struct timeval tv;
gettimeofday(&tv,NULL);
- cmdrepr = sdscatprintf(cmdrepr,"%ld.%ld ",(long)tv.tv_sec,(long)tv.tv_usec);
+ cmdrepr = sdscatprintf(cmdrepr,"%ld.%06ld ",(long)tv.tv_sec,(long)tv.tv_usec);
if (dictid != 0) cmdrepr = sdscatprintf(cmdrepr,"(db %d) ", dictid);
for (j = 0; j < argc; j++) {
/* Asynchronously read the SYNC payload we receive from a master */
void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
- unsigned char buf[4096]
- size_t nread, readlen;
+ char buf[4096];
+ ssize_t nread, readlen;
+ REDIS_NOTUSED(el);
+ REDIS_NOTUSED(privdata);
+ REDIS_NOTUSED(mask);
+
+ /* If repl_transfer_left == -1 we still have to read the bulk length
+ * from the master reply. */
+ if (server.repl_transfer_left == -1) {
+ if (syncReadLine(fd,buf,1024,3600) == -1) {
+ redisLog(REDIS_WARNING,
+ "I/O error reading bulk count from MASTER: %s",
+ strerror(errno));
+ replicationAbortSyncTransfer();
+ return;
+ }
+ if (buf[0] == '-') {
+ redisLog(REDIS_WARNING,
+ "MASTER aborted replication with an error: %s",
+ buf+1);
+ replicationAbortSyncTransfer();
+ return;
+ } 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 = time(NULL);
+ 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?");
+ replicationAbortSyncTransfer();
+ return;
+ }
+ server.repl_transfer_left = strtol(buf+1,NULL,10);
+ redisLog(REDIS_NOTICE,
+ "MASTER <-> SLAVE sync: receiving %ld bytes from master",
+ server.repl_transfer_left);
+ return;
+ }
- readlen = (server.repl_transfer_left < sizeof(buf)) ?
- server.repl_transfer_left : sizeof(buf);
+ /* Read bulk data */
+ readlen = (server.repl_transfer_left < (signed)sizeof(buf)) ?
+ server.repl_transfer_left : (signed)sizeof(buf);
nread = read(fd,buf,readlen);
if (nread <= 0) {
redisLog(REDIS_WARNING,"I/O error trying to sync with MASTER: %s",
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.dbfilename) != 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 */
- aeDeleteFileEvent(server.el,server.repl_transfer_s,AE_READABLE);
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.replstate = REDIS_REPL_CONNECTED;
+ redisLog(REDIS_NOTICE, "MASTER <-> SLAVE sync: Finished with success");
}
}
int syncWithMaster(void) {
char buf[1024], tmpfile[256], authcmd[1024];
- off_t dumpsize;
int fd = anetTcpConnect(NULL,server.masterhost,server.masterport);
int dfd, maxtries = 5;
strerror(errno));
return REDIS_ERR;
}
- /* Read the bulk write count */
- if (syncReadLine(fd,buf,1024,3600) == -1) {
- close(fd);
- redisLog(REDIS_WARNING,"I/O error reading bulk count from MASTER: %s",
- strerror(errno));
- return REDIS_ERR;
- }
- if (buf[0] == '-') {
- close(fd);
- redisLog(REDIS_WARNING,"MASTER aborted replication with an error: %s",
- buf+1);
- return REDIS_ERR;
- } else if (buf[0] != '$') {
- close(fd);
- redisLog(REDIS_WARNING,"Bad protocol from MASTER, the first byte is not '$', are you sure the host and port are right?");
- return REDIS_ERR;
- }
- dumpsize = strtol(buf+1,NULL,10);
- redisLog(REDIS_NOTICE,"Receiving %ld bytes data dump from MASTER",dumpsize);
- /* Read the bulk write data on a temp file */
+
+ /* Prepare a suitable temp file for bulk transfer */
while(maxtries--) {
snprintf(tmpfile,256,
"temp-%d.%ld.rdb",(int)time(NULL),(long int)getpid());
}
/* Setup the non blocking download of the bulk file. */
- if (aeCreateFileEvent(server.el, fd, AE_READABLE,readSyncBulkPayload) ==
- AE_ERR)
+ if (aeCreateFileEvent(server.el, fd, AE_READABLE, readSyncBulkPayload, NULL)
+ == AE_ERR)
{
close(fd);
redisLog(REDIS_WARNING,"Can't create readable event for SYNC");
return REDIS_ERR;
}
server.replstate = REDIS_REPL_TRANSFER;
- server.repl_transfer_left = dumpsize;
+ server.repl_transfer_left = -1;
server.repl_transfer_s = fd;
server.repl_transfer_fd = dfd;
server.repl_transfer_lastio = time(NULL);
/* --------------------------- REPLICATION CRON ---------------------------- */
-#define REDIS_REPL_TRANSFER_TIMEOUT 60
+#define REDIS_REPL_TIMEOUT 60
+#define REDIS_REPL_PING_SLAVE_PERIOD 10
void replicationCron(void) {
/* Bulk transfer I/O timeout? */
if (server.masterhost && server.replstate == REDIS_REPL_TRANSFER &&
- (time(NULL)-server.repl_transfer_lastio) > REDIS_REPL_TRANSFER_TIMEOUT)
+ (time(NULL)-server.repl_transfer_lastio) > REDIS_REPL_TIMEOUT)
{
redisLog(REDIS_WARNING,"Timeout receiving bulk data from MASTER...");
replicationAbortSyncTransfer();
}
+ /* Timed out master when we are an already connected slave? */
+ if (server.masterhost && server.replstate == REDIS_REPL_CONNECTED &&
+ (time(NULL)-server.master->lastinteraction) > REDIS_REPL_TIMEOUT)
+ {
+ redisLog(REDIS_WARNING,"MASTER time out: no data nor PING received...");
+ freeClient(server.master);
+ }
+
/* Check if we should connect to a MASTER */
- if (server.replstate == REDIS_REPL_CONNECT && !(loops % 10)) {
+ if (server.replstate == REDIS_REPL_CONNECT) {
redisLog(REDIS_NOTICE,"Connecting to MASTER...");
if (syncWithMaster() == REDIS_OK) {
- redisLog(REDIS_NOTICE,"MASTER <-> SLAVE sync succeeded");
+ redisLog(REDIS_NOTICE,"MASTER <-> SLAVE sync started: SYNC sent");
if (server.appendonly) rewriteAppendOnlyFileBackground();
}
}
+
+ /* 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 % (REDIS_REPL_PING_SLAVE_PERIOD*10))) {
+ 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("PING\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. */
+ }
+ }
+ }
+ }
}
projects / redis.git / blobdiff