redis源码之事件驱动（四）

简介

redis的事件分为两种：

• 定时事件（如定时任务），定时任务事件是通过将定时任务插入到一个任务链表中，定时遍历链表检查是否有到时间的任务需要处理。
• 文件句柄事件（如网络socket可读或可写），文件句柄事件的监听和处理是通过epoll系统调用实现的。

事件对象

基础结构

typedef struct aeEventLoop {
    int maxfd;   /* highest file descriptor currently registered */
    int setsize; /* max number of file descriptors tracked */
    long long timeEventNextId;
	   // 记录了文件句柄对应可读或可写事件的处理函数
    aeFileEvent *events; /* Registered events */
	   // 记录了文件句柄
    aeFiredEvent *fired; /* Fired events */
	   // 所有的事件事件会记录在timeEventHead链表中
    aeTimeEvent *timeEventHead;
    int stop;
    void *apidata; /* This is used for polling API specific data */
	   // epoll会进入睡眠等待，epoll前调用的函数在beforesleep中
    aeBeforeSleepProc *beforesleep;
	   // epoll后调用
    aeBeforeSleepProc *aftersleep;
    int flags;
} aeEventLoop;

/* File event structure */
typedef struct aeFileEvent {
    int mask; /* one of AE_(READABLE|WRITABLE|BARRIER) */
	   // 有可读事件的时候，调用rfileProc函数
    aeFileProc *rfileProc;
    aeFileProc *wfileProc;
    void *clientData;
} aeFileEvent;

/* Time event structure */
typedef struct aeTimeEvent {
    long long id; /* time event identifier. */
	   // 到期时间，这里是绝对时间，到期后需要执行timeProc
    monotime when;
    aeTimeProc *timeProc;
    aeEventFinalizerProc *finalizerProc;
    void *clientData;
	  // 指向链表的下一个和上一个节点
    struct aeTimeEvent *prev;
    struct aeTimeEvent *next;
    int refcount; /* refcount to prevent timer events from being
           * freed in recursive time event calls. */
} aeTimeEvent;

事件注册

// 设置fd对应的事件处理函数为proc
// eventLoop->events[fd]->rfileProc
int aeCreateFileEvent(aeEventLoop *eventLoop, int fd, int mask,
        aeFileProc *proc, void *clientData)
{
    // 判断fd是否超出eventLoop->events数组大小
    if (fd >= eventLoop->setsize) {
        errno = ERANGE;
        return AE_ERR;
    }
    aeFileEvent *fe = &eventLoop->events[fd];

    if (aeApiAddEvent(eventLoop, fd, mask) == -1)
        return AE_ERR;
    fe->mask |= mask;
    // 根据mask设置对应类型的处理函数为proc
    if (mask & AE_READABLE) fe->rfileProc = proc;
    if (mask & AE_WRITABLE) fe->wfileProc = proc;
    // clientData有什么用？
    fe->clientData = clientData;
    // 记录maxfd有什么意义
    if (fd > eventLoop->maxfd)
        eventLoop->maxfd = fd;
    return AE_OK;
}


// 将fd添加到epoll监听列表中
static int aeApiAddEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;
    struct epoll_event ee = {0}; /* avoid valgrind warning */
    /* If the fd was already monitored for some event, we need a MOD
     * operation. Otherwise we need an ADD operation. */
    int op = eventLoop->events[fd].mask == AE_NONE ?
            EPOLL_CTL_ADD : EPOLL_CTL_MOD;

    ee.events = 0;
    mask |= eventLoop->events[fd].mask; /* Merge old events */
    if (mask & AE_READABLE) ee.events |= EPOLLIN;
    if (mask & AE_WRITABLE) ee.events |= EPOLLOUT;
    ee.data.fd = fd;
    if (epoll_ctl(state->epfd,op,fd,&ee) == -1) return -1;
    return 0;
}

// 创建一个时间事件，插入到eventLoop->timeEventHead的最前面
// 处理函数是proc
// 这里没有对when排序，所以判断是否有超时事件，得遍历整个链表
long long aeCreateTimeEvent(aeEventLoop *eventLoop, long long milliseconds,
        aeTimeProc *proc, void *clientData,
        aeEventFinalizerProc *finalizerProc)
{
    long long id = eventLoop->timeEventNextId++;
    aeTimeEvent *te;

    te = zmalloc(sizeof(*te));
    if (te == NULL) return AE_ERR;
    te->id = id;
    te->when = getMonotonicUs() + milliseconds * 1000;
    te->timeProc = proc;
    te->finalizerProc = finalizerProc;
    te->clientData = clientData;
    te->prev = NULL;
    te->next = eventLoop->timeEventHead;
    te->refcount = 0;
    if (te->next)
        te->next->prev = te;
    eventLoop->timeEventHead = te;
    return id;
}

