Redis5.0.5源码解析 -- 多路复用模型_redis 5.0.5源码-优快云博客

本文链接：https://blog.youkuaiyun.com/junlon2006/article/details/101438339

本文详细介绍了Redis中四种I/O多路复用模型：epoll、evport、kqueue和select。针对不同操作系统，Redis会选择最适合的模型以达到最佳性能。文章深入探讨了每种模型的实现细节，包括源码解析和关键函数说明。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

redis源码地址
简介：I/O多路复用模型，在5.0.5的源码中，支持了4种，分别是：epoll、evport、kqueue、select。
源码地址
epoll：src/ae_epoll.c
evport：src/ae_evport.c
kqueue：src/ae_kqueue.c
select：ae_select.c
Redis对以上各类I/O接口都进行了封装，以满足src/ae.c的统一调度，ae.c选择模型的代码块如下：Redis根据性能从高到低进行选择（即evport > epoll > kqueue > select）

/* Include the best multiplexing layer supported by this system.
 * The following should be ordered by performances, descending. */
#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

以上的宏则是通过src/config.h加载而来
配置会更加具体的OS信息生成，比如
Ubuntu
(Linux ubuntu 4.13.0-41-generic #46~16.04.1-Ubuntu SMP Thu May 3 10:06:43 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux)内核版本下，Redis会采用epoll
MacOs
(Linux unisoundivm-MS-7B89 4.15.0-62-generic #69~16.04.1-Ubuntu SMP Fri Sep 6 02:43:35 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux)内核版本下，Redis会采用kqueue

1、epoll

#include <sys/epoll.h>

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

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;
}

static int aeApiResize(aeEventLoop *eventLoop, int setsize) {
    aeApiState *state = eventLoop->apidata;

    state->events = zrealloc(state->events, sizeof(struct epoll_event)*setsize);
    return 0;
}

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

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

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;
}

static void aeApiDelEvent(aeEventLoop *eventLoop, int fd, int delmask) {
    aeApiState *state = eventLoop->apidata;
    struct epoll_event ee = {0}; /* avoid valgrind warning */
    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.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);
    }
}

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;
        }
    }
    //printf("%s%d: numevents=%d\n", __FUNCTION__, __LINE__, numevents);
    return numevents;
}

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

1.1 epoll中的一些小疑问

1.1.1 epoll_create(int size)

size需要传多大的值呢，通过man epoll_create

linux-5.0的fs/eventpoll.c中，找到如下代码：
在这里插入图片描述
所以在高版本的kernel中，只要写大于0的数字效果都一样，低版本的可以默认写1024。

2、kqueue

#include <sys/types.h>
#include <sys/event.h>
#include <sys/time.h>

typedef struct aeApiState {
    int kqfd;
    struct kevent *events;
} aeApiState;

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

    if (!state) return -1;
    state->events = zmalloc(sizeof(struct kevent)*eventLoop->setsize);
    if (!state->events) {
        zfree(state);
        return -1;
    }
    state->kqfd = kqueue();
    if (state->kqfd == -1) {
        zfree(state->events);
        zfree(state);
        return -1;
    }
    eventLoop->apidata = state;
    return 0;
}

static int aeApiResize(aeEventLoop *eventLoop, int setsize) {
    aeApiState *state = eventLoop->apidata;

    state->events = zrealloc(state->events, sizeof(struct kevent)*setsize);
    return 0;
}

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

    close(state->kqfd);
    zfree(state->events);
    zfree(state);
}

static int aeApiAddEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;
    struct kevent ke;

    if (mask & AE_READABLE) {
        EV_SET(&ke, fd, EVFILT_READ, EV_ADD, 0, 0, NULL);
        if (kevent(state->kqfd, &ke, 1, NULL, 0, NULL) == -1) return -1;
    }
    if (mask & AE_WRITABLE) {
        EV_SET(&ke, fd, EVFILT_WRITE, EV_ADD, 0, 0, NULL);
        if (kevent(state->kqfd, &ke, 1, NULL, 0, NULL) == -1) return -1;
    }
    return 0;
}

static void aeApiDelEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;
    struct kevent ke;

    if (mask & AE_READABLE) {
        EV_SET(&ke, fd, EVFILT_READ, EV_DELETE, 0, 0, NULL);
        kevent(state->kqfd, &ke, 1, NULL, 0, NULL);
    }
    if (mask & AE_WRITABLE) {
        EV_SET(&ke, fd, EVFILT_WRITE, EV_DELETE, 0, 0, NULL);
        kevent(state->kqfd, &ke, 1, NULL, 0, NULL);
    }
}

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

    if (tvp != NULL) {
        struct timespec timeout;
        timeout.tv_sec = tvp->tv_sec;
        timeout.tv_nsec = tvp->tv_usec * 1000;
        retval = kevent(state->kqfd, NULL, 0, state->events, eventLoop->setsize,
                        &timeout);
    } else {
        retval = kevent(state->kqfd, NULL, 0, state->events, eventLoop->setsize,
                        NULL);
    }

    if (retval > 0) {
        int j;

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

            if (e->filter == EVFILT_READ) mask |= AE_READABLE;
            if (e->filter == EVFILT_WRITE) mask |= AE_WRITABLE;
            eventLoop->fired[j].fd = e->ident;
            eventLoop->fired[j].mask = mask;
        }
    }
    return numevents;
}

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

3、select

#include <sys/select.h>
#include <string.h>

typedef struct aeApiState {
    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(). */
    fd_set _rfds, _wfds;
} aeApiState;

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

    if (!state) return -1;
    FD_ZERO(&state->rfds);
    FD_ZERO(&state->wfds);
    eventLoop->apidata = state;
    return 0;
}

static int aeApiResize(aeEventLoop *eventLoop, int setsize) {
    /* Just ensure we have enough room in the fd_set type. */
    if (setsize >= FD_SETSIZE) return -1;
    return 0;
}

static void aeApiFree(aeEventLoop *eventLoop) {
    zfree(eventLoop->apidata);
}

static int aeApiAddEvent(aeEventLoop *eventLoop, int fd, int mask) {
    aeApiState *state = eventLoop->apidata;

    if (mask & AE_READABLE) FD_SET(fd,&state->rfds);
    if (mask & AE_WRITABLE) FD_SET(fd,&state->wfds);
    return 0;
}

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);
}

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

    memcpy(&state->_rfds,&state->rfds,sizeof(fd_set));
    memcpy(&state->_wfds,&state->wfds,sizeof(fd_set));

    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;
            eventLoop->fired[numevents].fd = j;
            eventLoop->fired[numevents].mask = mask;
            numevents++;
        }
    }
    return numevents;
}

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