/**
* 主函数定时事件触发的事件 频在配置表可以配置的 hz
*/
void replicationCron(void) {
    static long long replication_cron_loops = 0;

    /* Non blocking connection timeout? */
    if (server.masterhost &&
        (server.repl_state == REPL_STATE_CONNECTING ||
         slaveIsInHandshakeState()) &&
         (time(NULL)-server.repl_transfer_lastio) > server.repl_timeout)
    {
        serverLog(LL_WARNING,"Timeout connecting to the MASTER...");
        cancelReplicationHandshake();
    }

    /* Bulk transfer I/O timeout? */
    if (server.masterhost && server.repl_state == REPL_STATE_TRANSFER &&
        (time(NULL)-server.repl_transfer_lastio) > server.repl_timeout)
    {
        serverLog(LL_WARNING,"Timeout receiving bulk data from MASTER... If the problem persists try to set the 'repl-timeout' parameter in redis.conf to a larger value.");
        cancelReplicationHandshake();
    }

    /* Timed out master when we are an already connected slave? */
	// 这里断开连接了 使用状态和时间  ， master发送文件结束后 slave的状态就是  REPL_STATE_CONNECTED 需要的理解哦很巧妙的设计 
    if (server.masterhost && server.repl_state == REPL_STATE_CONNECTED &&
        (time(NULL)-server.master->lastinteraction) > server.repl_timeout)
    {
        serverLog(LL_WARNING,"MASTER timeout: no data nor PING received...");
		//在这里面把状态修改REPL_STATE_CONNECT
        freeClient(server.master);
    }

    /* Check if we should connect to a MASTER */
	// 在slave服务中的检查状态 连接master服务的
    if (server.repl_state == REPL_STATE_CONNECT) {
        serverLog(LL_NOTICE,"Connecting to MASTER %s:%d",
            server.masterhost, server.masterport);
        if (connectWithMaster() == C_OK) {
            serverLog(LL_NOTICE,"MASTER <-> REPLICA sync started");
        }
    }

    /* Send ACK to master from time to time.
     * Note that we do not send periodic acks to masters that don't
     * support PSYNC and replication offsets. */
	// slave 发送 同步信息包
    if (server.masterhost && server.master &&
        !(server.master->flags & CLIENT_PRE_PSYNC))
        replicationSendAck();

    /* If we have attached slaves, PING them from time to time.
     * So slaves can implement an explicit timeout to masters, and will
     * be able to detect a link disconnection even if the TCP connection
     * will not actually go down. */
    listIter li;
    listNode *ln;
    robj *ping_argv[1];

    /* First, send PING according to ping_slave_period. */
	// master 在里面发送ping包
    if ((replication_cron_loops % server.repl_ping_slave_period) == 0 &&
        listLength(server.slaves))
    {
        ping_argv[0] = createStringObject("PING",4);
        replicationFeedSlaves(server.slaves, server.slaveseldb,
            ping_argv, 1);
        decrRefCount(ping_argv[0]);
    }

    /* Second, send a newline to all the slaves in pre-synchronization
     * stage, that is, slaves waiting for the master to create the RDB file.
     *
     * Also send the a newline to all the chained slaves we have, if we lost
     * connection from our master, to keep the slaves aware that their
     * master is online. This is needed since sub-slaves only receive proxied
     * data from top-level masters, so there is no explicit pinging in order
     * to avoid altering the replication offsets. This special out of band
     * pings (newlines) can be sent, they will have no effect in the offset.
     *
     * The newline will be ignored by the slave but will refresh the
     * last interaction timer preventing a timeout. In this case we ignore the
     * ping period and refresh the connection once per second since certain
     * timeouts are set at a few seconds (example: PSYNC response). */
    listRewind(server.slaves,&li);
    while((ln = listNext(&li))) {
        client *slave = ln->value;

        int is_presync =
            (slave->replstate == SLAVE_STATE_WAIT_BGSAVE_START ||
            (slave->replstate == SLAVE_STATE_WAIT_BGSAVE_END &&
             server.rdb_child_type != RDB_CHILD_TYPE_SOCKET));

        if (is_presync) {
            if (write(slave->fd, "\n", 1) == -1) {
                /* Don't worry about socket errors, it's just a ping. */
            }
        }
    }

    /* Disconnect timedout slaves. */
	// slave连接超时的操作
    if (listLength(server.slaves)) {
        listIter li;
        listNode *ln;

        listRewind(server.slaves,&li);
        while((ln = listNext(&li))) {
            client *slave = ln->value;

            if (slave->replstate != SLAVE_STATE_ONLINE) continue;
            if (slave->flags & CLIENT_PRE_PSYNC) continue;
            if ((server.unixtime - slave->repl_ack_time) > server.repl_timeout)
            {
                serverLog(LL_WARNING, "Disconnecting timedout replica: %s",
                    replicationGetSlaveName(slave));
                freeClient(slave);
            }
        }
    }

