From 5b0cfa3f72ee1ffeced4bffe0bcbc4a8551a47b8 Mon Sep 17 00:00:00 2001
From: Amit Kapila <akapila@postgresql.org>
Date: Sat, 3 Dec 2022 12:11:29 +0530
Subject: [PATCH v4] Avoid unnecessary streaming of transactions during logical
 replication.

After restart, we don't perform streaming of an in-progress transaction if
it was previously decoded and confirmed by client. To achieve that we were
comparing the END location of the WAL record being decoded with the WAL
location we have already decoded and confirmed by the client. While
decoding the commit record, to decide whether to process and send the
complete transaction, we compare its START location with the WAL location
we have already decoded and confirmed by the client. Now, if we need to
queue some change in the transaction while decoding the commit record
(e.g. snapshot), it is possible that we decide to stream the transaction
but later commit processing decides to skip it. In such a case, we would
needlessly send the changes and later when we decide to skip it, we will
send stream abort.

We also sometimes decide to stream the changes when we actually just need
to process them locally like a change for invalidations. This will lead us
to send empty streams. To avoid this, while queuing each change for
decoding, we remember whether the transaction has any change that actually
needs to be sent downstream and use that information later to decide
whether to stream the transaction or not.

Author: Dilip Kumar
Reviewed-by: Hou Zhijie, Ashutosh Bapat, Shi yu, Amit Kapila
Discussion: https://postgr.es/m/CAFiTN-tHK=7LzfrPs8fbT2ksrOJGQbzywcgXst2bM9-rJJAAUg@mail.gmail.com
---
 .../replication/logical/reorderbuffer.c       | 42 +++++++++++++++----
 src/include/replication/reorderbuffer.h       | 23 ++++++----
 2 files changed, 48 insertions(+), 17 deletions(-)

diff --git a/src/backend/replication/logical/reorderbuffer.c b/src/backend/replication/logical/reorderbuffer.c
index 31f7381f2d..b50844b0c8 100644
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -695,9 +695,9 @@ ReorderBufferTXNByXid(ReorderBuffer *rb, TransactionId xid, bool create,
  * Record the partial change for the streaming of in-progress transactions.  We
  * can stream only complete changes so if we have a partial change like toast
  * table insert or speculative insert then we mark such a 'txn' so that it
- * can't be streamed.  We also ensure that if the changes in such a 'txn' are
- * above logical_decoding_work_mem threshold then we stream them as soon as we
- * have a complete change.
+ * can't be streamed.  We also ensure that if the changes in such a 'txn' can
+ * be streamed and are above logical_decoding_work_mem threshold then we stream
+ * them as soon as we have a complete change.
  */
 static void
 ReorderBufferProcessPartialChange(ReorderBuffer *rb, ReorderBufferTXN *txn,
@@ -762,7 +762,8 @@ ReorderBufferProcessPartialChange(ReorderBuffer *rb, ReorderBufferTXN *txn,
 	 */
 	if (ReorderBufferCanStartStreaming(rb) &&
 		!(rbtxn_has_partial_change(toptxn)) &&
-		rbtxn_is_serialized(txn))
+		rbtxn_is_serialized(txn) &&
+		rbtxn_has_streamable_change(toptxn))
 		ReorderBufferStreamTXN(rb, toptxn);
 }
 
@@ -793,6 +794,29 @@ ReorderBufferQueueChange(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn,
 		return;
 	}
 
+	/*
+	 * The changes that are sent downstream are considered streamable.  We
+	 * remember such transactions so that only those will later be considered
+	 * for streaming.
+	 */
+	if (change->action == REORDER_BUFFER_CHANGE_INSERT ||
+		change->action == REORDER_BUFFER_CHANGE_UPDATE ||
+		change->action == REORDER_BUFFER_CHANGE_DELETE ||
+		change->action == REORDER_BUFFER_CHANGE_INTERNAL_SPEC_INSERT ||
+		change->action == REORDER_BUFFER_CHANGE_TRUNCATE ||
+		change->action == REORDER_BUFFER_CHANGE_MESSAGE)
+	{
+		ReorderBufferTXN *toptxn;
+
+		/* get the top transaction */
+		if (txn->toptxn != NULL)
+			toptxn = txn->toptxn;
+		else
+			toptxn = txn;
+
+		toptxn->txn_flags |= RBTXN_HAS_STREAMABLE_CHANGE;
+	}
+
 	change->lsn = lsn;
 	change->txn = txn;
 
