From 521b91b2a5555f5688e88145714db1e990b803ea Mon Sep 17 00:00:00 2001
From: Justin Pryzby <pryzbyj@telsasoft.com>
Date: Sun, 7 Jun 2020 16:58:42 -0500
Subject: [PATCH v3 1/3] Implement CLUSTER of partitioned table..

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.
---
 doc/src/sgml/ref/cluster.sgml         |   6 +
 src/backend/commands/cluster.c        | 167 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/nodes/parsenodes.h        |   5 +-
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 208 insertions(+), 53 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index b9450e7366..0476cfff72 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -172,6 +172,12 @@ CLUSTER [VERBOSE]
     are periodically reclustered.
    </para>
 
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    index partition of the given partitioned index or (if not specified) the
+    partitioned index marked as clustered.
+   </para>
+
  </refsect1>
 
  <refsect1>
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 04d12a7ece..391e018bbd 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -32,7 +32,9 @@
 #include "catalog/index.h"
 #include "catalog/namespace.h"
 #include "catalog/objectaccess.h"
+#include "catalog/partition.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_inherits.h"
 #include "catalog/toasting.h"
 #include "commands/cluster.h"
 #include "commands/progress.h"
@@ -72,6 +74,9 @@ static void copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex,
 							bool verbose, bool *pSwapToastByContent,
 							TransactionId *pFreezeXid, MultiXactId *pCutoffMulti);
 static List *get_tables_to_cluster(MemoryContext cluster_context);
+static List *get_tables_to_cluster_partitioned(MemoryContext cluster_context,
+		Oid indexOid);
+static void cluster_multiple_rels(List *rvs, int options);
 
 
 /*---------------------------------------------------------------------------
@@ -113,7 +118,7 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 											AccessExclusiveLock,
 											0,
 											RangeVarCallbackOwnsTable, NULL);
-		rel = table_open(tableOid, NoLock);
+		rel = table_open(tableOid, ShareUpdateExclusiveLock);
 
 		/*
 		 * Reject clustering a remote temp table ... their local buffer
@@ -124,14 +129,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 					 errmsg("cannot cluster temporary tables of other sessions")));
 
-		/*
-		 * Reject clustering a partitioned table.
-		 */
-		if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
-			ereport(ERROR,
-					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-					 errmsg("cannot cluster a partitioned table")));
-
 		if (stmt->indexname == NULL)
 		{
 			ListCell   *index;
@@ -169,8 +166,32 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, stmt->options);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, stmt->options);
+		}
+		else
+		{
+			List	   *rvs;
+			MemoryContext cluster_context;
+
+			/* Refuse to hold strong locks in a user transaction */
+			PreventInTransactionBlock(isTopLevel, "CLUSTER");
+
+			cluster_context = AllocSetContextCreate(PortalContext,
+												"Cluster",
+												ALLOCSET_DEFAULT_SIZES);
+
+			rvs = get_tables_to_cluster_partitioned(cluster_context, indexOid);
+			cluster_multiple_rels(rvs, stmt->options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -180,7 +201,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -204,25 +224,7 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		 */
 		rvs = get_tables_to_cluster(cluster_context);
 
-		/* Commit to get out of starting transaction */
-		PopActiveSnapshot();
-		CommitTransactionCommand();
-
-		/* Ok, now that we've got them all, cluster them one by one */
-		foreach(rv, rvs)
-		{
-			RelToCluster *rvtc = (RelToCluster *) lfirst(rv);
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						stmt->options | CLUOPT_RECHECK);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, stmt->options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -328,9 +330,10 @@ cluster_rel(Oid tableOid, Oid indexOid, int options)
 			}
 
 			/*
-			 * Check that the index is still the one with indisclustered set.
+			 * Check that the index is still the one with indisclustered set, if needed.
 			 */
-			if (!get_index_isclustered(indexOid))
+			if ((options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -374,8 +377,13 @@ cluster_rel(Oid tableOid, Oid indexOid, int options)
 
 	/* Check heap and index are valid to cluster on */
 	if (OidIsValid(indexOid))
+	{
 		check_index_is_clusterable(OldHeap, indexOid, recheck, AccessExclusiveLock);
 
+		/* Mark the index as clustered */
+		mark_index_clustered(OldHeap, indexOid, true);
+	}
+
 	/*
 	 * Quietly ignore the request if this is a materialized view which has not
 	 * been populated from its query. No harm is done because there is no data
@@ -391,6 +399,14 @@ cluster_rel(Oid tableOid, Oid indexOid, int options)
 		return;
 	}
 
