TABLESAMPLE, SQL Standard and extensible

Add a TABLESAMPLE clause to SELECT statements that allows
user to specify random BERNOULLI sampling or block level
SYSTEM sampling. Implementation allows for extensible
sampling functions to be written, using a standard API.
Basic version follows SQLStandard exactly. Usable
concrete use cases for the sampling API follow in later
commits.

Petr Jelinek

Reviewed by Michael Paquier and Simon Riggs

20 files changed, 284 insertions, 3 deletions

diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 49c8ca4d66..eec7c95b21 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -114,8 +114,12 @@ extern HeapScanDesc heap_beginscan_strat(Relation relation, Snapshot snapshot,
 					 bool allow_strat, bool allow_sync);
 extern HeapScanDesc heap_beginscan_bm(Relation relation, Snapshot snapshot,
 				  int nkeys, ScanKey key);
+extern HeapScanDesc heap_beginscan_sampling(Relation relation,
+						Snapshot snapshot, int nkeys, ScanKey key,
+						bool allow_strat, bool allow_pagemode);
 extern void heap_setscanlimits(HeapScanDesc scan, BlockNumber startBlk,
 		   BlockNumber endBlk);
+extern void heapgetpage(HeapScanDesc scan, BlockNumber page);
 extern void heap_rescan(HeapScanDesc scan, ScanKey key);
 extern void heap_endscan(HeapScanDesc scan);
 extern HeapTuple heap_getnext(HeapScanDesc scan, ScanDirection direction);
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 5a0d724aca..1b9b299395 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -29,6 +29,7 @@ typedef struct HeapScanDescData
 	int			rs_nkeys;		/* number of scan keys */
 	ScanKey		rs_key;			/* array of scan key descriptors */
 	bool		rs_bitmapscan;	/* true if this is really a bitmap scan */
+	bool		rs_samplescan;	/* true if this is really a sample scan */
 	bool		rs_pageatatime; /* verify visibility page-at-a-time? */
 	bool		rs_allow_strat; /* allow or disallow use of access strategy */
 	bool		rs_allow_sync;	/* allow or disallow use of syncscan */
diff --git a/src/include/access/tablesample.h b/src/include/access/tablesample.h
new file mode 100644
index 0000000000..222fa8d556
--- /dev/null
+++ b/src/include/access/tablesample.h
@@ -0,0 +1,60 @@
+/*-------------------------------------------------------------------------
+ *
+ * tablesample.h
+ *        Public header file for TABLESAMPLE clause interface
+ *
+ *
+ * Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/access/tablesample.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef TABLESAMPLE_H
+#define TABLESAMPLE_H
+
+#include "access/relscan.h"
+#include "executor/executor.h"
+
+typedef struct TableSampleDesc {
+	HeapScanDesc	heapScan;
+	TupleDesc		tupDesc;	/* Mostly useful for tsmexaminetuple */
+
+	void		   *tsmdata;	/* private method data */
+
+	/* These point to he function of the TABLESAMPLE Method. */
+	FmgrInfo		tsminit;
+	FmgrInfo		tsmnextblock;
+	FmgrInfo		tsmnexttuple;
+	FmgrInfo		tsmexaminetuple;
+	FmgrInfo		tsmreset;
+	FmgrInfo		tsmend;
+} TableSampleDesc;
+
+
+extern TableSampleDesc *tablesample_init(SampleScanState *scanstate,
+										 TableSampleClause *tablesample);
+extern HeapTuple tablesample_getnext(TableSampleDesc *desc);
+extern void tablesample_reset(TableSampleDesc *desc);
+extern void tablesample_end(TableSampleDesc *desc);
+extern HeapTuple tablesample_source_getnext(TableSampleDesc *desc);
+extern HeapTuple tablesample_source_gettup(TableSampleDesc *desc, ItemPointer tid,
+										   bool *visible);
+
+extern Datum tsm_system_init(PG_FUNCTION_ARGS);
+extern Datum tsm_system_nextblock(PG_FUNCTION_ARGS);
+extern Datum tsm_system_nexttuple(PG_FUNCTION_ARGS);
+extern Datum tsm_system_end(PG_FUNCTION_ARGS);
+extern Datum tsm_system_reset(PG_FUNCTION_ARGS);
+extern Datum tsm_system_cost(PG_FUNCTION_ARGS);
+
+extern Datum tsm_bernoulli_init(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_nextblock(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_nexttuple(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_end(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_reset(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_cost(PG_FUNCTION_ARGS);
+
+
+#endif
diff --git a/src/include/catalog/indexing.h b/src/include/catalog/indexing.h
index 71e0010a6f..f20567ed5f 100644
--- a/src/include/catalog/indexing.h
+++ b/src/include/catalog/indexing.h
@@ -316,6 +316,11 @@ DECLARE_UNIQUE_INDEX(pg_replication_origin_roiident_index, 6001, on pg_replicati
 DECLARE_UNIQUE_INDEX(pg_replication_origin_roname_index, 6002, on pg_replication_origin using btree(roname varchar_pattern_ops));
 #define ReplicationOriginNameIndex 6002
 
