redis源码分析—AE事件处理机制

redis中有两类事件，一类是IO事件统一封装成aeFileEvent，底层调用系统支持的多路复用层（evport、epoll、kqueue、select），一类是定时器事件，以aeTimeEvent描述，巧妙借用系统函数epoll_wait等阻塞函数设置阻塞时间以达到触发条件

/* Include the best multiplexing layer supported by this system.
 * The following should be ordered by performances, descending. */
// 根据宏定义包含系统支持的多路复用模型，从上到下按性能高低排序
#ifdef HAVE_EVPORT
#include "ae_evport.c"
#else
    #ifdef HAVE_EPOLL
    #include "ae_epoll.c"
    #else
        #ifdef HAVE_KQUEUE
        #include "ae_kqueue.c"
        #else
        #include "ae_select.c"
        #endif
    #endif
#endif

AE循环的主要函数：

创建AE循环

主要是结构体成员申请内存和设置初始值

aeEventLoop *aeCreateEventLoop(int setsize) {
    aeEventLoop *eventLoop;
    int i;

    if ((eventLoop = zmalloc(sizeof(*eventLoop))) == NULL) goto err;
    eventLoop->events = zmalloc(sizeof(aeFileEvent)*setsize);
    eventLoop->fired = zmalloc(sizeof(aeFiredEvent)*setsize);
    if (eventLoop->events == NULL || eventLoop->fired == NULL) goto err;
    eventLoop->setsize = setsize;
    eventLoop->lastTime = time(NULL);
    eventLoop->timeEventHead = NULL;
    eventLoop->timeEventNextId = 0;
    eventLoop->stop = 0;
    eventLoop->maxfd = -1;
    eventLoop->beforesleep = NULL;
    eventLoop->aftersleep = NULL;
    if (aeApiCreate(eventLoop) == -1) goto err;
    /* Events with mask == AE_NONE are not set. So let's initialize the
     * vector with it. */
    for (i = 0; i < setsize; i++)
        eventLoop->events[i].mask = AE_NONE;
    return eventLoop;

err:
    if (eventLoop) {
        zfree(eventLoop->events);
        zfree(eventLoop->fired);
        zfree(eventLoop);
    }
    return NULL;
}

主循环

void aeMain(aeEventLoop *eventLoop) {
    eventLoop->stop = 0;
    while (!eventLoop->stop) {  //循环监听事件
        // 阻塞之前的处理
        if (eventLoop->beforesleep != NULL)
            eventLoop->beforesleep(eventLoop);
        // 事件处理，第二个参数决定处理哪类事件
        aeProcessEvents(eventLoop, AE_ALL_EVENTS|AE_CALL_AFTER_SLEEP);
    }
}

事件处理函数

int aeProcessEvents(aeEventLoop *eventLoop, int flags)
{
    int processed = 0, numevents;

    /* Nothing to do? return ASAP */
    // 如果不处理定时器事件，也不处理文件事件，就直接返回
    if (!(flags & AE_TIME_EVENTS) && !(flags & AE_FILE_EVENTS)) return 0;

    /* Note that we want call select() even if there are no
     * file events to process as long as we want to process time
     * events, in order to sleep until the next time event is ready
     * to fire. */
    // 如果有监控文件事件，或者要处理定时器事件并且没有设置不阻塞标志
    if (eventLoop->maxfd != -1 ||
        ((flags & AE_TIME_EVENTS) && !(flags & AE_DONT_WAIT))) {
        int j;
        aeTimeEvent *shortest = NULL;
        struct timeval tv, *tvp;
        
        // 如果处理定时器事件且没有设置不阻塞标志，取最快到达的定时器时间
        if (flags & AE_TIME_EVENTS && !(flags & AE_DONT_WAIT))
            shortest = aeSearchNearestTimer(eventLoop);
        if (shortest) {
            long now_sec, now_ms;

            aeGetTime(&now_sec, &now_ms);
            tvp = &tv;

