public inbox for [email protected]
help / color / mirror / Atom feed[PATCH v9 2/8] Implement CLUSTER of partitioned table..
149+ messages / 6 participants
[nested] [flat]
* [PATCH v7 2/7] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ messages in thread
* [PATCH v2 2/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 149+ 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 | 16 ++-
src/test/regress/sql/cluster.sql | 5 +-
4 files changed, 119 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 eb018854a5..d6a7ef2c30 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -578,6 +578,7 @@ static const SchemaQuery Query_for_list_of_vacuumables = {
.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..161c09ee42 100644
--- a/src/test/regress/expected/cluster.out
+++ b/src/test/regress/expected/cluster.out
@@ -439,13 +439,21 @@ 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 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
+\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: 0
+
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..db3c271706 100644
--- a/src/test/regress/sql/cluster.sql
+++ b/src/test/regress/sql/cluster.sql
@@ -196,11 +196,12 @@ 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 INDEX clstrpart_idx ON clstrpart (a);
-ALTER TABLE clstrpart CLUSTER ON clstrpart_idx;
+ALTER TABLE clstrpart SET WITHOUT CLUSTER;
CLUSTER clstrpart USING clstrpart_idx;
+\d clstrpart
DROP TABLE clstrpart;
-- Test CLUSTER with external tuplesorting
--
2.17.0
--JwB53PgKC5A7+0Ej
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="v2-0003-Implement-REINDEX-of-partitioned-tables-indexes.patch"
^ permalink raw reply [nested|flat] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ messages in thread
* [PATCH v11] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 149+ 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, ¶ms);
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ messages in thread
* [PATCH v3 3/3] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 149+ 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 eb018854a5..d6a7ef2c30 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -578,6 +578,7 @@ static const SchemaQuery Query_for_list_of_vacuumables = {
.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
--SCOJXUq1iwCn05li--
^ permalink raw reply [nested|flat] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ messages in thread
* [PATCH v11] Implement CLUSTER of partitioned table..
@ 2020-06-07 21:58 Justin Pryzby <[email protected]>
0 siblings, 0 replies; 149+ 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, ¶ms);
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ 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; 149+ 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, ¶ms);
+ if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+ {
+ /* Do the job. */
+ cluster_rel(tableOid, indexOid, ¶ms);
+ }
+ 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] 149+ messages in thread
* Re: Relation bulk write facility
@ 2023-11-24 23:19 Heikki Linnakangas <[email protected]>
2023-12-14 13:02 ` Re: Relation bulk write facility Heikki Linnakangas <[email protected]>
2024-01-09 06:50 ` Re: Relation bulk write facility vignesh C <[email protected]>
0 siblings, 2 replies; 149+ messages in thread
From: Heikki Linnakangas @ 2023-11-24 23:19 UTC (permalink / raw)
To: Andres Freund <[email protected]>; +Cc: pgsql-hackers
On 19/11/2023 02:04, Andres Freund wrote:
> On 2023-11-17 11:37:21 +0100, Heikki Linnakangas wrote:
>> The new facility makes it easier to optimize bulk loading, as the
>> logic for buffering, WAL-logging, and syncing the relation only needs
>> to be implemented once. It's also less error-prone: We have had a
>> number of bugs in how a relation is fsync'd - or not - at the end of a
>> bulk loading operation. By centralizing that logic to one place, we
>> only need to write it correctly once.
>
> One thing I'd like to use the centralized handling for is to track such
> writes in pg_stat_io. I don't mean as part of the initial patch, just that
> that's another reason I like the facility.
Oh I didn't realize they're not counted at the moment.
>> + bulkw = bulkw_start_smgr(dst, forkNum, use_wal);
>> +
>> nblocks = smgrnblocks(src, forkNum);
>>
>> for (blkno = 0; blkno < nblocks; blkno++)
>> {
>> + Page page;
>> +
>> /* If we got a cancel signal during the copy of the data, quit */
>> CHECK_FOR_INTERRUPTS();
>>
>> - smgrread(src, forkNum, blkno, buf.data);
>> + page = bulkw_alloc_buf(bulkw);
>> + smgrread(src, forkNum, blkno, page);
>>
>> if (!PageIsVerifiedExtended(page, blkno,
>> PIV_LOG_WARNING | PIV_REPORT_STAT))
>> @@ -511,30 +514,9 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
>> * page this is, so we have to log the full page including any unused
>> * space.
>> */
>> - if (use_wal)
>> - log_newpage(&dst->smgr_rlocator.locator, forkNum, blkno, page, false);
>> -
>> - PageSetChecksumInplace(page, blkno);
>> -
>> - /*
>> - * Now write the page. We say skipFsync = true because there's no
>> - * need for smgr to schedule an fsync for this write; we'll do it
>> - * ourselves below.
>> - */
>> - smgrextend(dst, forkNum, blkno, buf.data, true);
>> + bulkw_write(bulkw, blkno, page, false);
>
> I wonder if bulkw_alloc_buf() is a good name - if you naively read this
> change, it looks like it'll just leak memory. It also might be taken to be
> valid until freed, which I don't think is the case?
Yeah, I'm not very happy with this interface. The model is that you get
a buffer to write to by calling bulkw_alloc_buf(). Later, you hand it
over to bulkw_write(), which takes ownership of it and frees it later.
There is no other function to free it, although currently the buffer is
just palloc'd so you could call pfree on it.
However, I'd like to not expose that detail to the callers. I'm
imagining that in the future we might optimize further, by having a
larger e.g. 1 MB buffer, and carve the 8kB blocks from that. Then
opportunistically, if you fill the buffers sequentially, bulk_write.c
could do one smgrextend() to write the whole 1 MB chunk.
I renamed it to bulkw_get_buf() now, and made it return a new
BulkWriteBuffer typedef instead of a plain Page. The point of the new
typedef is to distinguish a buffer returned by bulkw_get_buf() from a
Page or char[BLCKSZ] that you might palloc on your own. That indeed
revealed some latent bugs in gistbuild.c where I had mixed up buffers
returned by bulkw_alloc_buf() and palloc'd buffers.
(The previous version of this patch called a different struct
BulkWriteBuffer, but I renamed that to PendingWrite; see below. Don't be
confused!)
I think this helps a little, but I'm still not very happy with it. I'll
give it some more thought after sleeping over it, but in the meanwhile,
I'm all ears for suggestions.
>> +/*-------------------------------------------------------------------------
>> + *
>> + * bulk_write.c
>> + * Efficiently and reliably populate a new relation
>> + *
>> + * The assumption is that no other backends access the relation while we are
>> + * loading it, so we can take some shortcuts. Alternatively, you can use the
>> + * buffer manager as usual, if performance is not critical, but you must not
>> + * mix operations through the buffer manager and the bulk loading interface at
>> + * the same time.
>
> From "Alternatively" onward this is is somewhat confusing.
Rewrote that to just "Do not mix operations through the regular buffer
manager and the bulk loading interface!"
>> + * One tricky point is that because we bypass the buffer manager, we need to
>> + * register the relation for fsyncing at the next checkpoint ourselves, and
>> + * make sure that the relation is correctly fsync by us or the checkpointer
>> + * even if a checkpoint happens concurrently.
>
> "fsync'ed" or such? Otherwise this reads awkwardly for me.
Yep, fixed.
>> +typedef struct BulkWriteBuffer
>> +{
>> + Page page;
>> + BlockNumber blkno;
>> + bool page_std;
>> + int16 order;
>> +} BulkWriteBuffer;
>> +
>
> The name makes it sound like this struct itself contains a buffer - but it's
> just pointing to one. *BufferRef or such maybe?
>
> I was wondering how you dealt with the alignment of buffers given the struct
> definition, which is what lead me to look at this...
I renamed this to PendingWrite, and the field that holds these
"pending_writes". Think of it as a queue of writes that haven't been
performed yet.
>> +/*
>> + * Bulk writer state for one relation fork.
>> + */
>> +typedef struct BulkWriteState
>> +{
>> + /* Information about the target relation we're writing */
>> + SMgrRelation smgr;
>
> Isn't there a danger of this becoming a dangling pointer? At least until
> https://postgr.es/m/CA%2BhUKGJ8NTvqLHz6dqbQnt2c8XCki4r2QvXjBQcXpVwxTY_pvA%40mail.gmail.com
> is merged?
Good point. I just added a FIXME comment to remind about that, hoping
that that patch gets merged soon. If not, I'll come up with a different fix.
>> + ForkNumber forknum;
>> + bool use_wal;
>> +
>> + /* We keep several pages buffered, and WAL-log them in batches */
>> + int nbuffered;
>> + BulkWriteBuffer buffers[MAX_BUFFERED_PAGES];
>> +
>> + /* Current size of the relation */
>> + BlockNumber pages_written;
>> +
>> + /* The RedoRecPtr at the time that the bulk operation started */
>> + XLogRecPtr start_RedoRecPtr;
>> +
>> + Page zeropage; /* workspace for filling zeroes */
>
> We really should just have one such page in shared memory somewhere... For WAL
> writes as well.
>
> But until then - why do you allocate the page? Seems like we could just use a
> static global variable?
I made it a static global variable for now. (The palloc way was copied
over from nbtsort.c)
>> +/*
>> + * Write all buffered pages to disk.
>> + */
>> +static void
>> +bulkw_flush(BulkWriteState *bulkw)
>> +{
>> + int nbuffered = bulkw->nbuffered;
>> + BulkWriteBuffer *buffers = bulkw->buffers;
>> +
>> + if (nbuffered == 0)
>> + return;
>> +
>> + if (nbuffered > 1)
>> + {
>> + int o;
>> +
>> + qsort(buffers, nbuffered, sizeof(BulkWriteBuffer), buffer_cmp);
>> +
>> + /*
>> + * Eliminate duplicates, keeping the last write of each block.
>> + * (buffer_cmp uses 'order' as the last sort key)
>> + */
>
> Huh - which use cases would actually cause duplicate writes?
Hmm, nothing anymore I guess. Many AMs used to write zero pages as a
placeholder and come back to fill them in later, but now that
bulk_write.c handles that,
Removed that, and replaced it with with an assertion in buffer_cmp()
that there are no duplicates.
--
Heikki Linnakangas
Neon (https://neon.tech)
Attachments:
[text/x-patch] v3-0001-Introduce-a-new-bulk-loading-facility.patch (53.2K, ../../[email protected]/2-v3-0001-Introduce-a-new-bulk-loading-facility.patch)
download | inline diff:
From 50b19da1a6d4c96084fc8388e64c1c646e9b5378 Mon Sep 17 00:00:00 2001
From: Heikki Linnakangas <[email protected]>
Date: Tue, 19 Sep 2023 18:09:34 +0300
Subject: [PATCH v3 1/1] Introduce a new bulk loading facility.
The new facility makes it easier to optimize bulk loading, as the
logic for buffering, WAL-logging, and syncing the relation only needs
to be implemented once. It's also less error-prone: We have had a
number of bugs in how a relation is fsync'd - or not - at the end of a
bulk loading operation. By centralizing that logic to one place, we
only need to write it correctly once.
The new facility is faster for small relations: Instead of of calling
smgrimmedsync(), we register the fsync to happen at next checkpoint,
which avoids the fsync latency. That can make a big difference if you
are e.g. restoring a schema-only dump with lots of relations.
