深刻理解GCD之dispatch_group

时间 2019-11-24

标签深刻理解 gcd dispatch group 繁體版

原文原文链接

以前已经介绍了dispatch_semaphore的底层实现，dispatch_group的实现是基于前者的。在看源码以前，咱们先看一下咱们是如何应用的。假设有这么场景：有一个A耗时操做，B和C两个网络请求和一个耗时操做C当ABC都执行完成后，刷新页面。咱们能够用dispatch_group实现。关键以下：网络

- (void)viewDidLoad {
    [super viewDidLoad];
    
        __block NSInteger number = 0;
    
    dispatch_group_t group = dispatch_group_create();
    
    //A耗时操做
    dispatch_group_async(group, dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{
        sleep(3);
        number += 2222;
    });
    
    //B网络请求
    dispatch_group_enter(group);
    [self sendRequestWithCompletion:^(id response) {
        number += [response integerValue];
        dispatch_group_leave(group);
    }];
    
    //C网络请求
    dispatch_group_enter(group);
    [self sendRequestWithCompletion:^(id response) {
        number += [response integerValue];
        dispatch_group_leave(group);
    }];
    
    dispatch_group_notify(group, dispatch_get_main_queue(), ^{
        NSLog(@"%zd", number);
    });
}

- (void)sendRequestWithCompletion:(void (^)(id response))completion {
    //模拟一个网络请求
    dispatch_queue_t queue = dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0);
    dispatch_async(queue, ^{
        sleep(2);
        dispatch_async(dispatch_get_main_queue(), ^{
            if (completion) completion(@1111);
        });
    });
}
复制代码

接下来咱们根据上面的流程来看一下dispatch_group的相关APIapp

dispatch_group_create

dispatch_group_t
dispatch_group_create(void)
{
	return (dispatch_group_t)dispatch_semaphore_create(LONG_MAX);
}
复制代码

dispatch_group_create其实就是建立了一个value为LONG_MAX的dispatch_semaphore信号量异步

dispatch_group_async

void
dispatch_group_async(dispatch_group_t dg, dispatch_queue_t dq,
		dispatch_block_t db)
{
	dispatch_group_async_f(dg, dq, _dispatch_Block_copy(db),
			_dispatch_call_block_and_release);
}
复制代码

dispatch_group_async只是dispatch_group_async_f的封装async

dispatch_group_async_f

void
dispatch_group_async_f(dispatch_group_t dg, dispatch_queue_t dq, void *ctxt,
		dispatch_function_t func)
{
	dispatch_continuation_t dc;

	_dispatch_retain(dg);
	dispatch_group_enter(dg);

	dc = fastpath(_dispatch_continuation_alloc_cacheonly());
	if (!dc) {
		dc = _dispatch_continuation_alloc_from_heap();
	}

	dc->do_vtable = (void *)(DISPATCH_OBJ_ASYNC_BIT | DISPATCH_OBJ_GROUP_BIT);
	dc->dc_func = func;
	dc->dc_ctxt = ctxt;
	dc->dc_group = dg;

	// No fastpath/slowpath hint because we simply don't know if (dq->dq_width != 1 && dq->do_targetq) { return _dispatch_async_f2(dq, dc); } _dispatch_queue_push(dq, dc); } 复制代码

从上面的代码咱们能够看出dispatch_group_async_f和dispatch_async_f类似。dispatch_group_async_f多了dispatch_group_enter(dg);，另外在do_vtable的赋值中dispatch_group_async_f多了一个DISPATCH_OBJ_GROUP_BIT的标记符。既然添加了dispatch_group_enter一定会存在dispatch_group_leave。在以前《深刻理解GCD之dispatch_queue》介绍_dispatch_continuation_pop函数的源码中有一段代码以下：函数

_dispatch_client_callout(dc->dc_ctxt, dc->dc_func);
	if (dg) {
		//group须要进行调用dispatch_group_leave并释放信号
		dispatch_group_leave(dg);
		_dispatch_release(dg);
	}
复制代码

因此dispatch_group_async_f函数中的dispatch_group_leave是在_dispatch_continuation_pop函数中调用的。post

这里归纳一下dispatch_group_async_f的工做流程：ui

调用dispatch_group_enter；
将block和queue等信息记录到dispatch_continuation_t结构体中，并将它加入到group的链表中；
_dispatch_continuation_pop执行时会判断任务是否为group，是的话执行完任务再调用dispatch_group_leave以达到信号量的平衡。

dispatch_group_enter

void
dispatch_group_enter(dispatch_group_t dg)
{
	dispatch_semaphore_t dsema = (dispatch_semaphore_t)dg;

