redis学习:redis启动流程分析

redis.c　主函数

  

• 初始化server的默认配置
• 如果服务器以sentinel模式开启，初始化sentinel的数据结构
• 解析参数
• 读取配置信息
• 初始化server
• 从rdb或aof中载入数据（优先选用aof）
• 开启事件循环

int main(int argc, char **argv) {
    struct timeval tv;

    /* We need to initialize our libraries, and the server configuration. */
    // 初始化库
#ifdef INIT_SETPROCTITLE_REPLACEMENT
    spt_init(argc, argv);
#endif
    setlocale(LC_COLLATE,"");
    zmalloc_enable_thread_safeness();
    zmalloc_set_oom_handler(redisOutOfMemoryHandler);
    srand(time(NULL)^getpid());
    gettimeofday(&tv,NULL);
    dictSetHashFunctionSeed(tv.tv_sec^tv.tv_usec^getpid());

    // 检查服务器是否以 Sentinel 模式启动
    server.sentinel_mode = checkForSentinelMode(argc,argv);//redis-sentinel

    // 初始化服务器，设置server的一些数据结构
    initServerConfig();

    /* 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. */
    // 如果服务器以 Sentinel 模式启动，那么进行 Sentinel 功能相关的初始化
    // 并为要监视的主服务器创建一些相应的数据结构
    if (server.sentinel_mode) {
        initSentinelConfig();
        initSentinel();
    }

    // 检查用户是否指定了配置文件，或者配置选项
    if (argc >= 2) {
        int j = 1; /* First option to parse in argv[] */
        sds options = sdsempty();
        char *configfile = NULL;

        /* Handle special options --help and --version */
        // 处理特殊选项 -h 、-v 和 --test-memory
        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? */
        // 如果第一个参数（argv[1]）不是以 "--" 开头
        // 那么它应该是一个配置文件
        if (argv[j][0] != '-' || argv[j][1] != '-')
            configfile = argv[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. */
        // 对用户给定的其余选项进行分析，并将分析所得的字符串追加稍后载入的配置文件的内容之后
        // 比如 --port 6380 会被分析为 "port 6380\n"
        while(j != argc) {
            if (argv[j][0] == '-' && argv[j][1] == '-') {
                /* Option name */
                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 (configfile) server.configfile = getAbsolutePath(configfile);
        // 重置保存条件
        resetServerSaveParams();

        // 载入配置文件， options 是前面分析出的给定选项
        loadServerConfig(configfile,options);
        sdsfree(options);

        // 获取配置文件的绝对路径
        if (configfile) server.configfile = getAbsolutePath(configfile);
    } else {
        redisLog(REDIS_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");
    }

    // 将服务器设置为守护进程
    if (server.daemonize) daemonize();

    // 创建并初始化服务器,很重要
    initServer();

    // 如果服务器是守护进程，那么创建 PID 文件
    if (server.daemonize) createPidFile();

    // 为服务器进程设置名字
    redisSetProcTitle(argv[0]);

    // 打印 ASCII LOGO
    redisAsciiArt();

    // 如果服务器不是运行在 SENTINEL 模式，那么执行以下代码
    if (!server.sentinel_mode) {
        /* Things not needed when running in Sentinel mode. */
        // 打印问候语
        redisLog(REDIS_WARNING,"Server started, Redis version " REDIS_VERSION);
    #ifdef __linux__
        // 打印内存警告
        linuxOvercommitMemoryWarning();
    #endif
        // 从 AOF 文件或者 RDB 文件中载入数据
        loadDataFromDisk();
        // 启动集群？
        if (server.cluster_enabled) {
            if (verifyClusterConfigWithData() == REDIS_ERR) {
                redisLog(REDIS_WARNING,
                    "You can't have keys in a DB different than DB 0 when in "
                    "Cluster mode. Exiting.");
                exit(1);
            }
        }
        // 打印 TCP 端口
        if (server.ipfd_count > 0)
            redisLog(REDIS_NOTICE,"The server is now ready to accept connections on port %d", server.port);
        // 打印本地套接字端口
        if (server.sofd > 0)
            redisLog(REDIS_NOTICE,"The server is now ready to accept connections at %s", server.unixsocket);
    } else {
        sentinelIsRunning();
    }

    /* Warning the user about suspicious maxmemory setting. */
    // 检查不正常的 maxmemory 配置
    if (server.maxmemory > 0 && server.maxmemory < 1024*1024) {
        redisLog(REDIS_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);
    }

    // 运行事件处理器，一直到服务器关闭为止
    aeSetBeforeSleepProc(server.el,beforeSleep);
    aeMain(server.el);

