Redis源码-事件库

网上看了很多Redis事件库的解读，自己也研究了好几遍，还是记录下来，虽然水平有限，但是进步总会是有的

网络事件库封装了Epoll的操作（当然是指Linux下的多路复用了），并且实现一个定时器，定时器也是服务端程序的基石，很多问题都需要靠定时器解决

（一）数据结构+算法构成一个完整的程序，要一窥Redis网络库，需要先从数据结构开始学习

1.整个事件循环是用一个全局的数据结构描述的，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;
} aeEventLoop;

maxfd：维护的注册事件的最大fd

setsize：事件数的个数，这也是文件事件数组和就绪事件数组的最大值。对每一个fd进行的所有操作都需要进行边界检查

timeEventNextId：每加入一个时间事件，都需要给它一个ID，时间事件链虽然不是有序的，但是这个ID是一直自增的，这个就是最大的ID

LastTime：用来修正系统时间的

events和fired：文件事件，就绪事件

stop：开关

apidata：不同实现代表不同，epoll里面是这样一个数据结构

typedef struct aeApiState {
    int epfd;
    struct epoll_event *events;
} aeApiState;

beforesleep：每次进入主循环都要执行的，这里会做很多的事情，具体后面会遇到

2.文件事件

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

可以看到文件事件维护了回调和相应fd的标志，这里可能就会好奇为什么没有维护fd呢，因为fd是存在就绪事件结构中的

3.就绪事件

/* A fired event */
typedef struct aeFiredEvent {
    int fd;
    int mask;
} aeFiredEvent;

就绪事件数组的下标就是自己维护的fd，同时通过这个fd，也可以找到对应的回调，这里先贴上这部分代码

aeFileEvent *fe = &eventLoop->events[eventLoop->fired[j].fd];
fe->rfileProc(eventLoop,fd,fe->clientData,mask);
fe->wfileProc(eventLoop,fd,fe->clientData,mask);

4.时间事件

这里目前我觉得redis的实现不够完美，当然文档的注释中也提到了，使用链表去维护时间事件，查找的复杂度就会0(n)，听别人说可以用小根堆实现，目前就简单分析一下

/* 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 *next;
} aeTimeEvent;

数据结构分析完了，接下来就看它的实现了，主循环部分：

void aeMain(aeEventLoop *eventLoop) {
    eventLoop->stop = 0;
    while (!eventLoop->stop) {
        if (eventLoop->beforesleep != NULL)
            eventLoop->beforesleep(eventLoop);
        aeProcessEvents(eventLoop, AE_ALL_EVENTS);
    }
}

逻辑都在aeProcessEvents：

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;

            /* Calculate the time missing for the nearest
             * timer to fire. */
            aeGetTime(&now_sec, &now_ms);
            tvp = &tv;
            tvp->tv_sec = shortest->when_sec - now_sec;
            if (shortest->when_ms < now_ms) {
                tvp->tv_usec = ((shortest->when_ms+1000) - now_ms)*1000;
                tvp->tv_sec --;
            } else {
                tvp->tv_usec = (shortest->when_ms - now_ms)*1000;
            }
            if (tvp->tv_sec < 0) tvp->tv_sec = 0;
            if (tvp->tv_usec < 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 */
            }
        }

        numevents = aeApiPoll(eventLoop, tvp);
        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 rfired = 0;

	    /* 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. */
            if (fe->mask & mask & AE_READABLE) {
                rfired = 1;
                fe->rfileProc(eventLoop,fd,fe->clientData,mask);
            }
            if (fe->mask & mask & AE_WRITABLE) {
                if (!rfired || fe->wfileProc != fe->rfileProc)
                    fe->wfileProc(eventLoop,fd,fe->clientData,mask);
            }
            processed++;
        }
    }
    /* Check time events */
    if (flags & AE_TIME_EVENTS)
        processed += processTimeEvents(eventLoop);

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

代码有点长，其实抽象出来就三个步骤：

1根据flag获取epoll_wait等待的时间，有这样几种情况，

如果有时间事件，那么就从事件事件中找最快超时的时间，并等待这个时间，这个策略很巧妙

如果设置为不等待，那么就立马返回

如果设置为其它标志，就永久阻塞直到触发事件

2.等到事件发生，并根据回调处理事件

3.处理时间事件

其中aeApiPoll的实现也就是封装了epoll_wait

static int aeApiPoll(aeEventLoop *eventLoop, struct timeval *tvp) {
    aeApiState *state = eventLoop->apidata;
    int retval, numevents = 0;

    retval = epoll_wait(state->epfd,state->events,eventLoop->setsize,
            tvp ? (tvp->tv_sec*1000 + tvp->tv_usec/1000) : -1);
    if (retval > 0) {
        int j;

        numevents = retval;
        for (j = 0; j < numevents; j++) {
            int mask = 0;
            struct epoll_event *e = state->events+j;

            if (e->events & EPOLLIN) mask |= AE_READABLE;
            if (e->events & EPOLLOUT) mask |= AE_WRITABLE;
            if (e->events & EPOLLERR) mask |= AE_WRITABLE;
            if (e->events & EPOLLHUP) mask |= AE_WRITABLE;
            eventLoop->fired[j].fd = e->data.fd;
            eventLoop->fired[j].mask = mask;
        }
    }
    return numevents;
}