	(void)dispatch_semaphore_wait(dsema, DISPATCH_TIME_FOREVER);
}
复制代码

dispatch_group_enter将dispatch_group_t转换成dispatch_semaphore_t，并调用dispatch_semaphore_wait，原子性减1后，进入等待状态直到有信号唤醒。因此说dispatch_group_enter就是对dispatch_semaphore_wait的封装。this

dispatch_group_leave

void
dispatch_group_leave(dispatch_group_t dg)
{
	dispatch_semaphore_t dsema = (dispatch_semaphore_t)dg;
	dispatch_atomic_release_barrier();
	long value = dispatch_atomic_inc2o(dsema, dsema_value);//dsema_value原子性加1
	if (slowpath(value == LONG_MIN)) {//内存溢出，因为dispatch_group_leave在dispatch_group_enter以前调用
		DISPATCH_CLIENT_CRASH("Unbalanced call to dispatch_group_leave()");
	}
	if (slowpath(value == dsema->dsema_orig)) {//表示全部任务已经完成，唤醒group
		(void)_dispatch_group_wake(dsema);
	}
}
复制代码

从上面的源代码中咱们看到dispatch_group_leave将dispatch_group_t转换成dispatch_semaphore_t后将dsema_value的值原子性加1。若是value为LONG_MIN程序crash；若是value等于dsema_orig表示全部任务已完成，调用_dispatch_group_wake唤醒group（_dispatch_group_wake的用于和notify有关，咱们会在后面介绍）。由于在enter的时候进行了原子性减1操做。因此在leave的时候须要原子性加1。atom

这里先说明一下enter和leave之间的关系：

dispatch_group_leave与dispatch_group_enter配对使用。当调用了dispatch_group_enter而没有调用dispatch_group_leave时，因为value不等于dsema_orig不会走到唤醒逻辑，dispatch_group_notify中的任务没法执行或者dispatch_group_wait收不到信号而卡住线程。
dispatch_group_enter必须在dispatch_group_leave以前出现。当dispatch_group_leave比dispatch_group_enter多调用了一次或者说在dispatch_group_enter以前被调用的时候，dispatch_group_leave进行原子性加1操做，至关于value为LONGMAX+1，发生数据长度溢出，变成LONG_MIN，因为value == LONG_MIN成立，程序发生crash。

dispatch_group_notify

void
dispatch_group_notify(dispatch_group_t dg, dispatch_queue_t dq,
		dispatch_block_t db)
{
	dispatch_group_notify_f(dg, dq, _dispatch_Block_copy(db),
			_dispatch_call_block_and_release);
}
复制代码

dispatch_group_notify是dispatch_group_notify_f的封装，具体实如今后者。

dispatch_group_notify_f

void
dispatch_group_notify_f(dispatch_group_t dg, dispatch_queue_t dq, void *ctxt,
		void (*func)(void *))
{
	dispatch_semaphore_t dsema = (dispatch_semaphore_t)dg;
	struct dispatch_sema_notify_s *dsn, *prev;

	//封装dispatch_continuation_t结构体
	// FIXME -- this should be updated to use the continuation cache
	while (!(dsn = calloc(1, sizeof(*dsn)))) {
		sleep(1);
	}

	dsn->dsn_queue = dq;
	dsn->dsn_ctxt = ctxt;
	dsn->dsn_func = func;
	_dispatch_retain(dq);
	dispatch_atomic_store_barrier();
	//将结构体放到链表尾部，若是链表为空同时设置链表头部节点并唤醒group
	prev = dispatch_atomic_xchg2o(dsema, dsema_notify_tail, dsn);
	if (fastpath(prev)) {
		prev->dsn_next = dsn;
	} else {
		_dispatch_retain(dg);
		(void)dispatch_atomic_xchg2o(dsema, dsema_notify_head, dsn);
		if (dsema->dsema_value == dsema->dsema_orig) {//任务已经完成，唤醒group
			_dispatch_group_wake(dsema);
		}
	}
}
复制代码

因此dispatch_group_notify函数只是用链表把全部回调通知保存起来，等待调用。

_dispatch_group_wake

static long
_dispatch_group_wake(dispatch_semaphore_t dsema)
{
	struct dispatch_sema_notify_s *next, *head, *tail = NULL;
	long rval;
	//将dsema的dsema_notify_head赋值为NULL，同时将以前的内容赋给head
	head = dispatch_atomic_xchg2o(dsema, dsema_notify_head, NULL);
	if (head) {
		// snapshot before anything is notified/woken <rdar://problem/8554546>
		//将dsema的dsema_notify_tail赋值为NULL，同时将以前的内容赋给tail
		tail = dispatch_atomic_xchg2o(dsema, dsema_notify_tail, NULL);
	}
	//将dsema的dsema_group_waiters设置为0，并返回原来的值
	rval = dispatch_atomic_xchg2o(dsema, dsema_group_waiters, 0);
	if (rval) {
		//循环调用semaphore_signal唤醒当初等待group的信号量，使得dispatch_group_wait函数返回。
		// wake group waiters
#if USE_MACH_SEM
		_dispatch_semaphore_create_port(&dsema->dsema_waiter_port);
		do {
			kern_return_t kr = semaphore_signal(dsema->dsema_waiter_port);
			DISPATCH_SEMAPHORE_VERIFY_KR(kr);
		} while (--rval);
#elif USE_POSIX_SEM
		do {
			int ret = sem_post(&dsema->dsema_sem);
			DISPATCH_SEMAPHORE_VERIFY_RET(ret);
		} while (--rval);
#endif
	}
	if (head) {
		//获取链表，依次调用dispatch_async_f异步执行在notify函数中的任务即Block。
		// async group notify blocks
		do {
			dispatch_async_f(head->dsn_queue, head->dsn_ctxt, head->dsn_func);
			_dispatch_release(head->dsn_queue);
			next = fastpath(head->dsn_next);
			if (!next && head != tail) {
				while (!(next = fastpath(head->dsn_next))) {
					_dispatch_hardware_pause();
				}
			}
			free(head);
		} while ((head = next));
		_dispatch_release(dsema);
	}
	return 0;
}
复制代码

