redisソース分析:プライマリ・スレーブ・モードでのサーバからの同期ポリシー
11096 ワード
サーバからプライマリサーバとの接続が確立された後、プライマリサーバに同期コマンドを送信し、同期を要求します.同期コマンドを送信すると、対応する読み込み操作をreadSyncBulkPayloadに設定します.
readSyncBulkPayload関数は、プライマリ・サーバによって確立された同期ファイルを接続から読み出し、すべての同期データを複数回に分けて読み取ることができます.データが8 MBを超えると、読み取り操作のたびに書き込みディスク操作が行われ、最後に書き込みディスク操作を行うと大きな遅延が発生する可能性があります.
サーバからのデータの同期が完了していない場合、サーバから読み取り専用が設定されていない場合は、データの書き込みを行うことができます.読み取り専用が設定されている場合、同期ではプライマリノードのみが書き込みを実行でき、他のノードは書き込みを実行できません.サーバから完全な同期ファイルを受信した後、メモリを空にしてrdbファイルをメモリにロードします.
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). */
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
",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 don't care about the reply, it can be +PONG or an error since
* the server requires AUTH. As long as it replies correctly, it's
* fine from our point of view. */
if (buf[0] != '-' && buf[0] != '+') {
redisLog(REDIS_WARNING,"Unexpected reply to PING from master.");
goto error;
} else {
redisLog(REDIS_NOTICE,
"Master replied to PING, replication can continue...");
}
}
/* 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;
}
}
/* 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);
}
}
/* Issue the SYNC command */
if (syncWrite(fd,"SYNC\r
",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");
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;
}
readSyncBulkPayload関数は、プライマリ・サーバによって確立された同期ファイルを接続から読み出し、すべての同期データを複数回に分けて読み取ることができます.データが8 MBを超えると、読み取り操作のたびに書き込みディスク操作が行われ、最後に書き込みディスク操作を行うと大きな遅延が発生する可能性があります.
/* Asynchronously read the SYNC payload we receive from a master */
#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) {
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;
}
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;
/* 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");
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 flags |= REDIS_MASTER;
server.master->authenticated = 1;
server.repl_state = REDIS_REPL_CONNECTED;
redisLog(REDIS_NOTICE, "MASTER SLAVE sync: Finished with success");
/* 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 synchrnization! 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;
}
サーバからのデータの同期が完了していない場合、サーバから読み取り専用が設定されていない場合は、データの書き込みを行うことができます.読み取り専用が設定されている場合、同期ではプライマリノードのみが書き込みを実行でき、他のノードは書き込みを実行できません.サーバから完全な同期ファイルを受信した後、メモリを空にしてrdbファイルをメモリにロードします.