[tarantool-patches] [PATCH 1/2] [replication] [recovery] recover missing data

[Konstantin Belyavskiy]

Part 1 of 2.
Add vclock comparison as a new synchronization condition.
And update catch test as now it works as expected.

Closes #3210
---
 branch: gh-3210-recover-missing-local-data-master-master
 src/box/applier.cc            | 16 +++++++++++-----
 test/replication/catch.result |  5 +++--
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/src/box/applier.cc b/src/box/applier.cc
index 6bfe5a99a..12bf1f0d2 100644
--- a/src/box/applier.cc
+++ b/src/box/applier.cc
@@ -305,7 +305,7 @@ applier_join(struct applier *applier)
 				 * server is 1.6. Since we have
 				 * not initialized replication
 				 * vclock yet, do it now. In 1.7+
-				 * this vlcock is not used.
+				 * this vclock is not used.
 				 */
 				xrow_decode_vclock_xc(&row, &replicaset.vclock);
 			}
@@ -370,6 +370,7 @@ applier_subscribe(struct applier *applier)
 	struct ev_io *coio = &applier->io;
 	struct ibuf *ibuf = &applier->ibuf;
 	struct xrow_header row;
+	struct vclock remote_vclock_at_subscribe;
 
 	xrow_encode_subscribe_xc(&row, &REPLICASET_UUID, &INSTANCE_UUID,
 				 &replicaset.vclock);
@@ -411,9 +412,8 @@ applier_subscribe(struct applier *applier)
 		 * In case of successful subscribe, the server
 		 * responds with its current vclock.
 		 */
-		struct vclock vclock;
-		vclock_create(&vclock);
-		xrow_decode_vclock_xc(&row, &vclock);
+		vclock_create(&remote_vclock_at_subscribe);
+		xrow_decode_vclock_xc(&row, &remote_vclock_at_subscribe);
 	}
 	/**
 	 * Tarantool < 1.6.7:
@@ -452,8 +452,14 @@ applier_subscribe(struct applier *applier)
 			applier_set_state(applier, APPLIER_FOLLOW);
 		}
 
+		/*
+		 * Must stay in read-only mode, until it synchronized.
+		 * Check lag and compare local vclock with remote one.
+		 */
 		if (applier->state == APPLIER_SYNC &&
-		    applier->lag <= replication_sync_lag) {
+		    applier->lag <= replication_sync_lag &&
+		    vclock_compare(&remote_vclock_at_subscribe,
+				   &replicaset.vclock) <= 0) {
 			/* Applier is synced, switch to "follow". */
 			applier_set_state(applier, APPLIER_FOLLOW);
 		}
diff --git a/test/replication/catch.result b/test/replication/catch.result
index 7d61ad26f..05c1c243e 100644
--- a/test/replication/catch.result
+++ b/test/replication/catch.result
@@ -99,10 +99,11 @@ box.space.test ~= nil
 ...
 d = box.space.test:delete{1}
 ---
+- error: Can't modify data because this instance is in read-only mode.
 ...
 box.space.test:get(1) == nil
 ---
-- true
+- false
 ...
 -- case #2: delete tuple by net.box
 test_run:cmd("switch default")
@@ -118,7 +119,7 @@ c = net_box.connect(r_uri)
 ...
 c.space.test:get(1) == nil
 ---
-- true
+- false
 ...
 -- check sync
 errinj.set("ERRINJ_RELAY_TIMEOUT", 0)
-- 
2.14.3 (Apple Git-98)