redis启动过程源码解析

  redis整个程序的入口函数在server.c中的main函数,函数调用关系如下图1,调用顺序为从上到下,从左至右。

图1 redis启动函数调用图

  main函数源码如下,1-55行根据配置文件和启动命令参数设置全局对象server ,57-59设置redis的服务器端为后台进程, initServer主要提前创建一些经常用到的对象用于节约内存,根据设置的ip地址和端口创建监听套接字用于客户端连接,并初始化时间事件,64行用于设置server->el ->beforesleep = beforesleep,aeMain函数是个循环函数,用于监听客户端连接，接收客户端命令并进行处理等。

//整个程序的入口函数
int main(int argc, char **argv) {
    //初始化服务器配置,设置全局对象server的状态
    initServerConfig();

    /* Store the executable path and arguments in a safe place in order
     * to be able to restart the server later. */
    //存储运行命令的绝对路径及运行参数
    server.executable = getAbsolutePath(argv[0]);
    server.exec_argv = zmalloc(sizeof(char*)*(argc+1));
    server.exec_argv[argc] = NULL;
    for (j = 0; j < argc; j++) server.exec_argv[j] = zstrdup(argv[j]);

    if (argc >= 2) {
        j = 1; /* First option to parse in argv[] */
        sds options = sdsempty();
        char *configfile = NULL;

        //命令指定了配置文件,对配置文件做处理,配置文件跟在程序名后第一位
        /* First argument is the config file name? */
        if (argv[j][0] != '-' || argv[j][1] != '-') {
            configfile = argv[j];
            server.configfile = getAbsolutePath(configfile);
            /* Replace the config file in server.exec_argv with
             * its absolute path. */
            zfree(server.exec_argv[j]);
            server.exec_argv[j] = zstrdup(server.configfile);
            j++;
        }

        /* All the other options are parsed and conceptually appended to the
         * configuration file. For instance --port 6380 will generate the
         * string "port 6380
" to be parsed after the actual file name
         * is parsed, if any. */
        while(j != argc) {//解析除配置文件外的其它参数
            if (argv[j][0] == '-' && argv[j][1] == '-') {
                /* Option name */
                if (!strcmp(argv[j], "--check-rdb")) {
                    /* Argument has no options, need to skip for parsing. */
                    j++;
                    continue;
                }
                if (sdslen(options)) options = sdscat(options,"
");
                options = sdscat(options,argv[j]+2);//去掉参数前面的--
                options = sdscat(options," ");//参数对应的值和参数名应" "分隔
            } else {
                /* Option argument */
                options = sdscatrepr(options,argv[j],strlen(argv[j]));
                options = sdscat(options," ");
            }
            j++;
        }
        //从指定配置文件和命令选项设置服务器对象server参数,覆盖默认配置
        loadServerConfig(configfile,options);
    }

    server.supervised = redisIsSupervised(server.supervised_mode);
    int background = server.daemonize && !server.supervised;
    if (background) daemonize();//后台进程模式

    //初始化服务器功能,包括时间事件1ms调用serverCron,文件事件(套接字可读可写时的处理函数)，集群初始化等
    initServer();
    aeSetBeforeSleepProc(server.el,beforeSleep);//设置beforeSleep事件处理函数
    aeSetAfterSleepProc(server.el,afterSleep);//设置aftersleep事件处理函数
    aeMain(server.el);//循环,接受客户端连接,处理命令等
    aeDeleteEventLoop(server.el);//退出循环,删除事件处理
    return 0;
}

  initServer函数源码如下,主要对server中的变量进行初始化,其中listenToPort根据监听的地址和端口, 设置server.ipfd(监听套接字数组)和server.ipfd_count(监听套接字数目),85行aeCreateTimeEvent设置定时器事件,每1ms执行serverCron函数,94行aeCreateFileEvent函数设置监听套接字有客户端连接时执行的事件处理函数acceptTcpHandler。

void initServer(void) {
    int j;
    server.hz = server.config_hz;
    server.pid = getpid();
    server.current_client = NULL;
    server.clients = listCreate();
    server.clients_index = raxNew();
    server.clients_to_close = listCreate();
    server.slaves = listCreate();
    server.monitors = listCreate();
    server.clients_pending_write = listCreate();
    server.slaveseldb = -1; /* Force to emit the first SELECT command. */
    server.unblocked_clients = listCreate();
    server.ready_keys = listCreate();
    server.clients_waiting_acks = listCreate();
    server.get_ack_from_slaves = 0;
    server.clients_paused = 0;
    server.system_memory_size = zmalloc_get_memory_size();
    //创建常用字符串,比如命令回复pong及命令字符串等
    createSharedObjects();
    //根据配置的最大连接客户端数和CONFIG_MIN_RESERVED_FDS(用于监听、日志文件等文件描述符)设置最大允许打开的文件描述符数
    adjustOpenFilesLimit();
    //初始化aeEventLoop对象并赋值给server中的指针变量el
    server.el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR);
    server.db = zmalloc(sizeof(redisDb)*server.dbnum);

