v2-0002-Avoid-TRUNCATE-when-restoring-load-via-partition-.patch

From 685b4a1c0aaa59b2b6047051d082838b88528587 Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Mon, 13 Mar 2023 19:05:05 -0400
Subject: [PATCH v2 2/6] Avoid TRUNCATE when restoring load-via-partition-root
 data.

This fixes the deadlock problem, allowing 004_pg_dump_parallel.pl to
succeed in the test where there's a manual --load-via-partition-root
switch.  It relies on the dump having used COPY commands, though.
---
 src/bin/pg_dump/pg_backup_archiver.c | 61 ++++++++++++++++++++++++----
 1 file changed, 54 insertions(+), 7 deletions(-)

diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c
index 61ebb8fe85..cb3a2c21f5 100644
--- a/src/bin/pg_dump/pg_backup_archiver.c
+++ b/src/bin/pg_dump/pg_backup_archiver.c
@@ -86,6 +86,7 @@ static RestorePass _tocEntryRestorePass(TocEntry *te);
 static bool _tocEntryIsACL(TocEntry *te);
 static void _disableTriggersIfNecessary(ArchiveHandle *AH, TocEntry *te);
 static void _enableTriggersIfNecessary(ArchiveHandle *AH, TocEntry *te);
+static bool is_load_via_partition_root(TocEntry *te);
 static void buildTocEntryArrays(ArchiveHandle *AH);
 static void _moveBefore(TocEntry *pos, TocEntry *te);
 static int	_discoverArchiveFormat(ArchiveHandle *AH);
@@ -887,6 +888,8 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te, bool is_parallel)
 				}
 				else
 				{
+					bool		use_truncate;
+
 					_disableTriggersIfNecessary(AH, te);
 
 					/* Select owner and schema as necessary */
@@ -898,13 +901,23 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te, bool is_parallel)
 
 					/*
 					 * In parallel restore, if we created the table earlier in
-					 * the run then we wrap the COPY in a transaction and
-					 * precede it with a TRUNCATE.  If archiving is not on
-					 * this prevents WAL-logging the COPY.  This obtains a
-					 * speedup similar to that from using single_txn mode in
-					 * non-parallel restores.
+					 * the run and we are not restoring a
+					 * load-via-partition-root data item then we wrap the COPY
+					 * in a transaction and precede it with a TRUNCATE.  If
+					 * archiving is not on this prevents WAL-logging the COPY.
+					 * This obtains a speedup similar to that from using
+					 * single_txn mode in non-parallel restores.
+					 *
+					 * We mustn't do this for load-via-partition-root cases
+					 * because some data might get moved across partition
+					 * boundaries, risking deadlock and/or loss of previously
+					 * loaded data.  (We assume that all partitions of a
+					 * partitioned table will be treated the same way.)
 					 */
-					if (is_parallel && te->created)
+					use_truncate = is_parallel && te->created &&
+						!is_load_via_partition_root(te);
+
+					if (use_truncate)
 					{
 						/*
 						 * Parallel restore is always talking directly to a
@@ -942,7 +955,7 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te, bool is_parallel)
 					AH->outputKind = OUTPUT_SQLCMDS;
 
 					/* close out the transaction started above */
-					if (is_parallel && te->created)
+					if (use_truncate)
 						CommitTransaction(&AH->public);
 
 					_enableTriggersIfNecessary(AH, te);
@@ -1036,6 +1049,40 @@ _enableTriggersIfNecessary(ArchiveHandle *AH, TocEntry *te)
 			 fmtQualifiedId(te->namespace, te->tag));
 }
 
+/*
+ * Detect whether a TABLE DATA TOC item is performing "load via partition
+ * root", that is the target table is an ancestor partition rather than the
+ * table the TOC item is nominally for.
+ *
+ * In newer archive files this can be detected by checking for a special
+ * comment placed in te->defn.  In older files we have to fall back to seeing
+ * if the COPY statement targets the named table or some other one.  This
+ * will not work for data dumped as INSERT commands, so we could give a false
+ * negative in that case; fortunately, that's a rarely-used option.
+ */
+static bool
+is_load_via_partition_root(TocEntry *te)
+{
+	if (te->copyStmt && *te->copyStmt)
+	{
+		PQExpBuffer copyStmt = createPQExpBuffer();
+		bool		result;
+
+		/*
+		 * Build the initial part of the COPY as it would appear if the
+		 * nominal target table is the actual target.  If we see anything
+		 * else, it must be a load-via-partition-root case.
+		 */
+		appendPQExpBuffer(copyStmt, "COPY %s ",
+						  fmtQualifiedId(te->namespace, te->tag));
+		result = strncmp(te->copyStmt, copyStmt->data, copyStmt->len) != 0;
+		destroyPQExpBuffer(copyStmt);
+		return result;
+	}
+	/* Assume it's not load-via-partition-root */
+	return false;
+}
+
 /*
  * This is a routine that is part of the dumper interface, hence the 'Archive*' parameter.
  */
-- 
2.31.1