public inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v9 2/8] Implement CLUSTER of partitioned table..
148+ messages / 5 participants
[nested] [flat]

* [PATCH v9 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

VACUUM (including vacuum full) has recursed into partition hierarchies since
partitions were introduced in v10 (3c3bb9933).
---
 doc/src/sgml/ref/cluster.sgml         |   7 ++
 src/backend/commands/cluster.c        | 173 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0d9720fd8e..17509b35eb 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -197,6 +197,13 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified 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 096a06f7b3..0c08ac56dc 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,76 @@ 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels (including the top indexOid) are included,
+		 * so as to be processed by cluster_rel, which calls
+		 * check_index_is_clusterable() and mark_index_clustered().
+		 */
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 9f0208ac49..53d585c4d3 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--fmvA4kSBHQVZhkR6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v9-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v9 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

VACUUM (including vacuum full) has recursed into partition hierarchies since
partitions were introduced in v10 (3c3bb9933).
---
 doc/src/sgml/ref/cluster.sgml         |   7 ++
 src/backend/commands/cluster.c        | 173 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0d9720fd8e..17509b35eb 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -197,6 +197,13 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified 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 096a06f7b3..0c08ac56dc 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,76 @@ 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels (including the top indexOid) are included,
+		 * so as to be processed by cluster_rel, which calls
+		 * check_index_is_clusterable() and mark_index_clustered().
+		 */
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 9f0208ac49..53d585c4d3 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--fmvA4kSBHQVZhkR6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v9-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v4 3/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.
---
 src/backend/commands/cluster.c        | 139 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/test/regress/expected/cluster.out |  23 ++++-
 src/test/regress/sql/cluster.sql      |  12 ++-
 4 files changed, 133 insertions(+), 42 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 04d12a7ece..7409c17b0b 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -33,6 +33,7 @@
 #include "catalog/namespace.h"
 #include "catalog/objectaccess.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 +73,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -124,14 +128,6 @@ 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 +165,37 @@ 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;
+
+			/* Check index directly since cluster_rel isn't called for partitioned table */
+			check_index_is_clusterable(rel, indexOid, true, AccessExclusiveLock);
+
+			/* 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();
+
+			rel = table_open(tableOid, ShareUpdateExclusiveLock);
+			mark_index_clustered(rel, indexOid, true);
+			table_close(rel, NoLock);
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -180,7 +205,6 @@ 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 +228,7 @@ 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);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -483,12 +489,6 @@ 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.
 	 */
@@ -1557,3 +1557,70 @@ 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 = MemoryContextSwitchTo(cluster_context);
+
+	inhoids = find_all_inheritors(indexOid, NoLock, NULL);
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * We have a full list of direct and indirect children, so skip
+		 * partitioned tables and just handle their children.
+		 */
+		if (get_rel_relkind(relid) == RELKIND_PARTITIONED_TABLE)
+			continue;
+
+		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 c4af40bfa9..e68808218a 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -587,6 +587,7 @@ 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/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..21b28fde6e 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,13 +439,28 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
-ERROR:  cannot mark index clustered in partitioned table
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
+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: 2 (Use \d+ to list them.)
+
 DROP TABLE clstrpart;
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index 188183647c..4a76848213 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,11 +196,19 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
+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
 DROP TABLE clstrpart;
 
 -- Test CLUSTER with external tuplesorting
-- 
2.17.0


--JYK4vJDZwFMowpUq--





^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v5 3/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.
---
 src/backend/commands/cluster.c        | 139 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/test/regress/expected/cluster.out |  23 ++++-
 src/test/regress/sql/cluster.sql      |  12 ++-
 4 files changed, 133 insertions(+), 42 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 04d12a7ece..7409c17b0b 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -33,6 +33,7 @@
 #include "catalog/namespace.h"
 #include "catalog/objectaccess.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 +73,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -124,14 +128,6 @@ 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 +165,37 @@ 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;
+
+			/* Check index directly since cluster_rel isn't called for partitioned table */
+			check_index_is_clusterable(rel, indexOid, true, AccessExclusiveLock);
+
+			/* 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();
+
+			rel = table_open(tableOid, ShareUpdateExclusiveLock);
+			mark_index_clustered(rel, indexOid, true);
+			table_close(rel, NoLock);
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -180,7 +205,6 @@ 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 +228,7 @@ 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);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -483,12 +489,6 @@ 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.
 	 */
@@ -1557,3 +1557,70 @@ 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 = MemoryContextSwitchTo(cluster_context);
+
+	inhoids = find_all_inheritors(indexOid, NoLock, NULL);
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * We have a full list of direct and indirect children, so skip
+		 * partitioned tables and just handle their children.
+		 */
+		if (get_rel_relkind(relid) == RELKIND_PARTITIONED_TABLE)
+			continue;
+
+		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 c4af40bfa9..e68808218a 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -587,6 +587,7 @@ 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/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..21b28fde6e 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,13 +439,28 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
-ERROR:  cannot mark index clustered in partitioned table
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
+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: 2 (Use \d+ to list them.)
+
 DROP TABLE clstrpart;
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index 188183647c..4a76848213 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,11 +196,19 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
+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
 DROP TABLE clstrpart;
 