It is also slightly more efficient with large relations, as the WAL
logging is performed multiple pages at a time. That avoids some WAL
header overhead. The sorted GiST index build did that already, this
moves the buffering to the new facility.
The changes to pageinspect GiST test needs an explanation: Before this
patch, the sorted GiST index build set the LSN on every page to the
special GistBuildLSN value, not the LSN of the WAL record, even though
they were WAL-logged. There was no particular need for it, it just
happened naturally when we wrote out the pages before WAL-logging
them. Now we WAL-log the pages first, like in B-tree build, so the
pages are stamped with the record's real LSN. When the build is not
WAL-logged, we still use GistBuildLSN. To make the test output
predictable, use an unlogged index.
Reviewed-by: Andres Freund
Discussion: https://www.postgresql.org/message-id/30e8f366-58b3-b239-c521-422122dd5150%40iki.fi
---
contrib/pageinspect/expected/gist.out | 14 +-
contrib/pageinspect/sql/gist.sql | 16 +-
src/backend/access/gist/gistbuild.c | 122 +++--------
src/backend/access/heap/rewriteheap.c | 75 ++-----
src/backend/access/nbtree/nbtree.c | 33 +--
src/backend/access/nbtree/nbtsort.c | 134 ++++--------
src/backend/access/spgist/spginsert.c | 49 ++---
src/backend/catalog/storage.c | 46 ++--
src/backend/storage/smgr/Makefile | 1 +
src/backend/storage/smgr/bulk_write.c | 301 ++++++++++++++++++++++++++
src/backend/storage/smgr/md.c | 43 ++++
src/backend/storage/smgr/meson.build | 1 +
src/backend/storage/smgr/smgr.c | 31 +++
src/include/storage/bulk_write.h | 38 ++++
src/include/storage/md.h | 1 +
src/include/storage/smgr.h | 1 +
src/tools/pgindent/typedefs.list | 3 +
17 files changed, 556 insertions(+), 353 deletions(-)
create mode 100644 src/backend/storage/smgr/bulk_write.c
create mode 100644 src/include/storage/bulk_write.h
diff --git a/contrib/pageinspect/expected/gist.out b/contrib/pageinspect/expected/gist.out
index d1adbab8ae2..2b1d54a6279 100644
--- a/contrib/pageinspect/expected/gist.out
+++ b/contrib/pageinspect/expected/gist.out
@@ -1,13 +1,6 @@
--- The gist_page_opaque_info() function prints the page's LSN. Normally,
--- that's constant 1 (GistBuildLSN) on every page of a freshly built GiST
--- index. But with wal_level=minimal, the whole relation is dumped to WAL at
--- the end of the transaction if it's smaller than wal_skip_threshold, which
--- updates the LSNs. Wrap the tests on gist_page_opaque_info() in the
--- same transaction with the CREATE INDEX so that we see the LSNs before
--- they are possibly overwritten at end of transaction.
-BEGIN;
--- Create a test table and GiST index.
-CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
+-- The gist_page_opaque_info() function prints the page's LSN.
+-- Use an unlogged index, so that the LSN is predictable.
+CREATE UNLOGGED TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
generate_series(1,1000) i;
CREATE INDEX test_gist_idx ON test_gist USING gist (p);
-- Page 0 is the root, the rest are leaf pages
@@ -29,7 +22,6 @@ SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
0/1 | 0/0 | 1 | {leaf}
(1 row)
-COMMIT;
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');
itemoffset | ctid | itemlen | dead | keys
------------+-----------+---------+------+-------------------------------
diff --git a/contrib/pageinspect/sql/gist.sql b/contrib/pageinspect/sql/gist.sql
index d263542ba15..85bc44b8000 100644
--- a/contrib/pageinspect/sql/gist.sql
+++ b/contrib/pageinspect/sql/gist.sql
@@ -1,14 +1,6 @@
--- The gist_page_opaque_info() function prints the page's LSN. Normally,
--- that's constant 1 (GistBuildLSN) on every page of a freshly built GiST
--- index. But with wal_level=minimal, the whole relation is dumped to WAL at
--- the end of the transaction if it's smaller than wal_skip_threshold, which
--- updates the LSNs. Wrap the tests on gist_page_opaque_info() in the
--- same transaction with the CREATE INDEX so that we see the LSNs before
--- they are possibly overwritten at end of transaction.
-BEGIN;
-
--- Create a test table and GiST index.
-CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
+-- The gist_page_opaque_info() function prints the page's LSN.
+-- Use an unlogged index, so that the LSN is predictable.
+CREATE UNLOGGED TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
generate_series(1,1000) i;
CREATE INDEX test_gist_idx ON test_gist USING gist (p);
@@ -17,8 +9,6 @@ SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0));
SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1));
SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
-COMMIT;
-
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 1), 'test_gist_idx') LIMIT 5;
diff --git a/src/backend/access/gist/gistbuild.c b/src/backend/access/gist/gistbuild.c
index a45e2fe3755..5b7cefdcaaf 100644
--- a/src/backend/access/gist/gistbuild.c
+++ b/src/backend/access/gist/gistbuild.c
@@ -43,7 +43,8 @@
#include "miscadmin.h"
#include "optimizer/optimizer.h"
#include "storage/bufmgr.h"
-#include "storage/smgr.h"
+#include "storage/bulk_write.h"
+
#include "utils/memutils.h"
#include "utils/rel.h"
#include "utils/tuplesort.h"
@@ -106,11 +107,8 @@ typedef struct
Tuplesortstate *sortstate; /* state data for tuplesort.c */
BlockNumber pages_allocated;
- BlockNumber pages_written;
- int ready_num_pages;
- BlockNumber ready_blknos[XLR_MAX_BLOCK_ID];
- Page ready_pages[XLR_MAX_BLOCK_ID];
+ BulkWriteState *bulkw;
} GISTBuildState;
#define GIST_SORTED_BUILD_PAGE_NUM 4
@@ -142,7 +140,6 @@ static void gist_indexsortbuild_levelstate_add(GISTBuildState *state,
IndexTuple itup);
static void gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
GistSortedBuildLevelState *levelstate);
-static void gist_indexsortbuild_flush_ready_pages(GISTBuildState *state);
static void gistInitBuffering(GISTBuildState *buildstate);
static int calculatePagesPerBuffer(GISTBuildState *buildstate, int levelStep);
@@ -405,27 +402,18 @@ gist_indexsortbuild(GISTBuildState *state)
{
IndexTuple itup;
GistSortedBuildLevelState *levelstate;
- Page page;
+ BulkWriteBuffer rootbuf;
- state->pages_allocated = 0;
- state->pages_written = 0;
- state->ready_num_pages = 0;
+ /* Reserve block 0 for the root page */
+ state->pages_allocated = 1;
- /*
- * Write an empty page as a placeholder for the root page. It will be
- * replaced with the real root page at the end.
- */
- page = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, MCXT_ALLOC_ZERO);
- smgrextend(RelationGetSmgr(state->indexrel), MAIN_FORKNUM, GIST_ROOT_BLKNO,
- page, true);
- state->pages_allocated++;
- state->pages_written++;
+ state->bulkw = bulkw_start_rel(state->indexrel, MAIN_FORKNUM);
/* Allocate a temporary buffer for the first leaf page batch. */
levelstate = palloc0(sizeof(GistSortedBuildLevelState));
- levelstate->pages[0] = page;
+ levelstate->pages[0] = palloc(BLCKSZ);
levelstate->parent = NULL;
- gistinitpage(page, F_LEAF);
+ gistinitpage(levelstate->pages[0], F_LEAF);
/*
* Fill index pages with tuples in the sorted order.
@@ -455,31 +443,16 @@ gist_indexsortbuild(GISTBuildState *state)
levelstate = parent;
}
- gist_indexsortbuild_flush_ready_pages(state);
-
/* Write out the root */
PageSetLSN(levelstate->pages[0], GistBuildLSN);
- PageSetChecksumInplace(levelstate->pages[0], GIST_ROOT_BLKNO);
- smgrwrite(RelationGetSmgr(state->indexrel), MAIN_FORKNUM, GIST_ROOT_BLKNO,
- levelstate->pages[0], true);
- if (RelationNeedsWAL(state->indexrel))
- log_newpage(&state->indexrel->rd_locator, MAIN_FORKNUM, GIST_ROOT_BLKNO,
- levelstate->pages[0], true);
-
- pfree(levelstate->pages[0]);
+
+ rootbuf = bulkw_get_buf(state->bulkw);
+ memcpy(rootbuf, levelstate->pages[0], BLCKSZ);
+ bulkw_write(state->bulkw, GIST_ROOT_BLKNO, rootbuf, true);
+
pfree(levelstate);
- /*
- * When we WAL-logged index pages, we must nonetheless fsync index files.
- * Since we're building outside shared buffers, a CHECKPOINT occurring
- * during the build has no way to flush the previously written data to
- * disk (indeed it won't know the index even exists). A crash later on
- * would replay WAL from the checkpoint, therefore it wouldn't replay our
- * earlier WAL entries. If we do not fsync those pages here, they might
- * still not be on disk when the crash occurs.
- */
- if (RelationNeedsWAL(state->indexrel))
- smgrimmedsync(RelationGetSmgr(state->indexrel), MAIN_FORKNUM);
+ bulkw_finish(state->bulkw);
}
/*
@@ -509,8 +482,7 @@ gist_indexsortbuild_levelstate_add(GISTBuildState *state,
levelstate->current_page++;
if (levelstate->pages[levelstate->current_page] == NULL)
- levelstate->pages[levelstate->current_page] =
- palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
+ levelstate->pages[levelstate->current_page] = palloc0(BLCKSZ);
newPage = levelstate->pages[levelstate->current_page];
gistinitpage(newPage, old_page_flags);
@@ -573,6 +545,7 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
for (; dist != NULL; dist = dist->next)
{
char *data;
+ BulkWriteBuffer buf;
Page target;
/* check once per page */
@@ -580,7 +553,8 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
/* Create page and copy data */
data = (char *) (dist->list);
- target = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, MCXT_ALLOC_ZERO);
+ buf = bulkw_get_buf(state->bulkw);
+ target = (Page) buf;
gistinitpage(target, isleaf ? F_LEAF : 0);
for (int i = 0; i < dist->block.num; i++)
{
@@ -593,20 +567,6 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
}
union_tuple = dist->itup;
- if (state->ready_num_pages == XLR_MAX_BLOCK_ID)
- gist_indexsortbuild_flush_ready_pages(state);
-
- /*
- * The page is now complete. Assign a block number to it, and add it
- * to the list of finished pages. (We don't write it out immediately,
- * because we want to WAL-log the pages in batches.)
- */
- blkno = state->pages_allocated++;
- state->ready_blknos[state->ready_num_pages] = blkno;
- state->ready_pages[state->ready_num_pages] = target;
- state->ready_num_pages++;
- ItemPointerSetBlockNumber(&(union_tuple->t_tid), blkno);
-
/*
* Set the right link to point to the previous page. This is just for
* debugging purposes: GiST only follows the right link if a page is
@@ -621,6 +581,15 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
*/
if (levelstate->last_blkno)
GistPageGetOpaque(target)->rightlink = levelstate->last_blkno;
+
+ /*
+ * The page is now complete. Assign a block number to it, and pass it
+ * to the bulk writer.
