Spurious debugging printf removed.

[redis.git] / src / replication.c

diff --git a/src/replication.c b/src/replication.c
index 9f8d9274827f36cca979c1838211adab27ea19f2..ef148f1c28e20f2d6620d26f383392cde2e6e1f6 100644 (file)
--- a/src/replication.c
+++ b/src/replication.c
@@ -10,38 +10,8 @@
 void replicationFeedSlaves(list *slaves, int dictid, robj **argv, int argc) {
     listNode *ln;
     listIter li;
 void replicationFeedSlaves(list *slaves, int dictid, robj **argv, int argc) {
     listNode *ln;
     listIter li;

-    int outc = 0, j;
-    robj **outv;
-    /* We need 1+(ARGS*3) objects since commands are using the new protocol
-     * and we one 1 object for the first "*<count>\r\n" multibulk count, then
-     * for every additional object we have "$<count>\r\n" + object + "\r\n". */
-    robj *static_outv[REDIS_STATIC_ARGS*3+1];
-    robj *lenobj;
-
-    if (argc <= REDIS_STATIC_ARGS) {
-        outv = static_outv;
-    } else {
-        outv = zmalloc(sizeof(robj*)*(argc*3+1));
-    }
-
-    lenobj = createObject(REDIS_STRING,
-            sdscatprintf(sdsempty(), "*%d\r\n", argc));
-    lenobj->refcount = 0;
-    outv[outc++] = lenobj;
-    for (j = 0; j < argc; j++) {
-        lenobj = createObject(REDIS_STRING,
-            sdscatprintf(sdsempty(),"$%lu\r\n",
-                (unsigned long) stringObjectLen(argv[j])));
-        lenobj->refcount = 0;
-        outv[outc++] = lenobj;
-        outv[outc++] = argv[j];
-        outv[outc++] = shared.crlf;
-    }
+    int j;

 
 

-    /* Increment all the refcounts at start and decrement at end in order to
-     * be sure to free objects if there is no slave in a replication state
-     * able to be feed with commands */
-    for (j = 0; j < outc; j++) incrRefCount(outv[j]);

     listRewind(slaves,&li);
     while((ln = listNext(&li))) {
         redisClient *slave = ln->value;
     listRewind(slaves,&li);
     while((ln = listNext(&li))) {
         redisClient *slave = ln->value;


@@ -49,47 +19,45 @@ void replicationFeedSlaves(list *slaves, int dictid, robj **argv, int argc) {
         /* Don't feed slaves that are still waiting for BGSAVE to start */
         if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START) continue;
 
         /* Don't feed slaves that are still waiting for BGSAVE to start */
         if (slave->replstate == REDIS_REPL_WAIT_BGSAVE_START) continue;
 

-        /* Feed all the other slaves, MONITORs and so on */
+        /* Feed slaves that are waiting for the initial SYNC (so these commands
+         * are queued in the output buffer until the intial SYNC completes),
+         * or are already in sync with the master. */

         if (slave->slaveseldb != dictid) {
             robj *selectcmd;
 
         if (slave->slaveseldb != dictid) {
             robj *selectcmd;
 

-            switch(dictid) {
-            case 0: selectcmd = shared.select0; break;
-            case 1: selectcmd = shared.select1; break;
-            case 2: selectcmd = shared.select2; break;
-            case 3: selectcmd = shared.select3; break;
-            case 4: selectcmd = shared.select4; break;
-            case 5: selectcmd = shared.select5; break;
-            case 6: selectcmd = shared.select6; break;
-            case 7: selectcmd = shared.select7; break;
-            case 8: selectcmd = shared.select8; break;
-            case 9: selectcmd = shared.select9; break;
-            default:
+            if (dictid >= 0 && dictid < REDIS_SHARED_SELECT_CMDS) {
+                selectcmd = shared.select[dictid];
+                incrRefCount(selectcmd);
+            } else {

                 selectcmd = createObject(REDIS_STRING,
                     sdscatprintf(sdsempty(),"select %d\r\n",dictid));
                 selectcmd = createObject(REDIS_STRING,
                     sdscatprintf(sdsempty(),"select %d\r\n",dictid));

-                selectcmd->refcount = 0;
-                break;

             }
             addReply(slave,selectcmd);
             }
             addReply(slave,selectcmd);

+            decrRefCount(selectcmd);

             slave->slaveseldb = dictid;
         }
             slave->slaveseldb = dictid;
         }

