[PATCH v3] replication: fix exit with ER_NO_SUCH_USER during bootstrap

[Vladimir Davydov]

Pushed to 1.9, here's the final version:

>From 33950162f3e766d413567cd75aaa7e6c384831bd Mon Sep 17 00:00:00 2001
From: Serge Petrenko <sergepetrenko at tarantool.org>
Date: Thu, 23 Aug 2018 14:08:51 +0300
Subject: [PATCH] replication: fix exit with ER_NO_SUCH_USER during bootstrap

When replication is configured via some user created in box.once()
function and box.once() takes more than replication_timeout seconds
to execute, appliers recieve ER_NO_SUCH_USER error, which they don't
handle. This leads to occasional test failures in replication suite.
Fix this by handling the aforementioned case in applier_f() and add a
test case.

Closes #3637

diff --git a/src/box/applier.cc b/src/box/applier.cc
index b9f041d8..16a87389 100644
--- a/src/box/applier.cc
+++ b/src/box/applier.cc
@@ -596,7 +596,8 @@ applier_f(va_list ap)
 				applier_log_error(applier, e);
 				applier_disconnect(applier, APPLIER_LOADING);
 				goto reconnect;
-			} else if (e->errcode() == ER_ACCESS_DENIED) {
+			} else if (e->errcode() == ER_ACCESS_DENIED ||
+				   e->errcode() == ER_NO_SUCH_USER) {
 				/* Invalid configuration */
 				applier_log_error(applier, e);
 				applier_disconnect(applier, APPLIER_DISCONNECTED);
diff --git a/test/replication/misc.result b/test/replication/misc.result
index 9df2a2c4..76e7fd5e 100644
--- a/test/replication/misc.result
+++ b/test/replication/misc.result
@@ -232,3 +232,55 @@ test_run:drop_cluster(SERVERS)
 box.schema.user.revoke('guest', 'replication')
 ---
 ...
+--
+-- Test case for gh-3637. Before the fix replica would exit with
+-- an error. Now check that we don't hang and successfully connect.
+--
+fiber = require('fiber')
+---
+...
+test_run:cleanup_cluster()
+---
+...
+test_run:cmd("create server replica_auth with rpl_master=default, script='replication/replica_auth.lua'")
+---
+- true
+...
+test_run:cmd("start server replica_auth with wait=False, wait_load=False, args='cluster:pass 0.05'")
+---
+- true
+...
+-- Wait a bit to make sure replica waits till user is created.
+fiber.sleep(0.1)
+---
+...
+box.schema.user.create('cluster', {password='pass'})
+---
+...
+box.schema.user.grant('cluster', 'replication')
+---
+...
+while box.info.replication[2] == nil do fiber.sleep(0.01) end
+---
+...
+vclock = test_run:get_vclock('default')
+---
+...
+_ = test_run:wait_vclock('replica_auth', vclock)
+---
+...
+test_run:cmd("stop server replica_auth")
+---
+- true
+...
+test_run:cmd("cleanup server replica_auth")
+---
+- true
+...
+test_run:cmd("delete server replica_auth")
+---
+- true
+...
+box.schema.user.drop('cluster')
+---
+...
diff --git a/test/replication/misc.test.lua b/test/replication/misc.test.lua
index 979c5d58..c60adf5a 100644
--- a/test/replication/misc.test.lua
+++ b/test/replication/misc.test.lua
@@ -91,3 +91,28 @@ test_run:cmd("switch default")
 test_run:drop_cluster(SERVERS)
 
 box.schema.user.revoke('guest', 'replication')
+
+--
+-- Test case for gh-3637. Before the fix replica would exit with
+-- an error. Now check that we don't hang and successfully connect.
+--
+fiber = require('fiber')
+
+test_run:cleanup_cluster()
+
+test_run:cmd("create server replica_auth with rpl_master=default, script='replication/replica_auth.lua'")
+test_run:cmd("start server replica_auth with wait=False, wait_load=False, args='cluster:pass 0.05'")
+-- Wait a bit to make sure replica waits till user is created.
+fiber.sleep(0.1)
+box.schema.user.create('cluster', {password='pass'})
+box.schema.user.grant('cluster', 'replication')
+
+while box.info.replication[2] == nil do fiber.sleep(0.01) end
+vclock = test_run:get_vclock('default')
+_ = test_run:wait_vclock('replica_auth', vclock)
+
+test_run:cmd("stop server replica_auth")
+test_run:cmd("cleanup server replica_auth")
+test_run:cmd("delete server replica_auth")
+
+box.schema.user.drop('cluster')
diff --git a/test/replication/replica_auth.lua b/test/replication/replica_auth.lua
new file mode 100644
index 00000000..22ba9146
--- /dev/null
+++ b/test/replication/replica_auth.lua
@@ -0,0 +1,14 @@
+#!/usr/bin/env tarantool
+
+local USER_PASS = arg[1]
+local TIMEOUT = arg[2] and tonumber(arg[2]) or 0.1
+local CON_TIMEOUT = arg[3] and tonumber(arg[3]) or 30.0
+
+require('console').listen(os.getenv('ADMIN'))
+
+box.cfg({
+    listen = os.getenv("LISTEN"),
+    replication = USER_PASS .. "@" .. os.getenv("MASTER"),
+    replication_timeout = TIMEOUT,
+    replication_connect_timeout = CON_TIMEOUT
+})