Do execGrouping.c via expression eval machinery, take two.

This has a performance benefit on own, although not hugely so. The
primary benefit is that it will allow for to JIT tuple deforming and
comparator invocations.

Large parts of this were previously committed (773aec7aa), but the
commit contained an omission around cross-type comparisons and was
thus reverted.

Author: Andres Freund
Discussion: https://postgr.es/m/[email protected]

4 files changed, 40 insertions, 36 deletions

diff --git a/src/include/executor/execExpr.h b/src/include/executor/execExpr.h
index 117fc892f4b..0cab431f656 100644
--- a/src/include/executor/execExpr.h
+++ b/src/include/executor/execExpr.h
@@ -148,6 +148,7 @@ typedef enum ExprEvalOp
 	/* evaluate assorted special-purpose expression types */
 	EEOP_IOCOERCE,
 	EEOP_DISTINCT,
+	EEOP_NOT_DISTINCT,
 	EEOP_NULLIF,
 	EEOP_SQLVALUEFUNCTION,
 	EEOP_CURRENTOFEXPR,
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 1d824eff361..621e7c3dc46 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -113,26 +113,19 @@ extern bool execCurrentOf(CurrentOfExpr *cexpr,
 /*
  * prototypes from functions in execGrouping.c
  */
-extern bool execTuplesMatch(TupleTableSlot *slot1,
-				TupleTableSlot *slot2,
-				int numCols,
-				AttrNumber *matchColIdx,
-				FmgrInfo *eqfunctions,
-				MemoryContext evalContext);
-extern bool execTuplesUnequal(TupleTableSlot *slot1,
-				  TupleTableSlot *slot2,
-				  int numCols,
-				  AttrNumber *matchColIdx,
-				  FmgrInfo *eqfunctions,
-				  MemoryContext evalContext);
-extern FmgrInfo *execTuplesMatchPrepare(int numCols,
-					   Oid *eqOperators);
+extern ExprState *execTuplesMatchPrepare(TupleDesc desc,
+					   int numCols,
+					   AttrNumber *keyColIdx,
+					   Oid *eqOperators,
+					   PlanState *parent);
 extern void execTuplesHashPrepare(int numCols,
 					  Oid *eqOperators,
-					  FmgrInfo **eqFunctions,
+					  Oid **eqFuncOids,
 					  FmgrInfo **hashFunctions);
-extern TupleHashTable BuildTupleHashTable(int numCols, AttrNumber *keyColIdx,
-					FmgrInfo *eqfunctions,
+extern TupleHashTable BuildTupleHashTable(PlanState *parent,
+					TupleDesc inputDesc,
+					int numCols, AttrNumber *keyColIdx,
+					Oid *eqfuncoids,
 					FmgrInfo *hashfunctions,
 					long nbuckets, Size additionalsize,
 					MemoryContext tablecxt,
@@ -142,7 +135,7 @@ extern TupleHashEntry LookupTupleHashEntry(TupleHashTable hashtable,
 					 bool *isnew);
 extern TupleHashEntry FindTupleHashEntry(TupleHashTable hashtable,
 				   TupleTableSlot *slot,
-				   FmgrInfo *eqfunctions,
+				   ExprState *eqcomp,
 				   FmgrInfo *hashfunctions);
 
 /*
@@ -257,6 +250,11 @@ extern ExprState *ExecInitCheck(List *qual, PlanState *parent);
 extern List *ExecInitExprList(List *nodes, PlanState *parent);
 extern ExprState *ExecBuildAggTrans(AggState *aggstate, struct AggStatePerPhaseData *phase,
 				  bool doSort, bool doHash);
+extern ExprState *ExecBuildGroupingEqual(TupleDesc ldesc, TupleDesc rdesc,
+					   int numCols,
+					   AttrNumber *keyColIdx,
+					   Oid *eqfunctions,
+					   PlanState *parent);
 extern ProjectionInfo *ExecBuildProjectionInfo(List *targetList,
 						ExprContext *econtext,
 						TupleTableSlot *slot,
diff --git a/src/include/executor/nodeAgg.h b/src/include/executor/nodeAgg.h
index 3b06db86fd8..aa6ebaaf97d 100644
--- a/src/include/executor/nodeAgg.h
+++ b/src/include/executor/nodeAgg.h
@@ -102,11 +102,12 @@ typedef struct AggStatePerTransData
 	bool	   *sortNullsFirst;
 
