1、 发现从服务器
在（27）中解析了sentinelReconnectInstance方法，这里继续解析sentinelHandleRedisInstance中的第二个方法：sentinelSendPeriodicCommands。这个方法的内容如下：
/* 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);
}
}这段代码的重点有三个。首先是第45行的if语句，这个语句内的代码会向服务器发送info命令。然后是56行的if语句，这里会向服务器发送ping命令。最后是62行的if语句，这里会向channel中发送消息。
为了和（27）中的分析联系起来，首先分析第62行的代码，这里调用的sentinelSendHello方法如下：
int sentinelSendHello(sentinelRedisInstance *ri) {
char ip[NET_IP_STR_LEN];
char payload[NET_IP_STR_LEN+1024];
int retval;
char *announce_ip;
int announce_port;
sentinelRedisInstance *master = (ri->flags & SRI_MASTER) ? ri : ri->master;
sentinelAddr *master_addr = sentinelGetCurrentMasterAddress(master);
if (ri->link->disconnected) return C_ERR;
/* Use the specified announce address if specified, otherwise try to
* obtain our own IP address. */
if (sentinel.announce_ip) {
announce_ip = sentinel.announce_ip;
} else {
if (anetSockName(ri->link->cc->c.fd,ip,sizeof(ip),NULL) == -1)
return C_ERR;
announce_ip = ip;
}
announce_port = sentinel.announce_port ?
sentinel.announce_port : server.port;
/* Format and send the Hello message. */
snprintf(payload,sizeof(payload),
"%s,%d,%s,%llu," /* Info about this sentinel. */
"%s,%s,%d,%llu", /* Info about current master. */
announce_ip, announce_port, sentinel.myid,
(unsigned long long) sentinel.current_epoch,
/* --- */
master->name,master_addr->ip,master_addr->port,
(unsigned long long) master->config_epoch);
retval = redisAsyncCommand(ri->link->cc,
sentinelPublishReplyCallback, ri, "%s %s %s",
sentinelInstanceMapCommand(ri,"PUBLISH"),
SENTINEL_HELLO_CHANNEL,payload);
if (retval != C_OK) return C_ERR;
ri->link->pending_commands++;
return C_OK;
}首先看第33行，这里使用了redisAsyncCommand方法向服务器发送命令，这个方法之前分析过。发送的命令为"%s %s %s"，第一个%s的内容为sentinelInstanceMapCommand(ri,“PUBLISH”)，这个方法之前也提到过，方法的返回值就是PUBLISH命令，第二个参数是SENTINEL_HELLO_CHANNEL，和（27）中解析的channel相同，最后第三参数是payload，这个参数在第25行被赋值，一共有8个数据，和（27）中分析的相同。
然后是处理PUBLISH命令返回值的sentinelPublishReplyCallback方法，其内容如下：
/* This is called when we get the reply about the PUBLISH command we send
* to the master to advertise this sentinel. */
void sentinelPublishReplyCallback(redisAsyncContext *c, void *reply, void *privdata) {
sentinelRedisInstance *ri = privdata;
instanceLink *link = c->data;
redisReply *r;
if (!reply || !link) return;
link->pending_commands--;
r = reply;
/* Only update pub_time if we actually published our message. Otherwise
* we'll retry again in 100 milliseconds. */
if (r->type != REDIS_REPLY_ERROR)
ri->last_pub_time = mstime();
}这里没有特殊的操作。接着我们继续分析sentinelSendPeriodicCommands方法中56行发送ping命令的方法，使用的sentinelSendPing方法内容如下：
* Send a PING to the specified instance and refresh the act_ping_time
* if it is zero (that is, if we received a pong for the previous ping).
*
* On error zero is returned, and we can't consider the PING command
* queued in the connection. */
int sentinelSendPing(sentinelRedisInstance *ri) {
int retval = redisAsyncCommand(ri->link->cc,
sentinelPingReplyCallback, ri, "%s",
sentinelInstanceMapCommand(ri,"PING"));
if (retval == C_OK) {
ri->link->pending_commands++;
ri->link->last_ping_time = mstime();
/* We update the active ping time only if we received the pong for
* the previous ping, otherwise we are technically waiting since the
* first ping that did not receive a reply. */
if (ri->link->act_ping_time == 0)
ri->link->act_ping_time = ri->link->last_ping_time;
return 1;
} else {
return 0;
}
}重点在第7行，这里可以看见它使用了和之前相同的方法来发送命令，并且发送的只有一个命令PING。对于PING命令的返回值，其调用了sentinelPingReplyCallback方法来处理，处理方法的内容如下：
void sentinelPingReplyCallback(redisAsyncContext *c, void *reply, void *privdata) {
sentinelRedisInstance *ri = privdata;
instanceLink *link = c->data;
redisReply *r;
if (!reply || !link) return;
link->pending_commands--;
r = reply;
if (r->type == REDIS_REPLY_STATUS ||
r->type == REDIS_REPLY_ERROR) {
/* Update the "instance available" field only if this is an
* acceptable reply. */
if (strncmp(r->str,"PONG",4) == 0 ||
strncmp(r->str,"LOADING",7) == 0 ||
strncmp(r->str,"MASTERDOWN",10) == 0)
{
link->last_avail_time = mstime();
link->act_ping_time = 0; /* Flag the pong as received. */
