在执行了slaveof命令后,复制流程进入
slaveofCommand参数内部处理
void slaveofCommand(redisClient *c) {
# 处理slaveof no one
if (!strcasecmp(c->argv[1]->ptr,"no") &&
!strcasecmp(c->argv[2]->ptr,"one")) {
if (server.masterhost) {
sdsfree(server.masterhost);
server.masterhost = NULL;
if (server.master) freeClient(server.master);
cancelReplicationHandshake();
server.repl_state = REDIS_REPL_NONE;
redisLog(REDIS_NOTICE,"MASTER MODE enabled (user request)");
}
} else {
long port;
#如果slaveof 的是已经配置的主,则返回
if ((getLongFromObjectOrReply(c, c->argv[2], &port, NULL) != REDIS_OK))
return;
/* Check if we are already attached to the specified slave */
if (server.masterhost && !strcasecmp(server.masterhost,c->argv[1]->ptr)
&& server.masterport == port) {
redisLog(REDIS_NOTICE,"SLAVE OF would result into synchronization with the master we are already connected with. No operation performed.");
addReplySds(c,sdsnew("+OK Already connected to specified master\r\n"));
return;
}
/* There was no previous master or the user specified a different one,
* we can continue. */
* #指定新的ip+port
sdsfree(server.masterhost);
server.masterhost = sdsdup(c->argv[1]->ptr);
server.masterport = port;
if (server.master) freeClient(server.master);
disconnectSlaves(); /* Force our slaves to resync with us as well. */
cancelReplicationHandshake();#吧之前的连接都取消掉
server.repl_state = REDIS_REPL_CONNECT;
redisLog(REDIS_NOTICE,"SLAVE OF %s:%d enabled (user request)",
server.masterhost, server.masterport);
}
addReply(c,shared.ok);
}
看到上面的过程中并没有与master建立连接的过程,在replicationCron函数内部
void replicationCron(void) {
/* Non blocking connection timeout? */
#先检查是否有连接超时的,超时的就undoconnectwithmaster
if (server.masterhost &&
(server.repl_state == REDIS_REPL_CONNECTING ||
server.repl_state == REDIS_REPL_RECEIVE_PONG) &&
(time(NULL)-server.repl_transfer_lastio) > server.repl_timeout)
{
redisLog(REDIS_WARNING,"Timeout connecting to the MASTER...");
undoConnectWithMaster();
}
/* Bulk transfer I/O timeout? */
#检查下载数据文件是否有超时的,有的话执行replicationAbortSyncTransfer
if (server.masterhost && server.repl_state == REDIS_REPL_TRANSFER &&
(time(NULL)-server.repl_transfer_lastio) > server.repl_timeout)
{
redisLog(REDIS_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.");
replicationAbortSyncTransfer();
}
/* Timed out master when we are an already connected slave? */
#检查交互时间超时的
if (server.masterhost && server.repl_state == REDIS_REPL_CONNECTED &&
(time(NULL)-server.master->lastinteraction) > server.repl_timeout)
{
redisLog(REDIS_WARNING,"MASTER time out: no data nor PING received...");
freeClient(server.master);
}
/* Check if we should connect to a MASTER */
#这部分通过connectwithmaster建立正式的连接
if (server.repl_state == REDIS_REPL_CONNECT) {
redisLog(REDIS_NOTICE,"Connecting to MASTER...");
if (connectWithMaster() == REDIS_OK) {
redisLog(REDIS_NOTICE,"MASTER <-> SLAVE sync started");
}
}
/* 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. */
if (!(server.cronloops % (server.repl_ping_slave_period * server.hz))) {
listIter li;
listNode *ln;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
/* Don't ping slaves that are in the middle of a bulk transfer
* with the master for first synchronization. */
if (slave->replstate == REDIS_REPL_SEND_BULK) continue;
if (slave->replstate == REDIS_REPL_ONLINE) {
/* If the slave is online send a normal ping */
addReplySds(slave,sdsnew("*1\r\n$4\r\nPING\r\n"));
} else {
/* Otherwise we are in the pre-synchronization stage.