    /* If this is a master without attached slaves and there is a replication
     * backlog active, in order to reclaim memory we can free it after some
     * (configured) time. Note that this cannot be done for slaves: slaves
     * without sub-slaves attached should still accumulate data into the
     * backlog, in order to reply to PSYNC queries if they are turned into
     * masters after a failover. */
    if (listLength(server.slaves) == 0 && server.repl_backlog_time_limit &&
        server.repl_backlog && server.masterhost == NULL)
    {
        time_t idle = server.unixtime - server.repl_no_slaves_since;

        if (idle > server.repl_backlog_time_limit) {
            /* When we free the backlog, we always use a new
             * replication ID and clear the ID2. This is needed
             * because when there is no backlog, the master_repl_offset
             * is not updated, but we would still retain our replication
             * ID, leading to the following problem:
             *
             * 1. We are a master instance.
             * 2. Our slave is promoted to master. It's repl-id-2 will
             *    be the same as our repl-id.
             * 3. We, yet as master, receive some updates, that will not
             *    increment the master_repl_offset.
             * 4. Later we are turned into a slave, connect to the new
             *    master that will accept our PSYNC request by second
             *    replication ID, but there will be data inconsistency
             *    because we received writes. */
            changeReplicationId();
            clearReplicationId2();
            freeReplicationBacklog();
            serverLog(LL_NOTICE,
                "Replication backlog freed after %d seconds "
                "without connected replicas.",
                (int) server.repl_backlog_time_limit);
        }
    }

    /* If AOF is disabled and we no longer have attached slaves, we can
     * free our Replication Script Cache as there is no need to propagate
     * EVALSHA at all. */
    if (listLength(server.slaves) == 0 &&
        server.aof_state == AOF_OFF &&
        listLength(server.repl_scriptcache_fifo) != 0)
    {
        replicationScriptCacheFlush();
    }

    /* Start a BGSAVE good for replication if we have slaves in
     * WAIT_BGSAVE_START state.
     *
     * In case of diskless replication, we make sure to wait the specified
     * number of seconds (according to configuration) so that other slaves
     * have the time to arrive before we start streaming. */
    if (server.rdb_child_pid == -1 && server.aof_child_pid == -1) {
        time_t idle, max_idle = 0;
        int slaves_waiting = 0;
        int mincapa = -1;
        listNode *ln;
        listIter li;

        listRewind(server.slaves,&li);
        while((ln = listNext(&li))) {
            client *slave = ln->value;
            if (slave->replstate == SLAVE_STATE_WAIT_BGSAVE_START) {
                idle = server.unixtime - slave->lastinteraction;
                if (idle > max_idle) max_idle = idle;
                slaves_waiting++;
                mincapa = (mincapa == -1) ? slave->slave_capa :
                                            (mincapa & slave->slave_capa);
            }
        }

        if (slaves_waiting &&
            (!server.repl_diskless_sync ||
             max_idle > server.repl_diskless_sync_delay))
        {
            /* Start the BGSAVE. The called function may start a
             * BGSAVE with socket target or disk target depending on the
             * configuration and slaves capabilities. */
            startBgsaveForReplication(mincapa);
        }
    }

    /* Refresh the number of slaves with lag <= min-slaves-max-lag. */
    refreshGoodSlavesCount();
    replication_cron_loops++; /* Incremented with frequency 1 HZ. */
}

/**
* 连接master服务
*/
int connectWithMaster(void) {
    int fd;
	// 1. 创建socket异步连接master服务
    fd = anetTcpNonBlockBestEffortBindConnect(NULL,
        server.masterhost,server.masterport,NET_FIRST_BIND_ADDR);
    if (fd == -1) {
        serverLog(LL_WARNING,"Unable to connect to MASTER: %s",
            strerror(errno));
        return C_ERR;
    }
	// 2. 注册事件   
    if (aeCreateFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE,syncWithMaster,NULL) ==
            AE_ERR)
    {
        close(fd);
        serverLog(LL_WARNING,"Can't create readable event for SYNC");
        return C_ERR;
    }

    server.repl_transfer_lastio = server.unixtime;
    server.repl_transfer_s = fd;
	// 3. 修改连接状态
    server.repl_state = REPL_STATE_CONNECTING;
    return C_OK;
}

/**
* 同步读写操作 在loop中
* @param el
* @param fd 连接服务的文件描述符
* @param privdata 数据
* @param mask 掩码
*/
void syncWithMaster(aeEventLoop *el, int fd, void *privdata, int mask) {
    char tmpfile[256], *err = NULL;
    int dfd = -1, maxtries = 5;
    int sockerr = 0, psync_result;
    socklen_t errlen = sizeof(sockerr);
    UNUSED(el);
    UNUSED(privdata);
    UNUSED(mask);

    /* If this event fired after the user turned the instance into a master
     * with SLAVEOF NO ONE we must just return ASAP. */
    if (server.repl_state == REPL_STATE_NONE) {
        close(fd);
        return;
    }

    /* Check for errors in the socket: after a non blocking connect() we
     * may find that the socket is in error state. */
    if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &sockerr, &errlen) == -1)
        sockerr = errno;
    if (sockerr) {
        serverLog(LL_WARNING,"Error condition on socket for SYNC: %s",
            strerror(sockerr));
        goto error;
    }

