【redis源码分析】Redis Sentinel 是如何实际解决分布式共识问题的

/* Main state. */
struct sentinelState {
    char myid[CONFIG_RUN_ID_SIZE+1]; /* This sentinel ID. */
    uint64_t current_epoch;         // 集群当前任期号，用于故障转移时使用 raft 算法选举 leader 节点
    dict *masters;      /* Dictionary of master sentinelRedisInstances.
                           Key is the instance name, value is the
                           sentinelRedisInstance structure pointer. */
	......
} sentinel;

typedef struct sentinelRedisInstance {
    int flags;      // 节点标志，见下文
    char *name;     /* Master name from the point of view of this sentinel. */
    char *runid;    /* Run ID of this instance, or unique ID if is a Sentinel.*/
    uint64_t config_epoch;  /* Configuration epoch. */
    sentinelAddr *addr; /* Master host. */
    instanceLink *link; /* Link to the instance, may be shared for Sentinels. */
    mstime_t last_pub_time;   /* Last time we sent hello via Pub/Sub. */
    mstime_t last_hello_time; /* Only used if SRI_SENTINEL is set. Last time
                                 we received a hello from this Sentinel
                                 via Pub/Sub. */
    mstime_t last_master_down_reply_time; /* Time of last reply to
                                             SENTINEL is-master-down command. */
    mstime_t s_down_since_time; /* Subjectively down since time. */
    mstime_t o_down_since_time; /* Objectively down since time. */
    mstime_t down_after_period; /* Consider it down after that period. */
    ......
    /* Role and the first time we observed it.
     * This is useful in order to delay replacing what the instance reports
     * with our own configuration. We need to always wait some time in order
     * to give a chance to the leader to report the new configuration before
     * we do silly things. */
    int role_reported;
    mstime_t role_reported_time;
    mstime_t slave_conf_change_time; /* Last time slave master addr changed. */

    /* Master specific. */
    dict *sentinels;    /* Other sentinels monitoring the same master. */
    dict *slaves;       /* Slaves for this master instance. */
    unsigned int quorum;/* Number of sentinels that need to agree on failure. */
    int parallel_syncs; /* How many slaves to reconfigure at same time. */
    char *auth_pass;    /* Password to use for AUTH against master & replica. */
    char *auth_user;    /* Username for ACLs AUTH against master & replica. */

    /* Slave specific. */
    mstime_t master_link_down_time; /* Slave replication link down time. */
    int slave_priority; /* Slave priority according to its INFO output. */
    mstime_t slave_reconf_sent_time; /* Time at which we sent SLAVE OF <new> */
    struct sentinelRedisInstance *master; /* Master instance if it's slave. */
    char *slave_master_host;    /* Master host as reported by INFO */
    int slave_master_port;      /* Master port as reported by INFO */
    int slave_master_link_status; /* Master link status as reported by INFO */
    unsigned long long slave_repl_offset; /* Slave replication offset. */
    /* Failover */
    char *leader;       /* If this is a master instance, this is the runid of
                           the Sentinel that should perform the failover. If
                           this is a Sentinel, this is the runid of the Sentinel
                           that this Sentinel voted as leader. */
    uint64_t leader_epoch; /* Epoch of the 'leader' field. */
    uint64_t failover_epoch; /* Epoch of the currently started failover. */
    int failover_state; /* See SENTINEL_FAILOVER_STATE_* defines. */
    mstime_t failover_state_change_time;
    mstime_t failover_start_time;   /* Last failover attempt start time. */
    mstime_t failover_timeout;      /* Max time to refresh failover state. */
    mstime_t failover_delay_logged; /* For what failover_start_time value we
                                       logged the failover delay. */
    struct sentinelRedisInstance *promoted_slave; /* Promoted slave instance. */
    ......
} sentinelRedisInstance;

/* A Sentinel Redis Instance object is monitoring. */
#define SRI_MASTER  (1<<0)
#define SRI_SLAVE   (1<<1)
#define SRI_SENTINEL (1<<2)
#define SRI_S_DOWN (1<<3)   //该节点已主观下线
#define SRI_O_DOWN (1<<4)   //该节点已客观下线
#define SRI_MASTER_DOWN (1<<5) /* A Sentinel with this flag set thinks that
                                   its master is down. */
#define SRI_FAILOVER_IN_PROGRESS (1<<6) //节点正在进行故障迁移
#define SRI_PROMOTED (1<<7)            //节点被选为前一种的晋升节点