 -- Test CLUSTER with external tuplesorting
-- 
2.17.0


--hYooF8G/hrfVAmum--





^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v7 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 174 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..9b6673867c 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index a75647b1cc..781aa95abc 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--AA9g+nFNFPYNJKiL
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v7-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v8 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 174 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..9b6673867c 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 1e1c315bae..ba301a6b08 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--O5XBE6gyVG5Rl6Rj
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v8-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v6 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 172 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 208 insertions(+), 54 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..838bcd9e72 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -191,8 +188,32 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 6abcbea963..3a6a4831e1 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
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


--FsscpQKzF/jJk6ya
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v6-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v9 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

VACUUM (including vacuum full) has recursed into partition hierarchies since
partitions were introduced in v10 (3c3bb9933).
---
 doc/src/sgml/ref/cluster.sgml         |   7 ++
 src/backend/commands/cluster.c        | 173 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0d9720fd8e..17509b35eb 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -197,6 +197,13 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified 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 096a06f7b3..0c08ac56dc 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,76 @@ 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels (including the top indexOid) are included,
+		 * so as to be processed by cluster_rel, which calls
+		 * check_index_is_clusterable() and mark_index_clustered().
+		 */
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 9f0208ac49..53d585c4d3 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--fmvA4kSBHQVZhkR6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v9-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v11] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

For now, partitioned indexes cannot be marked clustered, so clustering requires
specification of a partitioned index on the partitioned table.

VACUUM (including vacuum full) has recursed into partitione tables since
partitioning were introduced in v10 (3c3bb9933).  See expand_vacuum_rel().

See also a556549d7 and 19de0ab23.
---
 doc/src/sgml/ref/cluster.sgml         |   6 +
 src/backend/commands/cluster.c        | 170 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  46 ++++++-
 src/test/regress/sql/cluster.sql      |  22 +++-
 6 files changed, 197 insertions(+), 49 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 86f5fdc469..b3463ae5c4 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -196,6 +196,12 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified partitioned index (which must be specified).
+   </para>
+
  </refsect1>
 
  <refsect1>
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 9d22f648a8..c5923c5217 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -131,6 +136,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		Relation	rel;
 
 		/* Find, lock, and check permissions on the table */
+		/* Obtain AEL now to avoid lock-upgrade hazard in the single-transaction case */
 		tableOid = RangeVarGetRelidExtended(stmt->relation,
 											AccessExclusiveLock,
 											0,
@@ -146,14 +152,6 @@ cluster(ParseState *pstate, 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;
@@ -188,11 +186,45 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 								stmt->indexname, stmt->relation->relname)));
 		}
 
-		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* close relation, keep lock till commit */
+			table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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);
+
+			/*
+			 * For now, partitioned indexes are not actually marked clustered.
+			 */
+			check_index_is_clusterable(rel, indexOid, true, AccessShareLock);
+
+			/* close relation, releasing lock on parent table */
+			table_close(rel, AccessExclusiveLock);
+
+			/* Do the job. */
+			cluster_multiple_rels(rvs, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +234,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +256,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -327,10 +337,11 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		/*
 		 * Silently skip a temp table for a remote session.  Only doing this
 		 * check in the "recheck" case is appropriate (which currently means
-		 * somebody is executing a database-wide CLUSTER), because there is
-		 * another check in cluster() which will stop any attempt to cluster
-		 * remote temp tables by name.  There is another check in cluster_rel
-		 * which is redundant, but we leave it for extra safety.
+		 * somebody is executing a database-wide CLUSTER or on a partitioned
+		 * table), because there is another check in cluster() which will stop
+		 * any attempt to cluster remote temp tables by name.  There is another
+		 * check in cluster_rel which is redundant, but we leave it for extra
+		 * safety.
 		 */
 		if (RELATION_IS_OTHER_TEMP(OldHeap))
 		{
@@ -352,9 +363,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -415,6 +427,9 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		return;
 	}
 
+	// Should silently skip this rather than assert ?
+	Assert(RELKIND_HAS_STORAGE(OldHeap->rd_rel->relkind));
+
 	/*
 	 * All predicate locks on the tuples or pages are about to be made
 	 * invalid, because we move tuples around.  Promote them to relation
@@ -585,8 +600,8 @@ rebuild_relation(Relation OldHeap, Oid indexOid, bool verbose)
 	TransactionId frozenXid;
 	MultiXactId cutoffMulti;
 
-	/* Mark the correct index as clustered */
 	if (OidIsValid(indexOid))
+		/* Mark the correct index as clustered */
 		mark_index_clustered(OldHeap, indexOid, true);
 
 	/* Remember info about rel before closing OldHeap */
@@ -1604,3 +1619,74 @@ get_tables_to_cluster(MemoryContext cluster_context)
 
 	return rvs;
 }
+
+/*
+ * Return a List of tables and their associated indexes, 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		if (!RELKIND_HAS_STORAGE(get_rel_relkind(indexrelid)))
+			continue;
+
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 5cd5838668..c377511278 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -599,6 +599,7 @@ 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/commands/cluster.h b/src/include/commands/cluster.h
index b64d3bc204..d400b6e937 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index e46a66952f..7461e1c090 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -444,14 +444,52 @@ DROP TABLE clustertest;
 CREATE TABLE clustertest (f1 int PRIMARY KEY);
 CLUSTER clustertest USING clustertest_pkey;
 CLUSTER clustertest;
--- 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;
+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);
+-- Check that clustering sets new relfilenodes:
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+CLUSTER clstrpart USING clstrpart_idx;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Partitioned indexes aren't and can't be marked un/clustered:
+\d clstrpart
+       Partitioned table "public.clstrpart"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+Partition key: RANGE (a)
+Indexes:
+    "clstrpart_idx" btree (a)
+Number of partitions: 3 (Use \d+ to list them.)
+
+CLUSTER clstrpart;
+ERROR:  there is no previously clustered index for table "clstrpart"
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
+ERROR:  cannot mark index clustered in partitioned table
 ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
 ERROR:  cannot mark index clustered in partitioned table
-CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
-DROP TABLE clstrpart;
 -- 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 aee9cf83e0..f31f8ef2b2 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -202,12 +202,28 @@ CREATE TABLE clustertest (f1 int PRIMARY KEY);
 CLUSTER clustertest USING clustertest_pkey;
 CLUSTER clustertest;
 