    /* Open the TCP listening socket for the user commands. */
    //用于创建监听文件描述符
    if (server.port != 0 &&
        listenToPort(server.port,server.ipfd,&server.ipfd_count) == C_ERR)
        exit(1);

    /* Create the Redis databases, and initialize other internal state. */
    for (j = 0; j < server.dbnum; j++) {
        server.db[j].dict = dictCreate(&dbDictType,NULL);
        server.db[j].expires = dictCreate(&keyptrDictType,NULL);
        server.db[j].blocking_keys = dictCreate(&keylistDictType,NULL);
        server.db[j].ready_keys = dictCreate(&objectKeyPointerValueDictType,NULL);
        server.db[j].watched_keys = dictCreate(&keylistDictType,NULL);
        server.db[j].id = j;
        server.db[j].avg_ttl = 0;
        server.db[j].defrag_later = listCreate();
    }
    //创建lru池,内存超过设置的值时,根据淘汰策略,清除部分key
    evictionPoolAlloc(); /* Initialize the LRU keys pool. */
    server.pubsub_channels = dictCreate(&keylistDictType,NULL);
    server.pubsub_patterns = listCreate();
    listSetFreeMethod(server.pubsub_patterns,freePubsubPattern);
    listSetMatchMethod(server.pubsub_patterns,listMatchPubsubPattern);
    server.cronloops = 0;
    server.rdb_child_pid = -1;
    server.aof_child_pid = -1;
    server.rdb_child_type = RDB_CHILD_TYPE_NONE;
    server.rdb_bgsave_scheduled = 0;
    server.child_info_pipe[0] = -1;
    server.child_info_pipe[1] = -1;
    server.child_info_data.magic = 0;
    aofRewriteBufferReset();
    server.aof_buf = sdsempty();
    server.lastsave = time(NULL); /* At startup we consider the DB saved. */
    server.lastbgsave_try = 0;    /* At startup we never tried to BGSAVE. */
    server.rdb_save_time_last = -1;
    server.rdb_save_time_start = -1;
    server.dirty = 0;
    resetServerStats();
    /* A few stats we don't want to reset: server startup time, and peak mem. */
    server.stat_starttime = time(NULL);
    server.stat_peak_memory = 0;
    server.stat_rdb_cow_bytes = 0;
    server.stat_aof_cow_bytes = 0;
    server.cron_malloc_stats.zmalloc_used = 0;
    server.cron_malloc_stats.process_rss = 0;
    server.cron_malloc_stats.allocator_allocated = 0;
    server.cron_malloc_stats.allocator_active = 0;
    server.cron_malloc_stats.allocator_resident = 0;
    server.lastbgsave_status = C_OK;
    server.aof_last_write_status = C_OK;
    server.aof_last_write_errno = 0;
    server.repl_good_slaves_count = 0;

    /* Create the timer callback, this is our way to process many background
     * operations incrementally, like clients timeout, eviction of unaccessed
     * expired keys and so forth. */
    //创建时间事件,1ms调用serverCron
    if (aeCreateTimeEvent(server.el, 1, serverCron, NULL, NULL) == AE_ERR) {
        serverPanic("Can't create event loop timers.");
        exit(1);
    }

    /* Create an event handler for accepting new connections in TCP and Unix
     * domain sockets. */
    //设定套接字可读可写状态的处理函数
    for (j = 0; j < server.ipfd_count; j++) {
        if (aeCreateFileEvent(server.el, server.ipfd[j], AE_READABLE,
            acceptTcpHandler,NULL) == AE_ERR)
            {
                serverPanic(
                    "Unrecoverable error creating server.ipfd file event.");
            }
    }
}

  listenToPort函数会对所有配置需要监听的ip地址和端口调用_anetTcpServer函数(anet.c), _anetTcpServer函数源码如下,1-17行建立socket套接字s,23行调用函数anetListen完成服务端socket的bind和listen。

static int _anetTcpServer(char *err, int port, char *bindaddr, int af, int backlog)
{
    int s = -1, rv;
    char _port[6];  /* strlen("65535") */
    struct addrinfo hints, *servinfo, *p;
    snprintf(_port,6,"%d",port);
    memset(&hints,0,sizeof(hints));
    hints.ai_family = af;
    hints.ai_socktype = SOCK_STREAM;
    hints.ai_flags = AI_PASSIVE;    /* No effect if bindaddr != NULL */

