v12-0001-Introduce-internal-messages-to-track-dependencie.patch

From 84bd321a04dbef28951477b3904382a62300ac4d Mon Sep 17 00:00:00 2001
From: Hayato Kuroda <kuroda.hayato@fujitsu.com>
Date: Mon, 1 Dec 2025 10:37:27 +0900
Subject: [PATCH v12 1/9] Introduce internal messages to track dependencies

This patch introduces a new set of message WorkerInternalMsgType. These types of
messages are generated by a leader worker and sent to parallel apply workers
based on the needs. For now, two types of messages exist:
WORKER_INTERNAL_MSG_DEPENDENCY and WORKER_INTERNAL_MSG_RELATION.

WORKER_INTERNAL_MSG_DEPENDENCY ensures that dependent transactions are
committed in the correct order. It has a list of transaction IDs that parallel
workers must wait for. The message type would be generated when the leader
detects a dependency between the current and other transactions, or just before
the COMMIT message. The latter one is used to preserve the commit ordering
between the publisher and the subscriber.

WORKER_INTERNAL_MSG_RELATION is used to synchronize the relation
information between the leader and parallel workers. It has a list of relations
that the leader already knows, and parallel workers also update the relmap in
response to the message. This type of message is generated when the leader
allocates a new parallel worker to the transaction, or when the publisher sends
additional RELATION messages.

Author: Hou Zhijie <houzj.fnst@fujitsu.com>
Author: Hayato Kuroda <kuroda.hayato@fujitsu.com>
---
 .../replication/logical/applyparallelworker.c | 125 +++++++++++++++---
 src/include/replication/logicalproto.h        |  12 ++
 src/include/replication/worker_internal.h     |   4 +
 src/tools/pgindent/typedefs.list              |   1 +
 4 files changed, 125 insertions(+), 17 deletions(-)

diff --git a/src/backend/replication/logical/applyparallelworker.c b/src/backend/replication/logical/applyparallelworker.c
index 798e8d85b3e..e5e7cd92c18 100644
--- a/src/backend/replication/logical/applyparallelworker.c
+++ b/src/backend/replication/logical/applyparallelworker.c
@@ -733,6 +733,70 @@ ProcessParallelApplyInterrupts(void)
 	}
 }
 
+/*
+ * Handle internal dependency information.
+ *
+ * Wait for all transactions listed in the message to commit.
+ */
+static void
+apply_handle_internal_dependency(StringInfo s)
+{
+	int			nxids = pq_getmsgint(s, 4);
+
+	for (int i = 0; i < nxids; i++)
+	{
+		TransactionId xid = pq_getmsgint(s, 4);
+
+		pa_wait_for_depended_transaction(xid);
+	}
+}
+
+/*
+ * Handle internal relation information.
+ *
+ * Update all relation details in the relation map cache.
+ */
+static void
+apply_handle_internal_relation(StringInfo s)
+{
+	int			num_rels;
+
+	num_rels = pq_getmsgint(s, 4);
+
+	for (int i = 0; i < num_rels; i++)
+	{
+		LogicalRepRelation *rel = logicalrep_read_rel(s);
+
+		logicalrep_relmap_update(rel);
+
+		elog(DEBUG1, "parallel apply worker worker init relmap for %s",
+			 rel->relname);
+	}
+}
+
+/*
+ * Handle an internal message generated by the leader apply worker.
+ */
+static void
+handle_internal_message(StringInfo s)
+{
+	WorkerInternalMsgType action = pq_getmsgbyte(s);
+
+	switch (action)
+	{
+		case WORKER_INTERNAL_MSG_DEPENDENCY:
+			apply_handle_internal_dependency(s);
+			break;
+		case WORKER_INTERNAL_MSG_RELATION:
+			apply_handle_internal_relation(s);
+			break;
+		default:
+			ereport(ERROR,
+					(errcode(ERRCODE_PROTOCOL_VIOLATION),
+					 errmsg("invalid worker internal message type \"??? (%d)\"", action)));
+	}
+}
+
 /* Parallel apply worker main loop. */
 static void
 LogicalParallelApplyLoop(shm_mq_handle *mqh)
@@ -779,26 +843,37 @@ LogicalParallelApplyLoop(shm_mq_handle *mqh)
 
 			initReadOnlyStringInfo(&s, data, len);
 
-			/*
-			 * The first byte of messages sent from leader apply worker to
-			 * parallel apply workers can only be PqReplMsg_WALData.
-			 */
 			c = pq_getmsgbyte(&s);
-			if (c != PqReplMsg_WALData)
-				elog(ERROR, "unexpected message \"%c\"", c);
 