+DECLARE_UNIQUE_INDEX(pg_tablesample_method_name_index, 3331, on pg_tablesample_method using btree(tsmname name_ops));
+#define TableSampleMethodNameIndexId  3331
+DECLARE_UNIQUE_INDEX(pg_tablesample_method_oid_index, 3332, on pg_tablesample_method using btree(oid oid_ops));
+#define TableSampleMethodOidIndexId  3332
+
 /* last step of initialization script: build the indexes declared above */
 BUILD_INDICES
 
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index 1c9edbc3b3..c2185bd9ad 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -5297,6 +5297,33 @@ DESCR("get an individual replication origin's replication progress");
 DATA(insert OID = 6014 ( pg_show_replication_origin_status PGNSP PGUID 12 1 100 0 0 f f f f f t v 0 0 2249 "" "{26,25,3220,3220}" "{o,o,o,o}" "{local_id, external_id, remote_lsn, local_lsn}" _null_ _null_ pg_show_replication_origin_status _null_ _null_ _null_ ));
 DESCR("get progress for all replication origins");
 
+/* tablesample */
+DATA(insert OID = 3335 (  tsm_system_init		PGNSP PGUID 12 1 0 0 0 f f f f t f v 3 0 2278 "2281 23 700" _null_ _null_ _null_ _null_	_null_ tsm_system_init _null_ _null_ _null_ ));
+DESCR("tsm_system_init(internal)");
+DATA(insert OID = 3336 (  tsm_system_nextblock	PGNSP PGUID 12 1 0 0 0 f f f f t f v 2 0 23 "2281 16" _null_ _null_ _null_ _null_ _null_ tsm_system_nextblock _null_ _null_ _null_ ));
+DESCR("tsm_system_nextblock(internal)");
+DATA(insert OID = 3337 (  tsm_system_nexttuple	PGNSP PGUID 12 1 0 0 0 f f f f t f v 4 0 21 "2281 23 21 16" _null_ _null_ _null_ _null_	_null_ tsm_system_nexttuple _null_ _null_ _null_ ));
+DESCR("tsm_system_nexttuple(internal)");
+DATA(insert OID = 3338 (  tsm_system_end		PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 2278 "2281" _null_ _null_ _null_ _null_ _null_ tsm_system_end _null_ _null_ _null_ ));
+DESCR("tsm_system_end(internal)");
+DATA(insert OID = 3339 (  tsm_system_reset		PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 2278 "2281" _null_ _null_ _null_ _null_ _null_ tsm_system_reset _null_ _null_ _null_ ));
+DESCR("tsm_system_reset(internal)");
+DATA(insert OID = 3340 (  tsm_system_cost		PGNSP PGUID 12 1 0 0 0 f f f f t f v 7 0 2278 "2281 2281 2281 2281 2281 2281 2281" _null_ _null_ _null_ _null_ _null_ tsm_system_cost _null_ _null_ _null_ ));
+DESCR("tsm_system_cost(internal)");
+
+DATA(insert OID = 3341 (  tsm_bernoulli_init		PGNSP PGUID 12 1 0 0 0 f f f f t f v 3 0 2278 "2281 23 700" _null_ _null_ _null_ _null_	_null_ tsm_bernoulli_init _null_ _null_ _null_ ));
+DESCR("tsm_bernoulli_init(internal)");
+DATA(insert OID = 3342 (  tsm_bernoulli_nextblock	PGNSP PGUID 12 1 0 0 0 f f f f t f v 2 0 23 "2281 16" _null_ _null_ _null_ _null_ _null_ tsm_bernoulli_nextblock _null_ _null_ _null_ ));
+DESCR("tsm_bernoulli_nextblock(internal)");
+DATA(insert OID = 3343 (  tsm_bernoulli_nexttuple	PGNSP PGUID 12 1 0 0 0 f f f f t f v 4 0 21 "2281 23 21 16" _null_ _null_ _null_ _null_	_null_ tsm_bernoulli_nexttuple _null_ _null_ _null_ ));
+DESCR("tsm_bernoulli_nexttuple(internal)");
+DATA(insert OID = 3344 (  tsm_bernoulli_end			PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 2278 "2281" _null_ _null_ _null_ _null_ _null_ tsm_bernoulli_end _null_ _null_ _null_ ));
+DESCR("tsm_bernoulli_end(internal)");
+DATA(insert OID = 3345 (  tsm_bernoulli_reset		PGNSP PGUID 12 1 0 0 0 f f f f t f v 1 0 2278 "2281" _null_ _null_ _null_ _null_ _null_ tsm_bernoulli_reset _null_ _null_ _null_ ));
+DESCR("tsm_bernoulli_reset(internal)");
+DATA(insert OID = 3346 (  tsm_bernoulli_cost		PGNSP PGUID 12 1 0 0 0 f f f f t f v 7 0 2278 "2281 2281 2281 2281 2281 2281 2281" _null_ _null_ _null_ _null_ _null_ tsm_bernoulli_cost _null_ _null_ _null_ ));
+DESCR("tsm_bernoulli_cost(internal)");
+
 /*
  * Symbolic values for provolatile column: these indicate whether the result
  * of a function is dependent *only* on the values of its explicit arguments,
diff --git a/src/include/catalog/pg_tablesample_method.h b/src/include/catalog/pg_tablesample_method.h
new file mode 100644
index 0000000000..968d1e696a