1、它不再执行任何操作，如故障转移
2、当其他Sentinel节点询问它对于某个主节点主观下线的判定结果时，它将返回节点未下线的判定结果
3、如果TITL模式下Sentinel机制可以正常运行30秒，则该节点退出TITL模式

/* Perform scheduled operations for all the instances in the dictionary.
 * Recursively call the function against dictionaries of slaves. */
void sentinelHandleDictOfRedisInstances(dict *instances) {
    dictIterator *di;
    dictEntry *de;
    sentinelRedisInstance *switch_to_promoted = NULL;

    /* There are a number of things we need to perform against every master. */
    di = dictGetIterator(instances);
    while((de = dictNext(di)) != NULL) {
        sentinelRedisInstance *ri = dictGetVal(de);

        sentinelHandleRedisInstance(ri);	//调用主逻辑函数
        if (ri->flags & SRI_MASTER) {	
        //如果当前处理的是主节点，还需要递归处理主节点实例下的slaves 和 sentinels
            sentinelHandleDictOfRedisInstances(ri->slaves);
            sentinelHandleDictOfRedisInstances(ri->sentinels);
            if (ri->failover_state == SENTINEL_FAILOVER_STATE_UPDATE_CONFIG) {
                switch_to_promoted = ri;
            }
        }
    }
    //完成故障转移的最后一步
    if (switch_to_promoted)
        sentinelFailoverSwitchToPromotedSlave(switch_to_promoted);
    dictReleaseIterator(di);
}

/* ======================== SENTINEL timer handler ==========================
 * This is the "main" our Sentinel, being sentinel completely non blocking
 * in design. The function is called every second.
 * -------------------------------------------------------------------------- */

/* Perform scheduled operations for the specified Redis instance. */
void sentinelHandleRedisInstance(sentinelRedisInstance *ri) {
    /* ========== MONITORING HALF ============ */
    /* Every kind of instance */
    sentinelReconnectInstance(ri);		//建立网络连接
    sentinelSendPeriodicCommands(ri);	

    /* ============== ACTING HALF ============= */
    /* We don't proceed with the acting half if we are in TILT mode.
     * TILT happens when we find something odd with the time, like a
     * sudden change in the clock. */
    if (sentinel.tilt) {
        if (mstime()-sentinel.tilt_start_time < SENTINEL_TILT_PERIOD) return;
        sentinel.tilt = 0;
        sentinelEvent(LL_WARNING,"-tilt",NULL,"#tilt mode exited");
    }

    /* Every kind of instance */
    sentinelCheckSubjectivelyDown(ri);	//检查是否存在主观下线的节点

    /* Masters and slaves */
    if (ri->flags & (SRI_MASTER|SRI_SLAVE)) {
        /* Nothing so far. */
    }

    /* Only masters */
    if (ri->flags & SRI_MASTER) {	//只对主节点执行
        sentinelCheckObjectivelyDown(ri);	//检查是否存在客观下线的节点
        if (sentinelStartFailoverIfNeeded(ri))	//判断是够可以进行故障转移
            sentinelAskMasterStateToOtherSentinels(ri,SENTINEL_ASK_FORCED);	//发送投票请求
   	     	sentinelFailoverStateMachine(ri);	//实现一个故障转移状态机，实现故障转移逻辑
        	sentinelAskMasterStateToOtherSentinels(ri,SENTINEL_NO_FLAGS);	//询问其他 Sentinel 节点对该节点主观下线的判定结果
    }
}

/* Send periodic PING, INFO, and PUBLISH to the Hello channel to
 * the specified master or slave instance. */
void sentinelSendPeriodicCommands(sentinelRedisInstance *ri) {
    mstime_t now = mstime();
    mstime_t info_period, ping_period;
    int retval;

    /* Return ASAP if we have already a PING or INFO already pending, or
     * in the case the instance is not properly connected. */
    if (ri->link->disconnected) return;

    /* For INFO, PING, PUBLISH that are not critical commands to send we
     * also have a limit of SENTINEL_MAX_PENDING_COMMANDS. We don't
     * want to use a lot of memory just because a link is not working
     * properly (note that anyway there is a redundant protection about this,
     * that is, the link will be disconnected and reconnected if a long
     * timeout condition is detected. */
    if (ri->link->pending_commands >=
        SENTINEL_MAX_PENDING_COMMANDS * ri->link->refcount) return;

