Migrate logical slots to the new node during an upgrade.

While reading information from the old cluster, a list of logical
slots is fetched. At the later part of upgrading, pg_upgrade revisits the
list and restores slots by executing pg_create_logical_replication_slot()
on the new cluster. Migration of logical replication slots is only
supported when the old cluster is version 17.0 or later.

If the old node has invalid slots or slots with unconsumed WAL records,
the pg_upgrade fails. These checks are needed to prevent data loss.

The significant advantage of this commit is that it makes it easy to
continue logical replication even after upgrading the publisher node.
Previously, pg_upgrade allowed copying publications to a new node. With
this patch, adjusting the connection string to the new publisher will
cause the apply worker on the subscriber to connect to the new publisher
automatically. This enables seamless continuation of logical replication,
even after an upgrade.

Author: Hayato Kuroda, Hou Zhijie
Reviewed-by: Peter Smith, Bharath Rupireddy, Dilip Kumar, Vignesh C, Shlok Kyal
Discussion: http://postgr.es/m/TYAPR01MB58664C81887B3AF2EB6B16E3F5939@TYAPR01MB5866.jpnprd01.prod.outlook.com
Discussion: http://postgr.es/m/CAA4eK1+t7xYcfa0rEQw839=b2MzsfvYDPz3xbD+ZqOdP3zpKYg@mail.gmail.com

1 files changed, 75 insertions, 0 deletions

diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c
index 41243d0187a..8288da5277f 100644
--- a/src/backend/replication/logical/logical.c
+++ b/src/backend/replication/logical/logical.c
@@ -29,6 +29,7 @@
 #include "postgres.h"
 
 #include "access/xact.h"
+#include "access/xlogutils.h"
 #include "access/xlog_internal.h"
 #include "fmgr.h"
 #include "miscadmin.h"
@@ -41,6 +42,7 @@
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/builtins.h"
+#include "utils/inval.h"
 #include "utils/memutils.h"
 
 /* data for errcontext callback */
@@ -1949,3 +1951,76 @@ UpdateDecodingStats(LogicalDecodingContext *ctx)
 	rb->totalTxns = 0;
 	rb->totalBytes = 0;
 }
+
+/*
+ * Read up to the end of WAL starting from the decoding slot's restart_lsn.
+ * Return true if any meaningful/decodable WAL records are encountered,
+ * otherwise false.
+ */
+bool
+LogicalReplicationSlotHasPendingWal(XLogRecPtr end_of_wal)
+{
+	bool		has_pending_wal = false;
+
+	Assert(MyReplicationSlot);
+
+	PG_TRY();
+	{
+		LogicalDecodingContext *ctx;
+
+		/*
+		 * Create our decoding context in fast_forward mode, passing start_lsn
+		 * as InvalidXLogRecPtr, so that we start processing from the slot's
+		 * confirmed_flush.
+		 */
+		ctx = CreateDecodingContext(InvalidXLogRecPtr,
+									NIL,
+									true,	/* fast_forward */
+									XL_ROUTINE(.page_read = read_local_xlog_page,
+											   .segment_open = wal_segment_open,
+											   .segment_close = wal_segment_close),
+									NULL, NULL, NULL);
+
+		/*
+		 * Start reading at the slot's restart_lsn, which we know points to a
+		 * valid record.
+		 */
+		XLogBeginRead(ctx->reader, MyReplicationSlot->data.restart_lsn);
+
+		/* Invalidate non-timetravel entries */
+		InvalidateSystemCaches();
+
+		/* Loop until the end of WAL or some changes are processed */
+		while (!has_pending_wal && ctx->reader->EndRecPtr < end_of_wal)
+		{
+			XLogRecord *record;
+			char	   *errm = NULL;
+
+			record = XLogReadRecord(ctx->reader, &errm);
+
+			if (errm)
+				elog(ERROR, "could not find record for logical decoding: %s", errm);
+
+			if (record != NULL)
+				LogicalDecodingProcessRecord(ctx, ctx->reader);
+
+			has_pending_wal = ctx->processing_required;
+
+			CHECK_FOR_INTERRUPTS();
+		}
+
+		/* Clean up */
+		FreeDecodingContext(ctx);
+		InvalidateSystemCaches();
+	}
+	PG_CATCH();
+	{
+		/* clear all timetravel entries */
+		InvalidateSystemCaches();
+
+		PG_RE_THROW();
+	}
+	PG_END_TRY();
+
+	return has_pending_wal;
+}