+ */
+ blkno = state->pages_allocated++;
+ PageSetLSN(target, GistBuildLSN);
+ bulkw_write(state->bulkw, blkno, buf, true);
+ ItemPointerSetBlockNumber(&(union_tuple->t_tid), blkno);
levelstate->last_blkno = blkno;
/*
@@ -631,7 +600,7 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
if (parent == NULL)
{
parent = palloc0(sizeof(GistSortedBuildLevelState));
- parent->pages[0] = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
+ parent->pages[0] = palloc(BLCKSZ);
parent->parent = NULL;
gistinitpage(parent->pages[0], 0);
@@ -641,39 +610,6 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
}
}
-static void
-gist_indexsortbuild_flush_ready_pages(GISTBuildState *state)
-{
- if (state->ready_num_pages == 0)
- return;
-
- for (int i = 0; i < state->ready_num_pages; i++)
- {
- Page page = state->ready_pages[i];
- BlockNumber blkno = state->ready_blknos[i];
-
- /* Currently, the blocks must be buffered in order. */
- if (blkno != state->pages_written)
- elog(ERROR, "unexpected block number to flush GiST sorting build");
-
- PageSetLSN(page, GistBuildLSN);
- PageSetChecksumInplace(page, blkno);
- smgrextend(RelationGetSmgr(state->indexrel), MAIN_FORKNUM, blkno, page,
- true);
-
- state->pages_written++;
- }
-
- if (RelationNeedsWAL(state->indexrel))
- log_newpages(&state->indexrel->rd_locator, MAIN_FORKNUM, state->ready_num_pages,
- state->ready_blknos, state->ready_pages, true);
-
- for (int i = 0; i < state->ready_num_pages; i++)
- pfree(state->ready_pages[i]);
-
- state->ready_num_pages = 0;
-}
-
/*-------------------------------------------------------------------------
* Routines for non-sorted build
diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index 424958912c7..ad848e31b1d 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -87,8 +87,8 @@
* is optimized for bulk inserting a lot of tuples, knowing that we have
* exclusive access to the heap. raw_heap_insert builds new pages in
* local storage. When a page is full, or at the end of the process,
- * we insert it to WAL as a single record and then write it to disk
- * directly through smgr. Note, however, that any data sent to the new
+ * we insert it to WAL as a single record and then write it to disk with
+ * the bulk smgr writer. Note, however, that any data sent to the new
* heap's TOAST table will go through the normal bufmgr.
*
*
@@ -119,9 +119,9 @@
#include "replication/logical.h"
#include "replication/slot.h"
#include "storage/bufmgr.h"
+#include "storage/bulk_write.h"
#include "storage/fd.h"
#include "storage/procarray.h"
-#include "storage/smgr.h"
#include "utils/memutils.h"
#include "utils/rel.h"
@@ -133,9 +133,11 @@ typedef struct RewriteStateData
{
Relation rs_old_rel; /* source heap */
Relation rs_new_rel; /* destination heap */
- Page rs_buffer; /* page currently being built */
+
+ BulkWriteState *rs_bulkw;
+
+ BulkWriteBuffer rs_buffer; /* page currently being built */
BlockNumber rs_blockno; /* block where page will go */
- bool rs_buffer_valid; /* T if any tuples in buffer */
bool rs_logical_rewrite; /* do we need to do logical rewriting */
TransactionId rs_oldest_xmin; /* oldest xmin used by caller to determine
* tuple visibility */
@@ -255,15 +257,16 @@ begin_heap_rewrite(Relation old_heap, Relation new_heap, TransactionId oldest_xm
state->rs_old_rel = old_heap;
state->rs_new_rel = new_heap;
- state->rs_buffer = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
+ state->rs_buffer = NULL;
/* new_heap needn't be empty, just locked */
state->rs_blockno = RelationGetNumberOfBlocks(new_heap);
- state->rs_buffer_valid = false;
state->rs_oldest_xmin = oldest_xmin;
state->rs_freeze_xid = freeze_xid;
state->rs_cutoff_multi = cutoff_multi;
state->rs_cxt = rw_cxt;
+ state->rs_bulkw = bulkw_start_rel(new_heap, MAIN_FORKNUM);
+
/* Initialize hash tables used to track update chains */
hash_ctl.keysize = sizeof(TidHashKey);
hash_ctl.entrysize = sizeof(UnresolvedTupData);
@@ -314,30 +317,13 @@ end_heap_rewrite(RewriteState state)
}
/* Write the last page, if any */
- if (state->rs_buffer_valid)
+ if (state->rs_buffer)
{
- if (RelationNeedsWAL(state->rs_new_rel))
- log_newpage(&state->rs_new_rel->rd_locator,
- MAIN_FORKNUM,
- state->rs_blockno,
- state->rs_buffer,
- true);
-
- PageSetChecksumInplace(state->rs_buffer, state->rs_blockno);
-
- smgrextend(RelationGetSmgr(state->rs_new_rel), MAIN_FORKNUM,
- state->rs_blockno, state->rs_buffer, true);
+ bulkw_write(state->rs_bulkw, state->rs_blockno, state->rs_buffer, true);
+ state->rs_buffer = NULL;
}
- /*
- * When we WAL-logged rel pages, we must nonetheless fsync them. The
- * reason is the same as in storage.c's RelationCopyStorage(): we're
- * writing data that's not in shared buffers, and so a CHECKPOINT
- * occurring during the rewriteheap operation won't have fsync'd data we
- * wrote before the checkpoint.
- */
- if (RelationNeedsWAL(state->rs_new_rel))
- smgrimmedsync(RelationGetSmgr(state->rs_new_rel), MAIN_FORKNUM);
+ bulkw_finish(state->rs_bulkw);
logical_end_heap_rewrite(state);
@@ -611,7 +597,7 @@ rewrite_heap_dead_tuple(RewriteState state, HeapTuple old_tuple)
static void
raw_heap_insert(RewriteState state, HeapTuple tup)
{
- Page page = state->rs_buffer;
+ Page page;
Size pageFreeSpace,
saveFreeSpace;
Size len;
@@ -664,7 +650,8 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
HEAP_DEFAULT_FILLFACTOR);
/* Now we can check to see if there's enough free space already. */
- if (state->rs_buffer_valid)
+ page = (Page) state->rs_buffer;
+ if (page)
{
pageFreeSpace = PageGetHeapFreeSpace(page);
@@ -675,35 +662,19 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
* contains a tuple. Hence, unlike RelationGetBufferForTuple(),
* enforce saveFreeSpace unconditionally.
*/
-
- /* XLOG stuff */
- if (RelationNeedsWAL(state->rs_new_rel))
- log_newpage(&state->rs_new_rel->rd_locator,
- MAIN_FORKNUM,
- state->rs_blockno,
- page,
- true);
-
- /*
- * Now write the page. We say skipFsync = true because there's no
- * need for smgr to schedule an fsync for this write; we'll do it
- * ourselves in end_heap_rewrite.
- */
- PageSetChecksumInplace(page, state->rs_blockno);
-
- smgrextend(RelationGetSmgr(state->rs_new_rel), MAIN_FORKNUM,
- state->rs_blockno, page, true);
-
+ bulkw_write(state->rs_bulkw, state->rs_blockno, state->rs_buffer, true);
+ state->rs_buffer = NULL;
+ page = NULL;
state->rs_blockno++;
- state->rs_buffer_valid = false;
}
}
- if (!state->rs_buffer_valid)
+ if (!page)
{
/* Initialize a new empty page */
+ state->rs_buffer = bulkw_get_buf(state->rs_bulkw);
+ page = (Page) state->rs_buffer;
PageInit(page, BLCKSZ, 0);
- state->rs_buffer_valid = true;
}
/* And now we can insert the tuple into the page */
diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c
index a88b36a589a..38f957e6f4c 100644
--- a/src/backend/access/nbtree/nbtree.c
+++ b/src/backend/access/nbtree/nbtree.c
@@ -29,11 +29,11 @@
#include "nodes/execnodes.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
+#include "storage/bulk_write.h"
#include "storage/condition_variable.h"
#include "storage/indexfsm.h"
#include "storage/ipc.h"
#include "storage/lmgr.h"
-#include "storage/smgr.h"
#include "utils/builtins.h"
#include "utils/index_selfuncs.h"
#include "utils/memutils.h"
@@ -152,32 +152,17 @@ void
btbuildempty(Relation index)
{
bool allequalimage = _bt_allequalimage(index, false);
- Buffer metabuf;
- Page metapage;
+ BulkWriteState *bulkw;
+ BulkWriteBuffer metabuf;
- /*
- * Initalize the metapage.
- *
- * Regular index build bypasses the buffer manager and uses smgr functions
- * directly, with an smgrimmedsync() call at the end. That makes sense
- * when the index is large, but for an empty index, it's better to use the
- * buffer cache to avoid the smgrimmedsync().
- */
- metabuf = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
- Assert(BufferGetBlockNumber(metabuf) == BTREE_METAPAGE);
- _bt_lockbuf(index, metabuf, BT_WRITE);
-
- START_CRIT_SECTION();
-
- metapage = BufferGetPage(metabuf);
- _bt_initmetapage(metapage, P_NONE, 0, allequalimage);
- MarkBufferDirty(metabuf);
- log_newpage_buffer(metabuf, true);
+ bulkw = bulkw_start_rel(index, INIT_FORKNUM);
- END_CRIT_SECTION();
+ /* Construct metapage. */
+ metabuf = bulkw_get_buf(bulkw);
+ _bt_initmetapage((Page) metabuf, P_NONE, 0, allequalimage);
+ bulkw_write(bulkw, BTREE_METAPAGE, metabuf, true);
- _bt_unlockbuf(index, metabuf);
- ReleaseBuffer(metabuf);
+ bulkw_finish(bulkw);
}
/*
diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c
index c2665fce411..6034d7f61b2 100644
--- a/src/backend/access/nbtree/nbtsort.c
+++ b/src/backend/access/nbtree/nbtsort.c
@@ -23,13 +23,8 @@
* many upper pages if the keys are reasonable-size) without risking a lot of
* cascading splits during early insertions.
*
- * Formerly the index pages being built were kept in shared buffers, but
- * that is of no value (since other backends have no interest in them yet)
- * and it created locking problems for CHECKPOINT, because the upper-level
- * pages were held exclusive-locked for long periods. Now we just build
- * the pages in local memory and smgrwrite or smgrextend them as we finish
- * them. They will need to be re-read into shared buffers on first use after
- * the build finishes.
+ * We use the bulk smgr loading facility to bypass the buffer cache and
+ * WAL log the pages efficiently.
*
* This code isn't concerned about the FSM at all. The caller is responsible
* for initializing that.
