【redis原理】redis事件机制

一、前言

事件机制在很多组件中都有应用，例如：nginx、tomcat、netty等，同样redis也有事件机制，由于最近redis学习比较多，所以今天也学习一下redis的事件机制；

redis服务器是一个事件驱动程序，它主要处理以下两种事件：
文件事件：利用I/O复用机制，监听Socket等文件描述符上发生的事件，这类事件主要由客户端（或其他redis服务器）发送网络请求触发；
时间事件：定时触发的事件，负责完成redis内部定时任务，如生成RDB文件、清除过期数据等。

二、redis事件机制概述

redis利用I/O复用机制实现网络通讯，它利用单进程监听多个客户端连接，当某个连接状态发生变化（如可读、可写）时，操作系统会发生事件（这些事件称为已就绪事件）通知进程处理该连接的数据；
redis实现了自己的事件机制，支持不同系统的I/O复用API。

redis API：
aeApiCreate：初始化I/O复用机制的上下文环境；
aeApiAddEvent、aeApiDelEvent:添加或者删除一个监听对象；
aeApiPoll:阻塞进程，等待事件就绪或给定时间到期；

redis中的事件循环器aeEventLoop ：

/* State of an event based program */
typedef struct aeEventLoop {
    
    
    int maxfd;   /* highest file descriptor currently registered */
    int setsize; /* max number of file descriptors tracked */
    long long timeEventNextId;
    time_t lastTime;     /* Used to detect system clock skew */
    aeFileEvent *events; /* Registered events */
    aeFiredEvent *fired; /* Fired events */
    aeTimeEvent *timeEventHead;
    int stop;
    void *apidata; /* This is used for polling API specific data */
    aeBeforeSleepProc *beforesleep;
    aeBeforeSleepProc *aftersleep;
    int flags;
} aeEventLoop;

maxfd：当前已注册的最大文件描述符；
setsize:该事件循环器允许监听的最大的文件描述符；
timeEventNextId：下一个时间事件ID；
lastTime：上一次执行时间事件的时间，用于判断是否发生系统时钟偏移；
event：已注册的文件事件表；
fired：已就绪的事件表；
timeEventHead：时间事件表的头结点指针；
stop：事件循环器是否停止；
apidata：存放用于I/O复用层的附加数据；
beforesleep、aftersleep：进程阻塞前后调用的钩子函数。

aeFileEvent存储了一个文件描述符上已注册的文件事件：

/* File event structure */
typedef struct aeFileEvent {
    
    
    int mask; /* one of AE_(READABLE|WRITABLE|BARRIER) */
    aeFileProc *rfileProc;
    aeFileProc *wfileProc;
    void *clientData;
} aeFileEvent;

mask：监听的文件事件类型；
rfileProc：AE_READABLE事件处理函数；
wfileProc：AE_WRITABLE事件处理函数；
clientData：附加数据；

aeTimeEvent中存储了一个时间事件信息：

/* Time event structure */
typedef struct aeTimeEvent {
    
    
    long long id; /* time event identifier. */
    long when_sec; /* seconds */
    long when_ms; /* milliseconds */
    aeTimeProc *timeProc;
    aeEventFinalizerProc *finalizerProc;
    void *clientData;
    struct aeTimeEvent *prev;
    struct aeTimeEvent *next;
    int refcount; /* refcount to prevent timer events from being
  		   * freed in recursive time event calls. */
} aeTimeEvent;

id：时间事件的ID；
when_sec、when_ms：时间事件下一次执行的秒数（UNIX时间戳）和剩余毫秒数
timeProc：时间事件处理函数；
finalizerProc：时间事件终结函数；
clientData：客户端传入的附加数据；
prev、next：指向前一个和后一个世间事件；

三、创建事件

initServer函数调用aeCreateEventLoop函数创建事件循环器：

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;
    eventLoop->flags = 0;
    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;
}

aecreateFileEvent函数为TCP socket等文件描述符注册了监听AE_WRITABLE类型的文件事件：

int aeCreateFileEvent(aeEventLoop *eventLoop, int fd, int mask,
        aeFileProc *proc, void *clientData)
{
    
    
    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;
    if (mask & AE_READABLE) fe->rfileProc = proc;
    if (mask & AE_WRITABLE) fe->wfileProc = proc;
    fe->clientData = clientData;
    if (fd > eventLoop->maxfd)
        eventLoop->maxfd = fd;
    return AE_OK;
}

aeCreateTimeEvent函数创建了一个处理函数为serverCron的时间事件，负责处理redis中的定时任务：

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;
    aeAddMillisecondsToNow(milliseconds,&te->when_sec,&te->when_ms);
    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;
}