    if ((rv = getaddrinfo(bindaddr,_port,&hints,&servinfo)) != 0) {
        anetSetError(err, "%s", gai_strerror(rv));
        return ANET_ERR;
    }
    for (p = servinfo; p != NULL; p = p->ai_next) {
        if ((s = socket(p->ai_family,p->ai_socktype,p->ai_protocol)) == -1)
            continue;

        if (af == AF_INET6 && anetV6Only(err,s) == ANET_ERR) goto error;
        if (anetSetReuseAddr(err,s) == ANET_ERR) goto error;
        //anetListen调用listen和bind
        if (anetListen(err,s,p->ai_addr,p->ai_addrlen,backlog) == ANET_ERR) s = ANET_ERR;
        goto end;
    }
    if (p == NULL) {
        anetSetError(err, "unable to bind socket, errno: %d", errno);
        goto error;
    }

error:
    if (s != -1) close(s);
    s = ANET_ERR;
end:
    freeaddrinfo(servinfo);
    return s;
}

  anetListen函数源码如下:

static int anetListen(char *err, int s, struct sockaddr *sa, socklen_t len, int backlog) {
    if (bind(s,sa,len) == -1) {
        anetSetError(err, "bind: %s", strerror(errno));
        close(s);
        return ANET_ERR;
    }

    if (listen(s, backlog) == -1) {
        anetSetError(err, "listen: %s", strerror(errno));
        close(s);
        return ANET_ERR;
    }
    return ANET_OK;
}

  在分析aeCreateTimeEvent和aeCreateFileEvent函数之前,先给出server中的aeEventLoop类型变量el结构体定义(ae.h):

/* File event structure */
//文件事件结构体
typedef struct aeFileEvent {
    ////读或者写，也用于标识该事件结构体是否正在使用
    int mask; /* one of AE_(READABLE|WRITABLE|BARRIER) */
    //读事件的处理函数
    aeFileProc *rfileProc;
    //写事件的处理函数
    aeFileProc *wfileProc;
    //传递给上述两个函数的数据
    void *clientData;
} aeFileEvent;

/* Time event structure */
//时间事件
typedef struct aeTimeEvent {
    //时间事件标识符，用于唯一标识该时间事件，并且用于删除时间事件
    long long id; /* time event identifier. */
    long when_sec; /* seconds */
    long when_ms; /* milliseconds */
    //事件对应的处理程序
    aeTimeProc *timeProc;
    //时间事件的最后一次处理程序，若已设置，则删除时间事件时会被调用
    aeEventFinalizerProc *finalizerProc;
    void *clientData;
    struct aeTimeEvent *prev;
    struct aeTimeEvent *next;
} aeTimeEvent;

/* A fired event */
//用于保存已触发的事件
typedef struct aeFiredEvent {
    int fd;
    int mask;
} aeFiredEvent;

/* State of an event based program */
typedef struct aeEventLoop {
    //最大文件描述符
    int maxfd;   /* highest file descriptor currently registered */
    //文件描述符的最大监听数
    int setsize; /* max number of file descriptors tracked */
    //生成时间事件的唯一标识
    long long timeEventNextId;
    //检测系统时钟偏差
    time_t lastTime;     /* Used to detect system clock skew */
    //双向链表,注册文件事件
    aeFileEvent *events; /* Registered events */
    //已触发的文件事件
    aeFiredEvent *fired; /* Fired events */
    //注册的时间事件
    aeTimeEvent *timeEventHead;
    int stop;
    //处理底层特定API的数据，对于epoll来说，该结构体包含了epoll fd和epoll_event
    void *apidata; /* This is used for polling API specific data */
    aeBeforeSleepProc *beforesleep;
    aeBeforeSleepProc *aftersleep;
} aeEventLoop;

  函数aeCreateTimeEvent(ae.c)用于往server中的变量el时间事件队列添加元素,源码如下:

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;
    if (te->next)
        te->next->prev = te;
    eventLoop->timeEventHead = te;
    return id;
}

  aeCreateFileEvent(ae.c)函数用于server.el增加文件事件队列添加元素,源码如下:

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;
}

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;
}

  执行完initServer及aeSetBeforeSleepProc和aeSetAfterSleepProc函数设置好全局变量server后,进程调用aeMain函数进入循环,开始接收客户端连接和命令交互。aeMain(ae.c)函数源码如下:

//处理客户端命令的主函数，由main函数调用,aeEventLoop定义在(ae.h),beforesleep和aftersleep均在服务器启动初始化时设定
void aeMain(aeEventLoop *eventLoop) {
    eventLoop->stop = 0;
    while (!eventLoop->stop) {
        if (eventLoop->beforesleep != NULL)
            eventLoop->beforesleep(eventLoop);
        //处理文件时间及时间事件
        aeProcessEvents(eventLoop, AE_ALL_EVENTS|AE_CALL_AFTER_SLEEP);
    }
}