    // 服务器关闭，停止事件循环
    aeDeleteEventLoop(server.el);

    return 0;
}

initServer()函数

  主要执行的是:

• redisServer数据结构的初始化
• 添加serverCron的定时事件
• 如果开启aof，新建一个aof文件
• 如果开启cluster模式，初始化cluster模式相关的数据结构
• 初始化慢查日志

void initServer() {
    int j;

    // 设置信号处理函数
    signal(SIGHUP, SIG_IGN);
    signal(SIGPIPE, SIG_IGN);
    setupSignalHandlers();

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

    // 初始化并创建数据结构
    server.current_client = NULL;
    server.clients = listCreate();
    server.clients_to_close = listCreate();
    server.slaves = listCreate();
    server.monitors = 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;

    // 创建共享对象
    createSharedObjects();
    adjustOpenFilesLimit();
    server.el = aeCreateEventLoop(server.maxclients+REDIS_EVENTLOOP_FDSET_INCR);
    server.db = zmalloc(sizeof(redisDb)*server.dbnum);

    /* Open the TCP listening socket for the user commands. */
    // 打开 TCP 监听端口，用于等待客户端的命令请求
    if (server.port != 0 &&
        listenToPort(server.port,server.ipfd,&server.ipfd_count) == REDIS_ERR)
        exit(1);

    /* Open the listening Unix domain socket. */
    // 打开 UNIX 本地端口
    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) {
            redisLog(REDIS_WARNING, "Opening 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) {
        redisLog(REDIS_WARNING, "Configured to not listen anywhere, exiting.");
        exit(1);
    }

    /* Create the Redis databases, and initialize other internal state. */
    // 创建并初始化数据库结构
    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(&setDictType,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;
    }

    // 创建 PUBSUB 相关结构
    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;
    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 = REDIS_OK;
    server.aof_last_write_status = REDIS_OK;
    server.aof_last_write_errno = 0;
    server.repl_good_slaves_count = 0;
    updateCachedTime();

    /* Create the serverCron() time event, that's our main way to process
     * background operations. */
    // 为 serverCron() 创建时间事件
    if(aeCreateTimeEvent(server.el, 1, serverCron, NULL, NULL) == AE_ERR) {
        redisPanic("Can't create the serverCron time event.");
        exit(1);
    }

    /* Create an event handler for accepting new connections in TCP and Unix
     * domain sockets. */
    // 为 TCP 连接关联连接应答（accept）处理器
    // 用于接受并应答客户端的 connect() 调用
    for (j = 0; j < server.ipfd_count; j++) {
        if (aeCreateFileEvent(server.el, server.ipfd[j], AE_READABLE,
            acceptTcpHandler,NULL) == AE_ERR)
            {
                redisPanic(
                    "Unrecoverable error creating server.ipfd file event.");
            }
    }

    // 为本地套接字关联应答处理器
    if (server.sofd > 0 && aeCreateFileEvent(server.el,server.sofd,AE_READABLE,
        acceptUnixHandler,NULL) == AE_ERR) redisPanic("Unrecoverable error creating server.sofd file event.");

    /* Open the AOF file if needed. */
    // 如果 AOF 持久化功能已经打开，那么打开或创建一个 AOF 文件
    if (server.aof_state == REDIS_AOF_ON) {
        server.aof_fd = open(server.aof_filename,
                               O_WRONLY|O_APPEND|O_CREAT,0644);
        if (server.aof_fd == -1) {
            redisLog(REDIS_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. */
    // 对于 32 位实例来说，默认将最大可用内存限制在 3 GB
    if (server.arch_bits == 32 && server.maxmemory == 0) {
        redisLog(REDIS_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 = REDIS_MAXMEMORY_NO_EVICTION;
    }

    // 如果服务器以 cluster 模式打开，那么初始化 cluster
    if (server.cluster_enabled) clusterInit();

    // 初始化复制功能有关的脚本缓存
    replicationScriptCacheInit();

    // 初始化脚本系统
    scriptingInit();

    // 初始化慢查询功能
    slowlogInit();

    // 初始化 BIO 系统
    bioInit();
}

其中一个很重要的时间事件serverCron

  

• 更新时间缓存
• 更新lru缓存
• 记录内存峰值
• 关闭超时的client,clientCron();
• 删除过期的key,和数据库的渐进式rehash,databaseCron();
• 检查条件是否可以执行rdb,根据savepoint条件
• 检查是否可以执行aofRewrite
• 如果开启replicate,执行replicateCron()
• 如果开启cluster,执行clusterCron()
• 如果在sentinel模式下，sentinelTimer()
  

int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) {
    int j;
    REDIS_NOTUSED(eventLoop);
    REDIS_NOTUSED(id);
    REDIS_NOTUSED(clientData);