@@ -57,7 +52,7 @@
#include "executor/instrument.h"
#include "miscadmin.h"
#include "pgstat.h"
-#include "storage/smgr.h"
+#include "storage/bulk_write.h"
#include "tcop/tcopprot.h" /* pgrminclude ignore */
#include "utils/rel.h"
#include "utils/sortsupport.h"
@@ -234,7 +229,7 @@ typedef struct BTBuildState
*/
typedef struct BTPageState
{
- Page btps_page; /* workspace for page building */
+ BulkWriteBuffer btps_buf; /* workspace for page building */
BlockNumber btps_blkno; /* block # to write this page at */
IndexTuple btps_lowkey; /* page's strict lower bound pivot tuple */
OffsetNumber btps_lastoff; /* last item offset loaded */
@@ -251,11 +246,9 @@ typedef struct BTWriteState
{
Relation heap;
Relation index;
+ BulkWriteState *bulkw;
BTScanInsert inskey; /* generic insertion scankey */
- bool btws_use_wal; /* dump pages to WAL? */
BlockNumber btws_pages_alloced; /* # pages allocated */
- BlockNumber btws_pages_written; /* # pages written out */
- Page btws_zeropage; /* workspace for filling zeroes */
} BTWriteState;
@@ -267,7 +260,7 @@ static void _bt_spool(BTSpool *btspool, ItemPointer self,
static void _bt_leafbuild(BTSpool *btspool, BTSpool *btspool2);
static void _bt_build_callback(Relation index, ItemPointer tid, Datum *values,
bool *isnull, bool tupleIsAlive, void *state);
-static Page _bt_blnewpage(uint32 level);
+static BulkWriteBuffer _bt_blnewpage(BTWriteState *wstate, uint32 level);
static BTPageState *_bt_pagestate(BTWriteState *wstate, uint32 level);
static void _bt_slideleft(Page rightmostpage);
static void _bt_sortaddtup(Page page, Size itemsize,
@@ -569,16 +562,17 @@ _bt_leafbuild(BTSpool *btspool, BTSpool *btspool2)
wstate.inskey = _bt_mkscankey(wstate.index, NULL);
/* _bt_mkscankey() won't set allequalimage without metapage */
wstate.inskey->allequalimage = _bt_allequalimage(wstate.index, true);
- wstate.btws_use_wal = RelationNeedsWAL(wstate.index);
/* reserve the metapage */
wstate.btws_pages_alloced = BTREE_METAPAGE + 1;
- wstate.btws_pages_written = 0;
- wstate.btws_zeropage = NULL; /* until needed */
+
+ wstate.bulkw = bulkw_start_rel(wstate.index, MAIN_FORKNUM);
pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE,
PROGRESS_BTREE_PHASE_LEAF_LOAD);
_bt_load(&wstate, btspool, btspool2);
+
+ bulkw_finish(wstate.bulkw);
}
/*
@@ -613,13 +607,15 @@ _bt_build_callback(Relation index,
/*
* allocate workspace for a new, clean btree page, not linked to any siblings.
*/
-static Page
-_bt_blnewpage(uint32 level)
+static BulkWriteBuffer
+_bt_blnewpage(BTWriteState *wstate, uint32 level)
{
+ BulkWriteBuffer buf;
Page page;
BTPageOpaque opaque;
- page = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
+ buf = bulkw_get_buf(wstate->bulkw);
+ page = (Page) buf;
/* Zero the page and set up standard page header info */
_bt_pageinit(page, BLCKSZ);
@@ -634,63 +630,17 @@ _bt_blnewpage(uint32 level)
/* Make the P_HIKEY line pointer appear allocated */
((PageHeader) page)->pd_lower += sizeof(ItemIdData);
- return page;
+ return buf;
}
/*
* emit a completed btree page, and release the working storage.
*/
static void
-_bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
+_bt_blwritepage(BTWriteState *wstate, BulkWriteBuffer buf, BlockNumber blkno)
{
- /* XLOG stuff */
- if (wstate->btws_use_wal)
- {
- /* We use the XLOG_FPI record type for this */
- log_newpage(&wstate->index->rd_locator, MAIN_FORKNUM, blkno, page, true);
- }
-
- /*
- * If we have to write pages nonsequentially, fill in the space with
- * zeroes until we come back and overwrite. This is not logically
- * necessary on standard Unix filesystems (unwritten space will read as
- * zeroes anyway), but it should help to avoid fragmentation. The dummy
- * pages aren't WAL-logged though.
- */
- while (blkno > wstate->btws_pages_written)
- {
- if (!wstate->btws_zeropage)
- wstate->btws_zeropage = (Page) palloc_aligned(BLCKSZ,
- PG_IO_ALIGN_SIZE,
- MCXT_ALLOC_ZERO);
- /* don't set checksum for all-zero page */
- smgrextend(RelationGetSmgr(wstate->index), MAIN_FORKNUM,
- wstate->btws_pages_written++,
- wstate->btws_zeropage,
- true);
- }
-
- PageSetChecksumInplace(page, blkno);
-
- /*
- * Now write the page. There's no need for smgr to schedule an fsync for
- * this write; we'll do it ourselves before ending the build.
- */
- if (blkno == wstate->btws_pages_written)
- {
- /* extending the file... */
- smgrextend(RelationGetSmgr(wstate->index), MAIN_FORKNUM, blkno,
- page, true);
- wstate->btws_pages_written++;
- }
- else
- {
- /* overwriting a block we zero-filled before */
- smgrwrite(RelationGetSmgr(wstate->index), MAIN_FORKNUM, blkno,
- page, true);
- }
-
- pfree(page);
+ bulkw_write(wstate->bulkw, blkno, buf, true);
+ /* bulkw_write took ownership of 'buf' */
}
/*
@@ -703,7 +653,7 @@ _bt_pagestate(BTWriteState *wstate, uint32 level)
BTPageState *state = (BTPageState *) palloc0(sizeof(BTPageState));
/* create initial page for level */
- state->btps_page = _bt_blnewpage(level);
+ state->btps_buf = _bt_blnewpage(wstate, level);
/* and assign it a page position */
state->btps_blkno = wstate->btws_pages_alloced++;
@@ -839,6 +789,7 @@ static void
_bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
Size truncextra)
{
+ BulkWriteBuffer nbuf;
Page npage;
BlockNumber nblkno;
OffsetNumber last_off;
@@ -853,7 +804,8 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
*/
CHECK_FOR_INTERRUPTS();
- npage = state->btps_page;
+ nbuf = state->btps_buf;
+ npage = (Page) nbuf;
nblkno = state->btps_blkno;
last_off = state->btps_lastoff;
last_truncextra = state->btps_lastextra;
@@ -909,6 +861,7 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
/*
* Finish off the page and write it out.
*/
+ BulkWriteBuffer obuf = nbuf;
Page opage = npage;
BlockNumber oblkno = nblkno;
ItemId ii;
@@ -916,7 +869,8 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
IndexTuple oitup;
/* Create new page of same level */
- npage = _bt_blnewpage(state->btps_level);
+ nbuf = _bt_blnewpage(wstate, state->btps_level);
+ npage = (Page) nbuf;
/* and assign it a page position */
nblkno = wstate->btws_pages_alloced++;
@@ -1028,10 +982,10 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
}
/*
- * Write out the old page. We never need to touch it again, so we can
- * free the opage workspace too.
+ * Write out the old page. _bt_blwritepage takes ownership of the
+ * 'opage' buffer.
*/
- _bt_blwritepage(wstate, opage, oblkno);
+ _bt_blwritepage(wstate, obuf, oblkno);
/*
* Reset last_off to point to new page
@@ -1064,7 +1018,7 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
_bt_sortaddtup(npage, itupsz, itup, last_off,
!isleaf && last_off == P_FIRSTKEY);
- state->btps_page = npage;
+ state->btps_buf = nbuf;
state->btps_blkno = nblkno;
state->btps_lastoff = last_off;
}
@@ -1116,7 +1070,7 @@ _bt_uppershutdown(BTWriteState *wstate, BTPageState *state)
BTPageState *s;
BlockNumber rootblkno = P_NONE;
uint32 rootlevel = 0;
- Page metapage;
+ BulkWriteBuffer metabuf;
/*
* Each iteration of this loop completes one more level of the tree.
@@ -1127,7 +1081,7 @@ _bt_uppershutdown(BTWriteState *wstate, BTPageState *state)
BTPageOpaque opaque;
blkno = s->btps_blkno;
- opaque = BTPageGetOpaque(s->btps_page);
+ opaque = BTPageGetOpaque((Page) s->btps_buf);
/*
* We have to link the last page on this level to somewhere.
@@ -1161,9 +1115,9 @@ _bt_uppershutdown(BTWriteState *wstate, BTPageState *state)
* This is the rightmost page, so the ItemId array needs to be slid
* back one slot. Then we can dump out the page.
*/
- _bt_slideleft(s->btps_page);
- _bt_blwritepage(wstate, s->btps_page, s->btps_blkno);
- s->btps_page = NULL; /* writepage freed the workspace */
+ _bt_slideleft((Page) s->btps_buf);
+ _bt_blwritepage(wstate, s->btps_buf, s->btps_blkno);
+ s->btps_buf = NULL; /* writepage took ownership of the buffer */
}
/*
@@ -1172,10 +1126,10 @@ _bt_uppershutdown(BTWriteState *wstate, BTPageState *state)
* set to point to "P_NONE"). This changes the index to the "valid" state
* by filling in a valid magic number in the metapage.
*/
- metapage = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
- _bt_initmetapage(metapage, rootblkno, rootlevel,
+ metabuf = bulkw_get_buf(wstate->bulkw);
+ _bt_initmetapage((Page) metabuf, rootblkno, rootlevel,
wstate->inskey->allequalimage);
- _bt_blwritepage(wstate, metapage, BTREE_METAPAGE);
+ _bt_blwritepage(wstate, metabuf, BTREE_METAPAGE);
}
/*
@@ -1422,18 +1376,6 @@ _bt_load(BTWriteState *wstate, BTSpool *btspool, BTSpool *btspool2)
/* Close down final pages and write the metapage */
_bt_uppershutdown(wstate, state);
-
- /*
- * When we WAL-logged index pages, we must nonetheless fsync index files.
- * Since we're building outside shared buffers, a CHECKPOINT occurring
- * during the build has no way to flush the previously written data to
- * disk (indeed it won't know the index even exists). A crash later on
- * would replay WAL from the checkpoint, therefore it wouldn't replay our
- * earlier WAL entries. If we do not fsync those pages here, they might
- * still not be on disk when the crash occurs.
