Execute invalidation messages for each XLOG_XACT_INVALIDATIONS message

during logical decoding.

Prior to commit c55040c we have no way of knowing the invalidations
before commit. So, while decoding we use to execute all the invalidations
at each command end as we had no way of knowing which invalidations
happened before that command. Due to this, transactions involving large
amounts of DDLs use to take more time and also lead to high CPU usage. But
now we know specific invalidations at each command end so we execute only
required invalidations.

It has been observed that decoding of a transaction containing truncation
of a table with 1000 partitions would be finished in 1s whereas before
this patch it used to take 4-5 minutes.

Author: Dilip Kumar
Reviewed-by: Amit Kapila and Keisuke Kuroda
Discussion: https://postgr.es/m/CANDwggKYveEtXjXjqHA6RL3AKSHMsQyfRY6bK+NqhAWJyw8psQ@mail.gmail.com

Author: Amit Kapila

src/backend/replication/logical/reorderbuffer.c

@@ -235,7 +235,7 @@ static void ReorderBufferIterTXNInit(ReorderBuffer *rb, ReorderBufferTXN *txn,
 static ReorderBufferChange *ReorderBufferIterTXNNext(ReorderBuffer *rb, ReorderBufferIterTXNState *state);
 static void ReorderBufferIterTXNFinish(ReorderBuffer *rb,
 									   ReorderBufferIterTXNState *state);
-static void ReorderBufferExecuteInvalidations(ReorderBuffer *rb, ReorderBufferTXN *txn);
+static void ReorderBufferExecuteInvalidations(uint32 nmsgs, SharedInvalidationMessage *msgs);
 
 /*
  * ---------------------------------------
@@ -486,6 +486,11 @@ ReorderBufferReturnChange(ReorderBuffer *rb, ReorderBufferChange *change,
 				pfree(change->data.msg.message);
 			change->data.msg.message = NULL;
 			break;
+		case REORDER_BUFFER_CHANGE_INVALIDATION:
+			if (change->data.inval.invalidations)
+				pfree(change->data.inval.invalidations);
+			change->data.inval.invalidations = NULL;
+			break;
 		case REORDER_BUFFER_CHANGE_INTERNAL_SNAPSHOT:
 			if (change->data.snapshot)
 			{
@@ -2194,6 +2199,13 @@ ReorderBufferProcessTXN(ReorderBuffer *rb, ReorderBufferTXN *txn,
 					ReorderBufferApplyMessage(rb, txn, change, streaming);
 					break;
 
+				case REORDER_BUFFER_CHANGE_INVALIDATION:
+					/* Execute the invalidation messages locally */
+					ReorderBufferExecuteInvalidations(
+													  change->data.inval.ninvalidations,
+													  change->data.inval.invalidations);
+					break;
+
 				case REORDER_BUFFER_CHANGE_INTERNAL_SNAPSHOT:
 					/* get rid of the old */
 					TeardownHistoricSnapshot(false);
@@ -2244,13 +2256,6 @@ ReorderBufferProcessTXN(ReorderBuffer *rb, ReorderBufferTXN *txn,
 
 						TeardownHistoricSnapshot(false);
 						SetupHistoricSnapshot(snapshot_now, txn->tuplecid_hash);
-
-						/*
-						 * Every time the CommandId is incremented, we could
-						 * see new catalog contents, so execute all
-						 * invalidations.
-						 */
-						ReorderBufferExecuteInvalidations(rb, txn);
 					}
 
 					break;
@@ -2317,7 +2322,7 @@ ReorderBufferProcessTXN(ReorderBuffer *rb, ReorderBufferTXN *txn,
 		AbortCurrentTransaction();
 
 		/* make sure there's no cache pollution */
-		ReorderBufferExecuteInvalidations(rb, txn);
+		ReorderBufferExecuteInvalidations(txn->ninvalidations, txn->invalidations);
 
 		if (using_subtxn)
 			RollbackAndReleaseCurrentSubTransaction();
@@ -2356,7 +2361,8 @@ ReorderBufferProcessTXN(ReorderBuffer *rb, ReorderBufferTXN *txn,
 		AbortCurrentTransaction();
 
