Redis（一）：服务启动及基础请求处理流程源码解析

最新推荐文章于 2024-03-30 15:36:39 发布

Java后端架构V

最新推荐文章于 2024-03-30 15:36:39 发布

阅读量307

点赞数

分类专栏： Java 架构文章标签：架构 java redis 微服务架构

本文链接：https://blog.csdn.net/pisa8559/article/details/112154718

版权

Java 同时被 2 个专栏收录

179 篇文章 5 订阅

订阅专栏

架构

38 篇文章 0 订阅

订阅专栏

本文详细解析Redis服务启动过程，包括main函数入口、服务器初始化和主循环服务。主要内容包括配置文件加载、初始化服务器、恢复数据、设置回调函数、启动监听等。文章深入探讨了关键函数如aeEventLoop的创建、acceptTcpHandler和bioInit，并概述了主循环服务中的aeProcessEvents和beforeSleep函数。最后，通过UML时序图帮助理解整个流程。

摘要由CSDN通过智能技术生成

redis是用c语言的写的缓存服务器，有高性能和多种数据类型支持的特性，广受互联网公司喜爱。

　　我们要分析其启动过程，首先就要先找到其入口。

　　当然我们应该是要先分析 Makefile 文件，然后找到最终编译成的文件，然后再顺势找到C语言入口 main(); 这里咱们就不费那事了，一是这事很枯燥，二是我也不知道找不找到得到。所以，就直接找到入口吧: 在 src/server.c 中，main() 函数就是了。

引用网上大牛的话归纳一下，main 函数执行的过程分以下几步：

1. Redis 会设置一些回调函数，当前时间，随机数的种子。回调函数实际上什么？举个例子，比如 Q/3 要给 Redis 发送一个关闭的命令，让它去做一些优雅的关闭，做一些扫尾清楚的工作，这个工作如果不设计回调函数，它其实什么都不会干。其实 C 语言的程序跑在操作系统之上，Linux 操作系统本身就是提供给我们事件机制的回调注册功能，所以它会设计这个回调函数，让你注册上，关闭的时候优雅的关闭，然后它在后面可以做一些业务逻辑。
2. 不管任何软件，肯定有一份配置文件需要配置。首先在服务器端会把它默认的一份配置做一个初始化。
3. Redis 在 3.0 版本正式发布之前其实已经有筛选这个模式了，但是这个模式，我很少在生产环境在用。Redis 可以初始化这个模式，比较复杂。
4. 解析启动的参数。其实不管什么软件，它在初始化的过程当中，配置都是由两部分组成的。第一部分，静态的配置文件；第二部分，动态启动的时候，main，就是参数给它的时候进去配置。
5. 把服务端的东西拿过来，装载 Config 配置文件，loadServerConfig。
6. 初始化服务器，initServer。
7. 从磁盘装载数据。
8. 有一个主循环程序开始干活，用来处理客户端的请求，并且把这个请求转到后端的业务逻辑，帮你完成命令执行，然后吐数据，这么一个过程。

我们以源码浏览形式，来看看具体实现。

main 函数入口：

　　注意 server 是一个全局变量，各函数进行操作时，都直接对其操作。

// struct redisServer server; 
// src/server.c    
int main(int argc, char **argv) {
    struct timeval tv;
    int j;
// 测试环境变量设置
#ifdef REDIS_TEST
    if (argc == 3 && !strcasecmp(argv[1], "test")) {
        if (!strcasecmp(argv[2], "ziplist")) {
            return (argc, argv);
        } else if (!strcasecmp(argv[2], "quicklist")) {
            quicklistTest(argc, argv);
        } else if (!strcasecmp(argv[2], "intset")) {
            return intsetTest(argc, argv);
        } else if (!strcasecmp(argv[2], "zipmap")) {
            return zipmapTest(argc, argv);
        } else if (!strcasecmp(argv[2], "sha1test")) {
            return sha1Test(argc, argv);
        } else if (!strcasecmp(argv[2], "util")) {
            return utilTest(argc, argv);
        } else if (!strcasecmp(argv[2], "sds")) {
            return sdsTest(argc, argv);
        } else if (!strcasecmp(argv[2], "endianconv")) {
            return endianconvTest(argc, argv);
        } else if (!strcasecmp(argv[2], "crc64")) {
            return crc64Test(argc, argv);
        }

