[Tarantool-patches] [PATCH v14 4/6] qsync: order access to the limbo terms

[Cyrill Gorcunov via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

Limbo terms tracking is shared between appliers and when
one of appliers is waiting for write to complete inside
journal_write() routine, an other may need to access read
term value to figure out if promote request is valid to
apply. Due to cooperative multitasking access to the terms
is not consistent so we need to be sure that other fibers
either read up to date terms (ie written to the WAL).

For this sake we use latching mechanism, when one fiber
took terms lock for updating other readers are waiting
until the operation is complete.

For example here is a call graph of two appliers

applier 1
---------
applier_apply_tx
  (promote term = 3
   current max term = 2)
  applier_synchro_filter_tx
  apply_synchro_row
    journal_write
      (sleeping)

at this moment another applier comes in with obsolete
data and term 2

                              applier 2
                              ---------
                              applier_apply_tx
                                (term 2)
                                applier_synchro_filter_tx
                                  txn_limbo_is_replica_outdated -> false
                                journal_write (sleep)

applier 1
---------
journal wakes up
  apply_synchro_row_cb
    set max term to 3

So the applier 2 didn't notice that term 3 is already seen
and wrote obsolete data. With locking the applier 2 will
wait until applier 1 has finished its write.

Part-of #6036

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
---
 src/box/applier.cc  |  5 ++++-
 src/box/txn_limbo.c | 17 ++++++++++++++--
 src/box/txn_limbo.h | 48 ++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 62 insertions(+), 8 deletions(-)

diff --git a/src/box/applier.cc b/src/box/applier.cc
index b981bd436..845a7d015 100644
--- a/src/box/applier.cc
+++ b/src/box/applier.cc
@@ -857,7 +857,7 @@ apply_synchro_row_cb(struct journal_entry *entry)
 		applier_rollback_by_wal_io(entry->res);
 	} else {
 		replica_txn_wal_write_cb(synchro_entry->rcb);
-		txn_limbo_process(&txn_limbo, synchro_entry->req);
+		txn_limbo_process_locked(&txn_limbo, synchro_entry->req);
 		trigger_run(&replicaset.applier.on_wal_write, NULL);
 	}
 	fiber_wakeup(synchro_entry->owner);
@@ -873,6 +873,7 @@ apply_synchro_row(uint32_t replica_id, struct xrow_header *row)
 	if (xrow_decode_synchro(row, &req) != 0)
 		goto err;
 
+	txn_limbo_term_lock(&txn_limbo);
 	struct replica_cb_data rcb_data;
 	struct synchro_entry entry;
 	/*
@@ -915,8 +916,10 @@ apply_synchro_row(uint32_t replica_id, struct xrow_header *row)
 		diag_set_journal_res(entry.base.res);
 		goto err;
 	}
+	txn_limbo_term_unlock(&txn_limbo);
 	return 0;
 err:
+	txn_limbo_term_unlock(&txn_limbo);
 	diag_log();
 	return -1;
 }
diff --git a/src/box/txn_limbo.c b/src/box/txn_limbo.c
index 08463219d..65fbd0cac 100644
--- a/src/box/txn_limbo.c
+++ b/src/box/txn_limbo.c
@@ -47,6 +47,7 @@ txn_limbo_create(struct txn_limbo *limbo)
 	vclock_create(&limbo->vclock);
 	vclock_create(&limbo->promote_term_map);
 	limbo->promote_greatest_term = 0;
+	latch_create(&limbo->promote_latch);
 	limbo->confirmed_lsn = 0;
 	limbo->rollback_count = 0;
 	limbo->is_in_rollback = false;
@@ -737,11 +738,14 @@ txn_limbo_wait_empty(struct txn_limbo *limbo, double timeout)
 }
 
 void
-txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req)
+txn_limbo_process_locked(struct txn_limbo *limbo,
+			 const struct synchro_request *req)
 {
+	assert(latch_is_locked(&limbo->promote_latch));
+
 	uint64_t term = req->term;
 	uint32_t origin = req->origin_id;
-	if (txn_limbo_replica_term(limbo, origin) < term) {
+	if (txn_limbo_replica_term_locked(limbo, origin) < term) {
 		vclock_follow(&limbo->promote_term_map, origin, term);
 		if (term > limbo->promote_greatest_term)
 			limbo->promote_greatest_term = term;
@@ -799,6 +803,15 @@ txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req)
 	return;
 }
 