            /* How many milliseconds we need to wait for the next
             * time event to fire? */
            // 计算剩余时间
            long long ms =
                (shortest->when_sec - now_sec)*1000 +
                shortest->when_ms - now_ms;

            if (ms > 0) {
                tvp->tv_sec = ms/1000;
                tvp->tv_usec = (ms % 1000)*1000;
            } else {
                tvp->tv_sec = 0;
                tvp->tv_usec = 0;
            }
        } else {
            /* If we have to check for events but need to return
             * ASAP because of AE_DONT_WAIT we need to set the timeout
             * to zero */
            // 如果设置了不阻塞标志，阻塞时间为0，表示不阻塞
            if (flags & AE_DONT_WAIT) {
                tv.tv_sec = tv.tv_usec = 0;
                tvp = &tv;
            } else { //否则永久阻塞
                /* Otherwise we can block */
                tvp = NULL; /* wait forever */
            }
        }

        /* Call the multiplexing API, will return only on timeout or when
         * some event fires. */
        // 等待事件触发或者超时
        numevents = aeApiPoll(eventLoop, tvp);

        /* After sleep callback. */
        // 阻塞后处理函数
        if (eventLoop->aftersleep != NULL && flags & AE_CALL_AFTER_SLEEP)
            eventLoop->aftersleep(eventLoop);

        // 循环处理触发的文件事件
        for (j = 0; j < numevents; j++) {
            aeFileEvent *fe = &eventLoop->events[eventLoop->fired[j].fd];
            int mask = eventLoop->fired[j].mask;
            int fd = eventLoop->fired[j].fd;
            int fired = 0; /* Number of events fired for current fd. */

            /* Normally we execute the readable event first, and the writable
             * event laster. This is useful as sometimes we may be able
             * to serve the reply of a query immediately after processing the
             * query.
             *
             * However if AE_BARRIER is set in the mask, our application is
             * asking us to do the reverse: never fire the writable event
             * after the readable. In such a case, we invert the calls.
             * This is useful when, for instance, we want to do things
             * in the beforeSleep() hook, like fsynching a file to disk,
             * before replying to a client. */
            // 如果设置了AE_BARRIER标志，我们优先处理写事件
            int invert = fe->mask & AE_BARRIER;

            /* Note the "fe->mask & mask & ..." code: maybe an already
             * processed event removed an element that fired and we still
             * didn't processed, so we check if the event is still valid.
             *
             * Fire the readable event if the call sequence is not
             * inverted. */
            // 没有设置AE_BARRIER标志，优先处理读事件
            if (!invert && fe->mask & mask & AE_READABLE) {
                fe->rfileProc(eventLoop,fd,fe->clientData,mask);
                fired++;
            }

            /* Fire the writable event. */
            if (fe->mask & mask & AE_WRITABLE) {
                if (!fired || fe->wfileProc != fe->rfileProc) {
                    fe->wfileProc(eventLoop,fd,fe->clientData,mask);
                    fired++;
                }
            }

            /* If we have to invert the call, fire the readable event now
             * after the writable one. */
            // 如果需要反转读写处理顺序，处理完写事件后，可以处理读事件
            if (invert && fe->mask & mask & AE_READABLE) {
                if (!fired || fe->wfileProc != fe->rfileProc) {
                    fe->rfileProc(eventLoop,fd,fe->clientData,mask);
                    fired++;
                }
            }

            processed++;
        }
    }
    /* Check time events */
    // 处理定时器事件
    if (flags & AE_TIME_EVENTS)
        processed += processTimeEvents(eventLoop);

    return processed; /* return the number of processed file/time events */
}

处理定时器事件函数

/* Process time events */
static int processTimeEvents(aeEventLoop *eventLoop) {
    int processed = 0;
    aeTimeEvent *te;
    long long maxId;
    time_t now = time(NULL);