        return -1; /* test not found */
    }
#endif

    /* We need to initialize our libraries, and the server configuration. */
#ifdef INIT_SETPROCTITLE_REPLACEMENT
    spt_init(argc, argv)ziplistTest;
#endif
    // 设置些默认值, 随机数等等
    setlocale(LC_COLLATE,"");
    zmalloc_enable_thread_safeness();
    // oom 回调处理
    zmalloc_set_oom_handler(redisOutOfMemoryHandler);
    srand(time(NULL)^getpid());    
    gettimeofday(&tv,NULL);
    dictSetHashFunctionSeed(tv.tv_sec^tv.tv_usec^getpid());
    server.sentinel_mode = checkForSentinelMode(argc,argv);
    // 初始化服务器默认配置, 将变化体现到 server 变量上
    initServerConfig();

    /* Store the executable path and arguments in a safe place in order
     * to be able to restart the server later. */
    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]);

    /* We need to init sentinel right now as parsing the configuration file
     * in sentinel mode will have the effect of populating the sentinel
     * data structures with master nodes to monitor. */
    if (server.sentinel_mode) {
        initSentinelConfig();
        initSentinel();
    }

    // 加载配置文件及其他命令
    /* Check if we need to start in redis-check-rdb mode. We just execute
     * the program main. However the program is part of the Redis executable
     * so that we can easily execute an RDB check on loading errors. */
    if (strstr(argv[0],"redis-check-rdb") != NULL)
        exit(redis_check_rdb_main(argv,argc));

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

        /* Handle special options --help and --version */
        if (strcmp(argv[1], "-v") == 0 ||
            strcmp(argv[1], "--version") == 0) version();
        if (strcmp(argv[1], "--help") == 0 ||
            strcmp(argv[1], "-h") == 0) usage();
        if (strcmp(argv[1], "--test-memory") == 0) {
            if (argc == 3) {
                memtest(atoi(argv[2]),50);
                exit(0);
            } else {
                fprintf(stderr,"Please specify the amount of memory to test in megabytes.\n");
                fprintf(stderr,"Example: ./redis-server --test-memory 4096\n\n");
                exit(1);
            }
        }

        /* 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 absoulte 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\n" to be parsed after the actual file name
         * is parsed, if any. */
        while(j != argc) {
            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,"\n");
                options = sdscat(options,argv[j]+2);
                options = sdscat(options," ");
            } else {
                /* Option argument */
                options = sdscatrepr(options,argv[j],strlen(argv[j]));
                options = sdscat(options," ");
            }
            j++;
        }
        if (server.sentinel_mode && configfile && *configfile == '-') {
            serverLog(LL_WARNING,
                "Sentinel config from STDIN not allowed.");
            serverLog(LL_WARNING,
                "Sentinel needs config file on disk to save state.  Exiting...");
            exit(1);
        }
        resetServerSaveParams();
        loadServerConfig(configfile,options);
        sdsfree(options);
    } else {
        serverLog(LL_WARNING, "Warning: no config file specified, using the default config. In order to specify a config file use %s /path/to/%s.conf", argv[0], server.sentinel_mode ? "sentinel" : "redis");
    }

    server.supervised = redisIsSupervised(server.supervised_mode);
    int background = server.daemonize && !server.supervised;
    if (background) daemonize();

    // 初始化服务器
    // 重点如: 绑定监听端口号，设置 acceptTcpHandler 回调函数
    initServer();
    if (background || server.pidfile) createPidFile();
    redisSetProcTitle(argv[0]);
    redisAsciiArt();
    checkTcpBacklogSettings();

    if (!server.sentinel_mode) {
        /* Things not needed when running in Sentinel mode. */
        serverLog(LL_WARNING,"Server started, Redis version " REDIS_VERSION);
    #ifdef __linux__
        linuxMemoryWarnings();
    #endif
        // 从磁盘装载数据进行恢复或者初始化
        loadDataFromDisk();
        if (server.cluster_enabled) {
            if (verifyClusterConfigWithData() == C_ERR) {
                serverLog(LL_WARNING,
                    "You can't have keys in a DB different than DB 0 when in "
                    "Cluster mode. Exiting.");
                exit(1);
            }
        }
        if (server.ipfd_count > 0)
            serverLog(LL_NOTICE,"The server is now ready to accept connections on port %d", server.port);
        if (server.sofd > 0)
            serverLog(LL_NOTICE,"The server is now ready to accept connections at %s", server.unixsocket);
    } else {
        sentinelIsRunning();
    }