+void
+txn_limbo_process(struct txn_limbo *limbo,
+		  const struct synchro_request *req)
+{
+	txn_limbo_term_lock(limbo);
+	txn_limbo_process_locked(limbo, req);
+	txn_limbo_term_unlock(limbo);
+}
+
 void
 txn_limbo_on_parameters_change(struct txn_limbo *limbo)
 {
diff --git a/src/box/txn_limbo.h b/src/box/txn_limbo.h
index e0d17de4b..1ee815d1c 100644
--- a/src/box/txn_limbo.h
+++ b/src/box/txn_limbo.h
@@ -31,6 +31,7 @@
  */
 #include "small/rlist.h"
 #include "vclock/vclock.h"
+#include "latch.h"
 
 #include <stdint.h>
 
@@ -147,6 +148,10 @@ struct txn_limbo {
 	 * limbo and raft are in sync and the terms are the same.
 	 */
 	uint64_t promote_greatest_term;
+	/**
+	 * To order access to the promote data.
+	 */
+	struct latch promote_latch;
 	/**
 	 * Maximal LSN gathered quorum and either already confirmed in WAL, or
 	 * whose confirmation is in progress right now. Any attempt to confirm
@@ -217,14 +222,39 @@ txn_limbo_last_entry(struct txn_limbo *limbo)
 				in_queue);
 }
 
+/** Lock promote data. */
+static inline void
+txn_limbo_term_lock(struct txn_limbo *limbo)
+{
+	latch_lock(&limbo->promote_latch);
+}
+
+/** Unlock promote data. */
+static inline void
+txn_limbo_term_unlock(struct txn_limbo *limbo)
+{
+	latch_unlock(&limbo->promote_latch);
+}
+
+/** Fetch replica's term with lock taken. */
+static inline uint64_t
+txn_limbo_replica_term_locked(struct txn_limbo *limbo, uint32_t replica_id)
+{
+	assert(latch_is_locked(&limbo->promote_latch));
+	return vclock_get(&limbo->promote_term_map, replica_id);
+}
+
 /**
  * Return the latest term as seen in PROMOTE requests from instance with id
  * @a replica_id.
  */
 static inline uint64_t
-txn_limbo_replica_term(const struct txn_limbo *limbo, uint32_t replica_id)
+txn_limbo_replica_term(struct txn_limbo *limbo, uint32_t replica_id)
 {
-	return vclock_get(&limbo->promote_term_map, replica_id);
+	txn_limbo_term_lock(limbo);
+	uint64_t v = txn_limbo_replica_term_locked(limbo, replica_id);
+	txn_limbo_term_unlock(limbo);
+	return v;
 }
 
 /**
@@ -232,11 +262,14 @@ txn_limbo_replica_term(const struct txn_limbo *limbo, uint32_t replica_id)
  * data from it. The check is only valid when elections are enabled.
  */
 static inline bool
-txn_limbo_is_replica_outdated(const struct txn_limbo *limbo,
+txn_limbo_is_replica_outdated(struct txn_limbo *limbo,
 			      uint32_t replica_id)
 {
-	return txn_limbo_replica_term(limbo, replica_id) <
-	       limbo->promote_greatest_term;
+	txn_limbo_term_lock(limbo);
+	bool res = txn_limbo_replica_term_locked(limbo, replica_id) <
+		limbo->promote_greatest_term;
+	txn_limbo_term_unlock(limbo);
+	return res;
 }
 
 /**
@@ -308,6 +341,11 @@ txn_limbo_wait_complete(struct txn_limbo *limbo, struct txn_limbo_entry *entry);
 
 /** Execute a synchronous replication request. */
 void
+txn_limbo_process_locked(struct txn_limbo *limbo,
+			 const struct synchro_request *req);
+
+/** Lock limbo terms and execute a synchronous replication request. */
+void
 txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req);
 
 /**
-- 
2.31.1