--- /dev/null
+++ b/src/include/catalog/pg_tablesample_method.h
@@ -0,0 +1,78 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_tablesample_method.h
+ *	  definition of the table scan methods.
+ *
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/catalog/pg_tablesample_method.h
+ *
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_TABLESAMPLE_METHOD_H
+#define PG_TABLESAMPLE_METHOD_H
+
+#include "catalog/genbki.h"
+#include "catalog/objectaddress.h"
+
+/* ----------------
+ *		pg_tablesample_method definition.  cpp turns this into
+ *		typedef struct FormData_pg_tablesample_method
+ * ----------------
+ */
+#define TableSampleMethodRelationId	3330
+
+CATALOG(pg_tablesample_method,3330)
+{
+	NameData	tsmname;		/* tablesample method name */
+	bool		tsmseqscan;		/* does this method scan whole table sequentially? */
+	bool		tsmpagemode;	/* does this method scan page at a time? */
+	regproc		tsminit;		/* init scan function */
+	regproc		tsmnextblock;	/* function returning next block to sample
+								   or InvalidBlockOffset if finished */
+	regproc		tsmnexttuple;	/* function returning next tuple offset from current block
+								   or InvalidOffsetNumber if end of the block was reacher */
+	regproc		tsmexaminetuple;	/* optional function which can examine tuple contents and
+								   decide if tuple should be returned or not */
+	regproc		tsmend;			/* end scan function*/
+	regproc		tsmreset;		/* reset state - used by rescan */
+	regproc		tsmcost;		/* costing function */
+} FormData_pg_tablesample_method;
+
+/* ----------------
+ *		Form_pg_tablesample_method corresponds to a pointer to a tuple with
+ *		the format of pg_tablesample_method relation.
+ * ----------------
+ */
+typedef FormData_pg_tablesample_method *Form_pg_tablesample_method;
+
+/* ----------------
+ *		compiler constants for pg_tablesample_method
+ * ----------------
+ */
+#define Natts_pg_tablesample_method					10
+#define Anum_pg_tablesample_method_tsmname			1
+#define Anum_pg_tablesample_method_tsmseqscan		2
+#define Anum_pg_tablesample_method_tsmpagemode		3
+#define Anum_pg_tablesample_method_tsminit			4
+#define Anum_pg_tablesample_method_tsmnextblock		5
+#define Anum_pg_tablesample_method_tsmnexttuple		6
+#define Anum_pg_tablesample_method_tsmexaminetuple	7
+#define Anum_pg_tablesample_method_tsmend			8
+#define Anum_pg_tablesample_method_tsmreset			9
+#define Anum_pg_tablesample_method_tsmcost			10
+
+/* ----------------
+ *		initial contents of pg_tablesample_method
+ * ----------------
+ */
+
+DATA(insert OID = 3333 ( system false true tsm_system_init tsm_system_nextblock tsm_system_nexttuple - tsm_system_end tsm_system_reset tsm_system_cost ));
+DESCR("SYSTEM table sampling method");
+DATA(insert OID = 3334 ( bernoulli true false tsm_bernoulli_init tsm_bernoulli_nextblock tsm_bernoulli_nexttuple - tsm_bernoulli_end tsm_bernoulli_reset tsm_bernoulli_cost ));
+DESCR("BERNOULLI table sampling method");
+
+#endif   /* PG_TABLESAMPLE_METHOD_H */
diff --git a/src/include/executor/nodeSamplescan.h b/src/include/executor/nodeSamplescan.h
new file mode 100644
index 0000000000..4b769daec8
--- /dev/null
+++ b/src/include/executor/nodeSamplescan.h
@@ -0,0 +1,24 @@
+/*-------------------------------------------------------------------------
+ *
+ * nodeSamplescan.h
+ *
+ *
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/executor/nodeSamplescan.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef NODESAMPLESCAN_H
+#define NODESAMPLESCAN_H
+
+#include "nodes/execnodes.h"
+
+extern SampleScanState *ExecInitSampleScan(SampleScan *node, EState *estate, int eflags);
+extern TupleTableSlot *ExecSampleScan(SampleScanState *node);
+extern void ExecEndSampleScan(SampleScanState *node);
+extern void ExecReScanSampleScan(SampleScanState *node);
+
+#endif   /* NODESAMPLESCAN_H */
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index fcfe1107f9..972368019a 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -1238,6 +1238,15 @@ typedef struct ScanState
 typedef ScanState SeqScanState;
 