    /* Warning the user about suspicious maxmemory setting. */
    if (server.maxmemory > 0 && server.maxmemory < 1024*1024) {
        serverLog(LL_WARNING,"WARNING: You specified a maxmemory value that is less than 1MB (current value is %llu bytes). Are you sure this is what you really want?", server.maxmemory);
    }
    // 主循环服务, 只有收到 stop 命令后，才会退出
    aeSetBeforeSleepProc(server.el,beforeSleep);
    aeMain(server.el);
    // 关闭服务
    aeDeleteEventLoop(server.el);
    return 0;
}

如上，即是redis的整个main方法了，整个启动流程也算是一目了然了。大概流程也不出预料，环境设置、默认参数、配置文件加载、初始化服务、恢复数据、死循环。

　　配置参数什么的都不用瞅了，但是对于哨兵、集群什么的，又太深入了。咱们还是先蜻蜓点水下，主要看年初始化服务器的时候做了些啥事！

初始化服务器：

// src/server.c, 在main中调用
void initServer(void) {
    int j;
    // 注册几个事件响应处理器，比如前台模式运行或者调试模式的处理
    signal(SIGHUP, SIG_IGN);
    signal(SIGPIPE, SIG_IGN);
    setupSignalHandlers();

    if (server.syslog_enabled) {
        openlog(server.syslog_ident, LOG_PID | LOG_NDELAY | LOG_NOWAIT,
            server.syslog_facility);
    }

    // 初始化客户端相关的参数，设置到 server 中
    server.pid = getpid();
    server.current_client = NULL;
    server.clients = listCreate();
    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();
    // 全局共享对象, 比如 OK, 1-10000, ...
    // 性能优化, 避免对相同的对象反复创建
    createSharedObjects();
    adjustOpenFilesLimit();
    // 创建事件循环对象 (aeEventLoop), 在 ae.c 中实现
    server.el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR);
    // 创建db对象，所有数据存储其中
    server.db = zmalloc(sizeof(redisDb)*server.dbnum);

    /* Open the TCP listening socket for the user commands. */
    // 打开服务端口监听
    if (server.port != 0 &&
        listenToPort(server.port,server.ipfd,&server.ipfd_count) == C_ERR)
        exit(1);

    /* Open the listening Unix domain socket. */
    if (server.unixsocket != NULL) {
        unlink(server.unixsocket); /* don't care if this fails */
        server.sofd = anetUnixServer(server.neterr,server.unixsocket,
            server.unixsocketperm, server.tcp_backlog);
        if (server.sofd == ANET_ERR) {
            serverLog(LL_WARNING, "Opening Unix socket: %s", server.neterr);
            exit(1);
        }
        anetNonBlock(NULL,server.sofd);
    }

    /* Abort if there are no listening sockets at all. */
    if (server.ipfd_count == 0 && server.sofd < 0) {
        serverLog(LL_WARNING, "Configured to not listen anywhere, exiting.");
        exit(1);
    }

    /* Create the Redis databases, and initialize other internal state. */
    // 初始化各db，实际就是由这么几个数组来动作db的
    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].eviction_pool = evictionPoolAlloc();
        server.db[j].id = j;
        server.db[j].avg_ttl = 0;
    }
    // pub/sub 参数初始化
    server.pubsub_channels = dictCreate(&keylistDictType,NULL);
    server.pubsub_patterns = listCreate();
    listSetFreeMethod(server.pubsub_patterns,freePubsubPattern);
    listSetMatchMethod(server.pubsub_patterns,listMatchPubsubPattern);
    server.cronloops = 0;
    // rdb,aof 参数初始化
    server.rdb_child_pid = -1;
    server.aof_child_pid = -1;
    server.rdb_child_type = RDB_CHILD_TYPE_NONE;
    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.resident_set_size = 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;
    updateCachedTime();