* Just a newline will do the work of refreshing the
* connection last interaction time, and at the same time
* we'll be sure that being a single char there are no
* short-write problems. */
if (write(slave->fd, "\n", 1) == -1) {
/* Don't worry, it's just a ping. */
}
}
}
}
}
下面看下connectwithmaster
int connectWithMaster(void) {
int fd;
#建立连接
fd = anetTcpNonBlockConnect(NULL,server.masterhost,server.masterport);
if (fd == -1) {
redisLog(REDIS_WARNING,"Unable to connect to MASTER: %s",
strerror(errno));
return REDIS_ERR;
}
#注册事件,执行函数syncwithmaster,同master sync数据
if (aeCreateFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE,syncWithMaster,NULL) ==
AE_ERR)
{
close(fd);
redisLog(REDIS_WARNING,"Can't create readable event for SYNC");
return REDIS_ERR;
}
server.repl_transfer_lastio = server.unixtime;
server.repl_transfer_s = fd;
server.repl_state = REDIS_REPL_CONNECTING;
return REDIS_OK;
}
在看下syncwithmaster
void syncWithMaster(aeEventLoop *el, int fd, void *privdata, int mask) {
char tmpfile[256], *err;
int dfd, maxtries = 5;
int sockerr = 0;
socklen_t errlen = sizeof(sockerr);
REDIS_NOTUSED(el);
REDIS_NOTUSED(privdata);
REDIS_NOTUSED(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 == REDIS_REPL_NONE) {
close(fd);
return;
}
/* Check for errors in the socket. */
if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &sockerr, &errlen) == -1)
sockerr = errno;
if (sockerr) {
aeDeleteFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE);
redisLog(REDIS_WARNING,"Error condition on socket for SYNC: %s",
strerror(sockerr));
goto error;
}
/* If we were connecting, it's time to send a non blocking PING, we want to
* make sure the master is able to reply before going into the actual
* replication process where we have long timeouts in the order of
* seconds (in the meantime the slave would block). */
* # 先ping pong一下,看下连接是否正常
if (server.repl_state == REDIS_REPL_CONNECTING) {
redisLog(REDIS_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. */
aeDeleteFileEvent(server.el,fd,AE_WRITABLE);
server.repl_state = REDIS_REPL_RECEIVE_PONG;
/* Send the PING, don't check for errors at all, we have the timeout
* that will take care about this. */
syncWrite(fd,"PING\r\n",6,100);
return;
}
/* Receive the PONG command. */
if (server.repl_state == REDIS_REPL_RECEIVE_PONG) {
char buf[1024];
/* Delete the readable event, we no longer need it now that there is
* the PING reply to read. */
aeDeleteFileEvent(server.el,fd,AE_READABLE);
/* Read the reply with explicit timeout. */
buf[0] = '\0';
if (syncReadLine(fd,buf,sizeof(buf),
server.repl_syncio_timeout*1000) == -1)
{
redisLog(REDIS_WARNING,
"I/O error reading PING reply from master: %s",
strerror(errno));
goto error;
}
/* 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 (buf[0] != '+' &&
strncmp(buf,"-NOAUTH",7) != 0 &&
strncmp(buf,"-ERR operation not permitted",28) != 0)
{
redisLog(REDIS_WARNING,"Error reply to PING from master: '%s'",buf);
goto error;
} else {
redisLog(REDIS_NOTICE,
"Master replied to PING, replication can continue...");
}
}
#然后进行认证的过程
/* AUTH with the master if required. */
if(server.masterauth) {
err = sendSynchronousCommand(fd,"AUTH",server.masterauth,NULL);
if (err) {
redisLog(REDIS_WARNING,"Unable to AUTH to MASTER: %s",err);
sdsfree(err);
goto error;
}
}
#配置slave的port
/* Set the slave port, so that Master's INFO command can list the
* slave listening port correctly. */
{
sds port = sdsfromlonglong(server.port);
err = sendSynchronousCommand(fd,"REPLCONF","listening-port",port,
NULL);
sdsfree(port);
/* Ignore the error if any, not all the Redis versions support
* REPLCONF listening-port. */
if (err) {
redisLog(REDIS_NOTICE,"(non critical): Master does not understand REPLCONF listening-port: %s", err);
sdsfree(err);
}
}
#然后开始sync,搞个临时文件,通过readSyncBulkPayload接收rdb
/* Issue the SYNC command */
if (syncWrite(fd,"SYNC\r\n",6,server.repl_syncio_timeout*1000) == -1) {
redisLog(REDIS_WARNING,"I/O error writing to MASTER: %s",
strerror(errno));
goto error;
}
/* Prepare a suitable temp file for bulk transfer */
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) {
redisLog(REDIS_WARNING,"Opening the temp file needed for MASTER <-> SLAVE synchronization: %s",strerror(errno));
goto error;
}
/* Setup the non blocking download of the bulk file. */
if (aeCreateFileEvent(server.el,fd, AE_READABLE,readSyncBulkPayload,NULL)
== AE_ERR)
{
redisLog(REDIS_WARNING,
"Can't create readable event for SYNC: %s (fd=%d)",
strerror(errno),fd);
goto error;
}
server.repl_state = REDIS_REPL_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:
close(fd);
server.repl_transfer_s = -1;
server.repl_state = REDIS_REPL_CONNECT;
return;
}
下面看下readsyncbulkpayload
#define REPL_MAX_WRITTEN_BEFORE_FSYNC (1024*1024*8) /* 8 MB */
void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
char buf[4096];
ssize_t nread, readlen;
off_t left;
REDIS_NOTUSED(el);
REDIS_NOTUSED(privdata);
REDIS_NOTUSED(mask);
/* If repl_transfer_size == -1 we still have to read the bulk length
* from the master reply. */
if (server.repl_transfer_size == -1) {
#从master批量读取数据,1024字节批量获取的?