 /*
+ * SampleScan
+ */
+typedef struct SampleScanState
+{
+	ScanState	ss;
+	struct TableSampleDesc *tsdesc;
+} SampleScanState;
+
+/*
  * These structs store information about index quals that don't have simple
  * constant right-hand sides.  See comments for ExecIndexBuildScanKeys()
  * for discussion.
diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h
index 768f413a45..8b275f6e26 100644
--- a/src/include/nodes/nodes.h
+++ b/src/include/nodes/nodes.h
@@ -61,6 +61,7 @@ typedef enum NodeTag
 	T_ValuesScan,
 	T_CteScan,
 	T_WorkTableScan,
+	T_SampleScan,
 	T_ForeignScan,
 	T_CustomScan,
 	T_Join,
@@ -97,6 +98,7 @@ typedef enum NodeTag
 	T_BitmapOrState,
 	T_ScanState,
 	T_SeqScanState,
+	T_SampleScanState,
 	T_IndexScanState,
 	T_IndexOnlyScanState,
 	T_BitmapIndexScanState,
@@ -419,6 +421,8 @@ typedef enum NodeTag
 	T_OnConflictClause,
 	T_CommonTableExpr,
 	T_RoleSpec,
+	T_RangeTableSample,
+	T_TableSampleClause,
 
 	/*
 	 * TAGS FOR REPLICATION GRAMMAR PARSE NODES (replnodes.h)
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 053f1b0121..6723f46f3f 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -336,6 +336,26 @@ typedef struct FuncCall
 } FuncCall;
 
 /*
+ * TableSampleClause - a sampling method information
+ */
+typedef struct TableSampleClause
+{
+	NodeTag		type;
+	Oid			tsmid;
+	bool		tsmseqscan;
+	bool		tsmpagemode;
+	Oid			tsminit;
+	Oid			tsmnextblock;
+	Oid			tsmnexttuple;
+	Oid			tsmexaminetuple;
+	Oid			tsmend;
+	Oid			tsmreset;
+	Oid			tsmcost;
+	Node	   *repeatable;
+	List	   *args;
+} TableSampleClause;
+
+/*
  * A_Star - '*' representing all columns of a table or compound field
  *
  * This can appear within ColumnRef.fields, A_Indirection.indirection, and
@@ -536,6 +556,22 @@ typedef struct RangeFunction
 } RangeFunction;
 
