[Tarantool-patches] [PATCH 1/5] [tosquash] replication: fix multiple rollbacks

[Vladislav Shpilevoy <v.shpilevoy@tarantool.org>]

The problem was that if several transactions time out in one
event loop iteration, the all will write rollback. Moreover, they
will do that in a weird order, starting from the oldest, not in
a reversed order.

This patch makes limbo write only one rollback at once.
---
 src/box/txn_limbo.c                 | 25 +++++++++++++++++++++++++
 test/replication/qsync_basic.result |  2 +-
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/src/box/txn_limbo.c b/src/box/txn_limbo.c
index 0402664cb..2cb687f4d 100644
--- a/src/box/txn_limbo.c
+++ b/src/box/txn_limbo.c
@@ -44,6 +44,13 @@ txn_limbo_create(struct txn_limbo *limbo)
 	limbo->got_rollback = false;
 }
 
+static inline struct txn_limbo_entry *
+txn_limbo_first_entry(struct txn_limbo *limbo)
+{
+	return rlist_first_entry(&limbo->queue, struct txn_limbo_entry,
+				 in_queue);
+}
+
 struct txn_limbo_entry *
 txn_limbo_append(struct txn_limbo *limbo, uint32_t id, struct txn *txn)
 {
@@ -150,6 +157,24 @@ txn_limbo_wait_complete(struct txn_limbo *limbo, struct txn_limbo_entry *entry)
 	bool timed_out = fiber_yield_timeout(txn_limbo_confirm_timeout(limbo));
 	fiber_set_cancellable(cancellable);
 	if (timed_out) {
+		assert(!txn_limbo_is_empty(limbo));
+		if (txn_limbo_first_entry(limbo) != entry) {
+			/*
+			 * If this is not a first entry in the
+			 * limbo, it is definitely not a first
+			 * timed out entry. And since it managed
+			 * to time out too, it means there is
+			 * currently another fiber writing
+			 * rollback. Wait when it will finish and
+			 * wake us up.
+			 */
+			bool cancellable = fiber_set_cancellable(false);
+			fiber_yield();
+			fiber_set_cancellable(cancellable);
+			assert(txn_limbo_entry_is_complete(entry));
+			goto complete;
+		}
+
 		txn_limbo_write_rollback(limbo, entry);
 		struct txn_limbo_entry *e, *tmp;
 		rlist_foreach_entry_safe_reverse(e, &limbo->queue,
diff --git a/test/replication/qsync_basic.result b/test/replication/qsync_basic.result
index cdecf00e8..32deb2ac3 100644
--- a/test/replication/qsync_basic.result
+++ b/test/replication/qsync_basic.result
@@ -272,7 +272,7 @@ box.cfg{replication_synchro_timeout = 0.001, replication_synchro_quorum = 3}
  | ...
 f = fiber.create(box.space.sync.replace, box.space.sync, {6}) s:replace{6}
  | ---
- | - error: Quorum collection for a synchronous transaction is timed out
+ | - error: A rollback for a synchronous transaction is received
  | ...
 f:status()
  | ---
-- 
2.21.1 (Apple Git-122.3)