    /* Send a PING to check the master is able to reply without errors. */
    if (server.repl_state == REPL_STATE_CONNECTING) {
        serverLog(LL_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. */
		// 这里删除write事件 目的是为写入是io是同步进行的，而read还是异步进行中的
        aeDeleteFileEvent(server.el,fd,AE_WRITABLE);
        server.repl_state = REPL_STATE_RECEIVE_PONG;
        /* Send the PING, don't check for errors at all, we have the timeout
         * that will take care about this. */
        err = sendSynchronousCommand(SYNC_CMD_WRITE,fd,"PING",NULL);
        if (err) goto write_error;
        return;
    }

    /* Receive the PONG command. */
    if (server.repl_state == REPL_STATE_RECEIVE_PONG) {
        err = sendSynchronousCommand(SYNC_CMD_READ,fd,NULL);

        /* 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. */
        if (err[0] != '+' &&
            strncmp(err,"-NOAUTH",7) != 0 &&
            strncmp(err,"-ERR operation not permitted",28) != 0)
        {
            serverLog(LL_WARNING,"Error reply to PING from master: '%s'",err);
            sdsfree(err);
            goto error;
        } else {
            serverLog(LL_NOTICE,
                "Master replied to PING, replication can continue...");
        }
        sdsfree(err);
        server.repl_state = REPL_STATE_SEND_AUTH;
    }

    /* AUTH with the master if required. */
    if (server.repl_state == REPL_STATE_SEND_AUTH) {
        if (server.masterauth) {
            err = sendSynchronousCommand(SYNC_CMD_WRITE,fd,"AUTH",server.masterauth,NULL);
            if (err) goto write_error;
            server.repl_state = REPL_STATE_RECEIVE_AUTH;
            return;
        } else {
            server.repl_state = REPL_STATE_SEND_PORT;
        }
    }

    /* Receive AUTH reply. */
    if (server.repl_state == REPL_STATE_RECEIVE_AUTH) {
        err = sendSynchronousCommand(SYNC_CMD_READ,fd,NULL);
        if (err[0] == '-') {
            serverLog(LL_WARNING,"Unable to AUTH to MASTER: %s",err);
            sdsfree(err);
            goto error;
        }
        sdsfree(err);
        server.repl_state = REPL_STATE_SEND_PORT;
    }

    /* Set the slave port, so that Master's INFO command can list the
     * slave listening port correctly. */
    if (server.repl_state == REPL_STATE_SEND_PORT) {
        sds port = sdsfromlonglong(server.slave_announce_port ?
            server.slave_announce_port : server.port);
        err = sendSynchronousCommand(SYNC_CMD_WRITE,fd,"REPLCONF",
                "listening-port",port, NULL);
        sdsfree(port);
        if (err) goto write_error;
        sdsfree(err);
        server.repl_state = REPL_STATE_RECEIVE_PORT;
        return;
    }

    /* Receive REPLCONF listening-port reply. */
    if (server.repl_state == REPL_STATE_RECEIVE_PORT) {
        err = sendSynchronousCommand(SYNC_CMD_READ,fd,NULL);
        /* Ignore the error if any, not all the Redis versions support
         * REPLCONF listening-port. */
        if (err[0] == '-') {
            serverLog(LL_NOTICE,"(Non critical) Master does not understand "
                                "REPLCONF listening-port: %s", err);
        }
        sdsfree(err);
        server.repl_state = REPL_STATE_SEND_IP;
    }

    /* Skip REPLCONF ip-address if there is no slave-announce-ip option set. */
    if (server.repl_state == REPL_STATE_SEND_IP &&
        server.slave_announce_ip == NULL)
    {
            server.repl_state = REPL_STATE_SEND_CAPA;///？？？？？？？？
    }

    /* Set the slave ip, so that Master's INFO command can list the
     * slave IP address port correctly in case of port forwarding or NAT. */
    if (server.repl_state == REPL_STATE_SEND_IP) {
        err = sendSynchronousCommand(SYNC_CMD_WRITE,fd,"REPLCONF",
                "ip-address",server.slave_announce_ip, NULL);
        if (err) goto write_error;
        sdsfree(err);
        server.repl_state = REPL_STATE_RECEIVE_IP;
        return;
    }

    /* Receive REPLCONF ip-address reply. */
    if (server.repl_state == REPL_STATE_RECEIVE_IP) {
        err = sendSynchronousCommand(SYNC_CMD_READ,fd,NULL);
        /* Ignore the error if any, not all the Redis versions support
         * REPLCONF listening-port. */
        if (err[0] == '-') {
            serverLog(LL_NOTICE,"(Non critical) Master does not understand "
                                "REPLCONF ip-address: %s", err);
        }
        sdsfree(err);
        server.repl_state = REPL_STATE_SEND_CAPA;
    }