    /* Create out timers, that's our main way to process background
     * operations. */
    // 创建定时器，用于运行后台事务，每隔1s运行一次
    // 由 serverCron 承载任务，执行任务如 指标统计，操作日志持久化，db扩容,客户端管理...
    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. */
    // 创建socket文件监控, 由 acceptTcpHandler 承载处理
    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.");
            }
    }
    if (server.sofd > 0 && aeCreateFileEvent(server.el,server.sofd,AE_READABLE,
        acceptUnixHandler,NULL) == AE_ERR) serverPanic("Unrecoverable error creating server.sofd file event.");

    // 如果开启了AOF功能，就打开AOF文件
    /* Open the AOF file if needed. */
    if (server.aof_state == AOF_ON) {
        server.aof_fd = open(server.aof_filename,
                               O_WRONLY|O_APPEND|O_CREAT,0644);
        if (server.aof_fd == -1) {
            serverLog(LL_WARNING, "Can't open the append-only file: %s",
                strerror(errno));
            exit(1);
        }
    }

    /* 32 bit instances are limited to 4GB of address space, so if there is
     * no explicit limit in the user provided configuration we set a limit
     * at 3 GB using maxmemory with 'noeviction' policy'. This avoids
     * useless crashes of the Redis instance for out of memory. */
    if (server.arch_bits == 32 && server.maxmemory == 0) {
        serverLog(LL_WARNING,"Warning: 32 bit instance detected but no memory limit set. Setting 3 GB maxmemory limit with 'noeviction' policy now.");
        server.maxmemory = 3072LL*(1024*1024); /* 3 GB */
        server.maxmemory_policy = MAXMEMORY_NO_EVICTION;
    }
    
    if (server.cluster_enabled) clusterInit();
    replicationScriptCacheInit();
    // lua 脚本初始化
    scriptingInit(1);
    //     初始化慢查询日志变量
    slowlogInit();
    // 延迟监控初始化，仅创建变量
    latencyMonitorInit();
    // 初始化几个系统必须的线程（线程池），执行任务，while死循环
    bioInit();
}

通过以上，我们可以清楚明白，在初始化服务器时，高大上的C都干了啥。总体来说就是: 设置系统回调、开启端口监听、开启socket监听、开启后台任务、开启AOF、脚本初始化、线程池初始化。。。（做这些事是容易的，难的是设计之初如何架构其功能）

　　下面我们来看几个初始服务器时的关键函数方法。

1. aeEventLoop 的创建

　　aeEventLoop 是后续进行任务处理的重要数据结构。

// ae.c, 创建 aeEventLoop 对象，封装底层的 事件模式，统一对外服务
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;
    // 根据系统不同，选择不同的实现，C里面的多态自然是用 #ifdef 来实现了
    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;
}
// 选择不同的io模型, 优先级: evport > epoll > kqueue > select
#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
// epoll 实现
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;
}

// ae_epoll.c, linux 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;
}

2. acceptTcpHandler, 对于网络请求的接入处理

// networking.c, acceptTcpHandler
void acceptTcpHandler(aeEventLoop *el, int fd, void *privdata, int mask) {
    int cport, cfd, max = MAX_ACCEPTS_PER_CALL;
    char cip[NET_IP_STR_LEN];
    UNUSED(el);
    UNUSED(mask);
    UNUSED(privdata);

    while(max--) {
        // 获取fd, ip, port
        cfd = anetTcpAccept(server.neterr, fd, cip, sizeof(cip), &cport);
        if (cfd == ANET_ERR) {
            if (errno != EWOULDBLOCK)
                serverLog(LL_WARNING,
                    "Accepting client connection: %s", server.neterr);
            return;
        }
        serverLog(LL_VERBOSE,"Accepted %s:%d", cip, cport);
        // 创建客户端对象，加入到 server.clients 中
        acceptCommonHandler(cfd,0,cip);
    }
}
// anet.c, 解析 ip, port, fd
int anetTcpAccept(char *err, int s, char *ip, size_t ip_len, int *port) {
    int fd;
    struct sockaddr_storage sa;
    socklen_t salen = sizeof(sa);
    if ((fd = anetGenericAccept(err,s,(struct sockaddr*)&sa,&salen)) == -1)
        return ANET_ERR;

