From 8e55537459f8be2d4310117f9f36c5a2ffa1451c Mon Sep 17 00:00:00 2001
From: antirez <antirez@gmail.com>
Date: Mon, 7 Sep 2015 16:09:23 +0200
Subject: [PATCH] Undo slaves state change on failed rdbSaveToSlavesSockets().

As Oran Agra suggested, in startBgsaveForReplication() when the BGSAVE
attempt returns an error, we scan the list of slaves in order to remove
them since there is no way to serve them currently.

However we check for the replication state BGSAVE_START, which was
modified by rdbSaveToSlaveSockets() before forking(). So when fork fails
the state of slaves remain BGSAVE_END and no cleanup is performed.

This commit fixes the problem by making rdbSaveToSlavesSockets() able to
undo the state change on fork failure.
---
 src/rdb.c | 36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/src/rdb.c b/src/rdb.c
index 2c354bd5..5566acb0 100644
--- a/src/rdb.c
+++ b/src/rdb.c
@@ -1649,27 +1649,43 @@ int rdbSaveToSlavesSockets(void) {
         exitFromChild((retval == C_OK) ? 0 : 1);
     } else {
         /* Parent */
-        zfree(clientids); /* Not used by parent. Free ASAP. */
         server.stat_fork_time = ustime()-start;
         server.stat_fork_rate = (double) zmalloc_used_memory() * 1000000 / server.stat_fork_time / (1024*1024*1024); /* GB per second. */
         latencyAddSampleIfNeeded("fork",server.stat_fork_time/1000);
         if (childpid == -1) {
             serverLog(LL_WARNING,"Can't save in background: fork: %s",
                 strerror(errno));
-            zfree(fds);
+
+            /* Undo the state change. The caller will perform cleanup on
+             * all the slaves in BGSAVE_START state, but an early call to
+             * replicationSetupSlaveForFullResync() turned it into BGSAVE_END */
+            listRewind(server.slaves,&li);
+            while((ln = listNext(&li))) {
+                client *slave = ln->value;
+                int j;
+
+                for (j = 0; j < numfds; j++) {
+                    if (slave->id == clientids[j]) {
+                        slave->replstate = SLAVE_STATE_WAIT_BGSAVE_START;
+                        break;
+                    }
+                }
+            }
             close(pipefds[0]);
             close(pipefds[1]);
-            return C_ERR;
+        } else {
+            serverLog(LL_NOTICE,"Background RDB transfer started by pid %d",
+                childpid);
+            server.rdb_save_time_start = time(NULL);
+            server.rdb_child_pid = childpid;
+            server.rdb_child_type = RDB_CHILD_TYPE_SOCKET;
+            updateDictResizePolicy();
         }
-        serverLog(LL_NOTICE,"Background RDB transfer started by pid %d",childpid);
-        server.rdb_save_time_start = time(NULL);
-        server.rdb_child_pid = childpid;
-        server.rdb_child_type = RDB_CHILD_TYPE_SOCKET;
-        updateDictResizePolicy();
+        zfree(clientids);
         zfree(fds);
-        return C_OK;
+        return (childpid == -1) ? C_ERR : C_OK;
     }
-    return C_OK; /* unreached */
+    return C_OK; /* Unreached. */
 }
 
 void saveCommand(client *c) {