--- 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;
+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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Partitioned indexes aren't and can't be marked un/clustered:
+\d clstrpart
+CLUSTER clstrpart;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
+ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
 
 -- Test CLUSTER with external tuplesorting
 
-- 
2.17.0


--DwoPkXS38qd3dnhB--





^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v11] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

VACUUM (including vacuum full) has recursed into partitioned tables since
partitioning were introduced in v10 (3c3bb9933).  See expand_vacuum_rel().

For VACUUM FULL, vacuum_rel() calls cluster_rel() for each partition.
This patch is to make cluster() do all the same stuff before calling
cluster_rel().

For now, partitioned indexes cannot be marked clustered, so clustering requires
specification of a partitioned index on the partitioned table.

See also a556549d7 and 19de0ab23.
---
 doc/src/sgml/ref/cluster.sgml         |   6 +
 src/backend/commands/cluster.c        | 177 ++++++++++++++++++++------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  45 ++++++-
 src/test/regress/sql/cluster.sql      |  21 ++-
 6 files changed, 204 insertions(+), 47 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 86f5fdc469b..b3463ae5c46 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -196,6 +196,12 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified partitioned index (which must be specified).
+   </para>
+
  </refsect1>
 
  <refsect1>
diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 61853e6dec4..196c7f7eeb2 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -131,6 +136,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		Relation	rel;
 
 		/* Find, lock, and check permissions on the table */
+		/* Obtain AEL now to avoid lock-upgrade hazard in the single-transaction case */
 		tableOid = RangeVarGetRelidExtended(stmt->relation,
 											AccessExclusiveLock,
 											0,
@@ -146,14 +152,6 @@ cluster(ParseState *pstate, 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;
@@ -188,11 +186,50 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 								stmt->indexname, stmt->relation->relname)));
 		}
 
-		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* close relation, keep lock till commit */
+			table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		else
+		{
+			List	   *rvs;
+			MemoryContext cluster_context;
+
+			/*
+			 * Expand partitioned relations for CLUSTER (the corresponding
+			 * thing for VACUUM FULL happens in and around expand_vacuum_rel()
+			 */
+
+			/* 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);
+
+			/*
+			 * For now, partitioned indexes are not actually marked clustered.
+			 */
+			check_index_is_clusterable(rel, indexOid, true, AccessShareLock);
+
+			/* close relation, releasing lock on parent table */
+			table_close(rel, AccessExclusiveLock);
+
+			/* Do the job. */
+			cluster_multiple_rels(rvs, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +239,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +261,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -327,10 +342,11 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		/*
 		 * Silently skip a temp table for a remote session.  Only doing this
 		 * check in the "recheck" case is appropriate (which currently means
-		 * somebody is executing a database-wide CLUSTER), because there is
-		 * another check in cluster() which will stop any attempt to cluster
-		 * remote temp tables by name.  There is another check in cluster_rel
-		 * which is redundant, but we leave it for extra safety.
+		 * somebody is executing a database-wide CLUSTER or on a partitioned
+		 * table), because there is another check in cluster() which will stop
+		 * any attempt to cluster remote temp tables by name.  There is another
+		 * check in cluster_rel which is redundant, but we leave it for extra
+		 * safety.
 		 */
 		if (RELATION_IS_OTHER_TEMP(OldHeap))
 		{
@@ -352,9 +368,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -415,6 +432,9 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		return;
 	}
 
+	// Should silently skip this rather than assert ?
+	Assert(RELKIND_HAS_STORAGE(OldHeap->rd_rel->relkind));
+
 	/*
 	 * All predicate locks on the tuples or pages are about to be made
 	 * invalid, because we move tuples around.  Promote them to relation
@@ -585,8 +605,8 @@ rebuild_relation(Relation OldHeap, Oid indexOid, bool verbose)
 	TransactionId frozenXid;
 	MultiXactId cutoffMulti;
 
-	/* Mark the correct index as clustered */
 	if (OidIsValid(indexOid))
+		/* Mark the correct index as clustered */
 		mark_index_clustered(OldHeap, indexOid, true);
 