    /* Inform the master of our (slave) capabilities.
     *
     * EOF: supports EOF-style RDB transfer for diskless replication.
     * PSYNC2: supports PSYNC v2, so understands +CONTINUE <new repl ID>.
     *
     * The master will ignore capabilities it does not understand. */
    if (server.repl_state == REPL_STATE_SEND_CAPA) {
        err = sendSynchronousCommand(SYNC_CMD_WRITE,fd,"REPLCONF",
                "capa","eof","capa","psync2",NULL);
        if (err) goto write_error;
        sdsfree(err);
        server.repl_state = REPL_STATE_RECEIVE_CAPA;
        return;
    }

    /* Receive CAPA reply. */
    if (server.repl_state == REPL_STATE_RECEIVE_CAPA) {
        err = sendSynchronousCommand(SYNC_CMD_READ,fd,NULL);
        /* Ignore the error if any, not all the Redis versions support
         * REPLCONF capa. */
        if (err[0] == '-') {
            serverLog(LL_NOTICE,"(Non critical) Master does not understand "
                                  "REPLCONF capa: %s", err);
        }
        sdsfree(err);
        server.repl_state = REPL_STATE_SEND_PSYNC;
    }

    /* Try a partial resynchonization. If we don't have a cached master
     * slaveTryPartialResynchronization() will at least try to use PSYNC
     * to start a full resynchronization so that we get the master run id
     * and the global offset, to try a partial resync at the next
     * reconnection attempt. */
    if (server.repl_state == REPL_STATE_SEND_PSYNC) {
		// 校验master 偏移量数据 
        if (slaveTryPartialResynchronization(fd,0) == PSYNC_WRITE_ERROR) {
            err = sdsnew("Write error sending the PSYNC command.");
            goto write_error;
        }
        server.repl_state = REPL_STATE_RECEIVE_PSYNC;
        return;
    }

    /* If reached this point, we should be in REPL_STATE_RECEIVE_PSYNC. */
    if (server.repl_state != REPL_STATE_RECEIVE_PSYNC) {
        serverLog(LL_WARNING,"syncWithMaster(): state machine error, "
                             "state should be RECEIVE_PSYNC but is %d",
                             server.repl_state);
        goto error;
    }
	// master返回 校验的数据的 并返回 数据库
    psync_result = slaveTryPartialResynchronization(fd,1);
	// master服务 还没有返回数据有可能是断开连接了
    if (psync_result == PSYNC_WAIT_REPLY) return; /* Try again later... */

    /* If the master is in an transient error, we should try to PSYNC
     * from scratch later, so go to the error path. This happens when
     * the server is loading the dataset or is not connected with its
     * master and so forth. */
	/// master 服务在校验ping pong 的时候校验的同步的机制中的 master 与 slave 机制不同！！！！！
    if (psync_result == PSYNC_TRY_LATER) goto error;

    /* Note: if PSYNC does not return WAIT_REPLY, it will take care of
     * uninstalling the read handler from the file descriptor. */
	// master 服务返回数据了
    if (psync_result == PSYNC_CONTINUE) {
        serverLog(LL_NOTICE, "MASTER <-> REPLICA sync: Master accepted a Partial Resynchronization.");
        return;
    }

    /* PSYNC failed or is not supported: we want our slaves to resync with us
     * as well, if we have any sub-slaves. The master may transfer us an
     * entirely different data set and we have no way to incrementally feed
     * our slaves after that. */
    disconnectSlaves(); /* Force our slaves to resync with us as well. */
    freeReplicationBacklog(); /* Don't allow our chained slaves to PSYNC. */

    /* Fall back to SYNC if needed. Otherwise psync_result == PSYNC_FULLRESYNC
     * and the server.master_replid and master_initial_offset are
     * already populated. */
    if (psync_result == PSYNC_NOT_SUPPORTED) {
        serverLog(LL_NOTICE,"Retrying with SYNC...");
        if (syncWrite(fd,"SYNC\r\n",6,server.repl_syncio_timeout*1000) == -1) {
            serverLog(LL_WARNING,"I/O error writing to MASTER: %s",
                strerror(errno));
            goto error;
        }
    }

    /* Prepare a suitable temp file for bulk transfer */
	// 下面是完成同步数据的方案
    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) {
        serverLog(LL_WARNING,"Opening the temp file needed for MASTER <-> REPLICA synchronization: %s",strerror(errno));
        goto error;
    }

    /* Setup the non blocking download of the bulk file. */
	// 等待master发送 *.rdb文件流过来同步数据
    if (aeCreateFileEvent(server.el,fd, AE_READABLE,readSyncBulkPayload,NULL)
            == AE_ERR)
    {
        serverLog(LL_WARNING,
            "Can't create readable event for SYNC: %s (fd=%d)",
            strerror(errno),fd);
        goto error;
    }

    server.repl_state = REPL_STATE_TRANSFER;
    server.repl_transfer_size = -1;
    server.repl_transfer_read = 0;
    server.repl_transfer_last_fsync_off = 0;
    server.repl_transfer_fd = dfd;
    server.repl_transfer_lastio = server.unixtime;
    server.repl_transfer_tmpfile = zstrdup(tmpfile);
    return;

error:
    aeDeleteFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE);
    if (dfd != -1) close(dfd);
    close(fd);
    server.repl_transfer_s = -1;
    server.repl_state = REPL_STATE_CONNECT;
    return;

write_error: /* Handle sendSynchronousCommand(SYNC_CMD_WRITE) errors. */
    serverLog(LL_WARNING,"Sending command to master in replication handshake: %s", err);
    sdsfree(err);
    goto error;
}