+	/* For a partitioned rel, we're done. */
+	if (!RELKIND_HAS_STORAGE(get_rel_relkind(tableOid)))
+	{
+		relation_close(OldHeap, AccessExclusiveLock);
+		pgstat_progress_end_command();
+		return;
+	}
+
 	/*
 	 * All predicate locks on the tuples or pages are about to be made
 	 * invalid, because we move tuples around.  Promote them to relation
@@ -459,6 +475,9 @@ check_index_is_clusterable(Relation OldHeap, Oid indexOid, bool recheck, LOCKMOD
 	 * the worst consequence of following broken HOT chains would be that we
 	 * might put recently-dead tuples out-of-order in the new table, and there
 	 * is little harm in that.)
+	 *
+	 * This also refuses to cluster on an "incomplete" partitioned index
+	 * created with "ON ONLY".
 	 */
 	if (!OldIndex->rd_index->indisvalid)
 		ereport(ERROR,
@@ -483,12 +502,6 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
 	Relation	pg_index;
 	ListCell   *index;
 
-	/* Disallow applying to a partitioned table */
-	if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE)
-		ereport(ERROR,
-				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-				 errmsg("cannot mark index clustered in partitioned table")));
-
 	/*
 	 * If the index is already marked clustered, no need to do anything.
 	 */
@@ -560,10 +573,6 @@ rebuild_relation(Relation OldHeap, Oid indexOid, bool verbose)
 	TransactionId frozenXid;
 	MultiXactId cutoffMulti;
 
-	/* Mark the correct index as clustered */
-	if (OidIsValid(indexOid))
-		mark_index_clustered(OldHeap, indexOid, true);
-
 	/* Remember info about rel before closing OldHeap */
 	relpersistence = OldHeap->rd_rel->relpersistence;
 	is_system_catalog = IsSystemRelation(OldHeap);
@@ -1557,3 +1566,75 @@ get_tables_to_cluster(MemoryContext cluster_context)
 
 	return rvs;
 }
+
+/*
+ * Return a List of tables and associated index, where each index is a
+ * partition of the given index
+ */
+static List *
+get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid)
+{
+	List		*inhoids;
+	ListCell	*lc;
+	List		*rvs = NIL;
+	MemoryContext	old_context;
+
+	inhoids = find_all_inheritors(indexOid, NoLock, NULL);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels are also processed by cluster_rel, to
+		 * call check_index_is_clusterable() and mark_index_clustered().
+		 */
+
+		/*
+		 * We have to build the list in a different memory context so it will
+		 * survive the cross-transaction processing
+		 */
+		old_context = MemoryContextSwitchTo(cluster_context);
+
+		rvtc = (RelToCluster *) palloc(sizeof(RelToCluster));
+		rvtc->tableOid = relid;
+		rvtc->indexOid = indexrelid;
+		rvs = lappend(rvs, rvtc);
+
+		MemoryContextSwitchTo(old_context);
+	}
+
+	return rvs;
+}
+
+/* Cluster each relation in a separate transaction */
+static void
+cluster_multiple_rels(List *rvs, int options)
+{
+	ListCell *lc;
+
+	/* Commit to get out of starting transaction */
+	PopActiveSnapshot();
+	CommitTransactionCommand();
+
+	/* Ok, now that we've got them all, cluster them one by one */
+	foreach(lc, rvs)
+	{
+		RelToCluster *rvtc = (RelToCluster *) lfirst(lc);
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					options | CLUOPT_RECHECK);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 5238a960f7..07ef7fc1b7 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -588,6 +588,7 @@ static const SchemaQuery Query_for_list_of_clusterables = {
 	.catname = "pg_catalog.pg_class c",
 	.selcondition =
 	"c.relkind IN (" CppAsString2(RELKIND_RELATION) ", "
+	CppAsString2(RELKIND_PARTITIONED_TABLE) ", "
 	CppAsString2(RELKIND_MATVIEW) ")",
 	.viscondition = "pg_catalog.pg_table_is_visible(c.oid)",
 	.namespace = "c.relnamespace",
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 17b4e335c6..c862662a78 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3198,8 +3198,9 @@ typedef struct AlterSystemStmt
  */
 typedef enum ClusterOption
 {
-	CLUOPT_RECHECK = 1 << 0,	/* recheck relation state */
-	CLUOPT_VERBOSE = 1 << 1		/* print progress info */
+	CLUOPT_VERBOSE = 1 << 0,	/* print progress info */
+	CLUOPT_RECHECK = 1 << 1,	/* recheck relation state */
+	CLUOPT_RECHECK_ISCLUSTERED = 1 << 2,	/* recheck relation state for indisclustered */
 } ClusterOption;
 
 typedef struct ClusterStmt
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..e4448350e7 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,14 +439,62 @@ select * from clstr_temp;
 
