/* This function is called at the end of every background saving.
* The argument bgsaveerr is REDIS_OK if the background saving succeeded
* otherwise REDIS_ERR is passed to the function.
*
* The goal of this function is to handle slaves waiting for a successful
* background saving in order to perform non-blocking synchronization. */
void updateSlavesWaitingBgsave(int bgsaveerr) {
//backgroundSaveDoneHandler在BGSAVE操作完成后，调用这里来处理可能的从库事件。
listNode *ln;
int startbgsave = 0;
listIter li;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {//循环遍历每一个从库，查看其状态进行相应的处理。
redisClient *slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START) {
startbgsave = 1;//刚才在做bgsave的时候，有客户端来请求sync同步，但是我没有理他，现在得给他准备了。
slave->replstate = REDIS_REPL_WAIT_BGSAVE_END;//修改这个状态后，新的写入操作会记录到这个连接的缓存里
} else if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_END) {
//后台保存完成，下面需要发送rdb文件了，丫的够大的
struct redis_stat buf;
if (bgsaveerr != REDIS_OK) {
freeClient(slave);
redisLog(REDIS_WARNING,"SYNC failed. BGSAVE child returned an error");
continue;
}
//打开这个rdb_filename,要准备给这个slave发送数据了。
if ((slave->repldbfd = open(server.rdb_filename,O_RDONLY)) == -1 ||
redis_fstat(slave->repldbfd,&buf) == -1) {
freeClient(slave);
redisLog(REDIS_WARNING,"SYNC failed. Can't open/stat DB after BGSAVE: %s", strerror(errno));
continue;
}
slave->repldboff = 0;
slave->repldbsize = buf.st_size;
//记住此时slave->repldbfd没有关闭，可写事件的时候就不需要打开了。
slave->replstate = REDIS_REPL_SEND_BULK;
aeDeleteFileEvent(server.el,slave->fd,AE_WRITABLE);//删掉之前的可写回调，注册为sendBulkToSlave
if (aeCreateFileEvent(server.el, slave->fd, AE_WRITABLE, sendBulkToSlave, slave) == AE_ERR) {
freeClient(slave);
continue;
}
}
}
if (startbgsave) {//悲剧，又有要sync的，还得保存一次。
if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {
listIter li;
listRewind(server.slaves,&li);
redisLog(REDIS_WARNING,"SYNC failed. BGSAVE failed");
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
//这下面似乎有问题，replstate已经在上面被设置为了_END。https://github.com/antirez/redis/issues/1308
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START)
freeClient(slave);
}
}
}
}
void bgsaveCommand(redisClient *c) {
if (server.bgsavechildpid != -1) {
addReplyError(c,"Background save already in progress");
return;
}
if (rdbSaveBackground(server.dbfilename) == REDIS_OK) {
addReplyStatus(c,"Background saving started");
} else {
addReply(c,shared.err);
}
}
void bgsaveCommand(redisClient *c) {
if (server.bgsavechildpid != -1) {
addReplyError(c,"Background save already in progress");
} else if (server.bgrewritechildpid != -1) {
addReplyError(c,"Can't BGSAVE while AOF log rewriting is in progress");
} else if (rdbSaveBackground(server.dbfilename) == REDIS_OK) {
addReplyStatus(c,"Background saving started");
} else {
addReply(c,shared.err);
}
}
void bgsaveCommand(redisClient *c) {
if (server.bgsavechildpid != -1) {
addReplySds(c,sdsnew("-ERR background save already in progress\r\n"));
return;
}
if (rdbSaveBackground(server.dbfilename) == REDIS_OK) {
char *status = "+Background saving started\r\n";
addReplySds(c,sdsnew(status));
} else {
addReply(c,shared.err);
}
}
/* This function is called at the end of every backgrond saving.
* The argument bgsaveerr is REDIS_OK if the background saving succeeded
* otherwise REDIS_ERR is passed to the function.