/**
* 一, slave 发送校验 偏移量 offset   
* 1. 第一次时发送 cmd: psync ? -1   
* 2. 断线重连发送 cmd psync  crc16(server_id) offset
* 二, master 发送信息同步数据的两种策略
* 1. +FULLRESYNC   完全拷贝数据
* 2. +CONTINUE    slave 的偏移量进行同步数据
* 3. -NOMASTERLINK, -LOADING  master服务的状态不对
* @param fd master的文件描述符
* @param read_reply  false : 发送信息给master ， true :用于接收master信息
*/
int slaveTryPartialResynchronization(int fd, int read_reply) {
    char *psync_replid;
    char psync_offset[32];
    sds reply;

    /* Writing half */
    if (!read_reply) {
        /* Initially set 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.master_initial_offset = -1;
        // 断线重连的时候 从服务把master服务设置成了 缓存数据库了 
        if (server.cached_master) {
            psync_replid = server.cached_master->replid;
            snprintf(psync_offset,sizeof(psync_offset),"%lld", server.cached_master->reploff+1);
            serverLog(LL_NOTICE,"Trying a partial resynchronization (request %s:%s).", psync_replid, psync_offset);
        } else {
		// 完全同步数据的处理
            serverLog(LL_NOTICE,"Partial resynchronization not possible (no cached master)");
            psync_replid = "?";
            memcpy(psync_offset,"-1",3);
        }

        /* Issue the PSYNC command */
        reply = sendSynchronousCommand(SYNC_CMD_WRITE,fd,"PSYNC",psync_replid,psync_offset,NULL);
        if (reply != NULL) {
            serverLog(LL_WARNING,"Unable to send PSYNC to master: %s",reply);
            sdsfree(reply);
            aeDeleteFileEvent(server.el,fd,AE_READABLE);
            return PSYNC_WRITE_ERROR;
        }
        return PSYNC_WAIT_REPLY;
    }

    /* Reading half */
    reply = sendSynchronousCommand(SYNC_CMD_READ,fd,NULL);
    if (sdslen(reply) == 0) {
        /* The master may send empty newlines after it receives PSYNC
         * and before to reply, just to keep the connection alive. */
        sdsfree(reply);
        return PSYNC_WAIT_REPLY;
    }
	// 删除read的事件 现在彻底没有回函数了?????????????????? 怎么处理心跳包呢
	// 1.+CONTINUE 是在小偏移量中提交的事件的处理即函数:replicationResurrectCachedMaster
    aeDeleteFileEvent(server.el,fd,AE_READABLE);

    if (!strncmp(reply,"+FULLRESYNC",11)) {
        char *replid = NULL, *offset = NULL;

        /* FULL RESYNC, parse the reply in order to extract the run id
         * and the replication offset. */
        replid = strchr(reply,' ');
        if (replid) {
            replid++;
            offset = strchr(replid,' ');
            if (offset) offset++;
        }
        if (!replid || !offset || (offset-replid-1) != CONFIG_RUN_ID_SIZE) {
            serverLog(LL_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
             * replid to make sure next PSYNCs will fail. */
            memset(server.master_replid,0,CONFIG_RUN_ID_SIZE+1);
        } else {
            memcpy(server.master_replid, replid, offset-replid-1);
            server.master_replid[CONFIG_RUN_ID_SIZE] = '\0';
            server.master_initial_offset = strtoll(offset,NULL,10);
            serverLog(LL_NOTICE,"Full resync from master: %s:%lld",
                server.master_replid,
                server.master_initial_offset);
        }
        /* We are going to full resync, discard the cached master structure. */
        replicationDiscardCachedMaster();
        sdsfree(reply);
        return PSYNC_FULLRESYNC;
    }
	// master 返回 偏移量offset 的数据 同步数据的
    if (!strncmp(reply,"+CONTINUE",9)) {
        /* Partial resync was accepted. */
        serverLog(LL_NOTICE,
            "Successful partial resynchronization with master.");

        /* Check the new replication ID advertised by the master. If it
         * changed, we need to set the new ID as primary ID, and set or
         * secondary ID as the old master ID up to the current offset, so
         * that our sub-slaves will be able to PSYNC with us after a
         * disconnection. */
        char *start = reply+10;
        char *end = reply+9;
        while(end[0] != '\r' && end[0] != '\n' && end[0] != '\0') end++;
        if (end-start == CONFIG_RUN_ID_SIZE) {
            char new[CONFIG_RUN_ID_SIZE+1];
            memcpy(new,start,CONFIG_RUN_ID_SIZE);
            new[CONFIG_RUN_ID_SIZE] = '\0';

            if (strcmp(new,server.cached_master->replid)) {
                /* Master ID changed. */
                serverLog(LL_WARNING,"Master replication ID changed to %s",new);