 	/* Remember info about rel before closing OldHeap */
@@ -1604,3 +1624,76 @@ get_tables_to_cluster(MemoryContext cluster_context)
 
 	return rvs;
 }
+
+/*
+ * Return a List of tables and their associated indexes, where each index is a
+ * partition of the given index
+ * We're called with a lock held on the parent table.
+ */
+static List *
+get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid)
+{
+	List		*inhoids;
+	ListCell	*lc;
+	List		*rvs = NIL;
+	MemoryContext	old_context;
+
+	/* Do not lock the children until they're processed. */
+	inhoids = find_all_inheritors(indexOid, NoLock, NULL);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		if (!RELKIND_HAS_STORAGE(get_rel_relkind(indexrelid)))
+			continue;
+
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 39be6f556a8..9944f21f71c 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -599,6 +599,7 @@ 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/commands/cluster.h b/src/include/commands/cluster.h
index 3db375d7cc7..0605b053b61 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index e46a66952f0..3f2758d13f6 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -444,13 +444,52 @@ DROP TABLE clustertest;
 CREATE TABLE clustertest (f1 int PRIMARY KEY);
 CLUSTER clustertest USING clustertest_pkey;
 CLUSTER clustertest;
--- 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;
+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);
+-- Check that clustering sets new relfilenodes:
+CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+CLUSTER clstrpart USING clstrpart_idx;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Partitioned indexes aren't and can't be marked un/clustered:
+\d clstrpart
+       Partitioned table "public.clstrpart"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+Partition key: RANGE (a)
+Indexes:
+    "clstrpart_idx" btree (a)
+Number of partitions: 3 (Use \d+ to list them.)
+
+CLUSTER clstrpart;
+ERROR:  there is no previously clustered index for table "clstrpart"
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
+ERROR:  cannot mark index clustered in partitioned table
 ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
 ERROR:  cannot mark index clustered in partitioned table
-CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
 DROP TABLE clstrpart;
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index aee9cf83e04..74118993a82 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -202,11 +202,28 @@ CREATE TABLE clustertest (f1 int PRIMARY KEY);
 CLUSTER clustertest USING clustertest_pkey;
 CLUSTER clustertest;
 
--- 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;
+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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
 CLUSTER clstrpart USING clstrpart_idx;
+CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Partitioned indexes aren't and can't be marked un/clustered:
+\d clstrpart
+CLUSTER clstrpart;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
+ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
 DROP TABLE clstrpart;
 
 -- Test CLUSTER with external tuplesorting
-- 
2.17.1


--NqNl6FRZtoRUn5bW--





^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v9 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

VACUUM (including vacuum full) has recursed into partition hierarchies since
partitions were introduced in v10 (3c3bb9933).
---
 doc/src/sgml/ref/cluster.sgml         |   7 ++
 src/backend/commands/cluster.c        | 173 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0d9720fd8e..17509b35eb 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -197,6 +197,13 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified 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 096a06f7b3..0c08ac56dc 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,76 @@ 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels (including the top indexOid) are included,
+		 * so as to be processed by cluster_rel, which calls
+		 * check_index_is_clusterable() and mark_index_clustered().
+		 */
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 9f0208ac49..53d585c4d3 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--fmvA4kSBHQVZhkR6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v9-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v7 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 174 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..9b6673867c 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index a75647b1cc..781aa95abc 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--AA9g+nFNFPYNJKiL
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v7-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v8 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 174 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..9b6673867c 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 1e1c315bae..ba301a6b08 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--O5XBE6gyVG5Rl6Rj
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v8-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v10 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

VACUUM (including vacuum full) has recursed into partition hierarchies since
partitions were introduced in v10 (3c3bb9933).
---
 doc/src/sgml/ref/cluster.sgml         |   7 ++
 src/backend/commands/cluster.c        | 173 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0d9720fd8e..17509b35eb 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -197,6 +197,13 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified 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 096a06f7b3..0c08ac56dc 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,76 @@ 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels (including the top indexOid) are included,
+		 * so as to be processed by cluster_rel, which calls
+		 * check_index_is_clusterable() and mark_index_clustered().
+		 */
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index a053bc1e45..3fd192b8d2 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index e46a66952f..8fb496434e 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -444,14 +444,62 @@ DROP TABLE clustertest;
 CREATE TABLE clustertest (f1 int PRIMARY KEY);
 CLUSTER clustertest USING clustertest_pkey;
 CLUSTER clustertest;
--- 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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 aee9cf83e0..57fc661863 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -202,12 +202,30 @@ CREATE TABLE clustertest (f1 int PRIMARY KEY);
 CLUSTER clustertest USING clustertest_pkey;
 CLUSTER clustertest;
 
--- 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--mvpLiMfbWzRoNl4x
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v10-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v6 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 172 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 208 insertions(+), 54 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..838bcd9e72 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -191,8 +188,32 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 6abcbea963..3a6a4831e1 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
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


--FsscpQKzF/jJk6ya
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v6-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v9 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

VACUUM (including vacuum full) has recursed into partition hierarchies since
partitions were introduced in v10 (3c3bb9933).
---
 doc/src/sgml/ref/cluster.sgml         |   7 ++
 src/backend/commands/cluster.c        | 173 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 0d9720fd8e..17509b35eb 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -197,6 +197,13 @@ CLUSTER [VERBOSE]
     in the <structname>pg_stat_progress_cluster</structname> view. See
     <xref linkend="cluster-progress-reporting"/> for details.
   </para>
+
+   <para>
+    Clustering a partitioned table clusters each of its partitions using the
+    partition of the specified 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 096a06f7b3..0c08ac56dc 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,76 @@ 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);
+
+	/*
+	 * We have to build the list in a different memory context so it will
+	 * survive the cross-transaction processing
+	 */
+	old_context = MemoryContextSwitchTo(cluster_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * Partitioned rels (including the top indexOid) are included,
+		 * so as to be processed by cluster_rel, which calls
+		 * check_index_is_clusterable() and mark_index_clustered().
+		 */
+		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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 9f0208ac49..53d585c4d3 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--fmvA4kSBHQVZhkR6
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v9-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v7 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 174 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..9b6673867c 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index a75647b1cc..781aa95abc 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--AA9g+nFNFPYNJKiL
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v7-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v8 2/8] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 174 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 209 insertions(+), 55 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..9b6673867c 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -189,10 +186,34 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		}
 