- */
- if (wstate->btws_use_wal)
- smgrimmedsync(RelationGetSmgr(wstate->index), MAIN_FORKNUM);
}
/*
diff --git a/src/backend/access/spgist/spginsert.c b/src/backend/access/spgist/spginsert.c
index 4443f1918df..31b9d5244db 100644
--- a/src/backend/access/spgist/spginsert.c
+++ b/src/backend/access/spgist/spginsert.c
@@ -25,7 +25,7 @@
#include "catalog/index.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
-#include "storage/smgr.h"
+#include "storage/bulk_write.h"
#include "utils/memutils.h"
#include "utils/rel.h"
@@ -155,42 +155,27 @@ spgbuild(Relation heap, Relation index, IndexInfo *indexInfo)
void
spgbuildempty(Relation index)
{
- Buffer metabuffer,
- rootbuffer,
- nullbuffer;
-
- /*
- * Initialize the meta page and root pages
- */
- metabuffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
- LockBuffer(metabuffer, BUFFER_LOCK_EXCLUSIVE);
- rootbuffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
- LockBuffer(rootbuffer, BUFFER_LOCK_EXCLUSIVE);
- nullbuffer = ReadBufferExtended(index, INIT_FORKNUM, P_NEW, RBM_NORMAL, NULL);
- LockBuffer(nullbuffer, BUFFER_LOCK_EXCLUSIVE);
-
- Assert(BufferGetBlockNumber(metabuffer) == SPGIST_METAPAGE_BLKNO);
- Assert(BufferGetBlockNumber(rootbuffer) == SPGIST_ROOT_BLKNO);
- Assert(BufferGetBlockNumber(nullbuffer) == SPGIST_NULL_BLKNO);
+ BulkWriteState *bulkw;
+ BulkWriteBuffer buf;
- START_CRIT_SECTION();
+ bulkw = bulkw_start_rel(index, INIT_FORKNUM);
- SpGistInitMetapage(BufferGetPage(metabuffer));
- MarkBufferDirty(metabuffer);
- SpGistInitBuffer(rootbuffer, SPGIST_LEAF);
- MarkBufferDirty(rootbuffer);
- SpGistInitBuffer(nullbuffer, SPGIST_LEAF | SPGIST_NULLS);
- MarkBufferDirty(nullbuffer);
+ /* Construct metapage. */
+ buf = bulkw_get_buf(bulkw);
+ SpGistInitMetapage((Page) buf);
+ bulkw_write(bulkw, SPGIST_METAPAGE_BLKNO, buf, true);
- log_newpage_buffer(metabuffer, true);
- log_newpage_buffer(rootbuffer, true);
- log_newpage_buffer(nullbuffer, true);
+ /* Likewise for the root page. */
+ buf = bulkw_get_buf(bulkw);
+ SpGistInitPage((Page) buf, SPGIST_LEAF);
+ bulkw_write(bulkw, SPGIST_ROOT_BLKNO, buf, true);
- END_CRIT_SECTION();
+ /* Likewise for the null-tuples root page. */
+ buf = bulkw_get_buf(bulkw);
+ SpGistInitPage((Page) buf, SPGIST_LEAF | SPGIST_NULLS);
+ bulkw_write(bulkw, SPGIST_NULL_BLKNO, buf, true);
- UnlockReleaseBuffer(metabuffer);
- UnlockReleaseBuffer(rootbuffer);
- UnlockReleaseBuffer(nullbuffer);
+ bulkw_finish(bulkw);
}
/*
diff --git a/src/backend/catalog/storage.c b/src/backend/catalog/storage.c
index 93f07e49b72..c2d5b3ecb28 100644
--- a/src/backend/catalog/storage.c
+++ b/src/backend/catalog/storage.c
@@ -28,6 +28,7 @@
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
#include "miscadmin.h"
+#include "storage/bulk_write.h"
#include "storage/freespace.h"
#include "storage/smgr.h"
#include "utils/hsearch.h"
@@ -451,14 +452,11 @@ void
RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
ForkNumber forkNum, char relpersistence)
{
- PGIOAlignedBlock buf;
- Page page;
bool use_wal;
bool copying_initfork;
BlockNumber nblocks;
BlockNumber blkno;
-
- page = (Page) buf.data;
+ BulkWriteState *bulkw;
/*
* The init fork for an unlogged relation in many respects has to be
@@ -477,16 +475,21 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
use_wal = XLogIsNeeded() &&
(relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork);
+ bulkw = bulkw_start_smgr(dst, forkNum, use_wal);
+
nblocks = smgrnblocks(src, forkNum);
for (blkno = 0; blkno < nblocks; blkno++)
{
+ BulkWriteBuffer buf;
+
/* If we got a cancel signal during the copy of the data, quit */
CHECK_FOR_INTERRUPTS();
- smgrread(src, forkNum, blkno, buf.data);
+ buf = bulkw_get_buf(bulkw);
+ smgrread(src, forkNum, blkno, (Page) buf);
- if (!PageIsVerifiedExtended(page, blkno,
+ if (!PageIsVerifiedExtended((Page) buf, blkno,
PIV_LOG_WARNING | PIV_REPORT_STAT))
{
/*
@@ -507,34 +510,13 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
}
/*
- * WAL-log the copied page. Unfortunately we don't know what kind of a
- * page this is, so we have to log the full page including any unused
- * space.
- */
- if (use_wal)
- log_newpage(&dst->smgr_rlocator.locator, forkNum, blkno, page, false);
-
- PageSetChecksumInplace(page, blkno);
-
- /*
- * Now write the page. We say skipFsync = true because there's no
- * need for smgr to schedule an fsync for this write; we'll do it
- * ourselves below.
+ * Queue the page for WAL-logging and writing out. Unfortunately we
+ * don't know what kind of a page this is, so we have to log the full
+ * page including any unused space.
*/
- smgrextend(dst, forkNum, blkno, buf.data, true);
+ bulkw_write(bulkw, blkno, buf, false);
}
-
- /*
- * When we WAL-logged rel pages, we must nonetheless fsync them. The
- * reason is that since we're copying outside shared buffers, a CHECKPOINT
- * occurring during the copy has no way to flush the previously written
- * data to disk (indeed it won't know the new rel even exists). A crash
- * later on would replay WAL from the checkpoint, therefore it wouldn't
- * replay our earlier WAL entries. If we do not fsync those pages here,
- * they might still not be on disk when the crash occurs.
- */
- if (use_wal || copying_initfork)
- smgrimmedsync(dst, forkNum);
+ bulkw_finish(bulkw);
}
/*
diff --git a/src/backend/storage/smgr/Makefile b/src/backend/storage/smgr/Makefile
index 596b564656f..1d0b98764f9 100644
--- a/src/backend/storage/smgr/Makefile
+++ b/src/backend/storage/smgr/Makefile
@@ -13,6 +13,7 @@ top_builddir = ../../../..
include $(top_builddir)/src/Makefile.global
OBJS = \
+ bulk_write.o \
md.o \
smgr.o
diff --git a/src/backend/storage/smgr/bulk_write.c b/src/backend/storage/smgr/bulk_write.c
new file mode 100644
index 00000000000..1913c39bf21
--- /dev/null
+++ b/src/backend/storage/smgr/bulk_write.c
@@ -0,0 +1,301 @@
+/*-------------------------------------------------------------------------
+ *
+ * bulk_write.c
+ * Efficiently and reliably populate a new relation
+ *
+ * The assumption is that no other backends access the relation while we are
+ * loading it, so we can take some shortcuts. Do not mix operations through
+ * the regular buffer manager and the bulk loading interface!
+ *
+ * We bypass the buffer manager to avoid the locking overhead, and call
+ * smgrextend() directly. A downside is that the pages will need to be
+ * re-read into shared buffers on first use after the build finishes. That's
+ * usually a good tradeoff for large relations, and for small relations, the
+ * overhead isn't very significant compared to creating the relation in the
+ * first place.
+ *
+ * The pages are WAL-logged if needed. To save on WAL header overhead, we
+ * WAL-log several pages in one record.
+ *
+ * One tricky point is that because we bypass the buffer manager, we need to
+ * register the relation for fsyncing at the next checkpoint ourselves, and
+ * make sure that the relation is correctly fsync'd by us or the checkpointer
+ * even if a checkpoint happens concurrently.
+ *
+ *
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ * src/backend/storage/smgr/bulk_write.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/xloginsert.h"
+#include "access/xlogrecord.h"
+#include "storage/bufmgr.h"
+#include "storage/bufpage.h"
+#include "storage/bulk_write.h"
+#include "storage/proc.h"
+#include "storage/smgr.h"
+#include "utils/rel.h"
+
+#define MAX_PENDING_WRITES XLR_MAX_BLOCK_ID
+
+static const PGIOAlignedBlock zero_buffer = {{0}}; /* worth BLCKSZ */
+
+typedef struct PendingWrite
+{
+ BulkWriteBuffer buf;
+ BlockNumber blkno;
+ bool page_std;
+} PendingWrite;
+
+/*
+ * Bulk writer state for one relation fork.
+ */
+typedef struct BulkWriteState
+{
+ /* Information about the target relation we're writing */
+ /*
+ * FIXME: 'smgr' might get invalidated. Hopefully
+ * https://postgr.es/m/CA%2BhUKGJ8NTvqLHz6dqbQnt2c8XCki4r2QvXjBQcXpVwxTY_pvA%40mail.gmail.com
+ * is merged before this.
+ */
+ SMgrRelation smgr;
+ ForkNumber forknum;
+ bool use_wal;
+
+ /* We keep several writes queued, and WAL-log them in batches */
+ int npending;
+ PendingWrite pending_writes[MAX_PENDING_WRITES];
+
+ /* Current size of the relation */
+ BlockNumber pages_written;
+
+ /* The RedoRecPtr at the time that the bulk operation started */
+ XLogRecPtr start_RedoRecPtr;
+
+ MemoryContext memcxt;
+} BulkWriteState;
+
+static void bulkw_flush(BulkWriteState *bulkw);
+
+/*
+ * Start a bulk write operation on a relation fork.
+ */
+BulkWriteState *
+bulkw_start_rel(Relation rel, ForkNumber forknum)
+{
+ return bulkw_start_smgr(RelationGetSmgr(rel),
+ forknum,
+ RelationNeedsWAL(rel) || forknum == INIT_FORKNUM);
+}
+
+/*
+ * Start a bulk write operation on a relation fork.
+ *
+ * This is like bulkw_start_rel, but can be used without a relcache entry.
+ */
+BulkWriteState *
+bulkw_start_smgr(SMgrRelation smgr, ForkNumber forknum, bool use_wal)
+{
+ BulkWriteState *bulkw;
+
+ bulkw = palloc(sizeof(BulkWriteState));
+ bulkw->smgr = smgr;
+ bulkw->forknum = forknum;
+ bulkw->use_wal = use_wal;
+
+ bulkw->npending = 0;
+ bulkw->pages_written = 0;
+
+ bulkw->start_RedoRecPtr = GetRedoRecPtr();
+
+ /*
+ * Remember the memory context. We will use it to allocate all the
+ * buffers later.
+ */
+ bulkw->memcxt = CurrentMemoryContext;
+
+ return bulkw;
+}
+
+/*
+ * Finish bulk write operation.
+ *
+ * This WAL-logs and flushes any remaining pending writes to disk, and fsyncs
+ * the relation if needed.
+ */
+void
+bulkw_finish(BulkWriteState *bulkw)
+{
+ /* WAL-log and flush any remaining pages */
+ bulkw_flush(bulkw);
+
+ /*
+ * When we wrote out the pages, we passed skipFsync=true to avoid the
+ * overhead of registering all the writes with the checkpointer. Register
+ * the whole relation now.
+ *
+ * There is one hole in that idea: If a checkpoint occurred while we were
+ * writing the pages, it already missed fsyncing the pages we had written
+ * before the checkpoint started. A crash later on would replay the WAL
+ * starting from the checkpoint, therefore it wouldn't replay our earlier
+ * WAL records. So if a checkpoint started after the bulk write, fsync
+ * the files now.
+ */
+ if (!SmgrIsTemp(bulkw->smgr))
+ {
+ /*
+ * Prevent a checkpoint from starting between the GetRedoRecPtr() and
+ * smgrregistersync() calls.