                /* Set the old ID as our ID2, up to the current offset+1. */
                memcpy(server.replid2,server.cached_master->replid,
                    sizeof(server.replid2));
                server.second_replid_offset = server.master_repl_offset+1;

                /* Update the cached master ID and our own primary ID to the
                 * new one. */
                memcpy(server.replid,new,sizeof(server.replid));
                memcpy(server.cached_master->replid,new,sizeof(server.replid));

                /* Disconnect all the sub-slaves: they need to be notified. */
                disconnectSlaves();
            }
        }

        /* Setup the replication to continue. */
        sdsfree(reply);
        replicationResurrectCachedMaster(fd);

        /* If this instance was restarted and we read the metadata to
         * PSYNC from the persistence file, our replication backlog could
         * be still not initialized. Create it. */
        if (server.repl_backlog == NULL) createReplicationBacklog();
        return PSYNC_CONTINUE;
    }

    /* If we reach this point we received either an error (since the master does
     * not understand PSYNC or because it is in a special state and cannot
     * serve our request), or an unexpected reply from the master.
     *
     * Return PSYNC_NOT_SUPPORTED on errors we don't understand, otherwise
     * return PSYNC_TRY_LATER if we believe this is a transient error. */

    if (!strncmp(reply,"-NOMASTERLINK",13) ||
        !strncmp(reply,"-LOADING",8))
    {
        serverLog(LL_NOTICE,
            "Master is currently unable to PSYNC "
            "but should be in the future: %s", reply);
        sdsfree(reply);
        return PSYNC_TRY_LATER;
    }

    if (strncmp(reply,"-ERR",4)) {
        /* If it's not an error, log the unexpected event. */
        serverLog(LL_WARNING,
            "Unexpected reply to PSYNC from master: %s", reply);
    } else {
        serverLog(LL_NOTICE,
            "Master does not support PSYNC or is in "
            "error state (reply: %s)", reply);
    }
    sdsfree(reply);
    replicationDiscardCachedMaster();
    return PSYNC_NOT_SUPPORTED;
}

/**
* 对客户端的回话的修改状态   如果master和slave的作为客户端话就修改比较多一点
* @param c 客户端
*/
void freeClient(client *c) {
    listNode *ln;

    /* If a client is protected, yet we need to free it right now, make sure
     * to at least use asynchronous freeing. */
    if (c->flags & CLIENT_PROTECTED) {
        freeClientAsync(c);
        return;
    }

    /* If it is our master that's beging disconnected we should make sure
     * to cache the state to try a partial resynchronization later.
     *
     * Note that before doing this we make sure that the client is not in
     * some unexpected state, by checking its flags. */
    if (server.master && c->flags & CLIENT_MASTER) {
        serverLog(LL_WARNING,"Connection with master lost.");
        if (!(c->flags & (CLIENT_CLOSE_AFTER_REPLY|
                          CLIENT_CLOSE_ASAP|
                          CLIENT_BLOCKED)))
        {
			// 这边修改master数据为缓存数据
            replicationCacheMaster(c);
            return;
        }
    }

    /* Log link disconnection with slave */
    if ((c->flags & CLIENT_SLAVE) && !(c->flags & CLIENT_MONITOR)) {
        serverLog(LL_WARNING,"Connection with replica %s lost.",
            replicationGetSlaveName(c));
    }

    /* Free the query buffer */
    sdsfree(c->querybuf);
    sdsfree(c->pending_querybuf);
    c->querybuf = NULL;

    /* Deallocate structures used to block on blocking ops. */
    if (c->flags & CLIENT_BLOCKED) unblockClient(c);
    dictRelease(c->bpop.keys);

    /* UNWATCH all the keys */
    unwatchAllKeys(c);
    listRelease(c->watched_keys);

    /* Unsubscribe from all the pubsub channels */
    pubsubUnsubscribeAllChannels(c,0);
    pubsubUnsubscribeAllPatterns(c,0);
    dictRelease(c->pubsub_channels);
    listRelease(c->pubsub_patterns);

    /* Free data structures. */
    listRelease(c->reply);
    freeClientArgv(c);

    /* Unlink the client: this will close the socket, remove the I/O
     * handlers, and remove references of the client from different
     * places where active clients may be referenced. */
    unlinkClient(c);

    /* Master/slave cleanup Case 1:
     * we lost the connection with a slave. */
    if (c->flags & CLIENT_SLAVE) {
        if (c->replstate == SLAVE_STATE_SEND_BULK) {
            if (c->repldbfd != -1) close(c->repldbfd);
            if (c->replpreamble) sdsfree(c->replpreamble);
        }
        list *l = (c->flags & CLIENT_MONITOR) ? server.monitors : server.slaves;
        ln = listSearchKey(l,c);
        serverAssert(ln != NULL);
        listDelNode(l,ln);
        /* We need to remember the time when we started to have zero
         * attached slaves, as after some time we'll free the replication
         * backlog. */
        if (c->flags & CLIENT_SLAVE && listLength(server.slaves) == 0)
            server.repl_no_slaves_since = server.unixtime;
        refreshGoodSlavesCount();
    }