事件触发

// redis 服务器进程起始程序
int main(int argc, char **argv)  server.c
  // 事件处理主函数, 循环调用aeProcessEvents
  void aeMain(aeEventLoop *eventLoop) ae.c
    // 事件处理逻辑，主要是处理时间到期的事件和文件句柄的可读可写事件
    int aeProcessEvents(aeEventLoop *eventLoop, int flags) ae.c
	    // 处理时间事件
	    static int processTimeEvents(aeEventLoop *eventLoop) 

• 文件事件的处理是通过调用epoll_wait等待事件发生，然后调用对应文件句柄注册的事件处理函数处理事件；
• 定时事件的处理就是遍历链表eventLoop->timeEventHead检查是否有超时的事件发生。

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

    /* Nothing to do? return ASAP */
    if (!(flags & AE_TIME_EVENTS) && !(flags & AE_FILE_EVENTS)) return 0;

    /* Note that we want to 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. */
    // 如果要处理时间时间，且没有设置AE_DONT_WAIT
    if (eventLoop->maxfd != -1 ||
        ((flags & AE_TIME_EVENTS) && !(flags & AE_DONT_WAIT))) {
        int j;
        struct timeval tv, *tvp;
        int64_t usUntilTimer = -1;
        // 处理时间事件，没有设置AE_DONT_WAIT, 就计算需要多久才会有过期事件
        if (flags & AE_TIME_EVENTS && !(flags & AE_DONT_WAIT))
            usUntilTimer = usUntilEarliestTimer(eventLoop);
        // 时间格式转换, 如果大于0, tv就记录了还需要多久才会有到期事件
        if (usUntilTimer >= 0) {
            tv.tv_sec = usUntilTimer / 1000000;
            tv.tv_usec = usUntilTimer % 1000000;
            tvp = &tv;
        } 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AE_DONT_WAIT 直接设置tv为0
            if (flags & AE_DONT_WAIT) {
                tv.tv_sec = tv.tv_usec = 0;
                tvp = &tv;
            } else {
                /* Otherwise we can block */
                tvp = NULL; /* wait forever */
            }
        }
        // 如果eventLoop本身设置了AE_DONT_WAIT，表示epoll_wait不阻塞，直接返回
        if (eventLoop->flags & AE_DONT_WAIT) {
            tv.tv_sec = tv.tv_usec = 0;
            tvp = &tv;
        }

        // 这个调用顺序，是否说明aeApiPoll会阻塞
        if (eventLoop->beforesleep != NULL && flags & AE_CALL_BEFORE_SLEEP)
            eventLoop->beforesleep(eventLoop);

        /* Call the multiplexing API, will return only on timeout or when
         * some event fires. */
        // epoll_wait的返回结果放入eventLoop->fired
        numevents = aeApiPoll(eventLoop, tvp);

        /* After sleep callback. */
        if (eventLoop->aftersleep != NULL && flags & AE_CALL_AFTER_SLEEP)
            eventLoop->aftersleep(eventLoop);
        // 处理fired[n].fd找到对应的事件对象，调用事件对象的处理函数rfileProc或wfileProc
        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 later. 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 fsyncing a file to disk,
             * before replying to a client. */
            // 一般情况是先处理可读事件，然后处理可写事件
            // 而inver是表示需要先处理写事件，然后处理读事件
            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. */
            // 处理读事件
            if (!invert && fe->mask & mask & AE_READABLE) {
                fe->rfileProc(eventLoop,fd,fe->clientData,mask);
                fired++;
                fe = &eventLoop->events[fd]; /* Refresh in case of resize. */
            }

            /* Fire the writable event. */
            // 处理写事件
            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. */
            if (invert) {
                fe = &eventLoop->events[fd]; /* Refresh in case of resize. */
                if ((fe->mask & mask & AE_READABLE) &&
                    (!fired || fe->wfileProc != fe->rfileProc))
                {
                    fe->rfileProc(eventLoop,fd,fe->clientData,mask);
                    fired++;
                }
            }
            processed++;
        }
    }
    /* Check time events */
    // 处理eventLoop->timeEventHead链表中的到期事件
    if (flags & AE_TIME_EVENTS)
        processed += processTimeEvents(eventLoop);

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