 	/*
-	 * fmgr lookup data for input columns' equality operators --- only
-	 * set/used when aggregate has DISTINCT flag.  Note that these are in
-	 * order of sort column index, not parameter index.
+	 * Comparators for input columns --- only set/used when aggregate has
+	 * DISTINCT flag. equalfnOne version is used for single-column
+	 * commparisons, equalfnMulti for the case of multiple columns.
 	 */
-	FmgrInfo   *equalfns;		/* array of length numDistinctCols */
+	FmgrInfo	equalfnOne;
+	ExprState  *equalfnMulti;
 
 	/*
 	 * initial value from pg_aggregate entry
@@ -270,7 +271,8 @@ typedef struct AggStatePerPhaseData
 	int			numsets;		/* number of grouping sets (or 0) */
 	int		   *gset_lengths;	/* lengths of grouping sets */
 	Bitmapset **grouped_cols;	/* column groupings for rollup */
-	FmgrInfo   *eqfunctions;	/* per-grouping-field equality fns */
+	ExprState **eqfunctions;	/* expression returning equality, indexed by
+								 * nr of cols to compare */
 	Agg		   *aggnode;		/* Agg node for phase data */
 	Sort	   *sortnode;		/* Sort node for input ordering for phase */
 
@@ -290,7 +292,7 @@ typedef struct AggStatePerHashData
 	TupleHashIterator hashiter; /* for iterating through hash table */
 	TupleTableSlot *hashslot;	/* slot for loading hash table */
 	FmgrInfo   *hashfunctions;	/* per-grouping-field hash fns */
-	FmgrInfo   *eqfunctions;	/* per-grouping-field equality fns */
+	Oid		   *eqfuncoids;		/* per-grouping-field equality fns */
 	int			numCols;		/* number of hash key columns */
 	int			numhashGrpCols; /* number of columns in hash table */
 	int			largestGrpColIdx;	/* largest col required for hashing */
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 286d55be033..a953820f43a 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -594,10 +594,10 @@ typedef struct ExecAuxRowMark
  * Normally these are the only functions used, but FindTupleHashEntry()
  * supports searching a hashtable using cross-data-type hashing.  For that,
  * the caller must supply hash functions for the LHS datatype as well as
- * the cross-type equality operators to use.  in_hash_funcs and cur_eq_funcs
+ * the cross-type equality operators to use.  in_hash_funcs and cur_eq_func
  * are set to point to the caller's function arrays while doing such a search.
  * During LookupTupleHashEntry(), they point to tab_hash_funcs and
- * tab_eq_funcs respectively.
+ * tab_eq_func respectively.
  * ----------------------------------------------------------------
  */
 typedef struct TupleHashEntryData *TupleHashEntry;
@@ -625,7 +625,7 @@ typedef struct TupleHashTableData
 	int			numCols;		/* number of columns in lookup key */
 	AttrNumber *keyColIdx;		/* attr numbers of key columns */
 	FmgrInfo   *tab_hash_funcs; /* hash functions for table datatype(s) */
-	FmgrInfo   *tab_eq_funcs;	/* equality functions for table datatype(s) */
+	ExprState  *tab_eq_func;	/* comparator for table datatype(s) */
 	MemoryContext tablecxt;		/* memory context containing table */
 	MemoryContext tempcxt;		/* context for function evaluations */
 	Size		entrysize;		/* actual size to make each hash entry */
@@ -633,8 +633,9 @@ typedef struct TupleHashTableData
 	/* The following fields are set transiently for each table search: */
 	TupleTableSlot *inputslot;	/* current input tuple's slot */
 	FmgrInfo   *in_hash_funcs;	/* hash functions for input datatype(s) */
-	FmgrInfo   *cur_eq_funcs;	/* equality functions for input vs. table */
+	ExprState  *cur_eq_func;	/* comparator for for input vs. table */
 	uint32		hash_iv;		/* hash-function IV */
+	ExprContext *exprcontext;	/* expression context */
 }			TupleHashTableData;
 