    if (sa.ss_family == AF_INET) {
        struct sockaddr_in *s = (struct sockaddr_in *)&sa;
        if (ip) inet_ntop(AF_INET,(void*)&(s->sin_addr),ip,ip_len);
        if (port) *port = ntohs(s->sin_port);
    } else {
        struct sockaddr_in6 *s = (struct sockaddr_in6 *)&sa;
        if (ip) inet_ntop(AF_INET6,(void*)&(s->sin6_addr),ip,ip_len);
        if (port) *port = ntohs(s->sin6_port);
    }
    return fd;
}
// anet.c, 调用系统函数获取 socket 数据
static int anetGenericAccept(char *err, int s, struct sockaddr *sa, socklen_t *len) {
    int fd;
    while(1) {
        fd = accept(s,sa,len);
        if (fd == -1) {
            if (errno == EINTR)
                continue;
            else {
                anetSetError(err, "accept: %s", strerror(errno));
                return ANET_ERR;
            }
        }
        break;
    }
    return fd;
}

3. bioInit 线程创建

// bio.c
/* Initialize the background system, spawning the thread. */
void bioInit(void) {
    pthread_attr_t attr;
    pthread_t thread;
    size_t stacksize;
    int j;

    /* Initialization of state vars and objects */
    for (j = 0; j < BIO_NUM_OPS; j++) {
        pthread_mutex_init(&bio_mutex[j],NULL);
        pthread_cond_init(&bio_newjob_cond[j],NULL);
        pthread_cond_init(&bio_step_cond[j],NULL);
        bio_jobs[j] = listCreate();
        bio_pending[j] = 0;
    }

    /* Set the stack size as by default it may be small in some system */
    pthread_attr_init(&attr);
    pthread_attr_getstacksize(&attr,&stacksize);
    if (!stacksize) stacksize = 1; /* The world is full of Solaris Fixes */
    while (stacksize < REDIS_THREAD_STACK_SIZE) stacksize *= 2;
    pthread_attr_setstacksize(&attr, stacksize);

    /* Ready to spawn our threads. We use the single argument the thread
     * function accepts in order to pass the job ID the thread is
     * responsible of. */
    for (j = 0; j < BIO_NUM_OPS; j++) {
        void *arg = (void*)(unsigned long) j;
        // bioProcessBackgroundJobs 用于执行线程任务
        if (pthread_create(&thread,&attr,bioProcessBackgroundJobs,arg) != 0) {
            serverLog(LL_WARNING,"Fatal: Can't initialize Background Jobs.");
            exit(1);
        }
        bio_threads[j] = thread;
    }
}

二、主循环服务

接下来我们看看另一个重要的流程，主循环服务。 redis作为一个存储服务，必定需要一直运行等待，这就是while死循环的应用了。在前面各种环境初始化完成后，进入while循环服务。

// src/ae.c 主循环服务
void aeMain(aeEventLoop *eventLoop) {
    eventLoop->stop = 0;
    // eventLoop 会被 acceptTcpHandler 进行数据填充
    // 此处 beforesleep 为外部初始化的 
    // aeSetBeforeSleepProc(), 设置 beforeSleep
    while (!eventLoop->stop) {
        if (eventLoop->beforesleep != NULL)
            eventLoop->beforesleep(eventLoop);
        // 由 aeProcessEvents 处理事件
        aeProcessEvents(eventLoop, AE_ALL_EVENTS);
    }
}

很简单，就做两件事: beforesleep, aeProcessEvents, 看起来 aeProcessEvents() 是个核对服务。我们可以先观察其行为。

1. aeProcessEvents, 处理各种事件(数据准备)

// ae.c
/* 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.
 *
 * 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;

        // 获取最近 timer事件, 用于判定是否有需要执行至少一个时间事件
        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 */
            }
        }
        // 获取等待事件
        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. */
            // 此处将会调用前面设置好的 acceptTcpHandler 服务
            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++;
        }
    }
    // 时间事件处理, serverCron 调用
    /* Check time events */
    if (flags & AE_TIME_EVENTS)
        processed += processTimeEvents(eventLoop);

    return processed; /* return the number of processed file/time events */
}
// ae_epoll.c, 调用系统底层, 获取网络就绪事件, 放入 eventLoop->fired 中
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;
            // 将系统事件类型转换为 redis 的事件类型
            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;
}

2. 主循环服务之 beforeSleep

　　beforeSleep是在进入 aeMain之前，直接绑定在 el 上的。是在主循环中进行检测的条件，但其承担了重要的作用，比如客户请求的命令解析和处理！

// server.c, beforeSleep
/* This function gets called every time Redis is entering the
 * main loop of the event driven library, that is, before to sleep
 * for ready file descriptors. */
void beforeSleep(struct aeEventLoop *eventLoop) {
    UNUSED(eventLoop);

    /* Call the Redis Cluster before sleep function. Note that this function
     * may change the state of Redis Cluster (from ok to fail or vice versa),
     * so it's a good idea to call it before serving the unblocked clients
     * later in this function. */
    if (server.cluster_enabled) clusterBeforeSleep();

    /* Run a fast expire cycle (the called function will return
     * ASAP if a fast cycle is not needed). */
    if (server.active_expire_enabled && server.masterhost == NULL)
        activeExpireCycle(ACTIVE_EXPIRE_CYCLE_FAST);

    /* Send all the slaves an ACK request if at least one client blocked
     * during the previous event loop iteration. */
    if (server.get_ack_from_slaves) {
        robj *argv[3];

        argv[0] = createStringObject("REPLCONF",8);
        argv[1] = createStringObject("GETACK",6);
        argv[2] = createStringObject("*",1); /* Not used argument. */
        replicationFeedSlaves(server.slaves, server.slaveseldb, argv, 3);
        decrRefCount(argv[0]);
        decrRefCount(argv[1]);
        decrRefCount(argv[2]);
        server.get_ack_from_slaves = 0;
    }

    /* Unblock all the clients blocked for synchronous replication
     * in WAIT. */
    if (listLength(server.clients_waiting_acks))
        processClientsWaitingReplicas();

    /* Try to process pending commands for clients that were just unblocked. */
    // 处理可用的客户端请求
    if (listLength(server.unblocked_clients))
        processUnblockedClients();
    // AOF刷盘服务
    /* Write the AOF buffer on disk */
    flushAppendOnlyFile(0);
    // 将一些被挂起的数据写入客户端socket中
    /* Handle writes with pending output buffers. */
    handleClientsWithPendingWrites();
}

// blocking.c, 处理被解阻塞的客户端连接, 顺便处理客户端请求
/* This function is called in the beforeSleep() function of the event loop
 * in order to process the pending input buffer of clients that were
 * unblocked after a blocking operation. */
void processUnblockedClients(void) {
    listNode *ln;
    client *c;

    while (listLength(server.unblocked_clients)) {
        ln = listFirst(server.unblocked_clients);
        serverAssert(ln != NULL);
        c = ln->value;
        listDelNode(server.unblocked_clients,ln);
        c->flags &= ~CLIENT_UNBLOCKED;

        /* Process remaining data in the input buffer, unless the client
         * is blocked again. Actually processInputBuffer() checks that the
         * client is not blocked before to proceed, but things may change and
         * the code is conceptually more correct this way. */
        if (!(c->flags & CLIENT_BLOCKED)) {
            if (c->querybuf && sdslen(c->querybuf) > 0) {
                processInputBuffer(c);
            }
        }
    }
}

// networking.c, 处理接收到的数据, 调起下游处理服务
void processInputBuffer(client *c) {
    server.current_client = c;
    /* Keep processing while there is something in the input buffer */
    while(sdslen(c->querybuf)) {
        /* Return if clients are paused. */
        if (!(c->flags & CLIENT_SLAVE) && clientsArePaused()) break;

        /* Immediately abort if the client is in the middle of something. */
        if (c->flags & CLIENT_BLOCKED) break;

        /* CLIENT_CLOSE_AFTER_REPLY closes the connection once the reply is
         * written to the client. Make sure to not let the reply grow after
         * this flag has been set (i.e. don't process more commands). */
        if (c->flags & CLIENT_CLOSE_AFTER_REPLY) break;

        /* Determine request type when unknown. */
        // 根据第一个字符是否是 *, 分为两种类型协议, 处理方式不同
        if (!c->reqtype) {
            if (c->querybuf[0] == '*') {
                c->reqtype = PROTO_REQ_MULTIBULK;
            } else {
                c->reqtype = PROTO_REQ_INLINE;
            }
        }

        if (c->reqtype == PROTO_REQ_INLINE) {
            if (processInlineBuffer(c) != C_OK) break;
        } else if (c->reqtype == PROTO_REQ_MULTIBULK) {
            if (processMultibulkBuffer(c) != C_OK) break;
        } else {
            serverPanic("Unknown request type");
        }

