[Tarantool-patches] [PATCH v4 10/12] election: support manual elections in clear_synchro_queue()

[Serge Petrenko via Tarantool-patches <tarantool-patches@dev.tarantool.org>]

This patch adds support for manual elections from
`box.ctl.clear_synchro_queue()`. When an instance is in
`election_mode='manual'`, calling `clear_synchro_queue()` will make it
start a new election round.

Follow-up #5445
Part of #3055

@TarantoolBot document
Title: describe election_mode='manual'

Manual election mode is introduced. It may be used when the user wants to
control which instance is the leader explicitly instead of relying on
Raft election algorithm.

When an instance is configured with `election_mode='manual'`, it behaves
as follows:
 1) By default, the instance acts like a voter: it is read-only and may
    vote for other instances that are candidates.
 2) Once `box.ctl.clear_synchro_queue()` is called, the instance becomes a
    candidate and starts a new election round. If the instance wins the
    elections, it remains leader, but won't participate in any new elections.
---
 src/box/box.cc        | 71 ++++++++++++++++++++++++++++++++++++++++---
 src/box/errcode.h     |  2 ++
 src/box/raft.c        | 30 +++++++++++++++---
 src/box/raft.h        |  3 ++
 test/box/error.result |  2 ++
 5 files changed, 99 insertions(+), 9 deletions(-)

diff --git a/src/box/box.cc b/src/box/box.cc
index d5a55a30a..fcd812c09 100644
--- a/src/box/box.cc
+++ b/src/box/box.cc
@@ -1521,12 +1521,75 @@ box_clear_synchro_queue(bool try_wait)
 	if (!is_box_configured ||
 	    raft_node_term(box_raft(), instance_id) == box_raft()->term)
 		return 0;
+
+	bool run_elections = false;
+
+	switch (box_election_mode) {
+	case ELECTION_MODE_OFF:
+		break;
+	case ELECTION_MODE_VOTER:
+		assert(box_raft()->state == RAFT_STATE_FOLLOWER);
+		diag_set(ClientError, ER_UNSUPPORTED, "election_mode='voter'",
+			 "manual elections");
+		return -1;
+	case ELECTION_MODE_MANUAL:
+		assert(box_raft()->state == RAFT_STATE_FOLLOWER);
+		run_elections = true;
+		try_wait = false;
+		break;
+	case ELECTION_MODE_CANDIDATE:
+		/*
+		 * Leader elections are enabled, and this instance is allowed to
+		 * promote only if it's already an elected leader. No manual
+		 * elections.
+		 */
+		if (box_raft()->state != RAFT_STATE_LEADER) {
+			diag_set(ClientError, ER_UNSUPPORTED, "election_mode="
+				 "'candidate'", "manual elections");
+			return -1;
+		}
+		break;
+	default:
+		unreachable();
+	}
+
 	uint32_t former_leader_id = txn_limbo.owner_id;
 	int64_t wait_lsn = txn_limbo.confirmed_lsn;
 	int rc = 0;
 	int quorum = replication_synchro_quorum;
 	in_clear_synchro_queue = true;
 
+	if (run_elections) {
+		/*
+		 * Make this instance a candidate and run until some leader, not
+		 * necessarily this instance, emerges.
+		 */
+		raft_start_candidate(box_raft());
+		/*
+		 * Trigger new elections without waiting for an old leader to
+		 * disappear.
+		 */
+		raft_new_term(box_raft());
+		box_raft_wait_leader_found();
+		/*
+		 * Do not reset raft mode if it was changed while running the
+		 * elections.
+		 */
+		if (box_election_mode == ELECTION_MODE_MANUAL)
+			raft_stop_candidate(box_raft(), false);
+		if (!box_raft()->is_enabled) {
+			diag_set(ClientError, ER_RAFT_DISABLED);
+			in_clear_synchro_queue = false;
+			return -1;
+		}
+		if (box_raft()->state != RAFT_STATE_LEADER) {
+			diag_set(ClientError, ER_INTERFERING_PROMOTE,
+				 box_raft()->leader);
+			in_clear_synchro_queue = false;
+			return -1;
+		}
+	}
+
 	if (txn_limbo_is_empty(&txn_limbo))
 		goto promote;
 