既然这里有封装epoll_wait，必然想去看看epoll_ctl和epoll_create的封装了，如下封装了创建Epoll句柄

static int aeApiCreate(aeEventLoop *eventLoop) {
    aeApiState *state = zmalloc(sizeof(aeApiState));

    if (!state) return -1;
    state->events = zmalloc(sizeof(struct epoll_event)*eventLoop->setsize);
    if (!state->events) {
        zfree(state);
        return -1;
    }
    state->epfd = epoll_create(1024); /* 1024 is just a hint for the kernel */
    if (state->epfd == -1) {
        zfree(state->events);
        zfree(state);
        return -1;
    }
    eventLoop->apidata = state;
    return 0;
}

而epoll_ctl的封装就是系统需要暴露给外界的接口，即创建文件事件和时间事件的接口

例如：创建一个文件事件

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;
}

这里首先判断fd的值，前面有说过，然后取出fe，根据mask设置fe的值，并且调用aeApiEvent，里面才是调用了epoll_ctl

最后还要记得擦屁股，可能要修改一下maxfd

static int aeApiAddEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;
    struct epoll_event ee;
    /* 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.u64 = 0; /* avoid valgrind warning */
    ee.data.fd = fd;
    if (epoll_ctl(state->epfd,op,fd,&ee) == -1) return -1;
    return 0;
}

首先判断fd是否已近注册，没有就增加，有就需要修改，然后进行注册，这里底层接口的调用都是在直接上层，即ae_epoll进行处理的，上上层，即ae层只是对本层数据结构的维护，这种代码逻辑很严密，可见作者水平

再比如：删除一个文件事件

void aeDeleteFileEvent(aeEventLoop *eventLoop, int fd, int mask)
{
    if (fd >= eventLoop->setsize) return;
    aeFileEvent *fe = &eventLoop->events[fd];
    if (fe->mask == AE_NONE) return;

    aeApiDelEvent(eventLoop, fd, mask);
    fe->mask = fe->mask & (~mask);
    if (fd == eventLoop->maxfd && fe->mask == AE_NONE) {
        /* Update the max fd */
        int j;

        for (j = eventLoop->maxfd-1; j >= 0; j--)
            if (eventLoop->events[j].mask != AE_NONE) break;
        eventLoop->maxfd = j;
    }
}

首先判断fd是否未注册，未注册就直接返回了，注册了就删除fd上的事件，然后对fe进行处理，最后也有可能要修改maxfd的值

至于aeApiDelEvent的实现

static void aeApiDelEvent(aeEventLoop *eventLoop, int fd, int delmask) {
    aeApiState *state = eventLoop->apidata;
    struct epoll_event ee;
    int mask = eventLoop->events[fd].mask & (~delmask);

    ee.events = 0;
    if (mask & AE_READABLE) ee.events |= EPOLLIN;
    if (mask & AE_WRITABLE) ee.events |= EPOLLOUT;
    ee.data.u64 = 0; /* avoid valgrind warning */
    ee.data.fd = fd;
    if (mask != AE_NONE) {
        epoll_ctl(state->epfd,EPOLL_CTL_MOD,fd,&ee);
    } else {
        /* Note, Kernel < 2.6.9 requires a non null event pointer even for
         * EPOLL_CTL_DEL. */
        epoll_ctl(state->epfd,EPOLL_CTL_DEL,fd,&ee);
    }
}

可以看到，只是对fd进行修改注册或者删除上面的事件

处理时间事件

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

    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;

        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;
            retval = te->timeProc(eventLoop, id, te->clientData);
            processed++;

            if (retval != AE_NOMORE) {
                aeAddMillisecondsToNow(retval,&te->when_sec,&te->when_ms);
            } else {
                aeDeleteTimeEvent(eventLoop, id);
            }
            te = eventLoop->timeEventHead;
        } else {
            te = te->next;
        }
    }
    return processed;
}

其实就是搜索，然后处理，这里处理的时候把这个节点删除了，在aeDeleteTimeEvent中如下

int aeDeleteTimeEvent(aeEventLoop *eventLoop, long long id)
{
    aeTimeEvent *te, *prev = NULL;

    te = eventLoop->timeEventHead;
    while(te) {
        if (te->id == id) {
            if (prev == NULL)
                eventLoop->timeEventHead = te->next;
            else
                prev->next = te->next;
            if (te->finalizerProc)
                te->finalizerProc(eventLoop, te->clientData);
            zfree(te);
            return AE_OK;
        }
        prev = te;
        te = te->next;
    }
    return AE_ERR; /* NO event with the specified ID found */
}

目前就分析到这里，带有几个问题后面再去阅读源码：

beforesleep到底干了什么？

真个程序的流程，包括网络连接那部分又是如何组织到Epoll中的？