 /*
+ * RangeTableSample - represents <table> TABLESAMPLE <method> (<params>) REPEATABLE (<num>)
+ *
+ * SQL Standard specifies only one parameter which is percentage. But we allow
+ * custom tablesample methods which may need different input arguments so we
+ * accept list of arguments.
+ */
+typedef struct RangeTableSample
+{
+	NodeTag		type;
+	RangeVar   *relation;
+	char	   *method;		/* sampling method */
+	Node	   *repeatable;
+	List	   *args;		/* arguments for sampling method */
+} RangeTableSample;
+
+/*
  * ColumnDef - column definition (used in various creates)
  *
  * If the column has a default value, we may have the value expression
@@ -772,6 +808,7 @@ typedef struct RangeTblEntry
 	 */
 	Oid			relid;			/* OID of the relation */
 	char		relkind;		/* relation kind (see pg_class.relkind) */
+	TableSampleClause	*tablesample;	/* sampling method and parameters */
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index 65f71d8170..4e655b0e6c 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -287,6 +287,12 @@ typedef struct Scan
 typedef Scan SeqScan;
 
 /* ----------------
+ *		table sample scan node
+ * ----------------
+ */
+typedef Scan SampleScan;
+
+/* ----------------
  *		index scan node
  *
  * indexqualorig is an implicitly-ANDed list of index qual expressions, each
diff --git a/src/include/optimizer/cost.h b/src/include/optimizer/cost.h
index 9c2000b15a..24003ae359 100644
--- a/src/include/optimizer/cost.h
+++ b/src/include/optimizer/cost.h
@@ -68,6 +68,7 @@ extern double index_pages_fetched(double tuples_fetched, BlockNumber pages,
 					double index_pages, PlannerInfo *root);
 extern void cost_seqscan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
 			 ParamPathInfo *param_info);
+extern void cost_samplescan(Path *path, PlannerInfo *root, RelOptInfo *baserel);
 extern void cost_index(IndexPath *path, PlannerInfo *root,
 		   double loop_count);
 extern void cost_bitmap_heap_scan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h
index 9923f0eb3e..89c8deda95 100644
--- a/src/include/optimizer/pathnode.h
+++ b/src/include/optimizer/pathnode.h
@@ -32,6 +32,8 @@ extern bool add_path_precheck(RelOptInfo *parent_rel,
 
 extern Path *create_seqscan_path(PlannerInfo *root, RelOptInfo *rel,
 					Relids required_outer);
+extern Path *create_samplescan_path(PlannerInfo *root, RelOptInfo *rel,
+									Relids required_outer);
 extern IndexPath *create_index_path(PlannerInfo *root,
 				  IndexOptInfo *index,
 				  List *indexclauses,
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index faea99108c..7d5f857ae5 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -368,6 +368,7 @@ PG_KEYWORD("sysid", SYSID, UNRESERVED_KEYWORD)
 PG_KEYWORD("system", SYSTEM_P, UNRESERVED_KEYWORD)
 PG_KEYWORD("table", TABLE, RESERVED_KEYWORD)
 PG_KEYWORD("tables", TABLES, UNRESERVED_KEYWORD)
+PG_KEYWORD("tablesample", TABLESAMPLE, TYPE_FUNC_NAME_KEYWORD)
 PG_KEYWORD("tablespace", TABLESPACE, UNRESERVED_KEYWORD)
 PG_KEYWORD("temp", TEMP, UNRESERVED_KEYWORD)
 PG_KEYWORD("template", TEMPLATE, UNRESERVED_KEYWORD)
diff --git a/src/include/parser/parse_func.h b/src/include/parser/parse_func.h
index 32646918e2..40c007c35f 100644
--- a/src/include/parser/parse_func.h
+++ b/src/include/parser/parse_func.h
@@ -33,6 +33,11 @@ typedef enum
 extern Node *ParseFuncOrColumn(ParseState *pstate, List *funcname, List *fargs,
 				  FuncCall *fn, int location);
 