-        for (j = 0; j < outc; j++) addReply(slave,outv[j]);
+        addReplyMultiBulkLen(slave,argc);
+        for (j = 0; j < argc; j++) addReplyBulk(slave,argv[j]);

     }
     }

-    for (j = 0; j < outc; j++) decrRefCount(outv[j]);
-    if (outv != static_outv) zfree(outv);

 }
 
 }
 

-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;
     listNode *ln;
     listIter li;

-    int j;
+    int j, port;

     sds cmdrepr = sdsnew("+");
     robj *cmdobj;
     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);
     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) {
 
     for (j = 0; j < argc; j++) {
         if (argv[j]->encoding == REDIS_ENCODING_INT) {


@@ -118,7 +86,7 @@ void syncCommand(redisClient *c) {
 
     /* Refuse SYNC requests if we are a slave but the link with our master
      * is not ok... */
 
     /* 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;
     }
         addReplyError(c,"Can't SYNC while not connected with my master");
         return;
     }


@@ -135,7 +103,7 @@ 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 */
     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 */
         /* 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 */


@@ -151,8 +119,7 @@ void syncCommand(redisClient *c) {
         if (ln) {
             /* Perfect, the server is already registering differences for
              * another slave. Set the right state, and copy the buffer. */
         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 {
             c->replstate = REDIS_REPL_WAIT_BGSAVE_END;
             redisLog(REDIS_NOTICE,"Waiting for end of BGSAVE for SYNC");
         } else {


@@ -164,7 +131,7 @@ 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");
     } 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;
             redisLog(REDIS_NOTICE,"Replication failed, can't BGSAVE");
             addReplyError(c,"Unable to perform background save");
             return;


@@ -258,7 +225,7 @@ void updateSlavesWaitingBgsave(int bgsaveerr) {
                 redisLog(REDIS_WARNING,"SYNC failed. BGSAVE child returned an error");
                 continue;
             }
                 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));
                 redis_fstat(slave->repldbfd,&buf) == -1) {
                 freeClient(slave);
                 redisLog(REDIS_WARNING,"SYNC failed. Can't open/stat DB after BGSAVE: %s", strerror(errno));


@@ -275,7 +242,7 @@ void updateSlavesWaitingBgsave(int bgsaveerr) {
         }
     }
     if (startbgsave) {
         }
     }
     if (startbgsave) {

-        if (rdbSaveBackground(server.dbfilename) != REDIS_OK) {
+        if (rdbSaveBackground(server.rdb_filename) != REDIS_OK) {

             listIter li;
 
             listRewind(server.slaves,&li);
             listIter li;
 
             listRewind(server.slaves,&li);


@@ -294,14 +261,14 @@ void updateSlavesWaitingBgsave(int bgsaveerr) {
 
 /* Abort the async download of the bulk dataset while SYNC-ing with master */
 void replicationAbortSyncTransfer(void) {
 
 /* 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);
 
     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 */
 }
 
 /* Asynchronously read the SYNC payload we receive from a master */


@@ -315,23 +282,27 @@ void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int 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 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) {
+        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));
             redisLog(REDIS_WARNING,
                 "I/O error reading bulk count from MASTER: %s",
                 strerror(errno));

-            replicationAbortSyncTransfer();
-            return;
+            goto error;

         }
         }

+

         if (buf[0] == '-') {
             redisLog(REDIS_WARNING,
                 "MASTER aborted replication with an error: %s",
                 buf+1);
         if (buf[0] == '-') {
             redisLog(REDIS_WARNING,
                 "MASTER aborted replication with an error: %s",
                 buf+1);

-            replicationAbortSyncTransfer();
+            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?");
             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;
+            goto error;

         }
         server.repl_transfer_left = strtol(buf+1,NULL,10);
         redisLog(REDIS_NOTICE,
         }
         server.repl_transfer_left = strtol(buf+1,NULL,10);
         redisLog(REDIS_NOTICE,


@@ -350,16 +321,15 @@ void readSyncBulkPayload(aeEventLoop *el, int fd, void *privdata, int mask) {
         replicationAbortSyncTransfer();
         return;
     }
         replicationAbortSyncTransfer();
         return;
     }

-    server.repl_transfer_lastio = time(NULL);
+    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 synchrnonization: %s", strerror(errno));
     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 synchrnonization: %s", strerror(errno));

-        replicationAbortSyncTransfer();
-        return;
+        goto error;

