5 files changed, 53 insertions, 14 deletions

diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index 1512be5322c..40432fe6407 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -210,6 +210,7 @@ StartupDecodingContext(List *output_plugin_options,
 LogicalDecodingContext *
 CreateInitDecodingContext(char *plugin,
 						  List *output_plugin_options,
+						  bool need_full_snapshot,
 						  XLogPageReadCB read_page,
 						  LogicalOutputPluginWriterPrepareWrite prepare_write,
 						  LogicalOutputPluginWriterWrite do_write)
@@ -267,23 +268,31 @@ CreateInitDecodingContext(char *plugin,
 	 * the slot machinery about the new limit. Once that's done the
 	 * ProcArrayLock can be released as the slot machinery now is
 	 * protecting against vacuum.
+	 *
+	 * Note that, temporarily, the data, not just the catalog, xmin has to be
+	 * reserved if a data snapshot is to be exported.  Otherwise the initial
+	 * data snapshot created here is not guaranteed to be valid. After that
+	 * the data xmin doesn't need to be managed anymore and the global xmin
+	 * should be recomputed. As we are fine with losing the pegged data xmin
+	 * after crash - no chance a snapshot would get exported anymore - we can
+	 * get away with just setting the slot's
+	 * effective_xmin. ReplicationSlotRelease will reset it again.
+	 *
 	 * ----
 	 */
 	LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
 
-	slot->effective_catalog_xmin = GetOldestSafeDecodingTransactionId();
-	slot->data.catalog_xmin = slot->effective_catalog_xmin;
+	xmin_horizon = GetOldestSafeDecodingTransactionId(need_full_snapshot);
+
+	slot->effective_catalog_xmin = xmin_horizon;
+	slot->data.catalog_xmin = xmin_horizon;
+	if (need_full_snapshot)
+		slot->effective_xmin = xmin_horizon;
 
 	ReplicationSlotsComputeRequiredXmin(true);
 
 	LWLockRelease(ProcArrayLock);
 
-	/*
-	 * tell the snapshot builder to only assemble snapshot once reaching the
-	 * running_xact's record with the respective xmin.
-	 */
-	xmin_horizon = slot->data.catalog_xmin;
-
 	ReplicationSlotMarkDirty();
 	ReplicationSlotSave();
 
diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 6ae09ce4004..727ef778537 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -551,6 +551,18 @@ SnapBuildExportSnapshot(SnapBuild *builder)
 	 * mechanism. Due to that we can do this without locks, we're only
 	 * changing our own value.
 	 */
+#ifdef USE_ASSERT_CHECKING
+	{
+		TransactionId safeXid;
+
+		LWLockAcquire(ProcArrayLock, LW_SHARED);
+		safeXid = GetOldestSafeDecodingTransactionId(true);
+		LWLockRelease(ProcArrayLock);
+
+		Assert(TransactionIdPrecedesOrEquals(safeXid, snap->xmin));
+	}
+#endif
+
 	MyPgXact->xmin = snap->xmin;
 
 	/* allocate in transaction context */
diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c
index 0b2575ee9d0..d64cfc6dc9e 100644
--- a/src/backend/replication/slot.c
+++ b/src/backend/replication/slot.c
@@ -397,6 +397,22 @@ ReplicationSlotRelease(void)
 		SpinLockRelease(&slot->mutex);
 	}
 
+
+	/*
+	 * If slot needed to temporarily restrain both data and catalog xmin to
+	 * create the catalog snapshot, remove that temporary constraint.
+	 * Snapshots can only be exported while the initial snapshot is still
+	 * acquired.
+	 */
+	if (!TransactionIdIsValid(slot->data.xmin) &&
+		TransactionIdIsValid(slot->effective_xmin))
+	{
+		SpinLockAcquire(&slot->mutex);
+		slot->effective_xmin = InvalidTransactionId;
+		SpinLockRelease(&slot->mutex);
+		ReplicationSlotsComputeRequiredXmin(false);
+	}
+
 	MyReplicationSlot = NULL;
 
 	/* might not have been set when we've been a plain slot */
@@ -574,6 +590,9 @@ ReplicationSlotPersist(void)
 
 /*
  * Compute the oldest xmin across all slots and store it in the ProcArray.
+ *
+ * If already_locked is true, ProcArrayLock has already been acquired
+ * exclusively.
  */
 void
 ReplicationSlotsComputeRequiredXmin(bool already_locked)
@@ -584,8 +603,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked)
 
 	Assert(ReplicationSlotCtl != NULL);
 
-	if (!already_locked)
-		LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
+	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
 
 	for (i = 0; i < max_replication_slots; i++)
 	{
@@ -614,8 +632,7 @@ ReplicationSlotsComputeRequiredXmin(bool already_locked)
 			agg_catalog_xmin = effective_catalog_xmin;
 	}
 
-	if (!already_locked)
-		LWLockRelease(ReplicationSlotControlLock);
+	LWLockRelease(ReplicationSlotControlLock);
 
 	ProcArraySetReplicationSlotXmin(agg_xmin, agg_catalog_xmin, already_locked);
 }
diff --git a/src/backend/replication/slotfuncs.c b/src/backend/replication/slotfuncs.c
index f9087619d2b..de8cd2a67e4 100644
--- a/src/backend/replication/slotfuncs.c
+++ b/src/backend/replication/slotfuncs.c
@@ -125,8 +125,8 @@ pg_create_logical_replication_slot(PG_FUNCTION_ARGS)
 	/*
 	 * Create logical decoding context, to build the initial snapshot.
 	 */
-	ctx = CreateInitDecodingContext(
-									NameStr(*plugin), NIL,
+	ctx = CreateInitDecodingContext(NameStr(*plugin), NIL,
+									false, /* do not build snapshot */
 									logical_read_local_xlog_page, NULL, NULL);
 
 	/* build initial snapshot, might take a while */
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index b2c059e6b0b..834bf947a37 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -813,6 +813,7 @@ CreateReplicationSlot(CreateReplicationSlotCmd *cmd)
 		LogicalDecodingContext *ctx;
 
 		ctx = CreateInitDecodingContext(cmd->plugin, NIL,
+										true, /* build snapshot */
 										logical_read_xlog_page,
 										WalSndPrepareWrite, WalSndWriteData);