+ */
+ Assert((MyProc->delayChkptFlags & DELAY_CHKPT_START) == 0);
+ MyProc->delayChkptFlags |= DELAY_CHKPT_START;
+
+ if (bulkw->start_RedoRecPtr != GetRedoRecPtr())
+ {
+ /*
+ * A checkpoint occurred and it didn't know about our writes, so
+ * fsync() the relation ourselves.
+ */
+ MyProc->delayChkptFlags &= ~DELAY_CHKPT_START;
+ smgrimmedsync(bulkw->smgr, bulkw->forknum);
+ elog(DEBUG1, "flushed relation because a checkpoint occurred concurrently");
+ }
+ else
+ {
+ smgrregistersync(bulkw->smgr, bulkw->forknum);
+ MyProc->delayChkptFlags &= ~DELAY_CHKPT_START;
+ }
+ }
+}
+
+static int
+buffer_cmp(const void *a, const void *b)
+{
+ const PendingWrite *bufa = (const PendingWrite *) a;
+ const PendingWrite *bufb = (const PendingWrite *) b;
+
+ /* We should not see duplicated writes for the same block */
+ Assert(bufa->blkno != bufb->blkno);
+ if (bufa->blkno > bufb->blkno)
+ return 1;
+ else
+ return -1;
+}
+
+/*
+ * Finish all the pending writes.
+ */
+static void
+bulkw_flush(BulkWriteState *bulkw)
+{
+ int npending = bulkw->npending;
+ PendingWrite *pending_writes = bulkw->pending_writes;
+
+ if (npending == 0)
+ return;
+
+ if (npending > 1)
+ qsort(pending_writes, npending, sizeof(PendingWrite), buffer_cmp);
+
+ if (bulkw->use_wal)
+ {
+ BlockNumber blknos[MAX_PENDING_WRITES];
+ Page pages[MAX_PENDING_WRITES];
+ bool page_std = true;
+
+ for (int i = 0; i < npending; i++)
+ {
+ blknos[i] = pending_writes[i].blkno;
+ pages[i] = pending_writes[i].buf->data;
+
+ /*
+ * If any of the pages use !page_std, we log them all as such.
+ * That's a bit wasteful, but in practice, a mix of standard and
+ * non-standard page layout is rare. None of the built-in AMs do
+ * that.
+ */
+ if (!pending_writes[i].page_std)
+ page_std = false;
+ }
+ log_newpages(&bulkw->smgr->smgr_rlocator.locator, bulkw->forknum,
+ npending, blknos, pages, page_std);
+ }
+
+ for (int i = 0; i < npending; i++)
+ {
+ BlockNumber blkno = pending_writes[i].blkno;
+ Page page = pending_writes[i].buf->data;
+
+ PageSetChecksumInplace(page, blkno);
+
+ if (blkno >= bulkw->pages_written)
+ {
+ /*
+ * If we have to write pages nonsequentially, fill in the space
+ * with zeroes until we come back and overwrite. This is not
+ * logically necessary on standard Unix filesystems (unwritten
+ * space will read as zeroes anyway), but it should help to avoid
+ * fragmentation. The dummy pages aren't WAL-logged though.
+ */
+ while (blkno > bulkw->pages_written)
+ {
+ /* don't set checksum for all-zero page */
+ smgrextend(bulkw->smgr, bulkw->forknum,
+ bulkw->pages_written++,
+ &zero_buffer,
+ true);
+ }
+
+ smgrextend(bulkw->smgr, bulkw->forknum, blkno, page, true);
+ bulkw->pages_written = pending_writes[i].blkno + 1;
+ }
+ else
+ smgrwrite(bulkw->smgr, bulkw->forknum, blkno, page, true);
+ pfree(page);
+ }
+
+ bulkw->npending = 0;
+}
+
+/*
+ * Queue write of 'buf'.
+ *
+ * NB: this takes ownership of 'buf'!
+ *
+ * You are only allowed to write a given block once as part of one bulk write
+ * operation.
+ */
+void
+bulkw_write(BulkWriteState *bulkw, BlockNumber blocknum, BulkWriteBuffer buf, bool page_std)
+{
+ bulkw->pending_writes[bulkw->npending].buf = buf;
+ bulkw->pending_writes[bulkw->npending].blkno = blocknum;
+ bulkw->pending_writes[bulkw->npending].page_std = page_std;
+
+ bulkw->npending++;
+
+ if (bulkw->npending == MAX_PENDING_WRITES)
+ bulkw_flush(bulkw);
+}
+
+/*
+ * Allocate a new buffer which can later be written with bulkw_write().
+ *
+ * There is no function to free a buffer. When you pass it to bulkw_write(),
+ * it takes ownership and frees it when it's no longer needed.
+ *
+ * This is currently implemented as a simple palloc, but could be implemented
+ * using a ring buffer or larger chunks in the future, so don't rely on it.
+ */
+BulkWriteBuffer
+bulkw_get_buf(BulkWriteState *bulkw)
+{
+ return MemoryContextAllocAligned(bulkw->memcxt, BLCKSZ, PG_IO_ALIGN_SIZE, 0);
+}
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index fdecbad1709..343ee51048e 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -1082,6 +1082,49 @@ mdtruncate(SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
}
}
+/*
+ * mdregistersync() -- Mark whole relation as needing fsync
+ */
+void
+mdregistersync(SMgrRelation reln, ForkNumber forknum)
+{
+ int segno;
+ int min_inactive_seg;
+
+ /*
+ * NOTE: mdnblocks makes sure we have opened all active segments, so that
+ * the loop below will get them all!
+ */
+ mdnblocks(reln, forknum);
+
+ min_inactive_seg = segno = reln->md_num_open_segs[forknum];
+
+ /*
+ * Temporarily open inactive segments, then close them after sync. There
+ * may be some inactive segments left opened after error, but that is
+ * harmless. We don't bother to clean them up and take a risk of further
+ * trouble. The next mdclose() will soon close them.
+ */
+ while (_mdfd_openseg(reln, forknum, segno, 0) != NULL)
+ segno++;
+
+ while (segno > 0)
+ {
+ MdfdVec *v = &reln->md_seg_fds[forknum][segno - 1];
+
+ register_dirty_segment(reln, forknum, v);
+
+ /* Close inactive segments immediately */
+ if (segno > min_inactive_seg)
+ {
+ FileClose(v->mdfd_vfd);
+ _fdvec_resize(reln, forknum, segno - 1);
+ }
+
+ segno--;
+ }
+}
+
/*
* mdimmedsync() -- Immediately sync a relation to stable storage.
*
diff --git a/src/backend/storage/smgr/meson.build b/src/backend/storage/smgr/meson.build
index e1ba6ed74b8..133622a6528 100644
--- a/src/backend/storage/smgr/meson.build
+++ b/src/backend/storage/smgr/meson.build
@@ -1,6 +1,7 @@
# Copyright (c) 2022-2023, PostgreSQL Global Development Group
backend_sources += files(
+ 'bulk_write.c',
'md.c',
'smgr.c',
)
diff --git a/src/backend/storage/smgr/smgr.c b/src/backend/storage/smgr/smgr.c
index 5d0f3d515c3..9f7405e3c88 100644
--- a/src/backend/storage/smgr/smgr.c
+++ b/src/backend/storage/smgr/smgr.c
@@ -65,6 +65,7 @@ typedef struct f_smgr
void (*smgr_truncate) (SMgrRelation reln, ForkNumber forknum,
BlockNumber nblocks);
void (*smgr_immedsync) (SMgrRelation reln, ForkNumber forknum);
+ void (*smgr_registersync) (SMgrRelation reln, ForkNumber forknum);
} f_smgr;
static const f_smgr smgrsw[] = {
@@ -86,6 +87,7 @@ static const f_smgr smgrsw[] = {
.smgr_nblocks = mdnblocks,
.smgr_truncate = mdtruncate,
.smgr_immedsync = mdimmedsync,
+ .smgr_registersync = mdregistersync,
}
};
@@ -576,6 +578,14 @@ smgrread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
* on disk at return, only dumped out to the kernel. However,
* provisions will be made to fsync the write before the next checkpoint.
*
+ * NB: The mechanism to ensure fsync at next checkpoint assumes that there is
+ * something that prevents a concurrent checkpoint from "racing ahead" of the
+ * write. One way to prevent that is by holding a lock on the buffer; the
+ * buffer manager's writes are protected by that. The bulk writer facility in
+ * bulk_write.c checks the redo pointer and and calls smgrimmedsync() if a
+ * checkpoint happened; that relies on the fact that no other backend can be
+ * concurrently modify the page.
+ *
* skipFsync indicates that the caller will make other provisions to
* fsync the relation, so we needn't bother. Temporary relations also
* do not require fsync.
@@ -694,6 +704,24 @@ smgrtruncate(SMgrRelation reln, ForkNumber *forknum, int nforks, BlockNumber *nb
}
}
+/*
+ * smgrregistersync() -- Request a relation to be sync'd at next checkpoint
+ *
+ * This can be used after calling smgrwrite() or smgrextend() with skipFsync =
+ * true, to register the fsyncs that were skipped earlier.
+ *
+ * Note: be mindful that a checkpoint could already have happened between the
+ * smgrwrite or smgrextend calls and this! In that case, the checkpoint
+ * already missed fsyncing this relation, and you should use smgrimmedsync
+ * instead. Most callers should use the bulk loading facility in bulk_write.c
+ * instead, which handles all that.
+ */
+void
+smgrregistersync(SMgrRelation reln, ForkNumber forknum)
+{
+ smgrsw[reln->smgr_which].smgr_registersync(reln, forknum);
+}
+
/*
* smgrimmedsync() -- Force the specified relation to stable storage.
*
@@ -716,6 +744,9 @@ smgrtruncate(SMgrRelation reln, ForkNumber *forknum, int nforks, BlockNumber *nb
* Note that you need to do FlushRelationBuffers() first if there is
* any possibility that there are dirty buffers for the relation;
* otherwise the sync is not very meaningful.
+ *
+ * Most callers should use the bulk loading facility in bulk_write.c
+ * instead of calling this directly.
*/
void
smgrimmedsync(SMgrRelation reln, ForkNumber forknum)
diff --git a/src/include/storage/bulk_write.h b/src/include/storage/bulk_write.h
new file mode 100644
index 00000000000..4defaf20125
--- /dev/null
+++ b/src/include/storage/bulk_write.h
@@ -0,0 +1,38 @@
+/*-------------------------------------------------------------------------
+ *
+ * bulk_write.h
+ * Efficiently and reliably populate a new relation
+ *
+ *
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/storage/bulk_write.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef BULK_WRITE_H
+#define BULK_WRITE_H
+
+typedef struct BulkWriteState BulkWriteState;
+
+/*
+ * Temporary buffer to hold a page to until it's written out. Use
+ * bulkw_get_buf() to reserve one of these. This is a separate typedef to
+ * make distinguish from other block-sized buffers passed around in the
+ * system.
