on success if something did. */
int evmap_io_add_(struct event_base *base, evutil_socket_t fd, struct event *ev)
{
	const struct eventop *evsel = base->evsel;
	struct event_io_map *io = &base->io;
	struct evmap_io *ctx = NULL;
	int nread, nwrite, nclose, retval = 0;
	short res = 0, old = 0;
	struct event *old_ev;

	EVUTIL_ASSERT(fd == ev->ev_fd);

	if (fd < 0)
		return 0;

#ifndef EVMAP_USE_HT
	if (fd >= io->nentries) {
		if (evmap_make_space(io, fd, sizeof(struct evmap_io *)) == -1)
			return (-1);
	}
#endif

    //获取指定文件描述符（或信号号）对应的event链表入口
    //即上述数组成员并初始化与该文件描述符（信号号）相关联的数组成员。
    //申请或者new一个evmap_io的对象存在ctx里面
	GET_IO_SLOT_AND_CTOR(ctx, io, fd, evmap_io, evmap_io_init,
						 evsel->fdinfo_len);

	nread = ctx->nread;
	nwrite = ctx->nwrite;
	nclose = ctx->nclose;

	if (nread)
		old |= EV_READ;
	if (nwrite)
		old |= EV_WRITE;
	if (nclose)
		old |= EV_CLOSED;

	if (ev->ev_events & EV_READ) {
		if (++nread == 1)
			res |= EV_READ;
	}
	if (ev->ev_events & EV_WRITE) {
		if (++nwrite == 1)
			res |= EV_WRITE;
	}
	if (ev->ev_events & EV_CLOSED) {
		if (++nclose == 1)
			res |= EV_CLOSED;
	}
	if (EVUTIL_UNLIKELY(nread > 0xffff || nwrite > 0xffff || nclose > 0xffff)) {
		event_warnx("Too many events reading or writing on fd %d",
		    (int)fd);
		return -1;
	}
	if (EVENT_DEBUG_MODE_IS_ON() &&
	    (old_ev = LIST_FIRST(&ctx->events)) &&
	    (old_ev->ev_events&EV_ET) != (ev->ev_events&EV_ET)) {
		event_warnx("Tried to mix edge-triggered and non-edge-triggered"
		    " events on fd %d", (int)fd);
		return -1;
	}

	if (res) {
		void *extra = ((char*)ctx) + sizeof(struct evmap_io);
		/* XXX(niels): we cannot mix edge-triggered and
		 * level-triggered, we should probably assert on
		 * this. */
		if (evsel->add(base, ev->ev_fd,
			old, (ev->ev_events & EV_ET) | res, extra) == -1)
			return (-1);
		retval = 1;
	}

	ctx->nread = (ev_uint16_t) nread;
	ctx->nwrite = (ev_uint16_t) nwrite;
	ctx->nclose = (ev_uint16_t) nclose;
	LIST_INSERT_HEAD(&ctx->events, ev, ev_io_next);

	return (retval);
}

结构体evmap_io

struct evmap_io {
	struct event_dlist events;
	ev_uint16_t nread;
	ev_uint16_t nwrite;
	ev_uint16_t nclose;
};

其中GET_IO_SLOT_AND_CTOR为以下实现

GET_IO_SLOT_AND_CTOR(ctx, io, fd, evmap_io, evmap_io_init,evsel->fdinfo_len);
#define GET_SIGNAL_SLOT_AND_CTOR(x, map, slot, type, ctor, fdinfo_len)	\
	do {								\
		if ((map)->entries[slot] == NULL) {			\
			(map)->entries[slot] =				\
			    mm_calloc(1,sizeof(struct type)+fdinfo_len); \
			    // //等价于 if((map)->entries[slot] == NULL)
			    //EVUTIL_UNLIKELY((map)->entries[slot] == NULL) 表示(map)->entries[slot] == NULL)很大概率为假 即其不等于NULL
			    //__builtin_expect() (即EVUTIL_UNLIKELY)是 GCC (version >= 2.96）提供给程序员使用的，目的是将“分支转移”的信息提供给编译器，这样编译器可以对代码进行优化，以减少指令跳转带来的性能下降。
			if (EVUTIL_UNLIKELY((map)->entries[slot] == NULL)) \
				return (-1);				\
			(ctor)((struct type *)(map)->entries[slot]);	\
		}							\
		(x) = (struct type *)((map)->entries[slot]);		\
	} while (0)