     }
     server.repl_transfer_left -= nread;
     /* Check if the transfer is now complete */
     if (server.repl_transfer_left == 0) {
     }
     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;
             redisLog(REDIS_WARNING,"Failed trying to rename the temp DB into dump.rdb in MASTER <-> SLAVE synchronization: %s", strerror(errno));
             replicationAbortSyncTransfer();
             return;


@@ -371,7 +341,7 @@ 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);
          * 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;
             redisLog(REDIS_WARNING,"Failed trying to load the MASTER synchronization DB from disk");
             replicationAbortSyncTransfer();
             return;


@@ -382,84 +352,153 @@ 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.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");
         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;

 }
 
 }
 

-int syncWithMaster(void) {
-    char buf[1024], tmpfile[256], authcmd[1024];
-    int fd = anetTcpConnect(NULL,server.masterhost,server.masterport);
+void syncWithMaster(aeEventLoop *el, int fd, void *privdata, int mask) {
+    char buf[1024], tmpfile[256];

     int dfd, maxtries = 5;
     int dfd, maxtries = 5;

+    REDIS_NOTUSED(el);
+    REDIS_NOTUSED(privdata);
+    REDIS_NOTUSED(mask);

 
 

-    if (fd == -1) {
-        redisLog(REDIS_WARNING,"Unable to connect to MASTER: %s",
-            strerror(errno));
-        return REDIS_ERR;
+    /* 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_READABLE|AE_WRITABLE);
+

     /* AUTH with the master if required. */
     if(server.masterauth) {
     /* AUTH with the master if required. */
     if(server.masterauth) {

-       snprintf(authcmd, 1024, "AUTH %s\r\n", server.masterauth);
-       if (syncWrite(fd, authcmd, strlen(server.masterauth)+7, 5) == -1) {
-            close(fd);
+        char authcmd[1024];
+        size_t authlen;
+
+        authlen = snprintf(authcmd,sizeof(authcmd),"AUTH %s\r\n",server.masterauth);
+        if (syncWrite(fd,authcmd,authlen,server.repl_syncio_timeout*1000) == -1) {

             redisLog(REDIS_WARNING,"Unable to AUTH to MASTER: %s",
                 strerror(errno));
             redisLog(REDIS_WARNING,"Unable to AUTH to MASTER: %s",
                 strerror(errno));

-            return REDIS_ERR;
-       }
+            goto error;
+        }

         /* Read the AUTH result.  */
         /* Read the AUTH result.  */

-        if (syncReadLine(fd,buf,1024,3600) == -1) {
-            close(fd);
+        if (syncReadLine(fd,buf,1024,server.repl_syncio_timeout*1000) == -1) {

             redisLog(REDIS_WARNING,"I/O error reading auth result from MASTER: %s",
                 strerror(errno));
             redisLog(REDIS_WARNING,"I/O error reading auth result from MASTER: %s",
                 strerror(errno));

-            return REDIS_ERR;
+            goto error;

         }
         if (buf[0] != '+') {
         }
         if (buf[0] != '+') {

-            close(fd);

             redisLog(REDIS_WARNING,"Cannot AUTH to MASTER, is the masterauth password correct?");
             redisLog(REDIS_WARNING,"Cannot AUTH to MASTER, is the masterauth password correct?");

-            return REDIS_ERR;
+            goto error;

         }
     }
 
     /* Issue the SYNC command */
         }
     }
 
     /* Issue the SYNC command */

-    if (syncWrite(fd,"SYNC \r\n",7,5) == -1) {
-        close(fd);
+    if (syncWrite(fd,"SYNC \r\n",7,server.repl_syncio_timeout*1000) == -1) {

         redisLog(REDIS_WARNING,"I/O error writing to MASTER: %s",
             strerror(errno));
         redisLog(REDIS_WARNING,"I/O error writing to MASTER: %s",
             strerror(errno));

-        return REDIS_ERR;
+        goto error;

     }
 
     /* Prepare a suitable temp file for bulk transfer */
     while(maxtries--) {
         snprintf(tmpfile,256,
     }
 
     /* Prepare a suitable temp file for bulk transfer */
     while(maxtries--) {
         snprintf(tmpfile,256,

-            "temp-%d.%ld.rdb",(int)time(NULL),(long int)getpid());
+            "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) {
         dfd = open(tmpfile,O_CREAT|O_WRONLY|O_EXCL,0644);
         if (dfd != -1) break;
         sleep(1);
     }
     if (dfd == -1) {

