X-Git-Url: https://git.saurik.com/redis.git/blobdiff_plain/632e4c09acad87b999dd944413ac5b75207de571..dfc25454701638d39bc75fbc3f9c55619b503bd0:/src/replication.c?ds=inline

diff --git a/src/replication.c b/src/replication.c
index c8ebb6e7..6c0091e8 100644
--- a/src/replication.c
+++ b/src/replication.c
@@ -50,17 +50,23 @@ void replicationFeedSlaves(list *slaves, int dictid, robj **argv, int argc) {
     }
 }
 
-void replicationFeedMonitors(list *monitors, int dictid, robj **argv, int argc) {
+void replicationFeedMonitors(redisClient *c, list *monitors, int dictid, robj **argv, int argc) {
     listNode *ln;
     listIter li;
-    int j;
+    int j, port;
     sds cmdrepr = sdsnew("+");
     robj *cmdobj;
+    char ip[32];
     struct timeval tv;
 
     gettimeofday(&tv,NULL);
     cmdrepr = sdscatprintf(cmdrepr,"%ld.%06ld ",(long)tv.tv_sec,(long)tv.tv_usec);
-    if (dictid != 0) cmdrepr = sdscatprintf(cmdrepr,"(db %d) ", dictid);
+    if (c->flags & REDIS_LUA_CLIENT) {
+        cmdrepr = sdscatprintf(cmdrepr,"[%d lua] ", dictid);
+    } else {
+        anetPeerToString(c->fd,ip,&port);
+        cmdrepr = sdscatprintf(cmdrepr,"[%d %s:%d] ", dictid,ip,port);
+    }
 
     for (j = 0; j < argc; j++) {
         if (argv[j]->encoding == REDIS_ENCODING_INT) {
@@ -89,7 +95,7 @@ void syncCommand(redisClient *c) {
 
     /* 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) {
+    if (server.masterhost && server.repl_state != REDIS_REPL_CONNECTED) {
         addReplyError(c,"Can't SYNC while not connected with my master");
         return;
     }
@@ -106,7 +112,7 @@ void syncCommand(redisClient *c) {
     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) {
+    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 */
@@ -122,8 +128,7 @@ void syncCommand(redisClient *c) {
         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);
+            copyClientOutputBuffer(c,slave);
             c->replstate = REDIS_REPL_WAIT_BGSAVE_END;
             redisLog(REDIS_NOTICE,"Waiting for end of BGSAVE for SYNC");
         } else {
@@ -135,7 +140,7 @@ void syncCommand(redisClient *c) {
     } 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) {
+        if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {
             redisLog(REDIS_NOTICE,"Replication failed, can't BGSAVE");
             addReplyError(c,"Unable to perform background save");
             return;
@@ -229,7 +234,7 @@ void updateSlavesWaitingBgsave(int bgsaveerr) {
                 redisLog(REDIS_WARNING,"SYNC failed. BGSAVE child returned an error");
                 continue;
             }
-            if ((slave->repldbfd = open(server.dbfilename,O_RDONLY)) == -1 ||
+            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));
@@ -246,7 +251,7 @@ void updateSlavesWaitingBgsave(int bgsaveerr) {
         }
     }
     if (startbgsave) {
-        if (rdbSaveBackground(server.dbfilename) != REDIS_OK) {
+        if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {
             listIter li;
 
             listRewind(server.slaves,&li);
@@ -265,14 +270,14 @@ void updateSlavesWaitingBgsave(int bgsaveerr) {
 
 /* Abort the async download of the bulk dataset while SYNC-ing with master */
 void replicationAbortSyncTransfer(void) {
-    redisAssert(server.replstate == REDIS_REPL_TRANSFER);
+    redisAssert(server.repl_state == REDIS_REPL_TRANSFER);
 
     aeDeleteFileEvent(server.el,server.repl_transfer_s,AE_READABLE);
     close(server.repl_transfer_s);
     close(server.repl_transfer_fd);
     unlink(server.repl_transfer_tmpfile);
     zfree(server.repl_transfer_tmpfile);
-    server.replstate = REDIS_REPL_CONNECT;
+    server.repl_state = REDIS_REPL_CONNECT;
 }
 
 /* Asynchronously read the SYNC payload we receive from a master */
@@ -333,7 +338,7 @@ void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
     server.repl_transfer_left -= nread;
     /* Check if the transfer is now complete */
     if (server.repl_transfer_left == 0) {
-        if (rename(server.repl_transfer_tmpfile,server.dbfilename) == -1) {
+        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;
@@ -345,7 +350,7 @@ void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
          * 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) {
+        if (rdbLoad(server.rdb_filename) != REDIS_OK) {
             redisLog(REDIS_WARNING,"Failed trying to load the MASTER synchronization DB from disk");
             replicationAbortSyncTransfer();
             return;
@@ -356,8 +361,24 @@ void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
         server.master = createClient(server.repl_transfer_s);
         server.master->flags |= REDIS_MASTER;
         server.master->authenticated = 1;
-        server.replstate = REDIS_REPL_CONNECTED;
+        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;
@@ -374,10 +395,18 @@ void syncWithMaster(aeEventLoop *el, int fd, void *privdata, int mask) {
     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;
+    }
+
+    redisLog(REDIS_NOTICE,"Non blocking connect for SYNC fired the event.");
     /* This event should only be triggered once since it is used to have a
      * non-blocking connect(2) to the master. It has been triggered when this
      * function is called, so we can delete it. */
-    aeDeleteFileEvent(server.el,fd,AE_WRITABLE);
+    aeDeleteFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE);
 