    /* Software watchdog: deliver the SIGALRM that will reach the signal
     * handler if we don't return here fast enough. */
    if (server.watchdog_period) watchdogScheduleSignal(server.watchdog_period);

    /* Update the time cache. */
    updateCachedTime();

    // 记录服务器执行命令的次数
    run_with_period(100) trackOperationsPerSecond();

    /* We have just REDIS_LRU_BITS bits per object for LRU information.
     * So we use an (eventually wrapping) LRU clock.
     *
     * Note that even if the counter wraps it's not a big problem,
     * everything will still work but some object will appear younger
     * to Redis. However for this to happen a given object should never be
     * touched for all the time needed to the counter to wrap, which is
     * not likely.
     *
     * 即使服务器的时间最终比 1.5 年长也无所谓，
     * 对象系统仍会正常运作，不过一些对象可能会比服务器本身的时钟更年轻。
     * 不过这要这个对象在 1.5 年内都没有被访问过，才会出现这种现象。
     *
     * Note that you can change the resolution altering the
     * REDIS_LRU_CLOCK_RESOLUTION define.
     *
     * LRU 时间的精度可以通过修改 REDIS_LRU_CLOCK_RESOLUTION 常量来改变。
     */
    server.lruclock = getLRUClock();

    /* Record the max memory used since the server was started. */
    // 记录服务器的内存峰值
    if (zmalloc_used_memory() > server.stat_peak_memory)
        server.stat_peak_memory = zmalloc_used_memory();

    /* Sample the RSS here since this is a relatively slow call. */
    server.resident_set_size = zmalloc_get_rss();

    /* We received a SIGTERM, shutting down here in a safe way, as it is
     * not ok doing so inside the signal handler. */
    // 服务器进程收到 SIGTERM 信号，关闭服务器
    if (server.shutdown_asap) {

        // 尝试关闭服务器
        if (prepareForShutdown(0) == REDIS_OK) exit(0);

        // 如果关闭失败，那么打印 LOG ，并移除关闭标识
        redisLog(REDIS_WARNING,"SIGTERM received but errors trying to shut down the server, check the logs for more information");
        server.shutdown_asap = 0;
    }

    /* Show some info about non-empty databases */
    // 打印数据库的键值对信息
    run_with_period(5000) {
        for (j = 0; j < server.dbnum; j++) {
            long long size, used, vkeys;

            // 可用键值对的数量
            size = dictSlots(server.db[j].dict);
            // 已用键值对的数量
            used = dictSize(server.db[j].dict);
            // 带有过期时间的键值对数量
            vkeys = dictSize(server.db[j].expires);

            // 用 LOG 打印数量
            if (used || vkeys) {
                redisLog(REDIS_VERBOSE,"DB %d: %lld keys (%lld volatile) in %lld slots HT.",j,used,vkeys,size);
                /* dictPrintStats(server.dict); */
            }
        }
    }

    /* Show information about connected clients */
    // 如果服务器没有运行在 SENTINEL 模式下，那么打印客户端的连接信息
    if (!server.sentinel_mode) {
        run_with_period(5000) {
            redisLog(REDIS_VERBOSE,
                "%lu clients connected (%lu slaves), %zu bytes in use",
                listLength(server.clients)-listLength(server.slaves),
                listLength(server.slaves),
                zmalloc_used_memory());
        }
    }

    /* We need to do a few operations on clients asynchronously. */
    // 检查客户端，关闭超时客户端，并释放客户端多余的缓冲区
    clientsCron();

    /* Handle background operations on Redis databases. */
    // 对数据库执行各种操作
    databasesCron();

    /* Start a scheduled AOF rewrite if this was requested by the user while
     * a BGSAVE was in progress. */
    // 如果 BGSAVE 和 BGREWRITEAOF 都没有在执行
    // 并且有一个 BGREWRITEAOF 在等待，那么执行 BGREWRITEAOF
    if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 &&
        server.aof_rewrite_scheduled)
    {
        rewriteAppendOnlyFileBackground();
    }

    /* Check if a background saving or AOF rewrite in progress terminated. */
    // 检查 BGSAVE 或者 BGREWRITEAOF 是否已经执行完毕
    if (server.rdb_child_pid != -1 || server.aof_child_pid != -1) {
        int statloc;
        pid_t pid;

        // 接收子进程发来的信号，非阻塞
        if ((pid = wait3(&statloc,WNOHANG,NULL)) != 0) {
            int exitcode = WEXITSTATUS(statloc);
            int bysignal = 0;
            
            if (WIFSIGNALED(statloc)) bysignal = WTERMSIG(statloc);