    /* Master/slave cleanup Case 2:
     * we lost the connection with the master. */
	// 看到吧 状态改变吧 master -》REPL_STATE_CONNECT
    if (c->flags & CLIENT_MASTER) replicationHandleMasterDisconnection();

    /* If this client was scheduled for async freeing we need to remove it
     * from the queue. */
    if (c->flags & CLIENT_CLOSE_ASAP) {
        ln = listSearchKey(server.clients_to_close,c);
        serverAssert(ln != NULL);
        listDelNode(server.clients_to_close,ln);
    }

    /* Release other dynamically allocated client structure fields,
     * and finally release the client structure itself. */
    if (c->name) decrRefCount(c->name);
    zfree(c->argv);
    freeClientMultiState(c);
    sdsfree(c->peerid);
    zfree(c);
}

/**
* 设置master服务数据库为缓存数据库 在slave服务上使用的
* @param c 客户端
*/
void replicationCacheMaster(client *c) {
    serverAssert(server.master != NULL && server.cached_master == NULL);
    serverLog(LL_NOTICE,"Caching the disconnected master state.");

    /* Unlink the client from the server structures. */
    unlinkClient(c);

    /* Reset the master client so that's ready to accept new commands:
     * we want to discard te non processed query buffers and non processed
     * offsets, including pending transactions, already populated arguments,
     * pending outputs to the master. */
    sdsclear(server.master->querybuf);
    sdsclear(server.master->pending_querybuf);
    server.master->read_reploff = server.master->reploff;
    if (c->flags & CLIENT_MULTI) discardTransaction(c);
    listEmpty(c->reply);
    c->sentlen = 0;
    c->reply_bytes = 0;
    c->bufpos = 0;
    resetClient(c);

    /* Save the master. Server.master will be set to null later by
     * replicationHandleMasterDisconnection(). */
    server.cached_master = server.master;

    /* Invalidate the Peer ID cache. */
    if (c->peerid) {
        sdsfree(c->peerid);
        c->peerid = NULL;
    }

    /* Caching the master happens instead of the actual freeClient() call,
     * so make sure to adjust the replication state. This function will
     * also set server.master to NULL. */
    replicationHandleMasterDisconnection();
}

void replconfCommand(client *c) {
    int j;

    if ((c->argc % 2) == 0) {
        /* Number of arguments must be odd to make sure that every
         * option has a corresponding value. */
        addReply(c,shared.syntaxerr);
        return;
    }

    /* Process every option-value pair. */
    for (j = 1; j < c->argc; j+=2) {
        if (!strcasecmp(c->argv[j]->ptr,"listening-port")) {
            long port;

            if ((getLongFromObjectOrReply(c,c->argv[j+1],
                    &port,NULL) != C_OK))
                return;
            c->slave_listening_port = port;
        } else if (!strcasecmp(c->argv[j]->ptr,"ip-address")) {
            sds ip = c->argv[j+1]->ptr;
            if (sdslen(ip) < sizeof(c->slave_ip)) {
                memcpy(c->slave_ip,ip,sdslen(ip)+1);
            } else {
                addReplyErrorFormat(c,"REPLCONF ip-address provided by "
                    "replica instance is too long: %zd bytes", sdslen(ip));
                return;
            }
        } else if (!strcasecmp(c->argv[j]->ptr,"capa")) {
            /* Ignore capabilities not understood by this master. */
			// 配置psync----
            if (!strcasecmp(c->argv[j+1]->ptr,"eof"))
                c->slave_capa |= SLAVE_CAPA_EOF;
            else if (!strcasecmp(c->argv[j+1]->ptr,"psync2"))
                c->slave_capa |= SLAVE_CAPA_PSYNC2;
        } else if (!strcasecmp(c->argv[j]->ptr,"ack")) {
            /* REPLCONF ACK is used by slave to inform the master the amount
             * of replication stream that it processed so far. It is an
             * internal only command that normal clients should never use. */
            long long offset;
			//这边校验偏移量的
            if (!(c->flags & CLIENT_SLAVE)) return;
            if ((getLongLongFromObject(c->argv[j+1], &offset) != C_OK))
                return;
            if (offset > c->repl_ack_off)
                c->repl_ack_off = offset;
            c->repl_ack_time = server.unixtime;
            /* If this was a diskless replication, we need to really put
             * the slave online when the first ACK is received (which
             * confirms slave is online and ready to get more data). */
            if (c->repl_put_online_on_ack && c->replstate == SLAVE_STATE_ONLINE)
                putSlaveOnline(c);
            /* Note: this command does not reply anything! */
            return;
        } else if (!strcasecmp(c->argv[j]->ptr,"getack")) {
            /* REPLCONF GETACK is used in order to request an ACK ASAP
             * to the slave. */
            if (server.masterhost && server.master) replicationSendAck();
            return;
        } else {
            addReplyErrorFormat(c,"Unrecognized REPLCONF option: %s",
                (char*)c->argv[j]->ptr);
            return;
        }
    }
    addReply(c,shared.ok);
}

