[Tarantool-patches] [PATCH v6 1/3] replication: omit 0-th vclock component in replication responses

[Serge Petrenko]

If an anonymous replica is promoted to a normal one and becomes
replication master later, its vclock contains a non-empty zero
component, tracking local changes on this replica from the time when it
had been anonymous. No need to pollute joining instance's vclock with
our non-empty 0 component.
When an anonymous replica reports its status to a remote instance it
should also hide its 0-th vclock component.

This is needed for backward compatibility with old instances, which
don't ignore 0th vclock component coming from a remote instance by
default.

In order to do so, introduce a new function - vclock_size_ignore0(),
which doesn't count 0th clock component, and patch xrow_encode_vclock()
to skip 0th clock component if it's present.

Also make sure that new instances ignore 0th vclock component coming
from an unpatched remote instance.

Follow-up #3186
Prerequisite #4114
---
 src/box/relay.cc               |  2 +-
 src/box/replication.cc         |  4 ++--
 src/box/vclock.h               |  6 ++++++
 src/box/xrow.c                 | 10 +++++++---
 test/replication/anon.result   |  5 +++++
 test/replication/anon.test.lua |  2 ++
 6 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/src/box/relay.cc b/src/box/relay.cc
index c634348a4..fec9f07d1 100644
--- a/src/box/relay.cc
+++ b/src/box/relay.cc
@@ -464,7 +464,7 @@ relay_schedule_pending_gc(struct relay *relay, const struct vclock *vclock)
 		 * the greater signatures is due to changes pulled
 		 * from other members of the cluster.
 		 */
-		if (vclock_compare(&curr->vclock, vclock) > 0)
+		if (vclock_compare_ignore0(&curr->vclock, vclock) > 0)
 			break;
 		stailq_shift(&relay->pending_gc);
 		free(gc_msg);
diff --git a/src/box/replication.cc b/src/box/replication.cc
index 1345f189b..c833041a3 100644
--- a/src/box/replication.cc
+++ b/src/box/replication.cc
@@ -777,8 +777,8 @@ replicaset_needs_rejoin(struct replica **master)
 			continue;
 
 		const struct ballot *ballot = &applier->ballot;
-		if (vclock_compare(&ballot->gc_vclock,
-				   &replicaset.vclock) <= 0) {
+		if (vclock_compare_ignore0(&ballot->gc_vclock,
+					   &replicaset.vclock) <= 0) {
 			/*
 			 * There's at least one master that still stores
 			 * WALs needed by this instance. Proceed to local
diff --git a/src/box/vclock.h b/src/box/vclock.h
index 79e5a1bc0..5c0525b00 100644
--- a/src/box/vclock.h
+++ b/src/box/vclock.h
@@ -200,6 +200,12 @@ vclock_size(const struct vclock *vclock)
 	return bit_count_u32(vclock->map);
 }
 
+static inline uint32_t
+vclock_size_ignore0(const struct vclock *vclock)
+{
+	return bit_count_u32(vclock->map & ~1);
+}
+
 static inline int64_t
 vclock_calc_sum(const struct vclock *vclock)
 {
diff --git a/src/box/xrow.c b/src/box/xrow.c
index be026a43c..21a68220a 100644
--- a/src/box/xrow.c
+++ b/src/box/xrow.c
@@ -51,7 +51,7 @@ static_assert(IPROTO_DATA < 0x7f && IPROTO_METADATA < 0x7f &&
 static inline uint32_t
 mp_sizeof_vclock(const struct vclock *vclock)
 {
-	uint32_t size = vclock_size(vclock);
+	uint32_t size = vclock_size_ignore0(vclock);
 	return mp_sizeof_map(size) + size * (mp_sizeof_uint(UINT32_MAX) +
 					     mp_sizeof_uint(UINT64_MAX));
 }
@@ -59,10 +59,14 @@ mp_sizeof_vclock(const struct vclock *vclock)
 static inline char *
 mp_encode_vclock(char *data, const struct vclock *vclock)
 {
-	data = mp_encode_map(data, vclock_size(vclock));
+	data = mp_encode_map(data, vclock_size_ignore0(vclock));
 	struct vclock_iterator it;
 	vclock_iterator_init(&it, vclock);
-	vclock_foreach(&it, replica) {
+	struct vclock_c replica;
+	replica = vclock_iterator_next(&it);
+	if (replica.id == 0)
+		replica = vclock_iterator_next(&it);
+	for ( ; replica.id < VCLOCK_MAX; replica = vclock_iterator_next(&it)) {
 		data = mp_encode_uint(data, replica.id);
 		data = mp_encode_uint(data, replica.lsn);
 	}
diff --git a/test/replication/anon.result b/test/replication/anon.result
index 88061569f..cbbeeef09 100644
--- a/test/replication/anon.result
+++ b/test/replication/anon.result
@@ -187,6 +187,11 @@ a > 0
  | ---
  | - true
  | ...
+-- 0-th vclock component isn't propagated across the cluster.
+box.info.vclock[0]
+ | ---
+ | - null
+ | ...
 test_run:cmd('switch default')
  | ---
  | - true
diff --git a/test/replication/anon.test.lua b/test/replication/anon.test.lua
index 8a8d15c18..627dc5c8e 100644
--- a/test/replication/anon.test.lua
+++ b/test/replication/anon.test.lua
@@ -66,6 +66,8 @@ test_run:cmd('switch replica_anon2')
 a = box.info.vclock[1]
 -- The instance did fetch a snapshot.
 a > 0
+-- 0-th vclock component isn't propagated across the cluster.
+box.info.vclock[0]
 test_run:cmd('switch default')
 box.space.test:insert{2}
 test_run:cmd("switch replica_anon2")
-- 
2.21.1 (Apple Git-122.3)