replication: fix rebootstrap in case the instance is listed in box.cfg.replication

When checking wheter rejoin is needed, replica loops through all the
instances in box.cfg.replication, which makes it believe that there is a
master holding files, needed by it, since it accounts itself just like
all other instances.
So make replica skip itself when finding an instance which holds files
needed by it, and determining whether rebootstrap is needed.

We already have a working test for the issue, it missed the issue due to
replica.lua replication settings. Fix replica.lua to optionally include
itself in box.cfg.replication, so that the corresponding test works
correctly.

Closes #4759

(cherry picked from commit dbcfaf70)

src/box/replication.cc

@@ -730,7 +730,12 @@ replicaset_needs_rejoin(struct replica **master)
 	struct replica *leader = NULL;
 	replicaset_foreach(replica) {
 		struct applier *applier = replica->applier;
-		if (applier == NULL)
+		/*
+		 * Skip the local instance, we shouldn't perform a
+		 * check against our own gc vclock.
+		 */
+		if (applier == NULL || tt_uuid_is_equal(&replica->uuid,
+							&INSTANCE_UUID))
 			continue;
 
 		const struct ballot *ballot = &applier->ballot;

test/replication/replica.lua

 #!/usr/bin/env tarantool
 
+repl_include_self = arg[1] and arg[1] == 'true' or false
+repl_list = nil
+
+if repl_include_self then
+    repl_list = {os.getenv("MASTER"), os.getenv("LISTEN")}
+else
+    repl_list = os.getenv("MASTER")
+end
+
 box.cfg({
     listen              = os.getenv("LISTEN"),
-    replication         = os.getenv("MASTER"),
+    replication         = repl_list,
     memtx_memory        = 107374182,
     replication_timeout = 0.1,
     replication_connect_timeout = 0.5,

test/replication/replica_rejoin.result

@@ -37,7 +37,7 @@ test_run:cmd("create server replica with rpl_master=default, script='replication
 ---
 - true
 ...
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 ---
 - true
 ...
@@ -111,7 +111,7 @@ box.cfg{checkpoint_count = checkpoint_count}
 ...
 -- Restart the replica. Since xlogs have been removed,
 -- it is supposed to rejoin without changing id.
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 ---
 - true
 ...
@@ -158,7 +158,7 @@ box.space.test:select()
   - [30, 30]
 ...
 -- Check that restart works as usual.
-test_run:cmd("restart server replica")
+test_run:cmd("restart server replica with args='true'")
 box.info.replication[1].upstream.status == 'follow' or box.info
 ---
 - true
@@ -210,7 +210,7 @@ test_run:wait_cond(function() return #fio.glob(fio.pathjoin(box.cfg.wal_dir, '*.
 box.cfg{checkpoint_count = checkpoint_count}
 ---
 ...
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 ---
 - true
 ...
@@ -252,7 +252,7 @@ test_run:cleanup_cluster()
 box.space.test:truncate()
 ---
 ...
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 ---
 - true
 ...
@@ -349,7 +349,7 @@ _ = test_run:wait_vclock('default', vclock)
 ---
 ...
 -- Restart the replica. It should successfully rebootstrap.
-test_run:cmd("restart server replica")
+test_run:cmd("restart server replica with args='true'")
 box.space.test:select()
 ---
 - - [1]

test/replication/replica_rejoin.test.lua

@@ -17,7 +17,7 @@ _ = box.space.test:insert{3}
 
 -- Join a replica, then stop it.
 test_run:cmd("create server replica with rpl_master=default, script='replication/replica.lua'")
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 test_run:cmd("switch replica")
 box.info.replication[1].upstream.status == 'follow' or box.info
 box.space.test:select()
@@ -45,7 +45,7 @@ box.cfg{checkpoint_count = checkpoint_count}
 
 -- Restart the replica. Since xlogs have been removed,
 -- it is supposed to rejoin without changing id.
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 box.info.replication[2].downstream.vclock ~= nil or box.info
 test_run:cmd("switch replica")
 box.info.replication[1].upstream.status == 'follow' or box.info
@@ -60,7 +60,7 @@ test_run:cmd("switch replica")
 box.space.test:select()
 
 -- Check that restart works as usual.
-test_run:cmd("restart server replica")
+test_run:cmd("restart server replica with args='true'")
 box.info.replication[1].upstream.status == 'follow' or box.info
 box.space.test:select()
 
@@ -78,7 +78,7 @@ for i = 1, 3 do box.space.test:insert{i * 100} end
 fio = require('fio')
 test_run:wait_cond(function() return #fio.glob(fio.pathjoin(box.cfg.wal_dir, '*.xlog')) == 1 end) or fio.pathjoin(box.cfg.wal_dir, '*.xlog')
 box.cfg{checkpoint_count = checkpoint_count}
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 test_run:cmd("switch replica")
 box.info.status -- orphan
 box.space.test:select()
@@ -94,7 +94,7 @@ test_run:cmd("stop server replica")
 test_run:cmd("cleanup server replica")
 test_run:cleanup_cluster()
 box.space.test:truncate()
-test_run:cmd("start server replica")
+test_run:cmd("start server replica with args='true'")
 -- Subscribe the master to the replica.
 replica_listen = test_run:cmd("eval replica 'return box.cfg.listen'")
 replica_listen ~= nil
@@ -128,7 +128,7 @@ for i = 1, 10 do box.space.test:replace{2} end
 vclock = test_run:get_vclock('replica')
 _ = test_run:wait_vclock('default', vclock)
 -- Restart the replica. It should successfully rebootstrap.
-test_run:cmd("restart server replica")
+test_run:cmd("restart server replica with args='true'")
 box.space.test:select()
 box.snapshot()
 box.space.test:replace{2}