+ */
+typedef PGIOAlignedBlock *BulkWriteBuffer;
+
+/* forward declared from smgr.h */
+struct SMgrRelationData;
+
+extern BulkWriteState *bulkw_start_rel(Relation rel, ForkNumber forknum);
+extern BulkWriteState *bulkw_start_smgr(struct SMgrRelationData *smgr, ForkNumber forknum, bool use_wal);
+
+extern BulkWriteBuffer bulkw_get_buf(BulkWriteState *bulkw);
+extern void bulkw_write(BulkWriteState *bulkw, BlockNumber blocknum, BulkWriteBuffer buf, bool page_std);
+
+extern void bulkw_finish(BulkWriteState *bulkw);
+
+#endif /* BULK_WRITE_H */
diff --git a/src/include/storage/md.h b/src/include/storage/md.h
index 941879ee6a8..225701271d2 100644
--- a/src/include/storage/md.h
+++ b/src/include/storage/md.h
@@ -42,6 +42,7 @@ extern BlockNumber mdnblocks(SMgrRelation reln, ForkNumber forknum);
extern void mdtruncate(SMgrRelation reln, ForkNumber forknum,
BlockNumber nblocks);
extern void mdimmedsync(SMgrRelation reln, ForkNumber forknum);
+extern void mdregistersync(SMgrRelation reln, ForkNumber forknum);
extern void ForgetDatabaseSyncRequests(Oid dbid);
extern void DropRelationFiles(RelFileLocator *delrels, int ndelrels, bool isRedo);
diff --git a/src/include/storage/smgr.h b/src/include/storage/smgr.h
index a9a179aabac..cc5a91dc624 100644
--- a/src/include/storage/smgr.h
+++ b/src/include/storage/smgr.h
@@ -107,6 +107,7 @@ extern BlockNumber smgrnblocks_cached(SMgrRelation reln, ForkNumber forknum);
extern void smgrtruncate(SMgrRelation reln, ForkNumber *forknum,
int nforks, BlockNumber *nblocks);
extern void smgrimmedsync(SMgrRelation reln, ForkNumber forknum);
+extern void smgrregistersync(SMgrRelation reln, ForkNumber forknum);
extern void AtEOXact_SMgr(void);
extern bool ProcessBarrierSmgrRelease(void);
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index dba3498a13e..85b8491fd49 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -327,6 +327,8 @@ BuildAccumulator
BuiltinScript
BulkInsertState
BulkInsertStateData
+BulkWriteBuffer
+BulkWriteState
CACHESIGN
CAC_state
CCFastEqualFN
@@ -2005,6 +2007,7 @@ PendingFsyncEntry
PendingRelDelete
PendingRelSync
PendingUnlinkEntry
+PendingWrite
PendingWriteback
PerLockTagEntry
PerlInterpreter
--
2.39.2
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: Relation bulk write facility
2023-11-24 23:19 Re: Relation bulk write facility Heikki Linnakangas <[email protected]>
@ 2023-12-14 13:02 ` Heikki Linnakangas <[email protected]>
1 sibling, 0 replies; 149+ messages in thread
From: Heikki Linnakangas @ 2023-12-14 13:02 UTC (permalink / raw)
To: Melanie Plageman <[email protected]>; +Cc: pgsql-hackers; Andres Freund <[email protected]>
Melanie just reminded about an older thread about this same thing:
https://www.postgresql.org/message-id/CAAKRu_ZQEpk6Q1WtNLgfXBdCmdU5xN_w0boVO6faO_Ax%2Bckjig%40mail.g....
I had completely forgotten about that.
Melanie's patches in that thread implemented the same optimization of
avoiding the fsync() if no checkpoint has happened during the index
build. My patch here also implements batching the WAL records of
multiple blocks, which was not part of those older patches. OTOH, those
patches included an additional optimization of not bypassing the shared
buffer cache if the index is small. That seems sensible too.
In this new patch, I subconsciously implemented an API close to what I
suggested at the end of that old thread.
So I'd like to continue this effort based on this new patch. We can add
the bypass-buffer-cache optimization later on top of this. With the new
API that this introduces, it should be an isolated change to the
implementation, with no changes required to the callers.
--
Heikki Linnakangas
Neon (https://neon.tech)
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: Relation bulk write facility
2023-11-24 23:19 Re: Relation bulk write facility Heikki Linnakangas <[email protected]>
@ 2024-01-09 06:50 ` vignesh C <[email protected]>
1 sibling, 0 replies; 149+ messages in thread
From: vignesh C @ 2024-01-09 06:50 UTC (permalink / raw)
To: Heikki Linnakangas <[email protected]>; +Cc: Andres Freund <[email protected]>; pgsql-hackers
On Sat, 25 Nov 2023 at 06:49, Heikki Linnakangas <[email protected]> wrote:
>
> On 19/11/2023 02:04, Andres Freund wrote:
> > On 2023-11-17 11:37:21 +0100, Heikki Linnakangas wrote:
> >> The new facility makes it easier to optimize bulk loading, as the
> >> logic for buffering, WAL-logging, and syncing the relation only needs
> >> to be implemented once. It's also less error-prone: We have had a
> >> number of bugs in how a relation is fsync'd - or not - at the end of a
> >> bulk loading operation. By centralizing that logic to one place, we
> >> only need to write it correctly once.
> >
> > One thing I'd like to use the centralized handling for is to track such
> > writes in pg_stat_io. I don't mean as part of the initial patch, just that
> > that's another reason I like the facility.
>
> Oh I didn't realize they're not counted at the moment.
>
> >> + bulkw = bulkw_start_smgr(dst, forkNum, use_wal);
> >> +
> >> nblocks = smgrnblocks(src, forkNum);
> >>
> >> for (blkno = 0; blkno < nblocks; blkno++)
> >> {
> >> + Page page;
> >> +
> >> /* If we got a cancel signal during the copy of the data, quit */
> >> CHECK_FOR_INTERRUPTS();
> >>
> >> - smgrread(src, forkNum, blkno, buf.data);
> >> + page = bulkw_alloc_buf(bulkw);
> >> + smgrread(src, forkNum, blkno, page);
> >>
> >> if (!PageIsVerifiedExtended(page, blkno,
> >> PIV_LOG_WARNING | PIV_REPORT_STAT))
> >> @@ -511,30 +514,9 @@ RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
> >> * page this is, so we have to log the full page including any unused
> >> * space.
> >> */
> >> - if (use_wal)
> >> - log_newpage(&dst->smgr_rlocator.locator, forkNum, blkno, page, false);
> >> -
> >> - PageSetChecksumInplace(page, blkno);
> >> -
> >> - /*
> >> - * Now write the page. We say skipFsync = true because there's no
> >> - * need for smgr to schedule an fsync for this write; we'll do it
> >> - * ourselves below.
> >> - */
> >> - smgrextend(dst, forkNum, blkno, buf.data, true);
> >> + bulkw_write(bulkw, blkno, page, false);
> >
> > I wonder if bulkw_alloc_buf() is a good name - if you naively read this
> > change, it looks like it'll just leak memory. It also might be taken to be
> > valid until freed, which I don't think is the case?
>
> Yeah, I'm not very happy with this interface. The model is that you get
> a buffer to write to by calling bulkw_alloc_buf(). Later, you hand it
> over to bulkw_write(), which takes ownership of it and frees it later.
> There is no other function to free it, although currently the buffer is
> just palloc'd so you could call pfree on it.
>
> However, I'd like to not expose that detail to the callers. I'm
> imagining that in the future we might optimize further, by having a
> larger e.g. 1 MB buffer, and carve the 8kB blocks from that. Then
> opportunistically, if you fill the buffers sequentially, bulk_write.c
> could do one smgrextend() to write the whole 1 MB chunk.
>
> I renamed it to bulkw_get_buf() now, and made it return a new
> BulkWriteBuffer typedef instead of a plain Page. The point of the new
> typedef is to distinguish a buffer returned by bulkw_get_buf() from a
> Page or char[BLCKSZ] that you might palloc on your own. That indeed
> revealed some latent bugs in gistbuild.c where I had mixed up buffers
> returned by bulkw_alloc_buf() and palloc'd buffers.
>
> (The previous version of this patch called a different struct
> BulkWriteBuffer, but I renamed that to PendingWrite; see below. Don't be
> confused!)
>
> I think this helps a little, but I'm still not very happy with it. I'll
> give it some more thought after sleeping over it, but in the meanwhile,
> I'm all ears for suggestions.
>
> >> +/*-------------------------------------------------------------------------
> >> + *
> >> + * bulk_write.c
> >> + * Efficiently and reliably populate a new relation
> >> + *
> >> + * The assumption is that no other backends access the relation while we are
> >> + * loading it, so we can take some shortcuts. Alternatively, you can use the
> >> + * buffer manager as usual, if performance is not critical, but you must not
> >> + * mix operations through the buffer manager and the bulk loading interface at
> >> + * the same time.
> >
> > From "Alternatively" onward this is is somewhat confusing.
>
> Rewrote that to just "Do not mix operations through the regular buffer
> manager and the bulk loading interface!"
>
> >> + * One tricky point is that because we bypass the buffer manager, we need to
> >> + * register the relation for fsyncing at the next checkpoint ourselves, and
> >> + * make sure that the relation is correctly fsync by us or the checkpointer
> >> + * even if a checkpoint happens concurrently.
> >
> > "fsync'ed" or such? Otherwise this reads awkwardly for me.
>
> Yep, fixed.
>
> >> +typedef struct BulkWriteBuffer
> >> +{
> >> + Page page;
> >> + BlockNumber blkno;
> >> + bool page_std;
> >> + int16 order;
> >> +} BulkWriteBuffer;
> >> +
> >
> > The name makes it sound like this struct itself contains a buffer - but it's
> > just pointing to one. *BufferRef or such maybe?
> >
> > I was wondering how you dealt with the alignment of buffers given the struct
> > definition, which is what lead me to look at this...
>
> I renamed this to PendingWrite, and the field that holds these
> "pending_writes". Think of it as a queue of writes that haven't been
> performed yet.
>
> >> +/*
> >> + * Bulk writer state for one relation fork.
> >> + */
> >> +typedef struct BulkWriteState
> >> +{
> >> + /* Information about the target relation we're writing */
> >> + SMgrRelation smgr;
> >
> > Isn't there a danger of this becoming a dangling pointer? At least until
> > https://postgr.es/m/CA%2BhUKGJ8NTvqLHz6dqbQnt2c8XCki4r2QvXjBQcXpVwxTY_pvA%40mail.gmail.com
> > is merged?
>
> Good point. I just added a FIXME comment to remind about that, hoping
> that that patch gets merged soon. If not, I'll come up with a different fix.
>
> >> + ForkNumber forknum;
> >> + bool use_wal;
> >> +
> >> + /* We keep several pages buffered, and WAL-log them in batches */
> >> + int nbuffered;
> >> + BulkWriteBuffer buffers[MAX_BUFFERED_PAGES];
> >> +
> >> + /* Current size of the relation */
> >> + BlockNumber pages_written;
> >> +
> >> + /* The RedoRecPtr at the time that the bulk operation started */
> >> + XLogRecPtr start_RedoRecPtr;
> >> +
> >> + Page zeropage; /* workspace for filling zeroes */
> >
> > We really should just have one such page in shared memory somewhere... For WAL
> > writes as well.
> >
> > But until then - why do you allocate the page? Seems like we could just use a
> > static global variable?