        /* Multibulk processing could see a <= 0 length. */
        if (c->argc == 0) {
            resetClient(c);
        } else {
            /* Only reset the client when the command was executed. */
            // 经过前面请求解析后，进入请求处理核心流程
            if (processCommand(c) == C_OK)
                resetClient(c);
        }
    }
    server.current_client = NULL;
}

// server.c, 根据网络模块解析好的客户端命令，进行相应的业务处理
/* If this function gets called we already read a whole
 * command, arguments are in the client argv/argc fields.
 * processCommand() execute the command or prepare the
 * server for a bulk read from the client.
 *
 * If C_OK is returned the client is still alive and valid and
 * other operations can be performed by the caller. Otherwise
 * if C_ERR is returned the client was destroyed (i.e. after QUIT). */
int processCommand(client *c) {
    /* The QUIT command is handled separately. Normal command procs will
     * go through checking for replication and QUIT will cause trouble
     * when FORCE_REPLICATION is enabled and would be implemented in
     * a regular command proc. */
    if (!strcasecmp(c->argv[0]->ptr,"quit")) {
        addReply(c,shared.ok);
        c->flags |= CLIENT_CLOSE_AFTER_REPLY;
        return C_ERR;
    }

    /* Now lookup the command and check ASAP about trivial error conditions
     * such as wrong arity, bad command name and so forth. */
    // 根据第一个参数 查找处理命令，在 server.c 的顶部有定义: redisCommandTable
    c->cmd = c->lastcmd = lookupCommand(c->argv[0]->ptr);
    if (!c->cmd) {
        flagTransaction(c);
        addReplyErrorFormat(c,"unknown command '%s'",
            (char*)c->argv[0]->ptr);
        return C_OK;
    } else if ((c->cmd->arity > 0 && c->cmd->arity != c->argc) ||
               (c->argc < -c->cmd->arity)) {
        flagTransaction(c);
        addReplyErrorFormat(c,"wrong number of arguments for '%s' command",
            c->cmd->name);
        return C_OK;
    }
    // 以下是一系列判断，是否符合命令执行前提
    /* Check if the user is authenticated */
    if (server.requirepass && !c->authenticated && c->cmd->proc != authCommand)
    {
        flagTransaction(c);
        addReply(c,shared.noautherr);
        return C_OK;
    }

    /* If cluster is enabled perform the cluster redirection here.
     * However we don't perform the redirection if:
     * 1) The sender of this command is our master.
     * 2) The command has no key arguments. */
    if (server.cluster_enabled &&
        !(c->flags & CLIENT_MASTER) &&
        !(c->flags & CLIENT_LUA &&
          server.lua_caller->flags & CLIENT_MASTER) &&
        !(c->cmd->getkeys_proc == NULL && c->cmd->firstkey == 0))
    {
        int hashslot;

        if (server.cluster->state != CLUSTER_OK) {
            flagTransaction(c);
            clusterRedirectClient(c,NULL,0,CLUSTER_REDIR_DOWN_STATE);
            return C_OK;
        } else {
            int error_code;
            clusterNode *n = getNodeByQuery(c,c->cmd,c->argv,c->argc,&hashslot,&error_code);
            if (n == NULL || n != server.cluster->myself) {
                flagTransaction(c);
                clusterRedirectClient(c,n,hashslot,error_code);
                return C_OK;
            }
        }
    }

    /* Handle the maxmemory directive.
     *
     * First we try to free some memory if possible (if there are volatile
     * keys in the dataset). If there are not the only thing we can do
     * is returning an error. */
    if (server.maxmemory) {
        int retval = freeMemoryIfNeeded();
        /* freeMemoryIfNeeded may flush slave output buffers. This may result
         * into a slave, that may be the active client, to be freed. */
        if (server.current_client == NULL) return C_ERR;

        /* It was impossible to free enough memory, and the command the client
         * is trying to execute is denied during OOM conditions? Error. */
        if ((c->cmd->flags & CMD_DENYOOM) && retval == C_ERR) {
            flagTransaction(c);
            addReply(c, shared.oomerr);
            return C_OK;
        }
    }

