Redis 主从复制源码分析

  前置学习：Redis server启动源码-CSDN博客

1、RedisServer启动过程，首先初始化设置默认状态

 server.repl_state = REDIS_REPL_NONE;

2、Redis server初始化初始化了cluster和master的ip port等信息，并且触发连接事件，状态机置为

server.repl_state = REDIS_REPL_CONNECT;

主从复制需要用户自行配置，由以下三种方式：

通过主从复制命令完成

通过设置启动参数来完成

通过配置文件来完成 

3、主从握手阶段ping-->pong->auth，完成cluster ip、port、auth信息发送认证

3-1、cluster触发事件发送PING命令给master

3-2、cluster接受master返回的PONG命令，表示握手成功

3-3、cluster发起master身份认证，完成认证可以进入下一个阶段

syncWithMaster回调函数
    /* If we were connecting, it's time to send a non blocking PING, we want to
     * make sure the master is able to reply before going into the actual
     * replication process where we have long timeouts in the order of
     * seconds (in the meantime the slave would block). */
    // 如果状态为 CONNECTING ，那么在进行初次同步之前，
    // 向主服务器发送一个非阻塞的 PONG 
    // 因为接下来的 RDB 文件发送非常耗时，所以我们想确认主服务器真的能访问
    if (server.repl_state == REDIS_REPL_CONNECTING) {
        redisLog(REDIS_NOTICE,"Non blocking connect for SYNC fired the event.");
        /* Delete the writable event so that the readable event remains
         * registered and we can wait for the PONG reply. */
        // 手动发送同步 PING ，暂时取消监听写事件
        aeDeleteFileEvent(server.el,fd,AE_WRITABLE);
        // 更新状态
        server.repl_state = REDIS_REPL_RECEIVE_PONG;
        /* Send the PING, don't check for errors at all, we have the timeout
         * that will take care about this. */
        // 同步发送 PING
        syncWrite(fd,"PING\r\n",6,100);

        // 返回，等待 PONG 到达
        return;
    }

    /* Receive the PONG command. */
    // 接收 PONG 命令
    if (server.repl_state == REDIS_REPL_RECEIVE_PONG) {
        char buf[1024];

        /* Delete the readable event, we no longer need it now that there is
         * the PING reply to read. */
        // 手动同步接收 PONG ，暂时取消监听读事件
        aeDeleteFileEvent(server.el,fd,AE_READABLE);

        /* Read the reply with explicit timeout. */
        // 尝试在指定时间限制内读取 PONG
        buf[0] = '\0';
        // 同步接收 PONG
        if (syncReadLine(fd,buf,sizeof(buf),
            server.repl_syncio_timeout*1000) == -1)
        {
            redisLog(REDIS_WARNING,
                "I/O error reading PING reply from master: %s",
                strerror(errno));
            goto error;
        }

        /* We accept only two replies as valid, a positive +PONG reply
         * (we just check for "+") or an authentication error.
         * Note that older versions of Redis replied with "operation not
         * permitted" instead of using a proper error code, so we test
         * both. */
        // 接收到的数据只有两种可能：
        // 第一种是 +PONG ，第二种是因为未验证而出现的 -NOAUTH 错误
        if (buf[0] != '+' &&
            strncmp(buf,"-NOAUTH",7) != 0 &&
            strncmp(buf,"-ERR operation not permitted",28) != 0)
        {
            // 接收到未验证错误
            redisLog(REDIS_WARNING,"Error reply to PING from master: '%s'",buf);
            goto error;
        } else {
            // 接收到 PONG
            redisLog(REDIS_NOTICE,
                "Master replied to PING, replication can continue...");
        }
    }

    /* AUTH with the master if required. */
    // 进行身份验证
    if(server.masterauth) {
        err = sendSynchronousCommand(fd,"AUTH",server.masterauth,NULL);
        if (err[0] == '-') {
            redisLog(REDIS_WARNING,"Unable to AUTH to MASTER: %s",err);
            sdsfree(err);
            goto error;
        }
        sdsfree(err);
    }

4、主从复制模式，全量复制还是增量复制

slaveTryPartialResynchronization决定使用增量复制还是全量复制
int slaveTryPartialResynchronization(int fd) {
    char *psync_runid;
    char psync_offset[32];
    sds reply;

    /* Initially set repl_master_initial_offset to -1 to mark the current
     * master run_id and offset as not valid. Later if we'll be able to do
     * a FULL resync using the PSYNC command we'll set the offset at the
     * right value, so that this information will be propagated to the
     * client structure representing the master into server.master. */
    server.repl_master_initial_offset = -1;

    if (server.cached_master) {
        // 缓存存在，尝试部分重同步
        // 命令为 "PSYNC <master_run_id> <repl_offset>"
        psync_runid = server.cached_master->replrunid;
        snprintf(psync_offset,sizeof(psync_offset),"%lld", server.cached_master->reploff+1);
        redisLog(REDIS_NOTICE,"Trying a partial resynchronization (request %s:%s).", psync_runid, psync_offset);
    } else {
        // 缓存不存在
        // 发送 "PSYNC ? -1" ，要求完整重同步
        redisLog(REDIS_NOTICE,"Partial resynchronization not possible (no cached master)");
        psync_runid = "?";
        memcpy(psync_offset,"-1",3);
    }

    /* Issue the PSYNC command */
    // 向主服务器发送 PSYNC 命令
    reply = sendSynchronousCommand(fd,"PSYNC",psync_runid,psync_offset,NULL);

    // 接收到 FULLRESYNC ，进行 full-resync
    if (!strncmp(reply,"+FULLRESYNC",11)) {
        char *runid = NULL, *offset = NULL;