_dispatch_group_wake主要的做用有两个：

调用semaphore_signal唤醒当初等待group的信号量，使得dispatch_group_wait函数返回。
获取链表，依次调用dispatch_async_f异步执行在notify函数中的任务即Block。

到这里咱们已经差很少知道了dispatch_group工做过程，咱们用一张图表示：

dispatch_group_wait

long
dispatch_group_wait(dispatch_group_t dg, dispatch_time_t timeout)
{
	dispatch_semaphore_t dsema = (dispatch_semaphore_t)dg;

	if (dsema->dsema_value == dsema->dsema_orig) {//没有须要执行的任务
		return 0;
	}
	if (timeout == 0) {//返回超时
#if USE_MACH_SEM
		return KERN_OPERATION_TIMED_OUT;
#elif USE_POSIX_SEM
		errno = ETIMEDOUT;
		return (-1);
#endif
	}
	return _dispatch_group_wait_slow(dsema, timeout);
}
复制代码

dispatch_group_wait用于等待group中的任务完成。

_dispatch_group_wait_slow

static long
_dispatch_group_wait_slow(dispatch_semaphore_t dsema, dispatch_time_t timeout)
{
	long orig;

again:
	// check before we cause another signal to be sent by incrementing
	// dsema->dsema_group_waiters
	if (dsema->dsema_value == dsema->dsema_orig) {
		return _dispatch_group_wake(dsema);
	}
	// Mach semaphores appear to sometimes spuriously wake up. Therefore,
	// we keep a parallel count of the number of times a Mach semaphore is
	// signaled (6880961).
	(void)dispatch_atomic_inc2o(dsema, dsema_group_waiters);
	// check the values again in case we need to wake any threads
	if (dsema->dsema_value == dsema->dsema_orig) {
		return _dispatch_group_wake(dsema);
	}

#if USE_MACH_SEM
	mach_timespec_t _timeout;
	kern_return_t kr;

	_dispatch_semaphore_create_port(&dsema->dsema_waiter_port);

	// From xnu/osfmk/kern/sync_sema.c:
	// wait_semaphore->count = -1; /* we don't keep an actual count */ // // The code above does not match the documentation, and that fact is // not surprising. The documented semantics are clumsy to use in any // practical way. The above hack effectively tricks the rest of the // Mach semaphore logic to behave like the libdispatch algorithm. switch (timeout) { default: do { uint64_t nsec = _dispatch_timeout(timeout); _timeout.tv_sec = (typeof(_timeout.tv_sec))(nsec / NSEC_PER_SEC); _timeout.tv_nsec = (typeof(_timeout.tv_nsec))(nsec % NSEC_PER_SEC); kr = slowpath(semaphore_timedwait(dsema->dsema_waiter_port, _timeout)); } while (kr == KERN_ABORTED); if (kr != KERN_OPERATION_TIMED_OUT) { DISPATCH_SEMAPHORE_VERIFY_KR(kr); break; } // Fall through and try to undo the earlier change to // dsema->dsema_group_waiters case DISPATCH_TIME_NOW: while ((orig = dsema->dsema_group_waiters)) { if (dispatch_atomic_cmpxchg2o(dsema, dsema_group_waiters, orig, orig - 1)) { return KERN_OPERATION_TIMED_OUT; } } // Another thread called semaphore_signal(). // Fall through and drain the wakeup. case DISPATCH_TIME_FOREVER: do { kr = semaphore_wait(dsema->dsema_waiter_port); } while (kr == KERN_ABORTED); DISPATCH_SEMAPHORE_VERIFY_KR(kr); break; } #elif USE_POSIX_SEM //这部分代码省略 #endif goto again; } 复制代码

从上面的代码咱们发现_dispatch_group_wait_slow和_dispatch_semaphore_wait_slow的逻辑很接近。都利用mach内核的semaphore进行信号的发送。区别在于_dispatch_semaphore_wait_slow在等待结束后是return，而_dispatch_group_wait_slow在等待结束是调用_dispatch_group_wake去唤醒这个group。

总结

dispatch_group是一个初始值为LONG_MAX的信号量，group中的任务完成是判断其value是否恢复成初始值。
dispatch_group_enter和dispatch_group_leave必须成对使用而且支持嵌套。
若是dispatch_group_enter比dispatch_group_leave多，因为value不等于dsema_orig不会走到唤醒逻辑，dispatch_group_notify中的任务没法执行或者dispatch_group_wait收不到信号而卡住线程。若是是dispatch_group_leave多，则会引发崩溃。