From c95a582a749a83b117bdd51f4a7a29a616a0bf3c Mon Sep 17 00:00:00 2001
From: Madelyn Olson <matolson@amazon.com>
Date: Thu, 30 May 2019 11:50:31 -0700
Subject: [PATCH] Add configuration option for allowing reads on cluster down

---
 redis.conf    | 16 ++++++++++++++++
 src/cluster.c | 13 ++++++++++---
 src/config.c  |  2 ++
 src/server.h  |  2 ++
 4 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/redis.conf b/redis.conf
index d3776017..870849a7 100644
--- a/redis.conf
+++ b/redis.conf
@@ -1194,6 +1194,22 @@ lua-time-limit 5000
 #
 # cluster-replica-no-failover no
 
+# This option, when set to yes, allows nodes to serve read traffic while the
+# the cluster is in a down state, as long as it believes it owns the slots. 
+#
+# This is useful for two cases.  The first case is for when an application 
+# doesn't require consistency of data during node failures or network partitions.
+# One example of this is a cache, where as long as the node has the data it
+# should be able to serve it. 
+#
+# The second use case is for configurations that don't meet the recommended  
+# three shards but want to enable cluster mode and scale later. A 
+# master outage in a 1 or 2 shard configuration causes a read/write outage to the
+# entire cluster without this option set, with it set there is only a write outage.
+# Without a quorum of masters, slot ownership will not change automatically. 
+#
+# cluster-allow-reads-when-down no
+
 # In order to setup your cluster make sure to read the documentation
 # available at http://redis.io web site.
 
diff --git a/src/cluster.c b/src/cluster.c
index 9e6ddb2c..4024035e 100644
--- a/src/cluster.c
+++ b/src/cluster.c
@@ -5595,8 +5595,12 @@ clusterNode *getNodeByQuery(client *c, struct redisCommand *cmd, robj **argv, in
      * without redirections or errors in all the cases. */
     if (n == NULL) return myself;
 
-    /* Cluster is globally down but we got keys? We can't serve the request. */
-    if (server.cluster->state != CLUSTER_OK) {
+    /* Cluster is globally down but we got keys? We only serve the request
+     * if it is a read command and when allow_reads_when_down is enabled. */
+    if ((server.cluster->state != CLUSTER_OK) &&
+        !(server.cluster_allow_reads_when_down && ((cmd->flags & CMD_READONLY)
+        || (cmd->proc == evalCommand) || (cmd->proc == evalShaCommand)))) 
+    {
         if (error_code) *error_code = CLUSTER_REDIR_DOWN_STATE;
         return NULL;
     }
@@ -5701,7 +5705,10 @@ int clusterRedirectBlockedClientIfNeeded(client *c) {
         dictEntry *de;
         dictIterator *di;
 
-        /* If the cluster is down, unblock the client with the right error. */
+        /* If the cluster is down, unblock the client with the right error.
+         * If the cluster is configured to allow reads on cluster down, we
+         * still want to emit this error since a write will be required
+         * to unblock them which may never come.  */
         if (server.cluster->state == CLUSTER_FAIL) {
             clusterRedirectClient(c,NULL,0,CLUSTER_REDIR_DOWN_STATE);
             return 1;
diff --git a/src/config.c b/src/config.c
index 5bfb0de5..5ff333fe 100644
--- a/src/config.c
+++ b/src/config.c
@@ -2166,6 +2166,8 @@ standardConfig configs[] = {
     createBoolConfig("syslog-enabled", NULL, IMMUTABLE_CONFIG, server.syslog_enabled, 0, NULL, NULL),
     createBoolConfig("cluster-enabled", NULL, IMMUTABLE_CONFIG, server.cluster_enabled, 0, NULL, NULL),
     createBoolConfig("appendonly", NULL, MODIFIABLE_CONFIG, server.aof_enabled, 0, NULL, updateAppendonly),
+    createBoolConfig("cluster-allow-reads-when-down", NULL, MODIFIABLE_CONFIG, server.cluster_allow_reads_when_down, 0, NULL, NULL},
+
 
     /* String Configs */
     createStringConfig("aclfile", NULL, IMMUTABLE_CONFIG, ALLOW_EMPTY_STRING, server.acl_filename, "", NULL, NULL),
diff --git a/src/server.h b/src/server.h
index f2c93241..b5e51002 100644
--- a/src/server.h
+++ b/src/server.h
@@ -1334,6 +1334,8 @@ struct redisServer {
                                       to set in order to suppress certain
                                       native Redis Cluster features. Check the
                                       REDISMODULE_CLUSTER_FLAG_*. */
+    int cluster_allow_reads_when_down; /* Are reads allowed when the cluster
+                                        is down? */
     /* Scripting */
     lua_State *lua; /* The Lua interpreter. We use just one for all clients */
     client *lua_client;   /* The "fake client" to query Redis from Lua */