} else {
/* Send a SCRIPT KILL command if the instance appears to be
* down because of a busy script. */
if (strncmp(r->str,"BUSY",4) == 0 &&
(ri->flags & SRI_S_DOWN) &&
!(ri->flags & SRI_SCRIPT_KILL_SENT))
{
if (redisAsyncCommand(ri->link->cc,
sentinelDiscardReplyCallback, ri,
"%s KILL",
sentinelInstanceMapCommand(ri,"SCRIPT")) == C_OK)
{
ri->link->pending_commands++;
}
ri->flags |= SRI_SCRIPT_KILL_SENT;
}
}
}
link->last_pong_time = mstime();
}从上述代码可以看出，当返回值是PONG、LOADING、MASTERDOWN的时候，其并不会做什么特殊的操作，而返回值是BUSY的时候，其会发送一个SCRIPT KILL命令。
最后，我们再来分析sentinelSendPeriodicCommands方法中第45行中用来发送info命令的方法。在49行可以看见它是使用同样的方式来发送info命令。对于info命令的返回值调用sentinelInfoReplyCallback方法来处理，其内容如下：
void sentinelInfoReplyCallback(redisAsyncContext *c, void *reply, void *privdata) {
sentinelRedisInstance *ri = privdata;
instanceLink *link = c->data;
redisReply *r;
if (!reply || !link) return;
link->pending_commands--;
r = reply;
if (r->type == REDIS_REPLY_STRING)
sentinelRefreshInstanceInfo(ri,r->str);
}这里重点在第11行的sentinelRefreshInstanceInfo方法，其内容如下：
/* Process the INFO output from masters. */
void sentinelRefreshInstanceInfo(sentinelRedisInstance *ri, const char *info) {
sds *lines;
int numlines, j;
int role = 0;
/* cache full INFO output for instance */
sdsfree(ri->info);
ri->info = sdsnew(info);
/* The following fields must be reset to a given value in the case they
* are not found at all in the INFO output. */
ri->master_link_down_time = 0;
/* Process line by line. */
lines = sdssplitlen(info,strlen(info),"\r\n",2,&numlines);
for (j = 0; j < numlines; j++) {
sentinelRedisInstance *slave;
sds l = lines[j];
/* run_id:<40 hex chars>*/
if (sdslen(l) >= 47 && !memcmp(l,"run_id:",7)) {
if (ri->runid == NULL) {
ri->runid = sdsnewlen(l+7,40);
} else {
if (strncmp(ri->runid,l+7,40) != 0) {
sentinelEvent(LL_NOTICE,"+reboot",ri,"%@");
sdsfree(ri->runid);
ri->runid = sdsnewlen(l+7,40);
}
}
}
/* old versions: slave0:<ip>,<port>,<state>
* new versions: slave0:ip=127.0.0.1,port=9999,... */
if ((ri->flags & SRI_MASTER) &&
sdslen(l) >= 7 &&
!memcmp(l,"slave",5) && isdigit(l[5]))
{
char *ip, *port, *end;
if (strstr(l,"ip=") == NULL) {
/* Old format. */
ip = strchr(l,':'); if (!ip) continue;
ip++; /* Now ip points to start of ip address. */
port = strchr(ip,','); if (!port) continue;
*port = '\0'; /* nul term for easy access. */
port++; /* Now port points to start of port number. */
end = strchr(port,','); if (!end) continue;
*end = '\0'; /* nul term for easy access. */
} else {
/* New format. */
ip = strstr(l,"ip="); if (!ip) continue;
ip += 3; /* Now ip points to start of ip address. */
port = strstr(l,"port="); if (!port) continue;
port += 5; /* Now port points to start of port number. */
/* Nul term both fields for easy access. */
end = strchr(ip,','); if (end) *end = '\0';
end = strchr(port,','); if (end) *end = '\0';
}
/* Check if we already have this slave into our table,
* otherwise add it. */
if (sentinelRedisInstanceLookupSlave(ri,ip,atoi(port)) == NULL) {
if ((slave = createSentinelRedisInstance(NULL,SRI_SLAVE,ip,
atoi(port), ri->quorum, ri)) != NULL)
{
sentinelEvent(LL_NOTICE,"+slave",slave,"%@");
sentinelFlushConfig();
}
}
}
...
}这段代码很长，上述代码只展示了和发现从服务器相关部分的代码。
首先是17行，info命令返回的字符串会被按行拆分，然后用一个for循环逐行解析。然后是第37行解析到从服务器相关的信息后会进入这个if语句。这里首先会读取ip和port信息，然后是第65行，这里会调用sentinelRedisInstanceLookupSlave方法在从服务器中寻找该服务器是否已存在，这个方法的内容如下：
/* Lookup a slave in a master Redis instance, by ip and port. */
sentinelRedisInstance *sentinelRedisInstanceLookupSlave(
sentinelRedisInstance *ri, char *ip, int port)
{
sds key;
sentinelRedisInstance *slave;
char buf[NET_PEER_ID_LEN];
serverAssert(ri->flags & SRI_MASTER);
anetFormatAddr(buf,sizeof(buf),ip,port);
key = sdsnew(buf);
slave = dictFetchValue(ri->slaves,key);
sdsfree(key);
return slave;
}在第12行可以看见其是在slaves字典中查询的，而查询的key是在第10行生成的。若没有查询到从服务器则返回的slave为NULL，则会继续执行第66行的代码，这里会执行一个createSentinelRedisInstance方法。这个方法在之前也提到过，它会创建一个服务器的实例并添加到指定的字典中，具体存储的字典是由第二个参数来决定的。之前提到过存储主服务器是这个参数是SRI_MASTER，存储哨兵服务器时是SRI_SENTINEL，这里存储的是从服务器，其参数为SRI_SLAVE。
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