>
> I made it a static global variable for now. (The palloc way was copied
> over from nbtsort.c)
>
> >> +/*
> >> + * Write all buffered pages to disk.
> >> + */
> >> +static void
> >> +bulkw_flush(BulkWriteState *bulkw)
> >> +{
> >> + int nbuffered = bulkw->nbuffered;
> >> + BulkWriteBuffer *buffers = bulkw->buffers;
> >> +
> >> + if (nbuffered == 0)
> >> + return;
> >> +
> >> + if (nbuffered > 1)
> >> + {
> >> + int o;
> >> +
> >> + qsort(buffers, nbuffered, sizeof(BulkWriteBuffer), buffer_cmp);
> >> +
> >> + /*
> >> + * Eliminate duplicates, keeping the last write of each block.
> >> + * (buffer_cmp uses 'order' as the last sort key)
> >> + */
> >
> > Huh - which use cases would actually cause duplicate writes?
>
> Hmm, nothing anymore I guess. Many AMs used to write zero pages as a
> placeholder and come back to fill them in later, but now that
> bulk_write.c handles that,
>
> Removed that, and replaced it with with an assertion in buffer_cmp()
> that there are no duplicates.
There are few compilation errors reported by CFBot at [1], patch needs
to be rebased:
[02:38:12.675] In file included from ../../../../src/include/postgres.h:45,
[02:38:12.675] from nbtsort.c:41:
[02:38:12.675] nbtsort.c: In function ‘_bt_load’:
[02:38:12.675] nbtsort.c:1309:57: error: ‘BTPageState’ has no member
named ‘btps_page’
[02:38:12.675] 1309 | Assert(dstate->maxpostingsize <=
BTMaxItemSize(state->btps_page) &&
[02:38:12.675] | ^~
[02:38:12.675] ../../../../src/include/c.h:864:9: note: in definition
of macro ‘Assert’
[02:38:12.675] 864 | if (!(condition)) \
[02:38:12.675] | ^~~~~~~~~
[02:38:12.675] ../../../../src/include/c.h:812:29: note: in expansion
of macro ‘TYPEALIGN_DOWN’
[02:38:12.675] 812 | #define MAXALIGN_DOWN(LEN)
TYPEALIGN_DOWN(MAXIMUM_ALIGNOF, (LEN))
[02:38:12.675] | ^~~~~~~~~~~~~~
[02:38:12.675] ../../../../src/include/access/nbtree.h:165:3: note: in
expansion of macro ‘MAXALIGN_DOWN’
[02:38:12.675] 165 | (MAXALIGN_DOWN((PageGetPageSize(page) - \
[1] - https://cirrus-ci.com/task/5299954164432896
Regards,
Vignesh
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: gcc 15 "array subscript 0" warning at level -O3
@ 2025-06-04 19:00 Andres Freund <[email protected]>
2025-06-05 19:50 ` Re: gcc 15 "array subscript 0" warning at level -O3 Tom Lane <[email protected]>
2025-07-02 14:13 ` Re: gcc 15 "array subscript 0" warning at level -O3 jian he <[email protected]>
0 siblings, 2 replies; 149+ messages in thread
From: Andres Freund @ 2025-06-04 19:00 UTC (permalink / raw)
To: Tom Lane <[email protected]>; +Cc: [email protected]
Hi,
On 2025-04-25 15:58:29 -0400, Andres Freund wrote:
> On 2025-04-25 13:37:15 -0400, Tom Lane wrote:
> > Buildfarm member serinus has been producing the identical warning for
> > some time. I'd been ignoring that because it runs "experimental gcc",
> > but I guess the experiment has leaked out to production distros.
> >
> > What seems to be happening here is that after inlining
> > assign_simple_var into exec_set_found, the compiler decides that
> > "newvalue" might be zero (since it's a BoolGetDatum result),
> > and then it warns -- in a rather strange way -- about the
> > potential null dereference.
>
> I don't think it actually is complaining about a null dereference - it thinks
> we're interpreting a boolean as a pointer (for which it obviously is not wide
> enough)
>
>
> > The dereference is not reachable
> > because of the preceding "var->datatype->typlen == -1" check,
> > but that's not stopping the optimizer from bitching.
>
> > I experimented with modifying exec_set_found thus:
> >
> > var = (PLpgSQL_var *) (estate->datums[estate->found_varno]);
> > + Assert(var->datatype->typlen == 1);
> > assign_simple_var(estate, var, BoolGetDatum(state), false, false);
> >
> > which should be OK since we're expecting the "found" variable to
> > be boolean. That does silence the warning, but of course only
> > in --enable-cassert builds.
>
> One way to address this is outlined here:
>
> https://postgr.es/m/20230316172818.x6375uvheom3ibt2%40awork3.anarazel.de
> https://postgr.es/m/20240207203138.sknifhlppdtgtxnk%40awork3.anarazel.de
>
> I've been wondering about adding wrapping something like that in a
> pg_assume(expr) or such.
I've been once more annoyed by this warning. Here's a prototype for the
approach outlined above.
Greetings,
Andres Freund
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: gcc 15 "array subscript 0" warning at level -O3
2025-06-04 19:00 Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
@ 2025-06-05 19:50 ` Tom Lane <[email protected]>
2025-07-09 23:20 ` Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
1 sibling, 1 reply; 149+ messages in thread
From: Tom Lane @ 2025-06-05 19:50 UTC (permalink / raw)
To: Andres Freund <[email protected]>; +Cc: [email protected]
Andres Freund <[email protected]> writes:
>> I've been wondering about adding wrapping something like that in a
>> pg_assume(expr) or such.
> I've been once more annoyed by this warning. Here's a prototype for the
> approach outlined above.
Looks plausible by eyeball. I did notice a typo in the comment:
+ * pg_assume(expr) stats that we assume `expr` to evaluate to true. In assert
s/stats/states/, I think you meant.
regards, tom lane
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: gcc 15 "array subscript 0" warning at level -O3
2025-06-04 19:00 Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
2025-06-05 19:50 ` Re: gcc 15 "array subscript 0" warning at level -O3 Tom Lane <[email protected]>
@ 2025-07-09 23:20 ` Andres Freund <[email protected]>
0 siblings, 0 replies; 149+ messages in thread
From: Andres Freund @ 2025-07-09 23:20 UTC (permalink / raw)
To: Tom Lane <[email protected]>; +Cc: [email protected]
Hi,
On 2025-06-05 15:50:48 -0400, Tom Lane wrote:
> Andres Freund <[email protected]> writes:
> >> I've been wondering about adding wrapping something like that in a
> >> pg_assume(expr) or such.
>
> > I've been once more annoyed by this warning. Here's a prototype for the
> > approach outlined above.
>
> Looks plausible by eyeball. I did notice a typo in the comment:
>
> + * pg_assume(expr) stats that we assume `expr` to evaluate to true. In assert
>
> s/stats/states/, I think you meant.
Thanks. I pushed it with that tweak and a bit of minor comment burnishing.
Glad to see the last of that warning.
Greetings,
Andres Freund
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: gcc 15 "array subscript 0" warning at level -O3
2025-06-04 19:00 Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
@ 2025-07-02 14:13 ` jian he <[email protected]>
2025-07-09 23:21 ` Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
1 sibling, 1 reply; 149+ messages in thread
From: jian he @ 2025-07-02 14:13 UTC (permalink / raw)
To: Andres Freund <[email protected]>; +Cc: Tom Lane <[email protected]>; [email protected]
On Thu, Jun 5, 2025 at 3:00 AM Andres Freund <[email protected]> wrote:
>
> > > The dereference is not reachable
> > > because of the preceding "var->datatype->typlen == -1" check,
> > > but that's not stopping the optimizer from bitching.
> >
> > > I experimented with modifying exec_set_found thus:
> > >
> > > var = (PLpgSQL_var *) (estate->datums[estate->found_varno]);
> > > + Assert(var->datatype->typlen == 1);
> > > assign_simple_var(estate, var, BoolGetDatum(state), false, false);
> > >
> > > which should be OK since we're expecting the "found" variable to
> > > be boolean. That does silence the warning, but of course only
> > > in --enable-cassert builds.
> >
> > One way to address this is outlined here:
> >
> > https://postgr.es/m/20230316172818.x6375uvheom3ibt2%40awork3.anarazel.de
> > https://postgr.es/m/20240207203138.sknifhlppdtgtxnk%40awork3.anarazel.de
> >
> > I've been wondering about adding wrapping something like that in a
> > pg_assume(expr) or such.
>
> I've been once more annoyed by this warning. Here's a prototype for the
> approach outlined above.
>
I can confirm the warning disappears when using gcc-14.0 compile
source code with the attached patch.
I didn't review it though.
I didn’t find this in the CommitFest, so I added an entry [1] to make sure it
doesn’t get forgotten...
[1]: https://commitfest.postgresql.org/patch/5888/
^ permalink raw reply [nested|flat] 149+ messages in thread
* Re: gcc 15 "array subscript 0" warning at level -O3
2025-06-04 19:00 Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
2025-07-02 14:13 ` Re: gcc 15 "array subscript 0" warning at level -O3 jian he <[email protected]>
@ 2025-07-09 23:21 ` Andres Freund <[email protected]>
0 siblings, 0 replies; 149+ messages in thread
From: Andres Freund @ 2025-07-09 23:21 UTC (permalink / raw)
To: jian he <[email protected]>; +Cc: Tom Lane <[email protected]>; [email protected]
Hi,
On 2025-07-02 22:13:17 +0800, jian he wrote:
> On Thu, Jun 5, 2025 at 3:00 AM Andres Freund <[email protected]> wrote:
> > I've been once more annoyed by this warning. Here's a prototype for the
> > approach outlined above.
> >
>
> I can confirm the warning disappears when using gcc-14.0 compile
> source code with the attached patch.
> I didn't review it though.
> I didn’t find this in the CommitFest, so I added an entry [1] to make sure it
> doesn’t get forgotten...
Thanks. Pushed it now and closed the CF entry.
Greetings,
Andres Freund
^ permalink raw reply [nested|flat] 149+ messages in thread
end of thread, other threads:[~2025-07-09 23:21 UTC | newest]
Thread overview: 149+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v2 2/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v11] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v3 1/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v3 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/2] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v10 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v11] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v5 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v7 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v1 1/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v8 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 3/3] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v4 1/5] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v6 2/7] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2020-06-07 21:58 [PATCH v9 2/8] Implement CLUSTER of partitioned table.. Justin Pryzby <[email protected]>
2023-11-24 23:19 Re: Relation bulk write facility Heikki Linnakangas <[email protected]>
2023-12-14 13:02 ` Re: Relation bulk write facility Heikki Linnakangas <[email protected]>
2024-01-09 06:50 ` Re: Relation bulk write facility vignesh C <[email protected]>
2025-06-04 19:00 Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
2025-06-05 19:50 ` Re: gcc 15 "array subscript 0" warning at level -O3 Tom Lane <[email protected]>
2025-07-09 23:20 ` Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
2025-07-02 14:13 ` Re: gcc 15 "array subscript 0" warning at level -O3 jian he <[email protected]>
2025-07-09 23:21 ` Re: gcc 15 "array subscript 0" warning at level -O3 Andres Freund <[email protected]>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox