【redis源码】（六）Ae.c

和memcached不同的是，redis没有使用第三方的事件框架，而是自己封装了io处理机制。

有些细节上，redis并没有做到最优化，比如超时事件管理，redis仅仅使用了一个单链表，最新插入的超时事件放在链表头，作者在源码中也提到超时事件上的一些可以改进的地方【比如libevent超时事件采用最大堆实现】

“Note that's O(N) since time events are unsorted.
Possible optimizations (not needed by Redis so far, but...):
1) Insert the event in order, so that the nearest is just the head. Much better but still insertion or deletion of timers is O(N).
2) Use a skiplist to have this operation as O(1) and insertion as O(log(N)).”

另外一个小细节是，如果使用epoll做io复用模型的话，redis会使用水平触发作为工作方式。

哦了，贴代码，看了好久才想清楚~ 感觉表述越来越不清楚了，还是自己理解的不够透彻，再接再厉

Ae_select.c

/* Select()-based ae.c module
 * Copyright (C) 2009-2010 Salvatore Sanfilippo - antirez@gmail.com
 * Released under the BSD license. See the COPYING file for more info. */

#include <string.h>

//select底层底层封装，被ae.c使用，用来处理读写文件描述符的时间管理
typedef struct aeApiState {
    //用来保存注册到select文件描述符
    fd_set rfds, wfds;
    /* We need to have a copy of the fd sets as it's not safe to reuse
     * FD sets after select(). */
    //select操作时使用的fd_set文件
    fd_set _rfds, _wfds;
} aeApiState;

//给上层zip调用的方法，用于初始化一个select事件管理
static int aeApiCreate(aeEventLoop *eventLoop) {
    aeApiState *state = zmalloc(sizeof(aeApiState));

    if (!state) return -1;
    //初始化aeApiState中的fd_set
    FD_ZERO(&state->rfds);
    FD_ZERO(&state->wfds);
    eventLoop->apidata = state;
    return 0;
}

//释放aeApiState内存
static void aeApiFree(aeEventLoop *eventLoop) {
    zfree(eventLoop->apidata);
}

//向eventLoop添加指定mask的文件描述符
static int aeApiAddEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;

    //插入读事件文件描述符
    if (mask & AE_READABLE) FD_SET(fd,&state->rfds);
    //插入写事件文件描述符
    if (mask & AE_WRITABLE) FD_SET(fd,&state->wfds);
    return 0;
}

//从eventLoop中删除描述符fd的指定监听事件
static void aeApiDelEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;

    if (mask & AE_READABLE) FD_CLR(fd,&state->rfds);
    if (mask & AE_WRITABLE) FD_CLR(fd,&state->wfds);
}

//执行事件监听，超时时间为tvp
static int aeApiPoll(aeEventLoop *eventLoop, struct timeval *tvp) {
    aeApiState *state = eventLoop->apidata;
    int retval, j, numevents = 0;

    //复制最新的state->rfds & state->wfds到_rfds,_wfds
    memcpy(&state->_rfds,&state->rfds,sizeof(fd_set));
    memcpy(&state->_wfds,&state->wfds,sizeof(fd_set));

    //执行select，超时时间tvp
    retval = select(eventLoop->maxfd+1,
                &state->_rfds,&state->_wfds,NULL,tvp);
    if (retval > 0) {
        for (j = 0; j <= eventLoop->maxfd; j++) {
            int mask = 0;
            aeFileEvent *fe = &eventLoop->events[j];

            if (fe->mask == AE_NONE) continue;
            if (fe->mask & AE_READABLE && FD_ISSET(j,&state->_rfds))
                mask |= AE_READABLE;
            if (fe->mask & AE_WRITABLE && FD_ISSET(j,&state->_wfds))
                mask |= AE_WRITABLE;
            //将可读或者可写的文件描述符状态更新到eventLoop结构体中
            eventLoop->fired[numevents].fd = j;
            eventLoop->fired[numevents].mask = mask;
            numevents++;
        }
    }
    //返回可读可写的文件描述符总数量
    return numevents;
}

static char *aeApiName(void) {
    return "select";
}

Ae_epoll.c

/* Linux epoll(2) based ae.c module
 * Copyright (C) 2009-2010 Salvatore Sanfilippo - antirez@gmail.com
 * Released under the BSD license. See the COPYING file for more info. */

#include <sys/epoll.h>


typedef struct aeApiState {
    int epfd;
    struct epoll_event events[AE_SETSIZE];
} aeApiState;

//初始化一个epoll时间管理结构体eventLoop
static int aeApiCreate(aeEventLoop *eventLoop) {
    aeApiState *state = zmalloc(sizeof(aeApiState));

    if (!state) return -1;
    //epoll_create(size)中的size参数不使用
    //初始化epoll_fd
    state->epfd = epoll_create(1024); /* 1024 is just an hint for the kernel */
    if (state->epfd == -1) return -1;
    eventLoop->apidata = state;
    return 0;
}

//释放aeApiState空间
static void aeApiFree(aeEventLoop *eventLoop) {
    aeApiState *state = eventLoop->apidata;

    close(state->epfd);
    zfree(state);
}

//为eventLoop添加文件描述符与其相应的监听事件
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;
}

//从eventLoop中删除fd的delmask时间类型
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);
    }
}

//poll操作，返回事件就绪的fd数量
static int aeApiPoll(aeEventLoop *eventLoop, struct timeval *tvp) {
    aeApiState *state = eventLoop->apidata;
    int retval, numevents = 0;

    retval = epoll_wait(state->epfd,state->events,AE_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;
            eventLoop->fired[j].fd = e->data.fd;
            eventLoop->fired[j].mask = mask;
        }
    }
    return numevents;
}

static char *aeApiName(void) {
    return "epoll";
}

Ae.h

#ifndef __AE_H__
#define __AE_H__

//支持的最大监听fd的数量
#define AE_SETSIZE (1024*10)    /* Max number of fd supported */

#define AE_OK 0
#define AE_ERR -1

#define AE_NONE 0
#define AE_READABLE 1
#define AE_WRITABLE 2

#define AE_FILE_EVENTS 1
#define AE_TIME_EVENTS 2
#define AE_ALL_EVENTS (AE_FILE_EVENTS|AE_TIME_EVENTS)
#define AE_DONT_WAIT 4

#define AE_NOMORE -1

/* Macros */
#define AE_NOTUSED(V) ((void) V)

//声明aeEventLoop
struct aeEventLoop;

/* Types and data structures */

typedef void aeFileProc(struct aeEventLoop *eventLoop, int fd, void *clientData, int mask);
typedef int aeTimeProc(struct aeEventLoop *eventLoop, long long id, void *clientData);
typedef void aeEventFinalizerProc(struct aeEventLoop *eventLoop, void *clientData);
typedef void aeBeforeSleepProc(struct aeEventLoop *eventLoop);

//描述符时间结构体，要么读，要么写
/* File event structure */
typedef struct aeFileEvent {
    int mask; /* one of AE_(READABLE|WRITABLE) */
    aeFileProc *rfileProc;
    aeFileProc *wfileProc;
    void *clientData;
} aeFileEvent;

//超时事件结构体
/* 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;

//已激活事件结构体
/* A fired event */
typedef struct aeFiredEvent {
    int fd;
    int mask;
} aeFiredEvent;

/* State of an event based program */
typedef struct aeEventLoop {
    int maxfd;
    long long timeEventNextId;
    aeFileEvent events[AE_SETSIZE]; /* Registered events */
    aeFiredEvent fired[AE_SETSIZE]; /* Fired events */
    aeTimeEvent *timeEventHead;
    int stop;
    void *apidata; /* This is used for polling API specific data */
    aeBeforeSleepProc *beforesleep;
} aeEventLoop;

