[redis设计与实现][10]sentinel——简介和启动

Sentinel(Redis 3.0.0-rc1)

Sentinel是Redis HA方案,一个或多个Sentinel实例组成的Sentinel系统,可以监视任意多个主服务器(master),
以及这些主服务器属下的所有从服务器(slave),并在被监视的主服务器进入下线状态时,自动在将被下线主服务器属下的某个从服务器升级为新的主服务器,
然后由新的主服务器代替已下线的主服务器继续处理命令请求。

基础数据结构

typedef struct sentinelRedisInstance {
    // 当前实例的类型和状态(master, slave, sentinel,是否下线)
    int flags;
    // 主机名,ip:port
    char *name;
    // 实例的runid
    char *runid;
    // 配置纪元
    uint64_t config_epoch;
    // 实例的地址
    sentinelAddr *addr;
    redisAsyncContext *cc; /* Hiredis context for commands. */
    redisAsyncContext *pc; /* Hiredis context for Pub / Sub. */
    int pending_commands;   /* Number of commands sent waiting for a reply. */
    mstime_t cc_conn_time; /* cc connection time. */
    mstime_t pc_conn_time; /* pc connection time. */
    mstime_t pc_last_activity; /* Last time we received any message. */
    mstime_t last_avail_time; /* Last time the instance replied to ping with
                                 a reply we consider valid. */
    mstime_t last_ping_time;  /* Last time a pending ping was sent in the
                                 context of the current command connection
                                 with the instance. 0 if still not sent or
                                 if pong already received. */
    mstime_t last_pong_time;  /* Last time the instance replied to ping,
                                 whatever the reply was. That's used to check
                                 if the link is idle and must be reconnected. */
    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. */
    // 无响应多少毫秒之后,进入主观下线
    mstime_t down_after_period;
    mstime_t info_refresh;  /* Time at which we received INFO output from it. */

    /* 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. */
    // 判断为客观下线需要的支持票数
    unsigned int quorum;
    // 故障转移时,可以同时对新的master进行同步的slave数量
    int parallel_syncs; /* How many slaves to reconfigure at same time. */
    char *auth_pass;    /* Password to use for AUTH against master & slaves. */

    /* 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. */
    // 刷新故障迁移状态的最大时限
    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. */
    /* Scripts executed to notify admin or reconfigure clients: when they
     * are set to NULL no script is executed. */
    char *notification_script;
    char *client_reconfig_script;
} sentinelRedisInstance;

struct sentinelState {
    // 当前纪元
    uint64_t current_epoch;
    // 监控的master字典,key是master名称,value是sentinelRedisInstance对象
    dict *masters;
    // 是否处于TILT模式
    int tilt;
    // 目前正在执行脚本的数量
    int running_scripts;
    // 进入TITL模式时间
    mstime_t tilt_start_time;
    // 最后一次执行时间处理器的时间
    mstime_t previous_time;
    // 用户脚本执行队列
    list *scripts_queue;
} sentinel;

Sentinel初始化

启动命令:

redis-sentinel /path/to/sentinel.conf

或者

redis-server /path/to/sentinel.conf --sentinel

Sentinel启动的时候,必须指定配置文件,最小配置类似:

sentinel monitor mymaster 127.0.0.1 6379 2
sentinel down-after-milliseconds mymaster 60000
sentinel failover-timeout mymaster 180000
sentinel parallel-syncs mymaster 1

这个配置文件表示,当前sentinel监视一个Redis master(mymaster),ip为127.0.0.1,端口为6379,
需要两个sentinel声明下线,才进行主备切换。mymaster 60000ms未响应标记为失效。

在main函数中,会直接对sentinel启动特殊的配置:

int main(int argc, char **argv) {
    ...
    if (server.sentinel_mode) {
        initSentinelConfig();
        initSentinel();
    }
    ...
}

首先是覆盖redis server的端口设置,sentinel会默认监听在26379端口:

#define REDIS_SENTINEL_PORT 26379
void initSentinelConfig(void) {
    server.port = REDIS_SENTINEL_PORT;
}

然后覆盖server的命令表格,初始化sentinel对象:

void initSentinel(void) {
    unsigned int j;

    /* Remove usual Redis commands from the command table, then just add
     * the SENTINEL command. */
     // 清空Redis支持的命令表格,改成sentinel支持的命令表格
    dictEmpty(server.commands,NULL);
    for (j = 0; j < sizeof(sentinelcmds)/sizeof(sentinelcmds[0]); j++) {
        int retval;
        struct redisCommand *cmd = sentinelcmds+j;

        retval = dictAdd(server.commands, sdsnew(cmd->name), cmd);
        redisAssert(retval == DICT_OK);
    }

    /* Initialize various data structures. */
    sentinel.current_epoch = 0;
    sentinel.masters = dictCreate(&instancesDictType,NULL);
    sentinel.tilt = 0;
    sentinel.tilt_start_time = 0;
    sentinel.previous_time = mstime();
    sentinel.running_scripts = 0;
    sentinel.scripts_queue = listCreate();
    sentinel.announce_ip = NULL;
    sentinel.announce_port = 0;
}

sentinel只能支持监控相关的命令,无法执行通常的Redis命令,sentinel可以支持的命令表格为:

struct redisCommand sentinelcmds[] = {
    {"ping",pingCommand,1,"",0,NULL,0,0,0,0,0},
    {"sentinel",sentinelCommand,-2,"",0,NULL,0,0,0,0,0},
    {"subscribe",subscribeCommand,-2,"",0,NULL,0,0,0,0,0},
    {"unsubscribe",unsubscribeCommand,-1,"",0,NULL,0,0,0,0,0},
    {"psubscribe",psubscribeCommand,-2,"",0,NULL,0,0,0,0,0},
    {"punsubscribe",punsubscribeCommand,-1,"",0,NULL,0,0,0,0,0},
    {"publish",sentinelPublishCommand,3,"",0,NULL,0,0,0,0,0},
    {"info",sentinelInfoCommand,-1,"",0,NULL,0,0,0,0,0},
    {"role",sentinelRoleCommand,1,"l",0,NULL,0,0,0,0,0},
    {"shutdown",shutdownCommand,-1,"",0,NULL,0,0,0,0,0}
};

同时,由于sentinel不接受Redis普通命令,因此初始化的时候,也不会去加载rdb文件等原始数据。

发表评论

您的电子邮箱地址不会被公开。

此站点使用Akismet来减少垃圾评论。了解我们如何处理您的评论数据