if (syncReadLine(fd,buf,1024,server.repl_syncio_timeout*1000) == -1) {
redisLog(REDIS_WARNING,
"I/O error reading bulk count from MASTER: %s",
strerror(errno));
goto error;
}
#下面是校验接受的文件是否正确
if (buf[0] == '-') {
redisLog(REDIS_WARNING,
"MASTER aborted replication with an error: %s",
buf+1);
goto error;
} else if (buf[0] == '\0') {
/* At this stage just a newline works as a PING in order to take
* the connection live. So we refresh our last interaction
* timestamp. */
server.repl_transfer_lastio = server.unixtime;
return;
} else if (buf[0] != '$') {
redisLog(REDIS_WARNING,"Bad protocol from MASTER, the first byte is not '$', are you sure the host and port are right?");
goto error;
}
server.repl_transfer_size = strtol(buf+1,NULL,10);
redisLog(REDIS_NOTICE,
"MASTER <-> SLAVE sync: receiving %ld bytes from master",
server.repl_transfer_size);
return;
}
/* Read bulk data */
left = server.repl_transfer_size - server.repl_transfer_read;
readlen = (left < (signed)sizeof(buf)) ? left : (signed)sizeof(buf);
nread = read(fd,buf,readlen);
if (nread <= 0) {
redisLog(REDIS_WARNING,"I/O error trying to sync with MASTER: %s",
(nread == -1) ? strerror(errno) : "connection lost");
replicationAbortSyncTransfer();
return;
}
server.repl_transfer_lastio = server.unixtime;
if (write(server.repl_transfer_fd,buf,nread) != nread) {
redisLog(REDIS_WARNING,"Write error or short write writing to the DB dump file needed for MASTER <-> SLAVE synchronization: %s", strerror(errno));
goto error;
}
server.repl_transfer_read += nread;
#同步数据到磁盘上
/* Sync data on disk from time to time, otherwise at the end of the transfer
* we may suffer a big delay as the memory buffers are copied into the
* actual disk. */
if (server.repl_transfer_read >=
server.repl_transfer_last_fsync_off + REPL_MAX_WRITTEN_BEFORE_FSYNC)
{
off_t sync_size = server.repl_transfer_read -
server.repl_transfer_last_fsync_off;
rdb_fsync_range(server.repl_transfer_fd,
server.repl_transfer_last_fsync_off, sync_size);
server.repl_transfer_last_fsync_off += sync_size;
}
/* Check if the transfer is now complete */
if (server.repl_transfer_read == server.repl_transfer_size) {
if (rename(server.repl_transfer_tmpfile,server.rdb_filename) == -1) {
redisLog(REDIS_WARNING,"Failed trying to rename the temp DB into dump.rdb in MASTER <-> SLAVE synchronization: %s", strerror(errno));
replicationAbortSyncTransfer();
return;
}
redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Loading DB in memory");
#加载rdb文件
signalFlushedDb(-1);
emptyDb();
/* Before loading the DB into memory we need to delete the readable
* handler, otherwise it will get called recursively since
* rdbLoad() will call the event loop to process events from time to
* time for non blocking loading. */
aeDeleteFileEvent(server.el,server.repl_transfer_s,AE_READABLE);
if (rdbLoad(server.rdb_filename) != REDIS_OK) {
redisLog(REDIS_WARNING,"Failed trying to load the MASTER synchronization DB from disk");
replicationAbortSyncTransfer();
return;
}
/* Final setup of the connected slave <- master link */
zfree(server.repl_transfer_tmpfile);
close(server.repl_transfer_fd);
server.master = createClient(server.repl_transfer_s);
server.master->flags |= REDIS_MASTER;
server.master->authenticated = 1;
server.repl_state = REDIS_REPL_CONNECTED;
redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Finished with success");
#在加载完rdb文件后,出发了aof重写
/* Restart the AOF subsystem now that we finished the sync. This
* will trigger an AOF rewrite, and when done will start appending
* to the new file. */
if (server.aof_state != REDIS_AOF_OFF) {
int retry = 10;
stopAppendOnly();
while (retry-- && startAppendOnly() == REDIS_ERR) {
redisLog(REDIS_WARNING,"Failed enabling the AOF after successful master synchronization! Trying it again in one second.");
sleep(1);
}
if (!retry) {
redisLog(REDIS_WARNING,"FATAL: this slave instance finished the synchronization with its master, but the AOF can't be turned on. Exiting now.");
exit(1);
}
}
}
return;
error:
replicationAbortSyncTransfer();
return;
}
正常命令的同步执行代码路径是call()->propagate()->replicationFeedSlaves()