/* Prototypes */
aeEventLoop *aeCreateEventLoop(void);
void aeDeleteEventLoop(aeEventLoop *eventLoop);
void aeStop(aeEventLoop *eventLoop);
int aeCreateFileEvent(aeEventLoop *eventLoop, int fd, int mask,
        aeFileProc *proc, void *clientData);
void aeDeleteFileEvent(aeEventLoop *eventLoop, int fd, int mask);
long long aeCreateTimeEvent(aeEventLoop *eventLoop, long long milliseconds,
        aeTimeProc *proc, void *clientData,
        aeEventFinalizerProc *finalizerProc);
int aeDeleteTimeEvent(aeEventLoop *eventLoop, long long id);
int aeProcessEvents(aeEventLoop *eventLoop, int flags);
int aeWait(int fd, int mask, long long milliseconds);
void aeMain(aeEventLoop *eventLoop);
char *aeGetApiName(void);
void aeSetBeforeSleepProc(aeEventLoop *eventLoop, aeBeforeSleepProc *beforesleep);

#endif

Ae.c

#include <stdio.h>
#include <sys/time.h>
#include <sys/types.h>
#include <unistd.h>
#include <stdlib.h>

#include "ae.h"
#include "zmalloc.h"
#include "config.h"

/* Include the best multiplexing layer supported by this system.
 * The following should be ordered by performances, descending. */
//选择使用的底层事件管理API
#ifdef HAVE_EPOLL
#include "ae_epoll.c"
#else
    #ifdef HAVE_KQUEUE
    #include "ae_kqueue.c"
    #else
    #include "ae_select.c"
    #endif
#endif

//初始化eventLoop结构体
aeEventLoop *aeCreateEventLoop(void) {
    aeEventLoop *eventLoop;
    int i;
    //申请内存
    eventLoop = zmalloc(sizeof(*eventLoop));
    if (!eventLoop) return NULL;
    eventLoop->timeEventHead = NULL;
    eventLoop->timeEventNextId = 0;
    eventLoop->stop = 0;
    eventLoop->maxfd = -1;
    eventLoop->beforesleep = NULL;
    //初始化底层事件管理结构体aeApiState，赋值给*apidata
    if (aeApiCreate(eventLoop) == -1) {
        zfree(eventLoop);
        return NULL;
    }
    /* Events with mask == AE_NONE are not set. So let's initialize the
     * vector with it. */
    //为描述符事件初始化监视事件类型
    for (i = 0; i < AE_SETSIZE; i++)
        eventLoop->events[i].mask = AE_NONE;
    return eventLoop;
}

//释放aeEventLoop
void aeDeleteEventLoop(aeEventLoop *eventLoop) {
    aeApiFree(eventLoop);
    zfree(eventLoop);
}

void aeStop(aeEventLoop *eventLoop) {
    eventLoop->stop = 1;
}

//添加一个fd及其处理函数
int aeCreateFileEvent(aeEventLoop *eventLoop, int fd, int mask,
        aeFileProc *proc, void *clientData)
{
    //文件描述符超过过了最大的值
    if (fd >= AE_SETSIZE) 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;
}

//从eventLoop中删除对fd的mask中知名的监听类型的删除
void aeDeleteFileEvent(aeEventLoop *eventLoop, int fd, int mask)
{
    //文件描述符超过过了最大的值
    if (fd >= AE_SETSIZE) return;
    aeFileEvent *fe = &eventLoop->events[fd];

    //fd上并未绑定任何类型的时间
    if (fe->mask == AE_NONE) return;
    //对mask指定的bit置零
    fe->mask = fe->mask & (~mask);
    //如果去除的监听fd是最大的那个，并且此fd当前没有任何监听事件，则更新eventloop的maxfd字段
    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;
    }
    //在api中删除对此fd的mask类事件的监听
    aeApiDelEvent(eventLoop, fd, mask);
}

//得到当前时间
static void aeGetTime(long *seconds, long *milliseconds)
{
    struct timeval tv;

    gettimeofday(&tv, NULL);
    *seconds = tv.tv_sec;
    *milliseconds = tv.tv_usec/1000;
}