 		/* close relation, keep lock till commit */
-		table_close(rel, NoLock);
+		table_close(rel, ShareUpdateExclusiveLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 1e1c315bae..ba301a6b08 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..c74cfa88cc 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+   relname   | level | relkind | ?column? 
+-------------+-------+---------+----------
+ clstrpart   |     0 | p       | t
+ clstrpart1  |     1 | p       | t
+ clstrpart11 |     2 | r       | f
+ clstrpart12 |     2 | p       | t
+ clstrpart2  |     1 | r       | f
+ clstrpart3  |     1 | p       | t
+ clstrpart33 |     2 | r       | f
+(7 rows)
+
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+      relname      | 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..9bcc77695c 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, level, 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, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ;
+SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C";
+-- Check that clustering sets new indisclustered:
+SELECT relname, 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 relname COLLATE "C";
+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


--O5XBE6gyVG5Rl6Rj
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="v8-0003-f-progress-reporting.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v6 2/2] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

XXX: should mark_index_clustered() SET WITHOUT CLUSTER for any parent indexes
of an index partition which were previously-clustered ?
---
 src/backend/commands/cluster.c        | 141 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/test/regress/expected/cluster.out |  23 ++++-
 src/test/regress/sql/cluster.sql      |  12 ++-
 4 files changed, 134 insertions(+), 43 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 0d647e912c..6ead8ffc79 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -33,6 +33,7 @@
 #include "catalog/namespace.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_inherits.h"
 #include "catalog/toasting.h"
 #include "commands/cluster.h"
 #include "commands/progress.h"
@@ -75,6 +76,9 @@ static void copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex,
 							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, bool isTopLevel, int options);
 
 
 /*---------------------------------------------------------------------------
@@ -127,14 +131,6 @@ 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;
@@ -172,8 +168,37 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		} else {
+			List	   *rvs;
+			MemoryContext cluster_context;
+
+			/* Check index directly since cluster_rel isn't called for partitioned table */
+			check_index_is_clusterable(rel, indexOid, true, AccessExclusiveLock);
+
+			/* 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, isTopLevel, stmt->options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			rel = table_open(tableOid, ShareUpdateExclusiveLock);
+			mark_index_clustered(rel, indexOid, true);
+			table_close(rel, NoLock);
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -183,7 +208,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -207,26 +231,7 @@ 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,
-						isTopLevel);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, isTopLevel, stmt->options);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -487,12 +492,6 @@ 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.
 	 */
@@ -1563,3 +1562,71 @@ 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 = MemoryContextSwitchTo(cluster_context);
+
+	inhoids = find_all_inheritors(indexOid, NoLock, NULL);
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * We have a full list of direct and indirect children, so skip
+		 * partitioned tables and just handle their children.
+		 */
+		if (get_rel_relkind(relid) == RELKIND_PARTITIONED_TABLE)
+			continue;
+
+		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, bool isTopLevel, 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,
+						isTopLevel);
+
+			PopActiveSnapshot();
+			CommitTransactionCommand();
+		}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index f41785f11c..49a2648991 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -587,6 +587,7 @@ 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/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..21b28fde6e 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,13 +439,28 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
-ERROR:  cannot mark index clustered in partitioned table
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
+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: 2 (Use \d+ to list them.)
+
 DROP TABLE clstrpart;
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index 188183647c..4a76848213 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,11 +196,19 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
+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
 DROP TABLE clstrpart;
 
 -- Test CLUSTER with external tuplesorting
-- 
2.17.0


--JgQwtEuHJzHdouWu--





^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v7 2/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

XXX: should mark_index_clustered() SET WITHOUT CLUSTER for any parent indexes
of an index partition which were previously-clustered ?
---
 src/backend/commands/cluster.c        | 143 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/test/regress/expected/cluster.out |  25 ++++-
 src/test/regress/sql/cluster.sql      |  14 ++-
 4 files changed, 140 insertions(+), 43 deletions(-)

diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c
index 0d647e912c..0f61c78fb9 100644
--- a/src/backend/commands/cluster.c
+++ b/src/backend/commands/cluster.c
@@ -33,6 +33,7 @@
 #include "catalog/namespace.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_inherits.h"
 #include "catalog/toasting.h"
 #include "commands/cluster.h"
 #include "commands/progress.h"
@@ -75,6 +76,9 @@ static void copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex,
 							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, bool isTopLevel, int options);
 