-        close(fd);

         redisLog(REDIS_WARNING,"Opening the temp file needed for MASTER <-> SLAVE synchronization: %s",strerror(errno));
         redisLog(REDIS_WARNING,"Opening the temp file needed for MASTER <-> SLAVE synchronization: %s",strerror(errno));

-        return REDIS_ERR;
+        goto error;

     }
 
     /* Setup the non blocking download of the bulk file. */
     }
 
     /* Setup the non blocking download of the bulk file. */

-    if (aeCreateFileEvent(server.el, fd, AE_READABLE, readSyncBulkPayload, NULL)
+    if (aeCreateFileEvent(server.el,fd, AE_READABLE,readSyncBulkPayload,NULL)

             == AE_ERR)
     {
             == AE_ERR)
     {

-        close(fd);

         redisLog(REDIS_WARNING,"Can't create readable event for SYNC");
         redisLog(REDIS_WARNING,"Can't create readable event for SYNC");

-        return REDIS_ERR;
+        goto error;

     }
     }

-    server.replstate = REDIS_REPL_TRANSFER;
+
+    server.repl_state = REDIS_REPL_TRANSFER;

     server.repl_transfer_left = -1;
     server.repl_transfer_left = -1;

-    server.repl_transfer_s = fd;

     server.repl_transfer_fd = dfd;
     server.repl_transfer_fd = dfd;

-    server.repl_transfer_lastio = time(NULL);
+    server.repl_transfer_lastio = server.unixtime;

     server.repl_transfer_tmpfile = zstrdup(tmpfile);
     server.repl_transfer_tmpfile = zstrdup(tmpfile);

+    return;
+
+error:
+    server.repl_state = REDIS_REPL_CONNECT;
+    close(fd);
+    return;
+}
+
+int connectWithMaster(void) {
+    int fd;
+
+    fd = anetTcpNonBlockConnect(NULL,server.masterhost,server.masterport);
+    if (fd == -1) {
+        redisLog(REDIS_WARNING,"Unable to connect to MASTER: %s",
+            strerror(errno));
+        return REDIS_ERR;
+    }
+
+    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;
 }
 
     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")) {
 void slaveofCommand(redisClient *c) {
     if (!strcasecmp(c->argv[1]->ptr,"no") &&
         !strcasecmp(c->argv[2]->ptr,"one")) {


@@ -467,19 +506,36 @@ void slaveofCommand(redisClient *c) {
             sdsfree(server.masterhost);
             server.masterhost = NULL;
             if (server.master) freeClient(server.master);
             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();
                 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 {
             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);
         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.master) freeClient(server.master);

-        if (server.replstate == REDIS_REPL_TRANSFER)
+        disconnectSlaves(); /* Force our slaves to resync with us as well. */
+        if (server.repl_state == REDIS_REPL_TRANSFER)

             replicationAbortSyncTransfer();
             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);
     }
         redisLog(REDIS_NOTICE,"SLAVE OF %s:%d enabled (user request)",
             server.masterhost, server.masterport);
     }


@@ -488,23 +544,67 @@ void slaveofCommand(redisClient *c) {
 
 /* --------------------------- REPLICATION CRON  ---------------------------- */
 
 
 /* --------------------------- REPLICATION CRON  ---------------------------- */
 

-#define REDIS_REPL_TRANSFER_TIMEOUT 60
-

 void replicationCron(void) {
 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? */
     /* Bulk transfer I/O timeout? */

-    if (server.masterhost && server.replstate == REDIS_REPL_TRANSFER &&
-        (time(NULL)-server.repl_transfer_lastio) > REDIS_REPL_TRANSFER_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();
     }
 
     {
         redisLog(REDIS_WARNING,"Timeout receiving bulk data from MASTER...");
         replicationAbortSyncTransfer();
     }
 

+    /* Timed out master when we are an already connected slave? */
+    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 */
     /* 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...");
         redisLog(REDIS_NOTICE,"Connecting to MASTER...");

-        if (syncWithMaster() == REDIS_OK) {
-            redisLog(REDIS_NOTICE,"MASTER <-> SLAVE sync started: SYNC sent");
-            if (server.appendonly) rewriteAppendOnlyFileBackground();
+        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*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("*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. */
+                }
+            }

         }
     }
 }
         }
     }
 }