    /* If this is a slave of a master in O_DOWN condition we start sending
     * it INFO every second, instead of the usual SENTINEL_INFO_PERIOD
     * period. In this state we want to closely monitor slaves in case they
     * are turned into masters by another Sentinel, or by the sysadmin.
     *
     * Similarly we monitor the INFO output more often if the slave reports
     * to be disconnected from the master, so that we can have a fresh
     * disconnection time figure. */
    if ((ri->flags & SRI_SLAVE) &&
        ((ri->master->flags & (SRI_O_DOWN|SRI_FAILOVER_IN_PROGRESS)) ||
         (ri->master_link_down_time != 0)))
    {
        info_period = 1000;
    } else {
        info_period = SENTINEL_INFO_PERIOD;
    }

    /* We ping instances every time the last received pong is older than
     * the configured 'down-after-milliseconds' time, but every second
     * anyway if 'down-after-milliseconds' is greater than 1 second. */
    ping_period = ri->down_after_period;
    if (ping_period > SENTINEL_PING_PERIOD) ping_period = SENTINEL_PING_PERIOD;

    /* Send INFO to masters and slaves, not sentinels. */
    if ((ri->flags & SRI_SENTINEL) == 0 &&
        (ri->info_refresh == 0 ||
        (now - ri->info_refresh) > info_period))
    {
        retval = redisAsyncCommand(ri->link->cc,
            sentinelInfoReplyCallback, ri, "%s",
            sentinelInstanceMapCommand(ri,"INFO"));
        if (retval == C_OK) ri->link->pending_commands++;
    }

    /* Send PING to all the three kinds of instances. */
    if ((now - ri->link->last_pong_time) > ping_period &&
               (now - ri->link->last_ping_time) > ping_period/2) {
        sentinelSendPing(ri);
    }

    /* PUBLISH hello messages to all the three kinds of instances. */
    if ((now - ri->last_pub_time) > SENTINEL_PUBLISH_PERIOD) {
        sentinelSendHello(ri);
    }
}

/* ===================== SENTINEL availability checks ======================= */

/* Is this instance down from our point of view? */
void sentinelCheckSubjectivelyDown(sentinelRedisInstance *ri) {
    mstime_t elapsed = 0;

	//计算目标节点上次响应后过去的时间
    if (ri->link->act_ping_time)
        elapsed = mstime() - ri->link->act_ping_time;
    else if (ri->link->disconnected)
        elapsed = mstime() - ri->link->last_avail_time;

    /* Check if we are in need for a reconnection of one of the
     * links, because we are detecting low activity.
     *
     * 1) Check if the command link seems connected, was connected not less
     *    than SENTINEL_MIN_LINK_RECONNECT_PERIOD, but still we have a
     *    pending ping for more than half the timeout. */
    if (ri->link->cc &&
        (mstime() - ri->link->cc_conn_time) >
        SENTINEL_MIN_LINK_RECONNECT_PERIOD &&
        ri->link->act_ping_time != 0 && /* There is a pending ping... */
        /* The pending ping is delayed, and we did not receive
         * error replies as well. */
        (mstime() - ri->link->act_ping_time) > (ri->down_after_period/2) &&
        (mstime() - ri->link->last_pong_time) > (ri->down_after_period/2))
    {
        instanceLinkCloseConnection(ri->link,ri->link->cc);
    }

    /* 2) Check if the pubsub link seems connected, was connected not less
     *    than SENTINEL_MIN_LINK_RECONNECT_PERIOD, but still we have no
     *    activity in the Pub/Sub channel for more than
     *    SENTINEL_PUBLISH_PERIOD * 3.
     */
    if (ri->link->pc &&
        (mstime() - ri->link->pc_conn_time) >
         SENTINEL_MIN_LINK_RECONNECT_PERIOD &&
        (mstime() - ri->link->pc_last_activity) > (SENTINEL_PUBLISH_PERIOD*3))
    {
        instanceLinkCloseConnection(ri->link,ri->link->pc);
    }

    /* Update the SDOWN flag. We believe the instance is SDOWN if:
     *
     * 1) It is not replying.
     * 2) We believe it is a master, it reports to be a slave for enough time
     *    to meet the down_after_period, plus enough time to get two times
     *    INFO report from the instance. */
    if (elapsed > ri->down_after_period ||
        (ri->flags & SRI_MASTER &&
         ri->role_reported == SRI_SLAVE &&
         mstime() - ri->role_reported_time >
          (ri->down_after_period+SENTINEL_INFO_PERIOD*2)))
    {
        /* Is subjectively down */
        if ((ri->flags & SRI_S_DOWN) == 0) {
            sentinelEvent(LL_WARNING,"+sdown",ri,"%@");
            ri->s_down_since_time = mstime();
            ri->flags |= SRI_S_DOWN;
        }
    } else {
        /* Is subjectively up */
        if (ri->flags & SRI_S_DOWN) {
            sentinelEvent(LL_WARNING,"-sdown",ri,"%@");
            ri->flags &= ~(SRI_S_DOWN|SRI_SCRIPT_KILL_SENT);
        }
    }
}