     /* AUTH with the master if required. */
     if(server.masterauth) {
@@ -430,7 +459,7 @@ void syncWithMaster(aeEventLoop *el, int fd, void *privdata, int mask) {
         goto error;
     }
 
-    server.replstate = REDIS_REPL_TRANSFER;
+    server.repl_state = REDIS_REPL_TRANSFER;
     server.repl_transfer_left = -1;
     server.repl_transfer_fd = dfd;
     server.repl_transfer_lastio = time(NULL);
@@ -438,7 +467,7 @@ void syncWithMaster(aeEventLoop *el, int fd, void *privdata, int mask) {
     return;
 
 error:
-    server.replstate = REDIS_REPL_CONNECT;
+    server.repl_state = REDIS_REPL_CONNECT;
     close(fd);
     return;
 }
@@ -453,7 +482,7 @@ int connectWithMaster(void) {
         return REDIS_ERR;
     }
 
-    if (aeCreateFileEvent(server.el,fd,AE_WRITABLE,syncWithMaster,NULL) ==
+    if (aeCreateFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE,syncWithMaster,NULL) ==
             AE_ERR)
     {
         close(fd);
@@ -461,11 +490,24 @@ int connectWithMaster(void) {
         return REDIS_ERR;
     }
 
+    server.repl_transfer_lastio = time(NULL);
     server.repl_transfer_s = fd;
-    server.replstate = REDIS_REPL_CONNECTING;
+    server.repl_state = REDIS_REPL_CONNECTING;
     return REDIS_OK;
 }
 
+/* This function can be called when a non blocking connection is currently
+ * in progress to undo it. */
+void undoConnectWithMaster(void) {
+    int fd = server.repl_transfer_s;
+
+    redisAssert(server.repl_state == REDIS_REPL_CONNECTING);
+    aeDeleteFileEvent(server.el,fd,AE_READABLE|AE_WRITABLE);
+    close(fd);
+    server.repl_transfer_s = -1;
+    server.repl_state = REDIS_REPL_CONNECT;
+}
+
 void slaveofCommand(redisClient *c) {
     if (!strcasecmp(c->argv[1]->ptr,"no") &&
         !strcasecmp(c->argv[2]->ptr,"one")) {
@@ -473,19 +515,35 @@ void slaveofCommand(redisClient *c) {
             sdsfree(server.masterhost);
             server.masterhost = NULL;
             if (server.master) freeClient(server.master);
-            if (server.replstate == REDIS_REPL_TRANSFER)
+            if (server.repl_state == REDIS_REPL_TRANSFER)
                 replicationAbortSyncTransfer();
-            server.replstate = REDIS_REPL_NONE;
+            else if (server.repl_state == REDIS_REPL_CONNECTING)
+                undoConnectWithMaster();
+            server.repl_state = REDIS_REPL_NONE;
             redisLog(REDIS_NOTICE,"MASTER MODE enabled (user request)");
         }
     } else {
+        long port;
+
+        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. */
         sdsfree(server.masterhost);
         server.masterhost = sdsdup(c->argv[1]->ptr);
-        server.masterport = atoi(c->argv[2]->ptr);
+        server.masterport = port;
         if (server.master) freeClient(server.master);
-        if (server.replstate == REDIS_REPL_TRANSFER)
+        if (server.repl_state == REDIS_REPL_TRANSFER)
             replicationAbortSyncTransfer();
-        server.replstate = REDIS_REPL_CONNECT;
+        server.repl_state = REDIS_REPL_CONNECT;
         redisLog(REDIS_NOTICE,"SLAVE OF %s:%d enabled (user request)",
             server.masterhost, server.masterport);
     }
@@ -494,32 +552,36 @@ void slaveofCommand(redisClient *c) {
 
 /* --------------------------- REPLICATION CRON  ---------------------------- */
 
-#define REDIS_REPL_TIMEOUT 60
-#define REDIS_REPL_PING_SLAVE_PERIOD 10
-
 void replicationCron(void) {
+    /* Non blocking connection timeout? */
+    if (server.masterhost && server.repl_state == REDIS_REPL_CONNECTING &&
+        (time(NULL)-server.repl_transfer_lastio) > server.repl_timeout)
+    {
+        redisLog(REDIS_WARNING,"Timeout connecting to the MASTER...");
+        undoConnectWithMaster();
+    }
+
     /* Bulk transfer I/O timeout? */
-    if (server.masterhost && server.replstate == REDIS_REPL_TRANSFER &&
-        (time(NULL)-server.repl_transfer_lastio) > REDIS_REPL_TIMEOUT)
+    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...");
         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)
+    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 */
-    if (server.replstate == REDIS_REPL_CONNECT) {
+    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 (server.appendonly) rewriteAppendOnlyFileBackground();
         }
     }
     
@@ -527,7 +589,7 @@ void replicationCron(void) {
      * 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))) {
+    if (!(server.cronloops % (server.repl_ping_slave_period*10))) {
         listIter li;
         listNode *ln;
 
@@ -540,7 +602,7 @@ void replicationCron(void) {
             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"));
+                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