From 7fb14b73ba67c70eb6c8a728c892c8d5b3fe954e Mon Sep 17 00:00:00 2001
From: antirez <antirez@gmail.com>
Date: Thu, 27 Mar 2014 14:54:57 +0100
Subject: [PATCH] Cluster: save/restore vars that must persist after recovery.

This fixes issue #1479.
---
 src/cluster.c | 42 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/src/cluster.c b/src/cluster.c
index 42ed6098..5370e5ec 100644
--- a/src/cluster.c
+++ b/src/cluster.c
@@ -121,6 +121,25 @@ int clusterLoadConfig(char *filename) {
         argv = sdssplitargs(line,&argc);
         if (argv == NULL) goto fmterr;
 
+        /* Handle the special "vars" line. Don't pretend it is the last
+         * line even if it actually is when generated by Redis. */
+        if (strcasecmp(argv[0],"vars") == 0) {
+            for (j = 1; j < argc; j += 2) {
+                if (strcasecmp(argv[j],"currentEpoch") == 0) {
+                    server.cluster->currentEpoch =
+                            strtoull(argv[j+1],NULL,10);
+                } else if (strcasecmp(argv[j],"last_vote_epoch") == 0) {
+                    server.cluster->last_vote_epoch =
+                            strtoull(argv[j+1],NULL,10);
+                } else {
+                    redisLog(REDIS_WARNING,
+                        "Skipping unknown cluster config variable '%s'",
+                        argv[j]);
+                }
+            }
+            continue;
+        }
+
         /* Create this node if it does not exist */
         n = clusterLookupNode(argv[0]);
         if (!n) {
@@ -227,10 +246,13 @@ int clusterLoadConfig(char *filename) {
     /* Config sanity check */
     redisAssert(server.cluster->myself != NULL);
     redisLog(REDIS_NOTICE,"Node configuration loaded, I'm %.40s", myself->name);
-    /* Set the currentEpoch to the max epoch found in the master.
-     * FIXME: this should actually be part of the persistent state, as
-     * documented in the Github issue #1479. */
-    server.cluster->currentEpoch = clusterGetMaxEpoch();
+
+    /* Something that should never happen: currentEpoch smaller than
+     * the max epoch found in the nodes configuration. However we handle this
+     * as some form of protection against manual editing of critical files. */
+    if (clusterGetMaxEpoch() > server.cluster->currentEpoch) {
+        server.cluster->currentEpoch = clusterGetMaxEpoch();
+    }
     return REDIS_OK;
 
 fmterr:
@@ -253,10 +275,18 @@ fmterr:
  * bigger we pad our payload with newlines that are anyway ignored and truncate
  * the file afterward. */
 int clusterSaveConfig(int do_fsync) {
-    sds ci = clusterGenNodesDescription(REDIS_NODE_HANDSHAKE);
-    size_t content_size = sdslen(ci);
+    sds ci;
+    size_t content_size;
     struct stat sb;
     int fd;
+
+    /* Get the nodes description and concatenate our "vars" directive to
+     * save currentEpoch and last_vote_epoch. */
+    ci = clusterGenNodesDescription(REDIS_NODE_HANDSHAKE);
+    ci = sdscatprintf(ci,"vars currentEpoch %llu last_vote_epoch %llu\n",
+        (unsigned long long) server.cluster->currentEpoch,
+        (unsigned long long) server.cluster->last_vote_epoch);
+    content_size = sdslen(ci);
     
     if ((fd = open(server.cluster_configfile,O_WRONLY|O_CREAT,0644))
         == -1) goto err;