//该函数内含选举逻辑
//其他 Sentinel 节点会回复一个标志位，如果为 true，则代表他也认为那个节点下线了
void sentinelAskMasterStateToOtherSentinels(sentinelRedisInstance *master, int flags) {
    dictIterator *di;
    dictEntry *de;

    di = dictGetIterator(master->sentinels);
    while((de = dictNext(di)) != NULL) {
        sentinelRedisInstance *ri = dictGetVal(de);
        mstime_t elapsed = mstime() - ri->last_master_down_reply_time;
        char port[32];
        int retval;

        /* If the master state from other sentinel is too old, we clear it. */
        if (elapsed > SENTINEL_ASK_PERIOD*5) {
            ri->flags &= ~SRI_MASTER_DOWN;
            sdsfree(ri->leader);
            ri->leader = NULL;
        }

        /* Only ask if master is down to other sentinels if:
         *
         * 1) We believe it is down, or there is a failover in progress.
         * 2) Sentinel is connected.
         * 3) We did not receive the info within SENTINEL_ASK_PERIOD ms. */
        if ((master->flags & SRI_S_DOWN) == 0) continue;
        if (ri->link->disconnected) continue;
        if (!(flags & SENTINEL_ASK_FORCED) &&
            mstime() - ri->last_master_down_reply_time < SENTINEL_ASK_PERIOD)
            continue;

        /* Ask */
        ll2string(port,sizeof(port),master->addr->port);
        retval = redisAsyncCommand(ri->link->cc,
                    sentinelReceiveIsMasterDownReply, ri,
                    "%s is-master-down-by-addr %s %s %llu %s",
                    sentinelInstanceMapCommand(ri,"SENTINEL"),
                    master->addr->ip, port,
                    sentinel.current_epoch,
                    (master->failover_state > SENTINEL_FAILOVER_STATE_NONE) ?
                    sentinel.myid : "*");
        if (retval == C_OK) ri->link->pending_commands++;
    }
    dictReleaseIterator(di);
}

void sentinelAskMasterStateToOtherSentinels(sentinelRedisInstance *master, int flags) {
    dictIterator *di;
    dictEntry *de;

    di = dictGetIterator(master->sentinels);
    while((de = dictNext(di)) != NULL) {
        sentinelRedisInstance *ri = dictGetVal(de);
        mstime_t elapsed = mstime() - ri->last_master_down_reply_time;
        char port[32];
        int retval;

        /* If the master state from other sentinel is too old, we clear it. */
        if (elapsed > SENTINEL_ASK_PERIOD*5) {
            ri->flags &= ~SRI_MASTER_DOWN;
            sdsfree(ri->leader);
            ri->leader = NULL;
        }

        /* Only ask if master is down to other sentinels if:
         *
         * 1) We believe it is down, or there is a failover in progress.
         * 2) Sentinel is connected.
         * 3) We did not receive the info within SENTINEL_ASK_PERIOD ms. */
        if ((master->flags & SRI_S_DOWN) == 0) continue;
        if (ri->link->disconnected) continue;
        if (!(flags & SENTINEL_ASK_FORCED) &&
            mstime() - ri->last_master_down_reply_time < SENTINEL_ASK_PERIOD)
            continue;

        /* Ask */
        ll2string(port,sizeof(port),master->addr->port);
        retval = redisAsyncCommand(ri->link->cc,
                    sentinelReceiveIsMasterDownReply, ri,
                    "%s is-master-down-by-addr %s %s %llu %s",
                    sentinelInstanceMapCommand(ri,"SENTINEL"),
                    master->addr->ip, port,
                    sentinel.current_epoch,
                    (master->failover_state > SENTINEL_FAILOVER_STATE_NONE) ?
                    sentinel.myid : "*");
        if (retval == C_OK) ri->link->pending_commands++;
    }
    dictReleaseIterator(di);
}