 
 /*---------------------------------------------------------------------------
@@ -127,14 +131,6 @@ 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;
@@ -172,8 +168,39 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		}
+		else
+		{
+			List	   *rvs;
+			MemoryContext cluster_context;
+
+			/* Check index directly since cluster_rel isn't called for partitioned table */
+			check_index_is_clusterable(rel, indexOid, true, AccessExclusiveLock);
+
+			/* 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, isTopLevel, stmt->options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			rel = table_open(tableOid, ShareUpdateExclusiveLock);
+			mark_index_clustered(rel, indexOid, true);
+			table_close(rel, NoLock);
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -183,7 +210,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -207,26 +233,7 @@ 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,
-						isTopLevel);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, isTopLevel, stmt->options);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -487,12 +494,6 @@ 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.
 	 */
@@ -1563,3 +1564,71 @@ 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 = MemoryContextSwitchTo(cluster_context);
+	inhoids = find_all_inheritors(indexOid, NoLock, NULL);
+	MemoryContextSwitchTo(old_context);
+
+	foreach(lc, inhoids)
+	{
+		Oid		indexrelid = lfirst_oid(lc);
+		Oid		relid = IndexGetRelation(indexrelid, false);
+		RelToCluster	*rvtc;
+
+		/*
+		 * We have a full list of direct and indirect children, so skip
+		 * partitioned tables and just handle their children.
+		 */
+		if (get_rel_relkind(relid) == RELKIND_PARTITIONED_TABLE)
+			continue;
+
+		rvtc = (RelToCluster *) palloc(sizeof(RelToCluster));
+		rvtc->tableOid = relid;
+		rvtc->indexOid = indexrelid;
+		rvs = lappend(rvs, rvtc);
+	}
+
+	return rvs;
+}
+
+/* Cluster each relation in a separate transaction */
+static void
+cluster_multiple_rels(List *rvs, bool isTopLevel, 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,
+					isTopLevel);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index f41785f11c..49a2648991 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -587,6 +587,7 @@ 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/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out
index bdae8fe00c..e14e691b05 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,13 +439,30 @@ 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;
 CREATE INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
-ERROR:  cannot mark index clustered in partitioned table
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
-ERROR:  cannot cluster a partitioned table
+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.)
+
 DROP TABLE clstrpart;
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index 188183647c..4bed6afbac 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,11 +196,21 @@ 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;
 CREATE INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
 CLUSTER clstrpart USING clstrpart_idx;
+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
 DROP TABLE clstrpart;
 
 -- Test CLUSTER with external tuplesorting
-- 
2.17.0


--MAH+hnPXVZWQ5cD/
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v7-0003-WIP-implement-DROP-INDEX-CONCURRENTLY-on-partitio.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v8 2/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 230 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/nodes/parsenodes.h        |   5 +-
 src/test/regress/expected/cluster.out |  70 +++++++-
 src/test/regress/sql/cluster.sql      |  27 ++-
 6 files changed, 268 insertions(+), 71 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 4da60d8d56..2df8aaabc4 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 0d647e912c..d2e3ebc8af 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"
@@ -74,7 +76,11 @@ static void copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex,
 							bool *pSwapToastByContent,
 							TransactionId *pFreezeXid,
 							MultiXactId *pCutoffMulti);
+static void set_indisclustered(Oid indexOid, bool isclustered, Relation pg_index);
 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, bool isTopLevel, int options);
 
 
 /*---------------------------------------------------------------------------
@@ -116,7 +122,7 @@ 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
@@ -127,14 +133,6 @@ 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;
@@ -172,8 +170,32 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		}
+		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, isTopLevel, stmt->options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -183,7 +205,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -207,26 +228,7 @@ 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,
-						isTopLevel);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, isTopLevel, stmt->options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -332,9 +334,10 @@ cluster_rel(Oid tableOid, Oid indexOid, int options, bool isTopLevel)
 			}
 
 			/*
-			 * 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();
@@ -378,8 +381,13 @@ cluster_rel(Oid tableOid, Oid indexOid, int options, bool isTopLevel)
 
 	/* 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
@@ -395,6 +403,14 @@ cluster_rel(Oid tableOid, Oid indexOid, int options, bool isTopLevel)
 		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
@@ -463,6 +479,9 @@ 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,
@@ -474,6 +493,32 @@ check_index_is_clusterable(Relation OldHeap, Oid indexOid, bool recheck, LOCKMOD
 	index_close(OldIndex, NoLock);
 }
 
+/*
+ * Helper for mark_index_clustered
+ * Mark a single index as clustered or not.
+ * pg_index is passed by caller to avoid repeatedly re-opening it.
+ */
+static void
+set_indisclustered(Oid indexOid, bool isclustered, Relation pg_index)
+{
+	HeapTuple	indexTuple;
+	Form_pg_index indexForm;
+
+	indexTuple = SearchSysCacheCopy1(INDEXRELID,
+									ObjectIdGetDatum(indexOid));
+	if (!HeapTupleIsValid(indexTuple))
+		elog(ERROR, "cache lookup failed for index %u", indexOid);
+	indexForm = (Form_pg_index) GETSTRUCT(indexTuple);
+
+	/* this was checked earlier, but let's be real sure */
+	if (isclustered && !indexForm->indisvalid)
+		elog(ERROR, "cannot cluster on invalid index %u", indexOid);
+
+	indexForm->indisclustered = isclustered;
+	CatalogTupleUpdate(pg_index, &indexTuple->t_self, indexTuple);
+	heap_freetuple(indexTuple);
+}
+
 /*
  * mark_index_clustered: mark the specified index as the one clustered on
  *
@@ -482,17 +527,9 @@ check_index_is_clusterable(Relation OldHeap, Oid indexOid, bool recheck, LOCKMOD
 void
 mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
 {
-	HeapTuple	indexTuple;
-	Form_pg_index indexForm;
 	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.
 	 */
@@ -511,34 +548,32 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal)
 	{
 		Oid			thisIndexOid = lfirst_oid(index);
 