 drop table clstr_temp;
 RESET SESSION AUTHORIZATION;
--- Check that partitioned tables cannot be clustered
+-- Check that partitioned tables can be clustered
 CREATE TABLE clstrpart (a int) PARTITION BY RANGE (a);
+CREATE TABLE clstrpart1 PARTITION OF clstrpart FOR VALUES FROM (1)TO(10) PARTITION BY RANGE (a);
+CREATE TABLE clstrpart11 PARTITION OF clstrpart1 FOR VALUES FROM (1)TO(10);
+CREATE TABLE clstrpart12 PARTITION OF clstrpart1 FOR VALUES FROM (10)TO(20) PARTITION BY RANGE(a);
+CREATE TABLE clstrpart2 PARTITION OF clstrpart FOR VALUES FROM (20)TO(30);
+CREATE TABLE clstrpart3 PARTITION OF clstrpart DEFAULT PARTITION BY RANGE(a);
+CREATE TABLE clstrpart33 PARTITION OF clstrpart3 DEFAULT;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
+CREATE INDEX clstrpart_only_idx ON ONLY clstrpart (a);
+CLUSTER clstrpart USING clstrpart_only_idx; -- fails
+ERROR:  cannot cluster on invalid index "clstrpart_only_idx"
+DROP INDEX clstrpart_only_idx;
 CREATE INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
-ERROR:  cannot mark index clustered in partitioned table
+-- Check that clustering sets new relfilenodes:
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
 CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
-DROP TABLE clstrpart;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY 1;
+   relname   | relkind | ?column? 
+-------------+---------+----------
+ clstrpart   | p       | t
+ clstrpart1  | p       | t
+ clstrpart11 | r       | f
+ clstrpart12 | p       | t
+ clstrpart2  | r       | f
+ clstrpart3  | p       | t
+ clstrpart33 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT i.indexrelid::regclass::text, relkind, indisclustered FROM pg_partition_tree('clstrpart_idx'::regclass) AS tree JOIN pg_index i ON i.indexrelid=tree.relid JOIN pg_class c ON c.oid=indexrelid ORDER BY 1;
+    indexrelid     | relkind | indisclustered 
+-------------------+---------+----------------
+ clstrpart11_a_idx | i       | t
+ clstrpart12_a_idx | I       | t
+ clstrpart1_a_idx  | I       | t
+ clstrpart2_a_idx  | i       | t
+ clstrpart33_a_idx | i       | t
+ clstrpart3_a_idx  | I       | t
+ clstrpart_idx     | I       | t
+(7 rows)
+
+CLUSTER clstrpart1 USING clstrpart1_a_idx; -- partition which is itself partitioned
+CLUSTER clstrpart12 USING clstrpart12_a_idx; -- partition which is itself partitioned, no childs
+CLUSTER clstrpart2 USING clstrpart2_a_idx; -- leaf
+\d clstrpart
+       Partitioned table "public.clstrpart"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+Partition key: RANGE (a)
+Indexes:
+    "clstrpart_idx" btree (a) CLUSTER
+Number of partitions: 3 (Use \d+ to list them.)
+
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
 create index cluster_sort on clstr_4 (hundred, thousand, tenthous);
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index 188183647c..22225dc924 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,12 +196,30 @@ drop table clstr_temp;
 
 RESET SESSION AUTHORIZATION;
 
--- Check that partitioned tables cannot be clustered
+-- Check that partitioned tables can be clustered
 CREATE TABLE clstrpart (a int) PARTITION BY RANGE (a);
+CREATE TABLE clstrpart1 PARTITION OF clstrpart FOR VALUES FROM (1)TO(10) PARTITION BY RANGE (a);
+CREATE TABLE clstrpart11 PARTITION OF clstrpart1 FOR VALUES FROM (1)TO(10);
+CREATE TABLE clstrpart12 PARTITION OF clstrpart1 FOR VALUES FROM (10)TO(20) PARTITION BY RANGE(a);
+CREATE TABLE clstrpart2 PARTITION OF clstrpart FOR VALUES FROM (20)TO(30);
+CREATE TABLE clstrpart3 PARTITION OF clstrpart DEFAULT PARTITION BY RANGE(a);
+CREATE TABLE clstrpart33 PARTITION OF clstrpart3 DEFAULT;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
+CREATE INDEX clstrpart_only_idx ON ONLY clstrpart (a);
+CLUSTER clstrpart USING clstrpart_only_idx; -- fails
+DROP INDEX clstrpart_only_idx;
 CREATE INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+-- Check that clustering sets new relfilenodes:
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
 CLUSTER clstrpart USING clstrpart_idx;
-DROP TABLE clstrpart;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY 1;
+-- Check that clustering sets new indisclustered:
+SELECT i.indexrelid::regclass::text, relkind, indisclustered FROM pg_partition_tree('clstrpart_idx'::regclass) AS tree JOIN pg_index i ON i.indexrelid=tree.relid JOIN pg_class c ON c.oid=indexrelid ORDER BY 1;
+CLUSTER clstrpart1 USING clstrpart1_a_idx; -- partition which is itself partitioned
+CLUSTER clstrpart12 USING clstrpart12_a_idx; -- partition which is itself partitioned, no childs
+CLUSTER clstrpart2 USING clstrpart2_a_idx; -- leaf
+\d clstrpart
 
 -- Test CLUSTER with external tuplesorting
 
-- 
2.17.0