/* Vote for the sentinel with 'req_runid' or return the old vote if already
 * voted for the specified 'req_epoch' or one greater.
 *
 * If a vote is not available returns NULL, otherwise return the Sentinel
 * runid and populate the leader_epoch with the epoch of the vote. */
char *sentinelVoteLeader(sentinelRedisInstance *master, uint64_t req_epoch, char *req_runid, uint64_t *leader_epoch) {
    if (req_epoch > sentinel.current_epoch) {
        sentinel.current_epoch = req_epoch;
        sentinelFlushConfig();
        sentinelEvent(LL_WARNING,"+new-epoch",master,"%llu",
            (unsigned long long) sentinel.current_epoch);
    }

    if (master->leader_epoch < req_epoch && sentinel.current_epoch <= req_epoch)
    {
        sdsfree(master->leader);
        master->leader = sdsnew(req_runid);
        master->leader_epoch = sentinel.current_epoch;
        sentinelFlushConfig();
        sentinelEvent(LL_WARNING,"+vote-for-leader",master,"%s %llu",
            master->leader, (unsigned long long) master->leader_epoch);
        /* If we did not voted for ourselves, set the master failover start
         * time to now, in order to force a delay before we can start a
         * failover for the same master. */
        if (strcasecmp(master->leader,sentinel.myid))
            master->failover_start_time = mstime()+rand()%SENTINEL_MAX_DESYNC;
    }

    *leader_epoch = master->leader_epoch;
    return master->leader ? sdsnew(master->leader) : NULL;
}

/* This function checks if there are the conditions to start the failover,
 * that is:
 *
 * 1) Master must be in ODOWN condition.
 * 2) No failover already in progress.
 * 3) No failover already attempted recently.
 *
 * We still don't know if we'll win the election so it is possible that we
 * start the failover but that we'll not be able to act.
 *
 * Return non-zero if a failover was started. */
int sentinelStartFailoverIfNeeded(sentinelRedisInstance *master) {
    /* We can't failover if the master is not in O_DOWN state. */
    if (!(master->flags & SRI_O_DOWN)) return 0;

    /* Failover already in progress? */
    if (master->flags & SRI_FAILOVER_IN_PROGRESS) return 0;

    /* Last failover attempt started too little time ago? */
    //failover_start_time 可以理解为一个锁，直到上次故障转移的时间超过failover_start_time 的两倍，才可以开始新的故障转移，默认三分钟。
    if (mstime() - master->failover_start_time <
        master->failover_timeout*2)
    {
        if (master->failover_delay_logged != master->failover_start_time) {
            time_t clock = (master->failover_start_time +
                            master->failover_timeout*2) / 1000;
            char ctimebuf[26];

            ctime_r(&clock,ctimebuf);
            ctimebuf[24] = '\0'; /* Remove newline. */
            master->failover_delay_logged = master->failover_start_time;
            serverLog(LL_WARNING,
                "Next failover delay: I will not start a failover before %s",
                ctimebuf);
        }
        return 0;
    }

    sentinelStartFailover(master);
    return 1;
}

/* Setup the master state to start a failover. */
void sentinelStartFailover(sentinelRedisInstance *master) {
    serverAssert(master->flags & SRI_MASTER);

    master->failover_state = SENTINEL_FAILOVER_STATE_WAIT_START;
    master->flags |= SRI_FAILOVER_IN_PROGRESS;
    master->failover_epoch = ++sentinel.current_epoch;
    sentinelEvent(LL_WARNING,"+new-epoch",master,"%llu",
        (unsigned long long) sentinel.current_epoch);
    sentinelEvent(LL_WARNING,"+try-failover",master,"%@");
    master->failover_start_time = mstime()+rand()%SENTINEL_MAX_DESYNC;
    master->failover_state_change_time = mstime();
}

void sentinelFailoverStateMachine(sentinelRedisInstance *ri) {
    serverAssert(ri->flags & SRI_MASTER);

    if (!(ri->flags & SRI_FAILOVER_IN_PROGRESS)) return;

    switch(ri->failover_state) {
        case SENTINEL_FAILOVER_STATE_WAIT_START:
            sentinelFailoverWaitStart(ri);	//统计投票结果
            break;
        case SENTINEL_FAILOVER_STATE_SELECT_SLAVE:
            sentinelFailoverSelectSlave(ri);//选择从节点
            break;
        case SENTINEL_FAILOVER_STATE_SEND_SLAVEOF_NOONE:
            sentinelFailoverSendSlaveOfNoOne(ri);//取消该节点之前的主从关系，晋升成为主节点
            break;
        case SENTINEL_FAILOVER_STATE_WAIT_PROMOTION:
            sentinelFailoverWaitPromotion(ri);	//等待晋升完成
            break;
        case SENTINEL_FAILOVER_STATE_RECONF_SLAVES:
            sentinelFailoverReconfNextSlave(ri);//建立主从关系
            break;
    }
}