+extern TableSampleClause *ParseTableSample(ParseState *pstate,
+										   char *samplemethod,
+										   Node *repeatable, List *args,
+										   int location);
+
 extern FuncDetailCode func_get_detail(List *funcname,
 				List *fargs, List *fargnames,
 				int nargs, Oid *argtypes,
diff --git a/src/include/port.h b/src/include/port.h
index 3787cbfb76..71113c0394 100644
--- a/src/include/port.h
+++ b/src/include/port.h
@@ -357,6 +357,10 @@ extern off_t ftello(FILE *stream);
 #endif
 #endif
 
+#define RAND48_SEED_0	(0x330e)
+#define RAND48_SEED_1	(0xabcd)
+#define RAND48_SEED_2	(0x1234)
+
 extern double pg_erand48(unsigned short xseed[3]);
 extern long pg_lrand48(void);
 extern void pg_srand48(long seed);
diff --git a/src/include/utils/lsyscache.h b/src/include/utils/lsyscache.h
index ffbaa61e5e..e2e5734ea7 100644
--- a/src/include/utils/lsyscache.h
+++ b/src/include/utils/lsyscache.h
@@ -156,6 +156,7 @@ extern void free_attstatsslot(Oid atttype,
 extern char *get_namespace_name(Oid nspid);
 extern char *get_namespace_name_or_temp(Oid nspid);
 extern Oid	get_range_subtype(Oid rangeOid);
+extern char *get_tablesample_method_name(Oid tsmid);
 
 #define type_is_array(typid)  (get_element_type(typid) != InvalidOid)
 /* type_is_array_domain accepts both plain arrays and domains over arrays */
diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h
index 9e17d87413..fd40366bcd 100644
--- a/src/include/utils/rel.h
+++ b/src/include/utils/rel.h
@@ -63,7 +63,6 @@ typedef struct RelationAmInfo
 	FmgrInfo	amcanreturn;
 } RelationAmInfo;
 
-
 /*
  * Here are the contents of a relation cache entry.
  */
diff --git a/src/include/utils/sampling.h b/src/include/utils/sampling.h
index e3e7f9cf6a..4ac208dc36 100644
--- a/src/include/utils/sampling.h
+++ b/src/include/utils/sampling.h
@@ -15,7 +15,12 @@
 
 #include "storage/bufmgr.h"
 
-extern double sampler_random_fract(void);
+/* Random generator for sampling code */
+typedef unsigned short SamplerRandomState[3];
+
+extern void sampler_random_init_state(long seed,
+									  SamplerRandomState randstate);
+extern double sampler_random_fract(SamplerRandomState randstate);
 
 /* Block sampling methods */
 /* Data structure for Algorithm S from Knuth 3.4.2 */
@@ -25,6 +30,7 @@ typedef struct
 	int			n;				/* desired sample size */
 	BlockNumber t;				/* current block number */
 	int			m;				/* blocks selected so far */
+	SamplerRandomState randstate; /* random generator state */
 } BlockSamplerData;
 
 typedef BlockSamplerData *BlockSampler;
@@ -35,7 +41,12 @@ extern bool BlockSampler_HasMore(BlockSampler bs);
 extern BlockNumber BlockSampler_Next(BlockSampler bs);
 
 /* Reservoid sampling methods */
-typedef double ReservoirStateData;
+typedef struct
+{
+	double	W;
+	SamplerRandomState randstate; /* random generator state */
+} ReservoirStateData;
+
 typedef ReservoirStateData *ReservoirState;
 
 extern void reservoir_init_selection_state(ReservoirState rs, int n);
diff --git a/src/include/utils/syscache.h b/src/include/utils/syscache.h
index 6634099cbe..2dbd38488b 100644
--- a/src/include/utils/syscache.h
+++ b/src/include/utils/syscache.h
@@ -81,6 +81,8 @@ enum SysCacheIdentifier
 	REPLORIGNAME,
 	RULERELNAME,
 	STATRELATTINH,
+	TABLESAMPLEMETHODNAME,
+	TABLESAMPLEMETHODOID,
 	TABLESPACEOID,
 	TRFOID,
 	TRFTYPELANG,