    /* Don't accept write commands if there are problems persisting on disk
     * and if this is a master instance. */
    if (((server.stop_writes_on_bgsave_err &&
          server.saveparamslen > 0 &&
          server.lastbgsave_status == C_ERR) ||
          server.aof_last_write_status == C_ERR) &&
        server.masterhost == NULL &&
        (c->cmd->flags & CMD_WRITE ||
         c->cmd->proc == pingCommand))
    {
        flagTransaction(c);
        if (server.aof_last_write_status == C_OK)
            addReply(c, shared.bgsaveerr);
        else
            addReplySds(c,
                sdscatprintf(sdsempty(),
                "-MISCONF Errors writing to the AOF file: %s\r\n",
                strerror(server.aof_last_write_errno)));
        return C_OK;
    }

    /* Don't accept write commands if there are not enough good slaves and
     * user configured the min-slaves-to-write option. */
    if (server.masterhost == NULL &&
        server.repl_min_slaves_to_write &&
        server.repl_min_slaves_max_lag &&
        c->cmd->flags & CMD_WRITE &&
        server.repl_good_slaves_count < server.repl_min_slaves_to_write)
    {
        flagTransaction(c);
        addReply(c, shared.noreplicaserr);
        return C_OK;
    }

    /* Don't accept write commands if this is a read only slave. But
     * accept write commands if this is our master. */
    if (server.masterhost && server.repl_slave_ro &&
        !(c->flags & CLIENT_MASTER) &&
        c->cmd->flags & CMD_WRITE)
    {
        addReply(c, shared.roslaveerr);
        return C_OK;
    }

    /* Only allow SUBSCRIBE and UNSUBSCRIBE in the context of Pub/Sub */
    if (c->flags & CLIENT_PUBSUB &&
        c->cmd->proc != pingCommand &&
        c->cmd->proc != subscribeCommand &&
        c->cmd->proc != unsubscribeCommand &&
        c->cmd->proc != psubscribeCommand &&
        c->cmd->proc != punsubscribeCommand) {
        addReplyError(c,"only (P)SUBSCRIBE / (P)UNSUBSCRIBE / PING / QUIT allowed in this context");
        return C_OK;
    }

    /* Only allow INFO and SLAVEOF when slave-serve-stale-data is no and
     * we are a slave with a broken link with master. */
    if (server.masterhost && server.repl_state != REPL_STATE_CONNECTED &&
        server.repl_serve_stale_data == 0 &&
        !(c->cmd->flags & CMD_STALE))
    {
        flagTransaction(c);
        addReply(c, shared.masterdownerr);
        return C_OK;
    }

    /* Loading DB? Return an error if the command has not the
     * CMD_LOADING flag. */
    if (server.loading && !(c->cmd->flags & CMD_LOADING)) {
        addReply(c, shared.loadingerr);
        return C_OK;
    }

    /* Lua script too slow? Only allow a limited number of commands. */
    if (server.lua_timedout &&
          c->cmd->proc != authCommand &&
          c->cmd->proc != replconfCommand &&
        !(c->cmd->proc == shutdownCommand &&
          c->argc == 2 &&
          tolower(((char*)c->argv[1]->ptr)[0]) == 'n') &&
        !(c->cmd->proc == scriptCommand &&
          c->argc == 2 &&
          tolower(((char*)c->argv[1]->ptr)[0]) == 'k'))
    {
        flagTransaction(c);
        addReply(c, shared.slowscripterr);
        return C_OK;
    }

    /* Exec the command */
    if (c->flags & CLIENT_MULTI &&
        c->cmd->proc != execCommand && c->cmd->proc != discardCommand &&
        c->cmd->proc != multiCommand && c->cmd->proc != watchCommand)
    {
        queueMultiCommand(c);
        addReply(c,shared.queued);
    } else {
        // 由 call 函数执行各自的 command
        call(c,CMD_CALL_FULL);
        c->woff = server.master_repl_offset;
        if (listLength(server.ready_keys))
            handleClientsBlockedOnLists();
    }
    return C_OK;
}

到此，整个redis的启动及简要的请求处理流程就完成了。

下面以两个UML来重新审视整个流程。

1. redisServer 初始化时序图