Redis源码分析--主从复制(2)主服务器执行SYNC命令
主服务器执行SYNC命令
一、部分重同步原理介绍：
上文[1]介绍了从服务器执行SLAVEOF，向主服务器同步的过程。提到了部分重同步的实现要求主从两端都维护一个复制偏移量，这篇文章就先介绍另一个关键结构：复制积压缓冲区。
struct redisServer {
/* Replication (master) */
int slaveseldb; /* Last SELECTed DB in replication output */
long long master_repl_offset; /* Global replication offset */
int repl_ping_slave_period; /* Master pings the slave every N seconds */
char *repl_backlog; /* Replication backlog for partial syncs */
long long repl_backlog_size; /* Backlog circular buffer size */
long long repl_backlog_histlen; /* Backlog actual data length */
long long repl_backlog_idx; /* Backlog circular buffer current offset */
long long repl_backlog_off; /* Replication offset of first byte in the
backlog buffer. */
};
- L6~L11：复制积压缓冲区；
- L4：server维护的复制偏移量；
复制积压缓冲区是由主服务器维护的一个固定长度(fixed-size)先进先出(FIFO)队列。当主服务器进行命令传播时，主服务器不仅将写命令发送给所有从服务器，也会将命令写入复制积压缓冲区。
当从服务器断线重连后，主、从服务器的复制偏移量出现不一致。这时主服务器判断从服务器的PSYNC runid offset命令的offset参数是否还在复制积压缓冲区中，如在，回复+CONTINUE，进行部分重同步。否则回复+FULLSYNC，进行完整重同步。
二、PSYNC命令执行：
/* SYNC ad PSYNC command implemenation. */
void syncCommand(redisClient *c) {
/* ignore SYNC if already slave or in monitor mode */
/* 如果c已有slave标志，说明已经进行同步过
* 从服务器向主服务器发送PSYNC命令只有两种情况：
* 1) 从服务器执行完SLAVEOF命令，向主服务器第一次同步；
* 2) 从服务器断线重连，主服务器server对象丢失了从服务器的client信息；*/
if (c->flags & REDIS_SLAVE) return;
/* Refuse SYNC requests if we are a slave but the link with our master
* is not ok... */
if (server.masterhost && server.repl_state != REDIS_REPL_CONNECTED) {
addReplyError(c,"Can't SYNC while not connected with my master");
return;
}
/* SYNC can't be issued when the server has pending data to send to
* the client about already issued commands. We need a fresh reply
* buffer registering the differences between the BGSAVE and the current
* dataset, so that we can copy to other slaves if needed. */
if (listLength(c->reply) != 0 || c->bufpos != 0) {
addReplyError(c,"SYNC and PSYNC are invalid with pending output");
return;
}
redisLog(REDIS_NOTICE,"Slave asks for synchronization");
/* Try a partial resynchronization if this is a PSYNC command.
* If it fails, we continue with usual full resynchronization, however
* when this happens masterTryPartialResynchronization() already
* replied with:
*
* +FULLRESYNC <runid> <offset>
*
* So the slave knows the new runid and offset to try a PSYNC later
* if the connection with the master is lost. */
if (!strcasecmp(c->argv[0]->ptr,"psync")) {
if (masterTryPartialResynchronization(c) == REDIS_OK) {
server.stat_sync_partial_ok++;
return; /* No full resync needed, return. */
} else {
char *master_runid = c->argv[1]->ptr;
/* Increment stats for failed PSYNCs, but only if the
* runid is not "?", as this is used by slaves to force a full
* resync on purpose when they are not albe to partially
* resync. */
if (master_runid[0] != '?') server.stat_sync_partial_err++;
}
} else {
/* If a slave uses SYNC, we are dealing with an old implementation
* of the replication protocol (like redis-cli --slave). Flag the client
* so that we don't expect to receive REPLCONF ACK feedbacks. */
c->flags |= REDIS_PRE_PSYNC_SLAVE;
}
/* Full resynchronization. */
server.stat_sync_full++;
/* Here we need to check if there is a background saving operation
* in progress, or if it is required to start one */
if (server.rdb_child_pid != -1) {
/* Ok a background save is in progress. Let's check if it is a good
* one for replication, i.e. if there is another slave that is
* registering differences since the server forked to save */
redisClient *slave;
listNode *ln;
listIter li;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_END) break;
}
if (ln) {
/* Perfect, the server is already registering differences for
* another slave. Set the right state, and copy the buffer. */
copyClientOutputBuffer(c,slave);
c->replstate = REDIS_REPL_WAIT_BGSAVE_END;
redisLog(REDIS_NOTICE,"Waiting for end of BGSAVE for SYNC");
} else {
/* No way, we need to wait for the next BGSAVE in order to
* register differences */
c->replstate = REDIS_REPL_WAIT_BGSAVE_START;
redisLog(REDIS_NOTICE,"Waiting for next BGSAVE for SYNC");
}
} else {