 		/* make sure there's no cache pollution */
-		ReorderBufferExecuteInvalidations(rb, txn);
+		ReorderBufferExecuteInvalidations(txn->ninvalidations,
+										  txn->invalidations);
 
 		if (using_subtxn)
 			RollbackAndReleaseCurrentSubTransaction();
@@ -2813,23 +2819,30 @@ ReorderBufferAddNewTupleCids(ReorderBuffer *rb, TransactionId xid,
  * Setup the invalidation of the toplevel transaction.
  *
  * This needs to be called for each XLOG_XACT_INVALIDATIONS message and
- * accumulates all the invalidation messages in the toplevel transaction.
- * This is required because in some cases where we skip processing the
- * transaction (see ReorderBufferForget), we need to execute all the
- * invalidations together.
+ * accumulates all the invalidation messages in the toplevel transaction as
+ * well as in the form of change in reorder buffer.  We require to record it in
+ * form of the change so that we can execute only the required invalidations
+ * instead of executing all the invalidations on each CommandId increment.  We
+ * also need to accumulate these in the toplevel transaction because in some
+ * cases we skip processing the transaction (see ReorderBufferForget), we need
+ * to execute all the invalidations together.
  */
 void
 ReorderBufferAddInvalidations(ReorderBuffer *rb, TransactionId xid,
 							  XLogRecPtr lsn, Size nmsgs,
 							  SharedInvalidationMessage *msgs)
 {
 	ReorderBufferTXN *txn;
+	MemoryContext oldcontext;
+	ReorderBufferChange *change;
 
 	txn = ReorderBufferTXNByXid(rb, xid, true, NULL, lsn, true);
 
+	oldcontext = MemoryContextSwitchTo(rb->context);
+
 	/*
-	 * We collect all the invalidations under the top transaction so that we
-	 * can execute them all together.
+	 * Collect all the invalidations under the top transaction so that we can
+	 * execute them all together.  See comment atop this function
 	 */
 	if (txn->toptxn)
 		txn = txn->toptxn;
@@ -2841,8 +2854,7 @@ ReorderBufferAddInvalidations(ReorderBuffer *rb, TransactionId xid,
 	{
 		txn->ninvalidations = nmsgs;
 		txn->invalidations = (SharedInvalidationMessage *)
-			MemoryContextAlloc(rb->context,
-							   sizeof(SharedInvalidationMessage) * nmsgs);
+			palloc(sizeof(SharedInvalidationMessage) * nmsgs);
 		memcpy(txn->invalidations, msgs,
 			   sizeof(SharedInvalidationMessage) * nmsgs);
 	}
@@ -2856,19 +2868,31 @@ ReorderBufferAddInvalidations(ReorderBuffer *rb, TransactionId xid,
 			   nmsgs * sizeof(SharedInvalidationMessage));
 		txn->ninvalidations += nmsgs;
 	}
+
+	change = ReorderBufferGetChange(rb);
+	change->action = REORDER_BUFFER_CHANGE_INVALIDATION;
+	change->data.inval.ninvalidations = nmsgs;
+	change->data.inval.invalidations = (SharedInvalidationMessage *)
+		palloc(sizeof(SharedInvalidationMessage) * nmsgs);
+	memcpy(change->data.inval.invalidations, msgs,
+		   sizeof(SharedInvalidationMessage) * nmsgs);
+
+	ReorderBufferQueueChange(rb, xid, lsn, change, false);
+
+	MemoryContextSwitchTo(oldcontext);
 }
 
 /*
  * Apply all invalidations we know. Possibly we only need parts at this point
  * in the changestream but we don't know which those are.
  */
 static void
-ReorderBufferExecuteInvalidations(ReorderBuffer *rb, ReorderBufferTXN *txn)
+ReorderBufferExecuteInvalidations(uint32 nmsgs, SharedInvalidationMessage *msgs)
 {
 	int			i;
 