            // BGSAVE 执行完毕
            if (pid == server.rdb_child_pid) {
                backgroundSaveDoneHandler(exitcode,bysignal);

            // BGREWRITEAOF 执行完毕
            } else if (pid == server.aof_child_pid) {
                backgroundRewriteDoneHandler(exitcode,bysignal);

            } else {
                redisLog(REDIS_WARNING,
                    "Warning, detected child with unmatched pid: %ld",
                    (long)pid);
            }
            updateDictResizePolicy();
        }
    } else {

        /* If there is not a background saving/rewrite in progress check if
         * we have to save/rewrite now */
        // 既然没有 BGSAVE 或者 BGREWRITEAOF 在执行，那么检查是否需要执行它们

        // 遍历所有保存条件，看是否需要执行 BGSAVE 命令
         for (j = 0; j < server.saveparamslen; j++) {
            struct saveparam *sp = server.saveparams+j;

            /* Save if we reached the given amount of changes,
             * the given amount of seconds, and if the latest bgsave was
             * successful or if, in case of an error, at least
             * REDIS_BGSAVE_RETRY_DELAY seconds already elapsed. */
            // 检查是否有某个保存条件已经满足了
            if (server.dirty >= sp->changes &&
                server.unixtime-server.lastsave > sp->seconds &&
                (server.unixtime-server.lastbgsave_try >
                 REDIS_BGSAVE_RETRY_DELAY ||
                 server.lastbgsave_status == REDIS_OK))
            {
                redisLog(REDIS_NOTICE,"%d changes in %d seconds. Saving...",
                    sp->changes, (int)sp->seconds);
                // 执行 BGSAVE
                rdbSaveBackground(server.rdb_filename);
                break;
            }
         }

         /* Trigger an AOF rewrite if needed */
        // 出发 BGREWRITEAOF
         if (server.rdb_child_pid == -1 &&
             server.aof_child_pid == -1 &&
             server.aof_rewrite_perc &&
             // AOF 文件的当前大小大于执行 BGREWRITEAOF 所需的最小大小
             server.aof_current_size > server.aof_rewrite_min_size)
         {
            // 上一次完成 AOF 写入之后，AOF 文件的大小
            long long base = server.aof_rewrite_base_size ?
                            server.aof_rewrite_base_size : 1;

            // AOF 文件当前的体积相对于 base 的体积的百分比
            long long growth = (server.aof_current_size*100/base) - 100;

            // 如果增长体积的百分比超过了 growth ，那么执行 BGREWRITEAOF
            if (growth >= server.aof_rewrite_perc) {
                redisLog(REDIS_NOTICE,"Starting automatic rewriting of AOF on %lld%% growth",growth);
                // 执行 BGREWRITEAOF
                rewriteAppendOnlyFileBackground();
            }
         }
    }

    // 根据 AOF 政策，
    // 考虑是否需要将 AOF 缓冲区中的内容写入到 AOF 文件中
    /* AOF postponed flush: Try at every cron cycle if the slow fsync
     * completed. */
    if (server.aof_flush_postponed_start) flushAppendOnlyFile(0);

    /* AOF write errors: in this case we have a buffer to flush as well and
     * clear the AOF error in case of success to make the DB writable again,
     * however to try every second is enough in case of 'hz' is set to
     * an higher frequency. */
    run_with_period(1000) {
        if (server.aof_last_write_status == REDIS_ERR)
            flushAppendOnlyFile(0);
    }

    /* Close clients that need to be closed asynchronous */
    // 关闭那些需要异步关闭的客户端
    freeClientsInAsyncFreeQueue();

    /* Clear the paused clients flag if needed. */
    clientsArePaused(); /* Don't check return value, just use the side effect. */

    /* Replication cron function -- used to reconnect to master and
     * to detect transfer failures. */
    // 复制函数
    // 重连接主服务器、向主服务器发送 ACK 、判断数据发送失败情况、断开本服务器超时的从服务器，等等
    run_with_period(1000) replicationCron();

    /* Run the Redis Cluster cron. */
    // 如果服务器运行在集群模式下，那么执行集群操作
    run_with_period(100) {
        if (server.cluster_enabled) clusterCron();
    }

    /* Run the Sentinel timer if we are in sentinel mode. */
    // 如果服务器运行在 sentinel 模式下，那么执行 SENTINEL 的主函数
    run_with_period(100) {
        if (server.sentinel_mode) sentinelTimer();
    }

    /* Cleanup expired MIGRATE cached sockets. */
    // 集群。。。TODO
    run_with_period(1000) {
        migrateCloseTimedoutSockets();
    }

    // 增加 loop 计数器
    server.cronloops++;

    return 1000/server.hz;
}