 typedef tuplehash_iterator TupleHashIterator;
@@ -781,6 +782,7 @@ typedef struct SubPlanState
 	HeapTuple	curTuple;		/* copy of most recent tuple from subplan */
 	Datum		curArray;		/* most recent array from ARRAY() subplan */
 	/* these are used when hashing the subselect's output: */
+	TupleDesc	descRight;		/* subselect desc after projection */
 	ProjectionInfo *projLeft;	/* for projecting lefthand exprs */
 	ProjectionInfo *projRight;	/* for projecting subselect output */
 	TupleHashTable hashtable;	/* hash table for no-nulls subselect rows */
@@ -791,10 +793,12 @@ typedef struct SubPlanState
 	MemoryContext hashtempcxt;	/* temp memory context for hash tables */
 	ExprContext *innerecontext; /* econtext for computing inner tuples */
 	AttrNumber *keyColIdx;		/* control data for hash tables */
+	Oid		   *tab_eq_funcoids;/* equality func oids for table datatype(s) */
 	FmgrInfo   *tab_hash_funcs; /* hash functions for table datatype(s) */
 	FmgrInfo   *tab_eq_funcs;	/* equality functions for table datatype(s) */
 	FmgrInfo   *lhs_hash_funcs; /* hash functions for lefthand datatype(s) */
 	FmgrInfo   *cur_eq_funcs;	/* equality functions for LHS vs. table */
+	ExprState  *cur_eq_comp;	/* equality comparator for LHS vs. table */
 } SubPlanState;
 
 /* ----------------
@@ -1067,7 +1071,7 @@ typedef struct RecursiveUnionState
 	Tuplestorestate *working_table;
 	Tuplestorestate *intermediate_table;
 	/* Remaining fields are unused in UNION ALL case */
-	FmgrInfo   *eqfunctions;	/* per-grouping-field equality fns */
+	Oid		   *eqfuncoids;		/* per-grouping-field equality fns */
 	FmgrInfo   *hashfunctions;	/* per-grouping-field hash fns */
 	MemoryContext tempContext;	/* short-term context for comparisons */
 	TupleHashTable hashtable;	/* hash table for tuples already seen */
@@ -1795,7 +1799,7 @@ typedef struct SortState
 typedef struct GroupState
 {
 	ScanState	ss;				/* its first field is NodeTag */
-	FmgrInfo   *eqfunctions;	/* per-field lookup data for equality fns */
+	ExprState  *eqfunction;		/* equality function */
 	bool		grp_done;		/* indicates completion of Group scan */
 } GroupState;
 
@@ -1885,8 +1889,8 @@ typedef struct WindowAggState
 
 	WindowStatePerFunc perfunc; /* per-window-function information */
 	WindowStatePerAgg peragg;	/* per-plain-aggregate information */
-	FmgrInfo   *partEqfunctions;	/* equality funcs for partition columns */
-	FmgrInfo   *ordEqfunctions; /* equality funcs for ordering columns */
+	ExprState  *partEqfunction;	/* equality funcs for partition columns */
+	ExprState  *ordEqfunction; /* equality funcs for ordering columns */
 	Tuplestorestate *buffer;	/* stores rows of current partition */
 	int			current_ptr;	/* read pointer # for current row */
 	int			framehead_ptr;	/* read pointer # for frame head, if used */
@@ -1964,8 +1968,7 @@ typedef struct WindowAggState
 typedef struct UniqueState
 {
 	PlanState	ps;				/* its first field is NodeTag */
-	FmgrInfo   *eqfunctions;	/* per-field lookup data for equality fns */
-	MemoryContext tempContext;	/* short-term context for comparisons */
+	ExprState   *eqfunction;		/* tuple equality qual */
 } UniqueState;
 
 /* ----------------
@@ -2079,11 +2082,11 @@ typedef struct SetOpStatePerGroupData *SetOpStatePerGroup;
 typedef struct SetOpState
 {
 	PlanState	ps;				/* its first field is NodeTag */
-	FmgrInfo   *eqfunctions;	/* per-grouping-field equality fns */
+	ExprState  *eqfunction;		/* equality comparator */
+	Oid		   *eqfuncoids;		/* per-grouping-field equality fns */
 	FmgrInfo   *hashfunctions;	/* per-grouping-field hash fns */
 	bool		setop_done;		/* indicates completion of output scan */
 	long		numOutput;		/* number of dups left to output */
-	MemoryContext tempContext;	/* short-term context for comparisons */
 	/* these fields are used in SETOP_SORTED mode: */
 	SetOpStatePerGroup pergroup;	/* per-group working state */
 	HeapTuple	grp_firstTuple; /* copy of first tuple of current group */