-		indexTuple = SearchSysCacheCopy1(INDEXRELID,
-										 ObjectIdGetDatum(thisIndexOid));
-		if (!HeapTupleIsValid(indexTuple))
-			elog(ERROR, "cache lookup failed for index %u", thisIndexOid);
-		indexForm = (Form_pg_index) GETSTRUCT(indexTuple);
-
 		/*
 		 * Unset the bit if set.  We know it's wrong because we checked this
 		 * earlier.
 		 */
-		if (indexForm->indisclustered)
+		if (thisIndexOid != indexOid)
 		{
-			indexForm->indisclustered = false;
-			CatalogTupleUpdate(pg_index, &indexTuple->t_self, indexTuple);
+			Oid parentind = thisIndexOid;
+			set_indisclustered(thisIndexOid, false, pg_index);
+
+			/*
+			 * When setting a given index as clustered, also remove
+			 * indisclustered from all parents of other partitioned indexes
+			 */
+			while (get_rel_relispartition(parentind))
+			{
+				parentind = get_partition_parent(parentind);
+				set_indisclustered(parentind, false, pg_index);
+			}
 		}
-		else if (thisIndexOid == indexOid)
+		else
 		{
-			/* this was checked earlier, but let's be real sure */
-			if (!indexForm->indisvalid)
-				elog(ERROR, "cannot cluster on invalid index %u", indexOid);
-			indexForm->indisclustered = true;
-			CatalogTupleUpdate(pg_index, &indexTuple->t_self, indexTuple);
+			set_indisclustered(thisIndexOid, true, pg_index);
 		}
 
 		InvokeObjectPostAlterHookArg(IndexRelationId, thisIndexOid, 0,
 									 InvalidOid, is_internal);
-
-		heap_freetuple(indexTuple);
 	}
 
 	table_close(pg_index, RowExclusiveLock);
@@ -565,10 +600,6 @@ rebuild_relation(Relation OldHeap, Oid indexOid, bool isTopLevel, 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);
@@ -1563,3 +1594,76 @@ 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, bool isTopLevel, 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,
+					isTopLevel);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 9c6f5ecb6a..ad0cd2ec92 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -587,6 +587,7 @@ 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 60c2f45466..d428a94454 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3202,8 +3202,9 @@ 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..60d2a36255 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,13 +439,75 @@ 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
+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.)
+
+-- Check that the parent index is marked not clustered after clustering a partition on a different index:
+CREATE INDEX clstrpart1_idx_2 ON clstrpart1(a);
+CLUSTER clstrpart1 USING clstrpart1_idx_2;
+\d clstrpart
+       Partitioned table "public.clstrpart"
+ Column |  Type   | Collation | Nullable | Default 
+--------+---------+-----------+----------+---------
+ a      | integer |           |          | 
+Partition key: RANGE (a)
+Indexes:
+    "clstrpart_idx" btree (a)
+Number of partitions: 3 (Use \d+ to list them.)
+
 DROP TABLE clstrpart;
 -- Test CLUSTER with external tuplesorting
 create table clstr_4 as select * from tenk1;
diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql
index 188183647c..93e9c8c6ee 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,11 +196,34 @@ 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;
+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
+-- Check that the parent index is marked not clustered after clustering a partition on a different index:
+CREATE INDEX clstrpart1_idx_2 ON clstrpart1(a);
+CLUSTER clstrpart1 USING clstrpart1_idx_2;
+\d clstrpart
 DROP TABLE clstrpart;
 
 -- Test CLUSTER with external tuplesorting
-- 
2.17.0


--FCuugMFkClbJLl1L
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v8-0003-WIP-implement-DROP-INDEX-CONCURRENTLY-on-partitio.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v1 1/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

This requires either specification of a partitioned index on which to cluster,
or that an partitioned index was previously set clustered.

TODO: handle DB-WIDE "CLUSTER;" for partitioned tables
new partitions need to inherit indisclustered ?
---
 doc/src/sgml/ref/cluster.sgml         |   6 +
 src/backend/commands/cluster.c        | 169 +++++++++++++++++++-------
 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, 209 insertions(+), 54 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 0d647e912c..1db8382a27 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"
@@ -75,6 +77,9 @@ static void copy_table_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex,
 							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, bool isTopLevel, int options);
 
 
 /*---------------------------------------------------------------------------
@@ -116,7 +121,7 @@ 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
@@ -127,14 +132,6 @@ 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;
@@ -172,8 +169,32 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, stmt->options, isTopLevel);
+		}
+		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, isTopLevel, stmt->options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -183,7 +204,6 @@ cluster(ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -207,26 +227,7 @@ 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,
-						isTopLevel);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, isTopLevel, stmt->options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -332,9 +333,10 @@ cluster_rel(Oid tableOid, Oid indexOid, int options, bool isTopLevel)
 			}
 
 			/*
-			 * 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();
@@ -378,8 +380,13 @@ cluster_rel(Oid tableOid, Oid indexOid, int options, bool isTopLevel)
 
 	/* 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
@@ -395,6 +402,14 @@ cluster_rel(Oid tableOid, Oid indexOid, int options, bool isTopLevel)
 		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
@@ -463,6 +478,9 @@ 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,
@@ -487,12 +505,6 @@ 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.
 	 */
@@ -565,10 +577,6 @@ rebuild_relation(Relation OldHeap, Oid indexOid, bool isTopLevel, 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);
@@ -1563,3 +1571,76 @@ 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, bool isTopLevel, 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,
+					isTopLevel);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index b2b4f1fd4d..c3f080e691 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -587,6 +587,7 @@ 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 60c2f45466..d428a94454 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3202,8 +3202,9 @@ 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