/**
* client read  redis中io设计反应堆类似于libevent模式
* @param el
* @param fd
* @param privdata
* @param mask
*/
void readQueryFromClient(aeEventLoop *el, int fd, void *privdata, int mask) {
    client *c = (client*) privdata;
    int nread, readlen;
    size_t qblen;
    UNUSED(el);
    UNUSED(mask);

    readlen = PROTO_IOBUF_LEN;
    /* If this is a multi bulk request, and we are processing a bulk reply
     * that is large enough, try to maximize the probability that the query
     * buffer contains exactly the SDS string representing the object, even
     * at the risk of requiring more read(2) calls. This way the function
     * processMultiBulkBuffer() can avoid copying buffers to create the
     * Redis Object representing the argument. */
    if (c->reqtype == PROTO_REQ_MULTIBULK && c->multibulklen && c->bulklen != -1
        && c->bulklen >= PROTO_MBULK_BIG_ARG)
    {
        ssize_t remaining = (size_t)(c->bulklen+2)-sdslen(c->querybuf);

        /* Note that the 'remaining' variable may be zero in some edge case,
         * for example once we resume a blocked client after CLIENT PAUSE. */
        if (remaining > 0 && remaining < readlen) readlen = remaining;
    }

    qblen = sdslen(c->querybuf);
	//校验接受缓冲区可用的大小
    if (c->querybuf_peak < qblen) c->querybuf_peak = qblen;
	//这里如果没有使用怎么多的内存就造成了内存泄漏吗？？？怎么处理呢
	// redis封装sds处理分配内存大小的处理
    c->querybuf = sdsMakeRoomFor(c->querybuf, readlen);
    nread = read(fd, c->querybuf+qblen, readlen);
    if (nread == -1) {
        if (errno == EAGAIN) {
            return;
        } else {
            serverLog(LL_VERBOSE, "Reading from client: %s",strerror(errno));
            freeClient(c);
            return;
        }
    } else if (nread == 0) {
        serverLog(LL_VERBOSE, "Client closed connection");
        freeClient(c);
        return;
    } else if (c->flags & CLIENT_MASTER) {
        /* Append the query buffer to the pending (not applied) buffer
         * of the master. We'll use this buffer later in order to have a
         * copy of the string applied by the last command executed. */
		// 放到主从同步中的缓存中的buf
        c->pending_querybuf = sdscatlen(c->pending_querybuf,
                                        c->querybuf+qblen,nread);
    }
	// 打印客户端发送数据包的信息 --> redis是自己对redis信息sds
	// 很特色 都是以 '*' 开头
	printf("[%s][%s][%d][client send -> msg = %s]\n", __FILE__, __PRETTY_FUNCTION__, __LINE__, c->querybuf + qblen);
    sdsIncrLen(c->querybuf,nread);
    c->lastinteraction = server.unixtime;
	// 你看master 这边read_reploff +字符串的长度 这是为什么呢
    if (c->flags & CLIENT_MASTER) c->read_reploff += nread;
	// 数据统计使用的
    server.stat_net_input_bytes += nread;
	// 处理客户端发送消息包过大的处理
    if (sdslen(c->querybuf) > server.client_max_querybuf_len) {
        sds ci = catClientInfoString(sdsempty(),c), bytes = sdsempty();

        bytes = sdscatrepr(bytes,c->querybuf,64);
        serverLog(LL_WARNING,"Closing client that reached max query buffer length: %s (qbuf initial bytes: %s)", ci, bytes);
        sdsfree(ci);
        sdsfree(bytes);
        freeClient(c);
        return;
    }

    /* Time to process the buffer. If the client is a master we need to
     * compute the difference between the applied offset before and after
     * processing the buffer, to understand how much of the replication stream
     * was actually applied to the master state: this quantity, and its
     * corresponding part of the replication stream, will be propagated to
     * the sub-slaves and to the replication backlog. */
    processInputBufferAndReplicate(c);
}

void processInputBufferAndReplicate(client *c) {
    if (!(c->flags & CLIENT_MASTER)) {
        processInputBuffer(c);
    } else {
        size_t prev_offset = c->reploff;
        processInputBuffer(c);
        size_t applied = c->reploff - prev_offset;
		// 说明什么呢    
		// 1. master与 slave服务上偏移量不一致所以要master 与slave同步数据    这边要多想一点  不止是客户端的命令同步哦还有可能slave服务与mater的偏移量不同步时也可以广播数据哦
        if (applied) {
			// 主从同步 master -> savle
            replicationFeedSlavesFromMasterStream(server.slaves,
                    c->pending_querybuf, applied);
            sdsrange(c->pending_querybuf,applied,-1);
        }
    }
}