/* Ok we don't have a BGSAVE in progress, let's start one */
redisLog(REDIS_NOTICE,"Starting BGSAVE for SYNC");
if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {
redisLog(REDIS_NOTICE,"Replication failed, can't BGSAVE");
addReplyError(c,"Unable to perform background save");
return;
}
c->replstate = REDIS_REPL_WAIT_BGSAVE_END;
/* Flush the script cache for the new slave. */
replicationScriptCacheFlush();
}
if (server.repl_disable_tcp_nodelay)
anetDisableTcpNoDelay(NULL, c->fd); /* Non critical if it fails. */
c->repldbfd = -1;
/* 将c标记为从服务器，加入slaves链表 */
c->flags |= REDIS_SLAVE;
server.slaveseldb = -1; /* Force to re-emit the SELECT command. */
listAddNodeTail(server.slaves,c);
if (listLength(server.slaves) == 1 && server.repl_backlog == NULL)
createReplicationBacklog();
return;
}
- L4~L8：检查；
- L38：是PSYNC命令，尝试部分重同步；
二、部分重同步发送：
int masterTryPartialResynchronization(redisClient *c) {
long long psync_offset, psync_len;
char *master_runid = c->argv[1]->ptr;
char buf[128];
int buflen;
/* Is the runid of this master the same advertised by the wannabe slave
* via PSYNC? If runid changed this master is a different instance and
* there is no way to continue. */
if (strcasecmp(master_runid, server.runid)) {
/* Run id "?" is used by slaves that want to force a full resync. */
if (master_runid[0] != '?') {
redisLog(REDIS_NOTICE,"Partial resynchronization not accepted: "
"Runid mismatch (Client asked for '%s', I'm '%s')",
master_runid, server.runid);
} else {
redisLog(REDIS_NOTICE,"Full resync requested by slave.");
}
goto need_full_resync;
}
/* We still have the data our slave is asking for? */
/* PSYNC命令的offset参数放入psync_offset中 */
if (getLongLongFromObjectOrReply(c,c->argv[2],&psync_offset,NULL) !=
REDIS_OK) goto need_full_resync;
/* 从服务器维护的复制偏移量已经不在复制积压缓冲区中，只能进行完整重同步 */
if (!server.repl_backlog ||
psync_offset < server.repl_backlog_off ||
psync_offset > (server.repl_backlog_off + server.repl_backlog_histlen))
{
redisLog(REDIS_NOTICE,
"Unable to partial resync with the slave for lack of backlog (Slave request was: %lld).", psync_offset);
if (psync_offset > server.master_repl_offset) {
redisLog(REDIS_WARNING,
"Warning: slave tried to PSYNC with an offset that is greater than the master replication offset.");
}
goto need_full_resync;
}
/* If we reached this point, we are able to perform a partial resync:
* 1) Set client state to make it a slave.
* 2) Inform the client we can continue with +CONTINUE
* 3) Send the backlog data (from the offset to the end) to the slave. */
c->flags |= REDIS_SLAVE;
c->replstate = REDIS_REPL_ONLINE;
c->repl_ack_time = server.unixtime;
listAddNodeTail(server.slaves,c);
/* We can't use the connection buffers since they are used to accumulate
* new commands at this stage. But we are sure the socket send buffer is
* emtpy so this write will never fail actually. */
buflen = snprintf(buf,sizeof(buf),"+CONTINUE\r\n");
if (write(c->fd,buf,buflen) != buflen) {
freeClientAsync(c);
return REDIS_OK;
}
/* 将复制积压缓冲区中内容发给从服务器 */
psync_len = addReplyReplicationBacklog(c,psync_offset);
redisLog(REDIS_NOTICE,
"Partial resynchronization request accepted. Sending %lld bytes of backlog starting from offset %lld.", psync_len, psync_offset);
/* Note that we don't need to set the selected DB at server.slaveseldb
* to -1 to force the master to emit SELECT, since the slave already
* has this state from the previous connection with the master. */
refreshGoodSlavesCount();
return REDIS_OK; /* The caller can return, no full resync needed. */
need_full_resync:
/* We need a full resync for some reason... notify the client. */
psync_offset = server.master_repl_offset;
/* Add 1 to psync_offset if it the replication backlog does not exists
* as when it will be created later we'll increment the offset by one. */
if (server.repl_backlog == NULL) psync_offset++;
/* Again, we can't use the connection buffers (see above). */
buflen = snprintf(buf,sizeof(buf),"+FULLRESYNC %s %lld\r\n",
server.runid,psync_offset);
if (write(c->fd,buf,buflen) != buflen) {
freeClientAsync(c);
return REDIS_OK;
}
return REDIS_ERR;
}
- L12：从服务器第一次同步时，发送PYSNC ? -1命令，直接进行完整重同步；
- L28~L31：判断从服务器的复制偏移量在不在复制积压缓冲区中；