@@ -1544,12 +1607,10 @@ box_clear_synchro_queue(bool try_wait)
 		 * transactions. Exit in case someone did that for us.
 		 */
 		if (former_leader_id != txn_limbo.owner_id) {
-			/*
-			 * TODO: error once we see someone else has become the
-			 * leader already.
-			 */
+			diag_set(ClientError, ER_INTERFERING_PROMOTE,
+				 txn_limbo.owner_id);
 			in_clear_synchro_queue = false;
-			return 0;
+			return -1;
 		}
 	}
 
diff --git a/src/box/errcode.h b/src/box/errcode.h
index c63191fb6..d93820e96 100644
--- a/src/box/errcode.h
+++ b/src/box/errcode.h
@@ -275,6 +275,8 @@ struct errcode_record {
 	/*220 */_(ER_TOO_EARLY_SUBSCRIBE,	"Can't subscribe non-anonymous replica %s until join is done") \
 	/*221 */_(ER_SQL_CANT_ADD_AUTOINC,	"Can't add AUTOINCREMENT: space %s can't feature more than one AUTOINCREMENT field") \
 	/*222 */_(ER_QUORUM_WAIT,		"Couldn't wait for quorum %d: %s") \
+	/*223 */_(ER_INTERFERING_PROMOTE,	"Instance with replica id %u was promoted first") \
+	/*224 */_(ER_RAFT_DISABLED,		"Elections were turned off while running box.ctl.promote()")\
 
 /*
  * !IMPORTANT! Please follow instructions at start of the file
diff --git a/src/box/raft.c b/src/box/raft.c
index 285dbe4fd..425353207 100644
--- a/src/box/raft.c
+++ b/src/box/raft.c
@@ -91,11 +91,11 @@ box_raft_update_synchro_queue(struct raft *raft)
 	 * If the node became a leader, it means it will ignore all records from
 	 * all the other nodes, and won't get late CONFIRM messages anyway. Can
 	 * clear the queue without waiting for confirmations.
-	 * It's alright that the user may have called clear_synchro_queue
-	 * manually. In this case the call below will exit immediately and we'll
-	 * simply log a warning.
+	 * In case these are manual elections, we are already in the middle of a
+	 * `clear_synchro_queue` call. No need to call it once again.
 	 */
-	if (raft->state == RAFT_STATE_LEADER) {
+	if (raft->state == RAFT_STATE_LEADER &&
+	    box_election_mode != ELECTION_MODE_MANUAL) {
 		int rc = 0;
 		uint32_t errcode = 0;
 		do {
@@ -336,6 +336,28 @@ fail:
 	panic("Could not write a raft request to WAL\n");
 }
 
+static int
+box_raft_wait_leader_found_f(struct trigger *trig, void *event)
+{
+	struct raft *raft = event;
+	assert(raft == box_raft());
+	struct fiber *waiter = trig->data;
+	if (raft->leader != REPLICA_ID_NIL || !raft->is_enabled)
+		fiber_wakeup(waiter);
+	return 0;
+}
+
+void
+box_raft_wait_leader_found(void)
+{
+	struct trigger trig;
+	trigger_create(&trig, box_raft_wait_leader_found_f, fiber(), NULL);
+	raft_on_update(box_raft(), &trig);
+	fiber_yield();
+	assert(box_raft()->leader != REPLICA_ID_NIL || !box_raft()->is_enabled);
+	trigger_clear(&trig);
+}
+
 void
 box_raft_init(void)
 {
diff --git a/src/box/raft.h b/src/box/raft.h
index 15f4e80d9..8fce423e1 100644
--- a/src/box/raft.h
+++ b/src/box/raft.h
@@ -97,6 +97,9 @@ box_raft_checkpoint_remote(struct raft_request *req);
 int
 box_raft_process(struct raft_request *req, uint32_t source);
 
+void
+box_raft_wait_leader_found();
+
 void
 box_raft_init(void);
 
diff --git a/test/box/error.result b/test/box/error.result
index 7761c6949..cc8cbaaa9 100644
--- a/test/box/error.result
+++ b/test/box/error.result
@@ -441,6 +441,8 @@ t;
  |   220: box.error.TOO_EARLY_SUBSCRIBE
  |   221: box.error.SQL_CANT_ADD_AUTOINC
  |   222: box.error.QUORUM_WAIT
+ |   223: box.error.INTERFERING_PROMOTE
+ |   224: box.error.RAFT_DISABLED
  | ...
 
 test_run:cmd("setopt delimiter ''");
-- 
2.24.3 (Apple Git-128)