[PATCH] replication: fix bug with read-only replica as a bootstrap leader

[Konstantin Belyavskiy]

Another broken case. Adding a new replica to cluster:
+		if (replica->applier->remote_is_ro &&
+		    replica->applier->vclock.signature == 0)
In this case we may got an ER_READONLY, since signature is not 0.
So leader election now has two phases:
 1. To select among read-write replicas.
 2. If no such found, try old algorithm for backward compatibility
    (case then all replicas exist in cluster table).

Closes #3257
---
https://github.com/tarantool/tarantool/issues/3257
https://github.com/tarantool/tarantool/tree/kbelyavs/gh-3257-fix-bug-with-read-only-as-a-leader

 src/box/replication.cc                         | 22 +++++++++++++++++-----
 test/replication/replica_uuid_ro3.lua          |  1 +
 test/replication/replicaset_ro_mostly.result   | 20 ++++++++++++++++++++
 test/replication/replicaset_ro_mostly.test.lua |  8 ++++++++
 4 files changed, 46 insertions(+), 5 deletions(-)
 create mode 120000 test/replication/replica_uuid_ro3.lua

diff --git a/src/box/replication.cc b/src/box/replication.cc
index 0b770c913..8dcf1f656 100644
--- a/src/box/replication.cc
+++ b/src/box/replication.cc
@@ -691,16 +691,24 @@ struct replica *
 replicaset_leader(void)
 {
 	struct replica *leader = NULL;
+	bool skip_ro = true;
+	/**
+	 * Two loops, first prefers read-write replicas among others.
+	 * Second for backward compatibility, if there is no such
+	 * replicas at all.
+	 */
+loop:
 	replicaset_foreach(replica) {
 		if (replica->applier == NULL)
 			continue;
 		/**
-		 * While bootstrapping a new cluster,
-		 * read-only replicas shouldn't be considered
-		 * as a leader.
+		 * While bootstrapping a new cluster, read-only
+		 * replicas shouldn't be considered as a leader.
+		 * The only exception if there is no read-write
+		 * replicas since there is still a possibility
+		 * that all replicas exist in cluster table.
 		 */
-		if (replica->applier->remote_is_ro &&
-		    replica->applier->vclock.signature == 0)
+		if (skip_ro && replica->applier->remote_is_ro)
 			continue;
 		if (leader == NULL) {
 			leader = replica;
@@ -721,6 +729,10 @@ replicaset_leader(void)
 			continue;
 		leader = replica;
 	}
+	if (skip_ro && leader == NULL) {
+		skip_ro = false;
+		goto loop;
+	}
 	return leader;
 }
 
diff --git a/test/replication/replica_uuid_ro3.lua b/test/replication/replica_uuid_ro3.lua
new file mode 120000
index 000000000..342d71c57
--- /dev/null
+++ b/test/replication/replica_uuid_ro3.lua
@@ -0,0 +1 @@
+replica_uuid_ro.lua
\ No newline at end of file
diff --git a/test/replication/replicaset_ro_mostly.result b/test/replication/replicaset_ro_mostly.result
index d753a182d..b9e8f1fe8 100644
--- a/test/replication/replicaset_ro_mostly.result
+++ b/test/replication/replicaset_ro_mostly.result
@@ -53,6 +53,26 @@ create_cluster_uuid(SERVERS, UUID)
 test_run:wait_fullmesh(SERVERS)
 ---
 ...
+-- Add third replica
+name = 'replica_uuid_ro3'
+---
+...
+test_run:cmd(create_cluster_cmd1:format(name, name))
+---
+- true
+...
+test_run:cmd(create_cluster_cmd2:format(name, uuid.new()))
+---
+- true
+...
+test_run:cmd('switch replica_uuid_ro3')
+---
+- true
+...
+test_run:cmd('switch default')
+---
+- true
+...
 -- Cleanup.
 test_run:drop_cluster(SERVERS)
 ---
diff --git a/test/replication/replicaset_ro_mostly.test.lua b/test/replication/replicaset_ro_mostly.test.lua
index 539ca5a13..f2c2d0d11 100644
--- a/test/replication/replicaset_ro_mostly.test.lua
+++ b/test/replication/replicaset_ro_mostly.test.lua
@@ -26,5 +26,13 @@ test_run:cmd("setopt delimiter ''");
 -- Deploy a cluster.
 create_cluster_uuid(SERVERS, UUID)
 test_run:wait_fullmesh(SERVERS)
+
+-- Add third replica
+name = 'replica_uuid_ro3'
+test_run:cmd(create_cluster_cmd1:format(name, name))
+test_run:cmd(create_cluster_cmd2:format(name, uuid.new()))
+test_run:cmd('switch replica_uuid_ro3')
+test_run:cmd('switch default')
+
 -- Cleanup.
 test_run:drop_cluster(SERVERS)
-- 
2.14.3 (Apple Git-98)