-			/*
-			 * Ignore statistics fields that have been updated by the leader
-			 * apply worker.
-			 *
-			 * XXX We can avoid sending the statistics fields from the leader
-			 * apply worker but for that, it needs to rebuild the entire
-			 * message by removing these fields which could be more work than
-			 * simply ignoring these fields in the parallel apply worker.
-			 */
-			s.cursor += SIZE_STATS_MESSAGE;
+			if (c == PqReplMsg_WALData)
+			{
+				/*
+				 * Ignore statistics fields that have been updated by the
+				 * leader apply worker.
+				 *
+				 * XXX We can avoid sending the statistics fields from the
+				 * leader apply worker but for that, it needs to rebuild the
+				 * entire message by removing these fields which could be more
+				 * work than simply ignoring these fields in the parallel apply
+				 * worker.
+				 */
+				s.cursor += SIZE_STATS_MESSAGE;
 
-			apply_dispatch(&s);
+				apply_dispatch(&s);
+			}
+			else if (c == PARALLEL_APPLY_INTERNAL_MESSAGE)
+			{
+				/* Handle the internal message. */
+				handle_internal_message(&s);
+			}
+			else
+			{
+				/*
+				 * The first byte of messages sent from leader apply worker to
+				 * parallel apply workers can only be 'w' or 'i'.
+				 */
+				elog(ERROR, "unexpected message \"%c\"", c);
+			}
 		}
 		else if (shmq_res == SHM_MQ_WOULD_BLOCK)
 		{
@@ -1647,3 +1722,19 @@ pa_xact_finish(ParallelApplyWorkerInfo *winfo, XLogRecPtr remote_lsn)
 
 	pa_free_worker(winfo);
 }
+
+/*
+ * Wait for the given transaction to finish.
+ */
+void
+pa_wait_for_depended_transaction(TransactionId xid)
+{
+	elog(DEBUG1, "wait for depended xid %u", xid);
+
+	for (;;)
+	{
+		/* XXX wait until given transaction is finished */
+	}
+
+	elog(DEBUG1, "finish waiting for depended xid %u", xid);
+}
diff --git a/src/include/replication/logicalproto.h b/src/include/replication/logicalproto.h
index 058a955e20c..9c5530804c8 100644
--- a/src/include/replication/logicalproto.h
+++ b/src/include/replication/logicalproto.h
@@ -77,6 +77,18 @@ typedef enum LogicalRepMsgType
 	LOGICAL_REP_MSG_STREAM_PREPARE = 'p',
 } LogicalRepMsgType;
 
+/*
+ * Worker internal message types
+ *
+ * This type of messages would be generated by leader apply worker and sent to
+ * the parallel apply worker.
+ */
+typedef enum WorkerInternalMsgType
+{
+	WORKER_INTERNAL_MSG_DEPENDENCY = 'd',
+	WORKER_INTERNAL_MSG_RELATION = 'i',
+} WorkerInternalMsgType;
+
 /*
  * This struct stores a tuple received via logical replication.
  * Keep in mind that the columns correspond to the *remote* table.
diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h
index 745b7d9e969..ccdb7e104f2 100644
--- a/src/include/replication/worker_internal.h
+++ b/src/include/replication/worker_internal.h
@@ -359,6 +359,8 @@ extern void pa_decr_and_wait_stream_block(void);
 extern void pa_xact_finish(ParallelApplyWorkerInfo *winfo,
 						   XLogRecPtr remote_lsn);
 
+extern void pa_wait_for_depended_transaction(TransactionId xid);
+
 #define isParallelApplyWorker(worker) ((worker)->in_use && \
 									   (worker)->type == WORKERTYPE_PARALLEL_APPLY)
 #define isTableSyncWorker(worker) ((worker)->in_use && \
@@ -366,6 +368,8 @@ extern void pa_xact_finish(ParallelApplyWorkerInfo *winfo,
 #define isSequenceSyncWorker(worker) ((worker)->in_use && \
 									  (worker)->type == WORKERTYPE_SEQUENCESYNC)
 
+#define PARALLEL_APPLY_INTERNAL_MESSAGE	'i'
+
 static inline bool
 am_tablesync_worker(void)
 {
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index ea95e7984bc..86930f93cad 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -3460,6 +3460,7 @@ WorkTableScan
 WorkTableScanState
 WorkerInfo
 WorkerInfoData
+WorkerInternalMsgType
 WorkerJobDumpPtrType
 WorkerJobRestorePtrType
 WorkerNodeInstrumentation
-- 
2.47.3