[Tarantool-patches] [PATCH v31 2/3] 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
read up to date terms (ie written to the WAL).

For this sake we use a latching mechanism, when one fiber
takes a 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.

We introduce the following helpers:

1) txn_limbo_begin: which takes a lock
2) txn_limbo_commit and txn_limbo_rollback which simply release
   the lock but have different names for better semantics
3) txn_limbo_process is a general function which uses x_begin
   and x_commit helper internally
4) txn_limbo_apply to do a real job over processing the
   request, it implies that txn_limbo_begin been called

Testing such in-flight condition won't be easy so we introduce
"box.info.synchro.queue.busy" field to report if limbo is
currently latched and processing a sync request.

@TarantoolBot document
Title: synchronous replication changes

`box.info.synchro.queue` gets a new `busy` field. It is set to
`true` when there is a synchronous transaction is processing
but not yet complete. Thus any other incoming synchronous
transactions will be delayed until active one is finished.

Part-of #6036

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
---
 src/box/applier.cc  |  6 +++++-
 src/box/box.cc      |  8 ++++++--
 src/box/lua/info.c  |  4 +++-
 src/box/txn_limbo.c | 13 ++++++++++++-
 src/box/txn_limbo.h | 44 +++++++++++++++++++++++++++++++++++++++-----
 5 files changed, 65 insertions(+), 10 deletions(-)

diff --git a/src/box/applier.cc b/src/box/applier.cc
index 0ac7ac3c7..99484eea2 100644
--- a/src/box/applier.cc
+++ b/src/box/applier.cc
@@ -959,7 +959,7 @@ apply_synchro_req_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_apply(&txn_limbo, synchro_entry->req);
 		trigger_run(&replicaset.applier.on_wal_write, NULL);
 	}
 	fiber_wakeup(synchro_entry->owner);
@@ -1004,14 +1004,18 @@ apply_synchro_req(uint32_t replica_id, struct xrow_header *row, struct synchro_r
 	 * before trying to commit. But that requires extra steps from the
 	 * transactions side, including the async ones.
 	 */
+	txn_limbo_begin(&txn_limbo);
 	if (journal_write(&entry.base) != 0)
 		goto err;
 	if (entry.base.res < 0) {
 		diag_set_journal_res(entry.base.res);
 		goto err;
 	}
+	txn_limbo_commit(&txn_limbo);
 	return 0;
+
 err:
+	txn_limbo_rollback(&txn_limbo);
 	diag_log();
 	return -1;
 }
diff --git a/src/box/box.cc b/src/box/box.cc
index 6a33203df..fd34ddb0c 100644
--- a/src/box/box.cc
+++ b/src/box/box.cc
@@ -1780,6 +1780,7 @@ box_issue_promote(uint32_t prev_leader_id, int64_t promote_lsn)
 	struct raft *raft = box_raft();
 	assert(raft->volatile_term == raft->term);
 	assert(promote_lsn >= 0);
+	txn_limbo_begin(&txn_limbo);
 	txn_limbo_write_promote(&txn_limbo, promote_lsn,
 				raft->term);
 	struct synchro_request req = {
@@ -1789,7 +1790,8 @@ box_issue_promote(uint32_t prev_leader_id, int64_t promote_lsn)
 		.lsn = promote_lsn,
 		.term = raft->term,
 	};
-	txn_limbo_process(&txn_limbo, &req);
+	txn_limbo_apply(&txn_limbo, &req);
+	txn_limbo_commit(&txn_limbo);
 	assert(txn_limbo_is_empty(&txn_limbo));
 }
 
@@ -1802,6 +1804,7 @@ box_issue_demote(uint32_t prev_leader_id, int64_t promote_lsn)
 {
 	assert(box_raft()->volatile_term == box_raft()->term);
 	assert(promote_lsn >= 0);
+	txn_limbo_begin(&txn_limbo);
 	txn_limbo_write_demote(&txn_limbo, promote_lsn,
 				box_raft()->term);
 	struct synchro_request req = {
@@ -1811,7 +1814,8 @@ box_issue_demote(uint32_t prev_leader_id, int64_t promote_lsn)
 		.lsn = promote_lsn,
 		.term = box_raft()->term,
 	};
-	txn_limbo_process(&txn_limbo, &req);
+	txn_limbo_apply(&txn_limbo, &req);
+	txn_limbo_commit(&txn_limbo);
 	assert(txn_limbo_is_empty(&txn_limbo));
 }
 
diff --git a/src/box/lua/info.c b/src/box/lua/info.c
index b75a301eb..8d7bb1d4a 100644
--- a/src/box/lua/info.c
+++ b/src/box/lua/info.c
@@ -637,11 +637,13 @@ lbox_info_synchro(struct lua_State *L)
 
 	/* Queue information. */
 	struct txn_limbo *queue = &txn_limbo;
-	lua_createtable(L, 0, 2);
+	lua_createtable(L, 0, 3);
 	lua_pushnumber(L, queue->len);
 	lua_setfield(L, -2, "len");
 	lua_pushnumber(L, queue->owner_id);
 	lua_setfield(L, -2, "owner");
+	lua_pushboolean(L, latch_is_locked(&queue->promote_latch));
+	lua_setfield(L, -2, "busy");
 	lua_setfield(L, -2, "queue");
 
 	return 1;
diff --git a/src/box/txn_limbo.c b/src/box/txn_limbo.c
index 70447caaf..5e708a951 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;
@@ -724,8 +725,10 @@ 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_apply(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) {
@@ -786,6 +789,14 @@ 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_begin(limbo);
+	txn_limbo_apply(limbo, req);
+	txn_limbo_commit(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 53e52f676..e2ac75c08 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
@@ -226,11 +231,13 @@ 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,
-			      uint32_t replica_id)
+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;
+	latch_lock(&limbo->promote_latch);
+	uint64_t v = vclock_get(&limbo->promote_term_map, replica_id);
+	bool res = v < limbo->promote_greatest_term;
+	latch_unlock(&limbo->promote_latch);
+	return res;
 }
 
 /**
@@ -300,7 +307,34 @@ txn_limbo_ack(struct txn_limbo *limbo, uint32_t replica_id, int64_t lsn);
 int
 txn_limbo_wait_complete(struct txn_limbo *limbo, struct txn_limbo_entry *entry);
 
-/** Execute a synchronous replication request. */
+/**
+ * Initiate execution of a synchronous replication request.
+ */
+static inline void
+txn_limbo_begin(struct txn_limbo *limbo)
+{
+	latch_lock(&limbo->promote_latch);
+}
+
+/** Commit a synchronous replication request. */
+static inline void
+txn_limbo_commit(struct txn_limbo *limbo)
+{
+	latch_unlock(&limbo->promote_latch);
+}
+
+/** Rollback a synchronous replication request. */
+static inline void
+txn_limbo_rollback(struct txn_limbo *limbo)
+{
+	latch_unlock(&limbo->promote_latch);
+}
+
+/** Apply a synchronous replication request after processing stage. */
+void
+txn_limbo_apply(struct txn_limbo *limbo, const struct synchro_request *req);
+
+/** Process a synchronous replication request. */
 void
 txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req);
 
-- 
2.35.1