调用aeMain函数，启动事件循环器：

void aeMain(aeEventLoop *eventLoop) {
    
    
    eventLoop->stop = 0;
    while (!eventLoop->stop) {
    
    
        aeProcessEvents(eventLoop, AE_ALL_EVENTS|
                                   AE_CALL_BEFORE_SLEEP|
                                   AE_CALL_AFTER_SLEEP);
    }
}

四、事件循环器的运行

aeProcessEvents函数被不断循环调用，处理redis中的事件：

/* Process every pending time event, then every pending file event
 * (that may be registered by time event callbacks just processed).
 * Without special flags the function sleeps until some file event
 * fires, or when the next time event occurs (if any).
 *
 * If flags is 0, the function does nothing and returns.
 * if flags has AE_ALL_EVENTS set, all the kind of events are processed.
 * if flags has AE_FILE_EVENTS set, file events are processed.
 * if flags has AE_TIME_EVENTS set, time events are processed.
 * if flags has AE_DONT_WAIT set the function returns ASAP until all
 * the events that's possible to process without to wait are processed.
 * if flags has AE_CALL_AFTER_SLEEP set, the aftersleep callback is called.
 * if flags has AE_CALL_BEFORE_SLEEP set, the beforesleep callback is called.
 *
 * The function returns the number of events processed. */
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 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. */
    if (eventLoop->maxfd != -1 ||
        ((flags & AE_TIME_EVENTS) && !(flags & AE_DONT_WAIT))) {
    
    
        int j;
        aeTimeEvent *shortest = NULL;
        struct timeval tv, *tvp;

        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? */
            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 */
            if (flags & AE_DONT_WAIT) {
    
    
                tv.tv_sec = tv.tv_usec = 0;
                tvp = &tv;
            } else {
    
    
                /* Otherwise we can block */
                tvp = NULL; /* wait forever */
            }
        }

        if (eventLoop->flags & AE_DONT_WAIT) {
    
    
            tv.tv_sec = tv.tv_usec = 0;
            tvp = &tv;
        }

        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. */
        numevents = aeApiPoll(eventLoop, tvp);

        /* After sleep callback. */
        if (eventLoop->aftersleep != NULL && flags & AE_CALL_AFTER_SLEEP)
            eventLoop->aftersleep(eventLoop);

        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. */
            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. */
            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. */
            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 */
    if (flags & AE_TIME_EVENTS)
        processed += processTimeEvents(eventLoop);

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

flags：指定aeProcessEvents函数处理的事件类型和事件处理策略；

processTimeEvents函数处理时间事件：

/* 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. */
    if (now < eventLoop->lastTime) {
    
    
        te = eventLoop->timeEventHead;
        while(te) {
    
    
            te->when_sec = 0;
            te = te->next;
        }
    }
    eventLoop->lastTime = now;

    te = eventLoop->timeEventHead;
    maxId = eventLoop->timeEventNextId-1;
    while(te) {
    
    
        long now_sec, now_ms;
        long long id;

        /* Remove events scheduled for deletion. */
        if (te->id == AE_DELETED_EVENT_ID) {
    
    
            aeTimeEvent *next = te->next;
            /* If a reference exists for this timer event,
             * don't free it. This is currently incremented
             * for recursive timerProc calls */
            if (te->refcount) {
    
    
                te = next;
                continue;
            }
            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. */
        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;
            te->refcount++;
            retval = te->timeProc(eventLoop, id, te->clientData);
            te->refcount--;
            processed++;
            if (retval != AE_NOMORE) {
    
    
                aeAddMillisecondsToNow(retval,&te->when_sec,&te->when_ms);
            } else {
    
    
                te->id = AE_DELETED_EVENT_ID;
            }
        }
        te = te->next;
    }
    return processed;
}

注：由于redis中只有serverCron时间事件，所以这里直接遍历所有时间事件也不会有性能问题；

五、总结

• redis采用事件驱动机制，即通过一个死循环，不断处理服务中发生的事件；
• redis事件机制可以处理文件事件和时间事件，文件事件由系统I/O复用机制产生，通常由客户端请求触发，时间事件定时触发，负责定时执行redis内部任务。