//得到millissconds后的时间
static void aeAddMillisecondsToNow(long long milliseconds, long *sec, long *ms) {
    long cur_sec, cur_ms, when_sec, when_ms;

    aeGetTime(&cur_sec, &cur_ms);
    when_sec = cur_sec + milliseconds/1000;
    when_ms = cur_ms + milliseconds%1000;
    if (when_ms >= 1000) {
        when_sec ++;
        when_ms -= 1000;
    }
    *sec = when_sec;
    *ms = when_ms;
}

//注册一个超时事件
long long aeCreateTimeEvent(aeEventLoop *eventLoop, long long milliseconds,
        aeTimeProc *proc, void *clientData,
        aeEventFinalizerProc *finalizerProc)
{
    //得到新的超时事件的id
    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;
    //将新的超时事件数据插到单链表的头部
    te->next = eventLoop->timeEventHead;
    eventLoop->timeEventHead = te;
    return id;
}

//删除id为id的超时事件，单链表操作
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 */
}

/* Search the first timer to fire.
 * This operation is useful to know how many time the select can be
 * put in sleep without to delay any event.
 * If there are no timers NULL is returned.
 *
 * Note that's O(N) since time events are unsorted.
 * Possible optimizations (not needed by Redis so far, but...):
 * 1) Insert the event in order, so that the nearest is just the head.
 *    Much better but still insertion or deletion of timers is O(N).
 *    最大堆呀最大堆，libevent
 * 2) Use a skiplist to have this operation as O(1) and insertion as O(log(N)).
 */
static aeTimeEvent *aeSearchNearestTimer(aeEventLoop *eventLoop)
{
    aeTimeEvent *te = eventLoop->timeEventHead;
    aeTimeEvent *nearest = NULL;

    while(te) {
        if (!nearest || te->when_sec < nearest->when_sec ||
                (te->when_sec == nearest->when_sec &&
                 te->when_ms < nearest->when_ms))
            nearest = te;
        te = te->next;
    }
    return nearest;
}

//遍历超时事件链表，把时间到了的一个一个处理
/* Process time events */
static int processTimeEvents(aeEventLoop *eventLoop) {
    int processed = 0;
    aeTimeEvent *te;
    long long maxId;

    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++;
            /* After an event is processed our time event list may
             * no longer be the same, so we restart from head.
             * Still we make sure to don't process events registered
             * by event handlers itself in order to don't loop forever.
             * To do so we saved the max ID we want to handle.
             *
             * FUTURE OPTIMIZATIONS:
             * Note that this is NOT great algorithmically. Redis uses
             * a single time event so it's not a problem but the right
             * way to do this is to add the new elements on head, and
             * to flag deleted elements in a special way for later
             * deletion (putting references to the nodes to delete into
             * another linked list). */
            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;
}


//处理可处理的所有事件，包括文件事件和超时事件
/* 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 occurrs (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.
 *
 * 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;

            /* 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 se 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 */
}


//使用select模型，等待millseconds，返回0，表示超时，返回1，表明fd可读，返回2，表明fd可写
/* Wait for millseconds until the given file descriptor becomes
 * writable/readable/exception */
int aeWait(int fd, int mask, long long milliseconds) {
    struct timeval tv;
    fd_set rfds, wfds, efds;
    int retmask = 0, retval;

    tv.tv_sec = milliseconds/1000;
    tv.tv_usec = (milliseconds%1000)*1000;
    FD_ZERO(&rfds);
    FD_ZERO(&wfds);
    FD_ZERO(&efds);

    if (mask & AE_READABLE) FD_SET(fd,&rfds);
    if (mask & AE_WRITABLE) FD_SET(fd,&wfds);
    if ((retval = select(fd+1, &rfds, &wfds, &efds, &tv)) > 0) {
        if (FD_ISSET(fd,&rfds)) retmask |= AE_READABLE;
        if (FD_ISSET(fd,&wfds)) retmask |= AE_WRITABLE;
        return retmask;
    } else {
        return retval;
    }
}

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

char *aeGetApiName(void) {
    return aeApiName();
}

void aeSetBeforeSleepProc(aeEventLoop *eventLoop, aeBeforeSleepProc *beforesleep) {
    eventLoop->beforesleep = beforesleep;
}