*
* The goal of this function is to handle slaves waiting for a successful
* background saving in order to perform non-blocking synchronization. */
void updateSlavesWaitingBgsave(int bgsaveerr) {
listNode *ln;
int startbgsave = 0;
listIter li;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START) {
startbgsave = 1;
slave->replstate = REDIS_REPL_WAIT_BGSAVE_END;
} else if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_END) {
struct redis_stat buf;
if (bgsaveerr != REDIS_OK) {
freeClient(slave);
redisLog(REDIS_WARNING,"SYNC failed. BGSAVE child returned an error");
continue;
}
if ((slave->repldbfd = open(server.dbfilename,O_RDONLY)) == -1 ||
redis_fstat(slave->repldbfd,&buf) == -1) {
freeClient(slave);
redisLog(REDIS_WARNING,"SYNC failed. Can't open/stat DB after BGSAVE: %s", strerror(errno));
continue;
}
slave->repldboff = 0;
slave->repldbsize = buf.st_size;
slave->replstate = REDIS_REPL_SEND_BULK;
aeDeleteFileEvent(server.el,slave->fd,AE_WRITABLE);
if (aeCreateFileEvent(server.el, slave->fd, AE_WRITABLE, sendBulkToSlave, slave) == AE_ERR) {
freeClient(slave);
continue;
}
}
}
if (startbgsave) {
if (rdbSaveBackground(server.dbfilename) != REDIS_OK) {
listIter li;
listRewind(server.slaves,&li);
redisLog(REDIS_WARNING,"SYNC failed. BGSAVE failed");
while((ln = listNext(&li))) {
redisClient *slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START)
freeClient(slave);
}
}
}
}
/* ----------------------- */
void
checkpointCommand (client * c)
{
sds bitarray;
serverLog (LL_NOTICE, "Client ask for checkpoint");
/* Here we need to check if there is a background saving operation in progress */
if (server.rdb_child_pid != -1 || server.aof_child_pid != -1)
{
serverLog (LL_NOTICE,
"Another background operation is in progress. Unable to perform CHECKPOINT.");
addReplyError (c, "Unable to perform CHECKPOINT");
return;
}
/* set bitarray from argument */
bitarray = get_bitmap_from_argv (c->argc - 1, c->argv + 1);
if (!bitarray)
{
addReplyError (c, "Invalid argument format.");
return;
}
serverLog (LL_NOTICE, "Starting CHECKPOINT");
arc.checkpoint_slots = bitarray;
if (rdbSaveBackground (arc.checkpoint_filename) != C_OK)
{
serverLog (LL_NOTICE, "Replication failed, can't CHECKPOINT");
addReplyError (c, "Unable to perform CHECKPOINT");
sdsfree (bitarray);
arc.checkpoint_slots = NULL;
return;
}
arc.checkpoint_seqnum = arc.smr_seqnum; //TODO 이건 여기가 아님.
serverLog (LL_NOTICE,
"Partial Checkpoint sequence num:%lld", arc.smr_seqnum);
c->replstate = SLAVE_STATE_WAIT_BGSAVE_END;
c->repldbfd = -1;
arc.checkpoint_client = c;
return;
}
void syncCommand(redisClient *c) {
/* ignore SYNC if aleady slave or in monitor mode */
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.replstate != 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) {
addReplyError(c,"SYNC is invalid with pending input");
return;
}
redisLog(REDIS_NOTICE,"Slave ask for synchronization");
/* Here we need to check if there is a background saving operation
* in progress, or if it is required to start one */
if (server.bgsavechildpid != -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. */
listRelease(c->reply);
c->reply = listDup(slave->reply);
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.dbfilename) != 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;
}
c->repldbfd = -1;
c->flags |= REDIS_SLAVE;
c->slaveseldb = 0;
listAddNodeTail(server.slaves,c);
return;
}
void syncCommand(redisClient *c) {
//响应redis的sync指令
/* ignore SYNC if already slave or in monitor mode */
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) {//如果服务端还有数据没有发送给客户端，那先不处理sync请求
addReplyError(c,"SYNC is invalid with pending input");
return;
}
redisLog(REDIS_NOTICE,"Slave ask for synchronization");
/* 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);
//正好现在有RDB程序在保存日志，那么我需要查看一下是否正好有从库在等待这个RDB结束的操作
//如果有，我就可以偷偷的将其尚未发送，累积起来的写操作日志拷贝一份，插队到后面作为从库。
//等待全部RDB文件发送完后将这部分累积的日志发送给这个新从库，其实就是类似插队的意思，插上对后，顺便打一碗饭
while((ln = listNext(&li))) {
slave = ln->value;
if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_END) break;
}
if (ln) {//正好有其他slave出发了BGSAVE操作，那么就正好可以通过copy同伴的缓冲区的方式追上。
//这些buffer是一个客户端注册成为从库之后，主库会主动的在replicationFeedSlaves
//里面将新写入日志追加到这里的。只是那个时候还不能发送，没注册写事件
/* Perfect, the server is already registering differences for
* another slave. Set the right state, and copy the buffer. */
copyClientOutputBuffer(c,slave);//将要发送给之前的slave的数据拷贝一份，也就是也要发送给新的这个从库。
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 */
//由于之前正好没有客户端在后台保存过程中发送sync，所以只能老老实话等待下一个bgsave了。
c->replstate = REDIS_REPL_WAIT_BGSAVE_START;
redisLog(REDIS_NOTICE,"Waiting for next BGSAVE for SYNC");
}
} else {//没办法了，老老实实进行BGSAVE，
/* 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;
}
//SYNC命令只是尝试启动RDB快照，真正的数据发送再快照完成后的updateSlavesWaitingBgsave
if (server.repl_disable_tcp_nodelay)
anetDisableTcpNoDelay(NULL, c->fd); /* Non critical if it fails. */
c->repldbfd = -1;
c->flags |= REDIS_SLAVE;//成功，标记为slave
c->slaveseldb = 0;
listAddNodeTail(server.slaves,c);
return;
}