    /* If the system clock is moved to the future, and then set back to the
     * right value, time events may be delayed in a random way. Often this
     * means that scheduled operations will not be performed soon enough.
     *
     * Here we try to detect system clock skews, and force all the time
     * events to be processed ASAP when this happens: the idea is that
     * processing events earlier is less dangerous than delaying them
     * indefinitely, and practice suggests it is. */
    // 如果上次处理定时器事件的时间比当前时间还要大，说明时间有偏差，强制将所有的定时器尽快处理掉(将所有定时器的间隔秒数设置为0)
    if (now < eventLoop->lastTime) {
        te = eventLoop->timeEventHead;
        while(te) {
            te->when_sec = 0;
            te = te->next;
        }
    }
    // 更新最近处理定时器事件的时间
    eventLoop->lastTime = now;

    te = eventLoop->timeEventHead;
    maxId = eventLoop->timeEventNextId-1; // 获取最大的定时器ID
    while(te) {
        long now_sec, now_ms;
        long long id;

        /* Remove events scheduled for deletion. */
        // 删除已经标记失效的定时器
        if (te->id == AE_DELETED_EVENT_ID) {
            aeTimeEvent *next = te->next;
            if (te->prev)
                te->prev->next = te->next;
            else
                eventLoop->timeEventHead = te->next;
            if (te->next)
                te->next->prev = te->prev;
            if (te->finalizerProc)
                te->finalizerProc(eventLoop, te->clientData);
            zfree(te);
            te = next;
            continue;
        }

        /* Make sure we don't process time events created by time events in
         * this iteration. Note that this check is currently useless: we always
         * add new timers on the head, however if we change the implementation
         * detail, this check may be useful again: we keep it here for future
         * defense. */
        // 保证不处理定时器处理过程中创建的定时器事件，暂时没用，因为添加定时器事件总是在头部添加
        if (te->id > maxId) {
            te = te->next;
            continue;
        }
        aeGetTime(&now_sec, &now_ms);
        if (now_sec > te->when_sec ||
            (now_sec == te->when_sec && now_ms >= te->when_ms))
        {
            int retval;

            id = te->id;
            // 回调定时器事件处理函数
            retval = te->timeProc(eventLoop, id, te->clientData);
            processed++;
            if (retval != AE_NOMORE) { // 如果定时器还需要重复使用
                aeAddMillisecondsToNow(retval,&te->when_sec,&te->when_ms); // 设置新的触发时间
            } else { // 否则，标记定时器失效
                te->id = AE_DELETED_EVENT_ID; 
            }
        }
        te = te->next;
    }
    return processed;
}

创建File事件

int aeCreateFileEvent(aeEventLoop *eventLoop, int fd, int mask,
        aeFileProc *proc, void *clientData)
{
    // 文件描述符不能大于setsize，否则eventLoop->events会溢出
    if (fd >= eventLoop->setsize) {
        errno = ERANGE;
        return AE_ERR;
    }
    // 这里以描述作为下标记录事件，可以避免循环查找
    aeFileEvent *fe = &eventLoop->events[fd];
    // 调用底层封装的多路复用接口添加事件监控
    if (aeApiAddEvent(eventLoop, fd, mask) == -1)
        return AE_ERR;
    // 更新描述符监控的事件信息和处理函数以及客户端信息
    fe->mask |= mask;
    if (mask & AE_READABLE) fe->rfileProc = proc;
    if (mask & AE_WRITABLE) fe->wfileProc = proc;
    fe->clientData = clientData;
    // 记录当前最大的文件描述符
    if (fd > eventLoop->maxfd)
        eventLoop->maxfd = fd;
    return AE_OK;
}

还有一些其他的接口函数比较简单，就没必要一一分析了

void aeDeleteFileEvent(aeEventLoop *eventLoop, int fd, int mask)  // 删除FileEvent

long long aeCreateTimeEvent(aeEventLoop *eventLoop, long long milliseconds, aeTimeProc *proc, void *clientData, aeEventFinalizerProc *finalizerProc)  // 添加定时器事件

int aeDeleteTimeEvent(aeEventLoop *eventLoop, long long id) //删除定时器事件

static aeTimeEvent *aeSearchNearestTimer(aeEventLoop *eventLoop) //获取最接近的定时器事件