@@ -2942,9 +2966,8 @@ ReorderBufferForget(ReorderBuffer *rb, TransactionId xid, XLogRecPtr lsn)
 	if (txn == NULL)
 		return;
 
-	/* For streamed transactions notify the remote node about the abort. */
-	if (rbtxn_is_streamed(txn))
-		rb->stream_abort(rb, txn, lsn);
+	/* this transaction mustn't be streamed */
+	Assert(!rbtxn_is_streamed(txn));
 
 	/* cosmetic... */
 	txn->final_lsn = lsn;
@@ -3502,7 +3525,8 @@ ReorderBufferLargestTopTXN(ReorderBuffer *rb)
 		Assert(txn->base_snapshot != NULL);
 
 		if ((largest == NULL || txn->total_size > largest_size) &&
-			(txn->total_size > 0) && !(rbtxn_has_partial_change(txn)))
+			(txn->total_size > 0) && !(rbtxn_has_partial_change(txn)) &&
+			rbtxn_has_streamable_change(txn))
 		{
 			largest = txn;
 			largest_size = txn->total_size;
@@ -3919,7 +3943,7 @@ ReorderBufferCanStartStreaming(ReorderBuffer *rb)
 	 * restarting.
 	 */
 	if (ReorderBufferCanStream(rb) &&
-		!SnapBuildXactNeedsSkip(builder, ctx->reader->EndRecPtr))
+		!SnapBuildXactNeedsSkip(builder, ctx->reader->ReadRecPtr))
 		return true;
 
 	return false;
diff --git a/src/include/replication/reorderbuffer.h b/src/include/replication/reorderbuffer.h
index b23d8cc4f9..c700b55b1c 100644
--- a/src/include/replication/reorderbuffer.h
+++ b/src/include/replication/reorderbuffer.h
@@ -168,14 +168,15 @@ typedef struct ReorderBufferChange
 } ReorderBufferChange;
 
 /* ReorderBufferTXN txn_flags */
-#define RBTXN_HAS_CATALOG_CHANGES 0x0001
-#define RBTXN_IS_SUBXACT          0x0002
-#define RBTXN_IS_SERIALIZED       0x0004
-#define RBTXN_IS_SERIALIZED_CLEAR 0x0008
-#define RBTXN_IS_STREAMED         0x0010
-#define RBTXN_HAS_PARTIAL_CHANGE  0x0020
-#define RBTXN_PREPARE             0x0040
-#define RBTXN_SKIPPED_PREPARE	  0x0080
+#define RBTXN_HAS_CATALOG_CHANGES 	0x0001
+#define RBTXN_IS_SUBXACT          	0x0002
+#define RBTXN_IS_SERIALIZED       	0x0004
+#define RBTXN_IS_SERIALIZED_CLEAR 	0x0008
+#define RBTXN_IS_STREAMED         	0x0010
+#define RBTXN_HAS_PARTIAL_CHANGE  	0x0020
+#define RBTXN_PREPARE             	0x0040
+#define RBTXN_SKIPPED_PREPARE	  	0x0080
+#define RBTXN_HAS_STREAMABLE_CHANGE	0x0100
 
 /* Does the transaction have catalog changes? */
 #define rbtxn_has_catalog_changes(txn) \
@@ -207,6 +208,12 @@ typedef struct ReorderBufferChange
 	((txn)->txn_flags & RBTXN_HAS_PARTIAL_CHANGE) != 0 \
 )
 
+/* Does this transaction contain streamable changes? */
+#define rbtxn_has_streamable_change(txn) \
+( \
+	((txn)->txn_flags & RBTXN_HAS_STREAMABLE_CHANGE) != 0 \
+)
+
 /*
  * Has this transaction been streamed to downstream?
  *
-- 
2.28.0.windows.1