        /* FULL RESYNC, parse the reply in order to extract the run id
         * and the replication offset. */
        // 分析并记录主服务器的 run id
        runid = strchr(reply,' ');
        if (runid) {
            runid++;
            offset = strchr(runid,' ');
            if (offset) offset++;
        }
        // 检查 run id 的合法性
        if (!runid || !offset || (offset-runid-1) != REDIS_RUN_ID_SIZE) {
            redisLog(REDIS_WARNING,
                "Master replied with wrong +FULLRESYNC syntax.");
            /* This is an unexpected condition, actually the +FULLRESYNC
             * reply means that the master supports PSYNC, but the reply
             * format seems wrong. To stay safe we blank the master
             * runid to make sure next PSYNCs will fail. */
            // 主服务器支持 PSYNC ，但是却发来了异常的 run id
            // 只好将 run id 设为 0 ，让下次 PSYNC 时失败
            memset(server.repl_master_runid,0,REDIS_RUN_ID_SIZE+1);
        } else {
            // 保存 run id
            memcpy(server.repl_master_runid, runid, offset-runid-1);
            server.repl_master_runid[REDIS_RUN_ID_SIZE] = '\0';
            // 以及 initial offset
            server.repl_master_initial_offset = strtoll(offset,NULL,10);
            // 打印日志，这是一个 FULL resync
            redisLog(REDIS_NOTICE,"Full resync from master: %s:%lld",
                server.repl_master_runid,
                server.repl_master_initial_offset);
        }
        /* We are going to full resync, discard the cached master structure. */
        // 要开始完整重同步，缓存中的 master 已经没用了，清除它
        replicationDiscardCachedMaster();
        sdsfree(reply);
        
        // 返回状态
        return PSYNC_FULLRESYNC;
    }

    // 接收到 CONTINUE ，进行 partial resync
    if (!strncmp(reply,"+CONTINUE",9)) {
        /* Partial resync was accepted, set the replication state accordingly */
        redisLog(REDIS_NOTICE,
            "Successful partial resynchronization with master.");
        sdsfree(reply);
        // 将缓存中的 master 设为当前 master
        replicationResurrectCachedMaster(fd);

        // 返回状态
        return PSYNC_CONTINUE;
    }

    /* If we reach this point we receied either an error since the master does
     * not understand PSYNC, or an unexpected reply from the master.
     * Return PSYNC_NOT_SUPPORTED to the caller in both cases. */

    // 接收到错误？
    if (strncmp(reply,"-ERR",4)) {
        /* If it's not an error, log the unexpected event. */
        redisLog(REDIS_WARNING,
            "Unexpected reply to PSYNC from master: %s", reply);
    } else {
        redisLog(REDIS_NOTICE,
            "Master does not support PSYNC or is in "
            "error state (reply: %s)", reply);
    }
    sdsfree(reply);
    replicationDiscardCachedMaster();

    // 主服务器不支持 PSYNC
    return PSYNC_NOT_SUPPORTED;
}

回到syncWithMaster回调函数,psync_result保证了使用那种方式进行复制，并且过滤使用那种指令同步
psync_result = slaveTryPartialResynchronization(fd);

// 可以执行部分 resync
    if (psync_result == PSYNC_CONTINUE) {
        redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Master accepted a Partial Resynchronization.");
        // 返回
        return;
    }

    /* Fall back to SYNC if needed. Otherwise psync_result == PSYNC_FULLRESYNC
     * and the server.repl_master_runid and repl_master_initial_offset are
     * already populated. */
    // 主服务器不支持 PSYNC ，发送 SYNC
    if (psync_result == PSYNC_NOT_SUPPORTED) {
        redisLog(REDIS_NOTICE,"Retrying with SYNC...");
        // 向主服务器发送 SYNC 命令
        if (syncWrite(fd,"SYNC\r\n",6,server.repl_syncio_timeout*1000) == -1) {
            redisLog(REDIS_WARNING,"I/O error writing to MASTER: %s",
                strerror(errno));
            goto error;
        }
    }

打开rdb临时文件复制，可以看到3.0版本直接不采用落盘的方式进行复制。
   /* Prepare a suitable temp file for bulk transfer */
    // 打开一个临时文件，用于写入和保存接下来从主服务器传来的 RDB 文件数据
    while(maxtries--) {
        snprintf(tmpfile,256,
            "temp-%d.%ld.rdb",(int)server.unixtime,(long int)getpid());
        dfd = open(tmpfile,O_CREAT|O_WRONLY|O_EXCL,0644);
        if (dfd != -1) break;
        sleep(1);
    }
    if (dfd == -1) {
        redisLog(REDIS_WARNING,"Opening the temp file needed for MASTER <-> SLAVE synchronization: %s",strerror(errno));
        goto error;
    }

    /* Setup the non blocking download of the bulk file. */
    // 设置一个读事件处理器，来读取主服务器的 RDB 文件
    if (aeCreateFileEvent(server.el,fd, AE_READABLE,readSyncBulkPayload,NULL)
            == AE_ERR)
    {
        redisLog(REDIS_WARNING,
            "Can't create readable event for SYNC: %s (fd=%d)",
            strerror(errno),fd);
        goto error;
    }
最后设置了状态机为REDIS_REPL_TRANSFER，意味着正在传输
   server.repl_state = REDIS_REPL_TRANSFER;

差异：

redis6.0整体流程会更加的规范，每个事件都会有对应的状态机，PING和PONG会有对应的事件，不像3.0，只是一个回调函数。