--8Tx+BDMK09J610+l
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v1-0002-preserve-indisclustered-on-children-of-clustered-.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v3 1/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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


--EDJsL2R9iCFAt7IV
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v3-0002-preserve-indisclustered-on-children-of-clustered-.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v4 1/5] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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 53de31f3b1..087b1c7af6 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -3199,8 +3199,9 @@ 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


--Sr1nOIr3CvdE5hEN
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v4-0002-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v5 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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 8afc780acc..1deafd2707 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 d1f9ef29ca..43b6d16a13 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


--/i8j2F0k9BYX4qLc
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v5-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread

* [PATCH v6 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58  Justin Pryzby <[email protected]>
  0 siblings, 0 replies; 148+ messages in thread

From: Justin Pryzby @ 2020-06-07 21:58 UTC (permalink / raw)

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        | 172 +++++++++++++++++++-------
 src/bin/psql/tab-complete.c           |   1 +
 src/include/commands/cluster.h        |   1 +
 src/test/regress/expected/cluster.out |  58 ++++++++-
 src/test/regress/sql/cluster.sql      |  24 +++-
 6 files changed, 208 insertions(+), 54 deletions(-)

diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml
index 5dd21a0189..fb5deddb35 100644
--- a/doc/src/sgml/ref/cluster.sgml
+++ b/doc/src/sgml/ref/cluster.sgml
@@ -192,6 +192,12 @@ 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 096a06f7b3..838bcd9e72 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/defrem.h"
@@ -73,6 +75,9 @@ 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);
 
 
 /*---------------------------------------------------------------------------
@@ -135,7 +140,7 @@ cluster(ParseState *pstate, 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
@@ -146,14 +151,6 @@ cluster(ParseState *pstate, 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;
@@ -191,8 +188,32 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		/* close relation, keep lock till commit */
 		table_close(rel, NoLock);
 
-		/* Do the job. */
-		cluster_rel(tableOid, indexOid, &params);
+		if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		{
+			/* Do the job. */
+			cluster_rel(tableOid, indexOid, &params);
+		}
+		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, params.options);
+
+			/* Start a new transaction for the cleanup work. */
+			StartTransactionCommand();
+
+			/* Clean up working storage */
+			MemoryContextDelete(cluster_context);
+		}
 	}
 	else
 	{
@@ -202,7 +223,6 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 */
 		MemoryContext cluster_context;
 		List	   *rvs;
-		ListCell   *rv;
 
 		/*
 		 * We cannot run this form of CLUSTER inside a user transaction block;
@@ -225,28 +245,7 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel)
 		 * cluster_context.
 		 */
 		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);
-			ClusterParams cluster_params = params;
-
-			/* Start a new transaction for each relation. */
-			StartTransactionCommand();
-			/* functions in indexes may want a snapshot set */
-			PushActiveSnapshot(GetTransactionSnapshot());
-			/* Do the job. */
-			cluster_params.options |= CLUOPT_RECHECK;
-			cluster_rel(rvtc->tableOid, rvtc->indexOid,
-						&cluster_params);
-			PopActiveSnapshot();
-			CommitTransactionCommand();
-		}
+		cluster_multiple_rels(rvs, params.options | CLUOPT_RECHECK_ISCLUSTERED);
 
 		/* Start a new transaction for the cleanup work. */
 		StartTransactionCommand();
@@ -352,9 +351,10 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 			}
 
 			/*
-			 * 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 ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 &&
+					!get_index_isclustered(indexOid))
 			{
 				relation_close(OldHeap, AccessExclusiveLock);
 				pgstat_progress_end_command();
@@ -398,8 +398,13 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 
 	/* 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
@@ -415,6 +420,14 @@ cluster_rel(Oid tableOid, Oid indexOid, ClusterParams *params)
 		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
@@ -483,6 +496,9 @@ 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,
@@ -507,12 +523,6 @@ 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.
 	 */
@@ -584,10 +594,6 @@ 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);
@@ -1582,3 +1588,77 @@ 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);
+		ClusterParams cluster_params = { .options = options, };
+
+		/* Start a new transaction for each relation. */
+		StartTransactionCommand();
+
+		/* functions in indexes may want a snapshot set */
+		PushActiveSnapshot(GetTransactionSnapshot());
+
+		/* Do the job. */
+		cluster_params.options |= CLUOPT_RECHECK;
+		cluster_rel(rvtc->tableOid, rvtc->indexOid,
+					&cluster_params);
+
+		PopActiveSnapshot();
+		CommitTransactionCommand();
+	}
+}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 6abcbea963..3a6a4831e1 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/commands/cluster.h b/src/include/commands/cluster.h
index a941f2accd..c30ca01726 100644
--- a/src/include/commands/cluster.h
+++ b/src/include/commands/cluster.h
@@ -22,6 +22,7 @@
 /* flag bits for ClusterParams->flags */
 #define CLUOPT_RECHECK 0x01		/* recheck relation state */
 #define CLUOPT_VERBOSE 0x02		/* print progress info */
+#define CLUOPT_RECHECK_ISCLUSTERED 0x04	/* recheck relation state for indisclustered */
 
 /* options for CLUSTER */
 typedef struct ClusterParams
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


--FsscpQKzF/jJk6ya
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="v6-0003-Propagate-changes-to-indisclustered-to-child-pare.patch"



^ permalink  raw  reply  [nested|flat] 148+ messages in thread