-	for (i = 0; i < txn->ninvalidations; i++)
-		LocalExecuteInvalidationMessage(&txn->invalidations[i]);
+	for (i = 0; i < nmsgs; i++)
+		LocalExecuteInvalidationMessage(&msgs[i]);
 }
 
 /*
@@ -3301,6 +3325,24 @@ ReorderBufferSerializeChange(ReorderBuffer *rb, ReorderBufferTXN *txn,
 					   change->data.msg.message_size);
 				data += change->data.msg.message_size;
 
+				break;
+			}
+		case REORDER_BUFFER_CHANGE_INVALIDATION:
+			{
+				char	   *data;
+				Size		inval_size = sizeof(SharedInvalidationMessage) *
+				change->data.inval.ninvalidations;
+
+				sz += inval_size;
+
+				ReorderBufferSerializeReserve(rb, sz);
+				data = ((char *) rb->outbuf) + sizeof(ReorderBufferDiskChange);
+
+				/* might have been reallocated above */
+				ondisk = (ReorderBufferDiskChange *) rb->outbuf;
+				memcpy(data, change->data.inval.invalidations, inval_size);
+				data += inval_size;
+
 				break;
 			}
 		case REORDER_BUFFER_CHANGE_INTERNAL_SNAPSHOT:
@@ -3578,6 +3620,12 @@ ReorderBufferChangeSize(ReorderBufferChange *change)
 
 				break;
 			}
+		case REORDER_BUFFER_CHANGE_INVALIDATION:
+			{
+				sz += sizeof(SharedInvalidationMessage) *
+					change->data.inval.ninvalidations;
+				break;
+			}
 		case REORDER_BUFFER_CHANGE_INTERNAL_SNAPSHOT:
 			{
 				Snapshot	snap;
@@ -3844,6 +3892,19 @@ ReorderBufferRestoreChange(ReorderBuffer *rb, ReorderBufferTXN *txn,
 					   change->data.msg.message_size);
 				data += change->data.msg.message_size;
 
+				break;
+			}
+		case REORDER_BUFFER_CHANGE_INVALIDATION:
+			{
+				Size		inval_size = sizeof(SharedInvalidationMessage) *
+				change->data.inval.ninvalidations;
+
+				change->data.inval.invalidations =
+					MemoryContextAlloc(rb->context, inval_size);
+
+				/* read the message */
+				memcpy(change->data.inval.invalidations, data, inval_size);
+
 				break;
 			}
 		case REORDER_BUFFER_CHANGE_INTERNAL_SNAPSHOT:

src/include/replication/reorderbuffer.h

@@ -57,6 +57,7 @@ enum ReorderBufferChangeType
 	REORDER_BUFFER_CHANGE_UPDATE,
 	REORDER_BUFFER_CHANGE_DELETE,
 	REORDER_BUFFER_CHANGE_MESSAGE,
+	REORDER_BUFFER_CHANGE_INVALIDATION,
 	REORDER_BUFFER_CHANGE_INTERNAL_SNAPSHOT,
 	REORDER_BUFFER_CHANGE_INTERNAL_COMMAND_ID,
 	REORDER_BUFFER_CHANGE_INTERNAL_TUPLECID,
@@ -149,6 +150,13 @@ typedef struct ReorderBufferChange
 			CommandId	cmax;
 			CommandId	combocid;
 		}			tuplecid;
+
+		/* Invalidation. */
+		struct
+		{
+			uint32		ninvalidations; /* Number of messages */
+			SharedInvalidationMessage *invalidations;	/* invalidation message */
+		}			inval;
 	}			data;
 
 	/*
@@ -313,8 +321,8 @@ typedef struct ReorderBufferTXN
 	uint64		nentries_mem;
 
 	/*
-	 * List of ReorderBufferChange structs, including new Snapshots and new
-	 * CommandIds
+	 * List of ReorderBufferChange structs, including new Snapshots, new
+	 * CommandIds and command invalidation messages.
 	 */
 	dlist_head	changes;