Support parallel aggregation.

Parallel workers can now partially aggregate the data and pass the
transition values back to the leader, which can combine the partial
results to produce the final answer.

David Rowley, based on earlier work by Haribabu Kommi.  Reviewed by
Álvaro Herrera, Tomas Vondra, Amit Kapila, James Sewell, and me.

4 files changed, 25 insertions, 3 deletions

diff --git a/src/include/optimizer/clauses.h b/src/include/optimizer/clauses.h
index 3b3fd0fc9a0..3ab57f155d2 100644
--- a/src/include/optimizer/clauses.h
+++ b/src/include/optimizer/clauses.h
@@ -27,6 +27,23 @@ typedef struct
 	List	  **windowFuncs;	/* lists of WindowFuncs for each winref */
 } WindowFuncLists;
 
+/*
+ * PartialAggType
+ *	PartialAggType stores whether partial aggregation is allowed and
+ *	which context it is allowed in. We require three states here as there are
+ *	two different contexts in which partial aggregation is safe. For aggregates
+ *	which have an 'stype' of INTERNAL, it is okay to pass a pointer to the
+ *  aggregate state within a single process, since the datum is just a
+ *	pointer. In cases where the aggregate state must be passed between
+ *  different processes, for example during parallel aggregation, passing
+ *  pointers directly is not going to work.
+ */
+typedef enum
+{
+	PAT_ANY = 0,		/* Any type of partial aggregation is okay. */
+	PAT_INTERNAL_ONLY,	/* Some aggregates support only internal mode. */
+	PAT_DISABLED		/* Some aggregates don't support partial mode at all */
+} PartialAggType;
 
 extern Expr *make_opclause(Oid opno, Oid opresulttype, bool opretset,
 			  Expr *leftop, Expr *rightop,
@@ -47,6 +64,7 @@ extern Node *make_and_qual(Node *qual1, Node *qual2);
 extern Expr *make_ands_explicit(List *andclauses);
 extern List *make_ands_implicit(Expr *clause);
 
+extern PartialAggType aggregates_allow_partial(Node *clause);
 extern bool contain_agg_clause(Node *clause);
 extern void count_agg_clauses(PlannerInfo *root, Node *clause,
 				  AggClauseCosts *costs);
diff --git a/src/include/optimizer/cost.h b/src/include/optimizer/cost.h
index fea2bb77f4d..d4adca6836a 100644
--- a/src/include/optimizer/cost.h
+++ b/src/include/optimizer/cost.h
@@ -150,7 +150,7 @@ extern void final_cost_hashjoin(PlannerInfo *root, HashPath *path,
 					SpecialJoinInfo *sjinfo,
 					SemiAntiJoinFactors *semifactors);
 extern void cost_gather(GatherPath *path, PlannerInfo *root,
-			RelOptInfo *baserel, ParamPathInfo *param_info);
+			RelOptInfo *baserel, ParamPathInfo *param_info, double *rows);
 extern void cost_subplan(PlannerInfo *root, SubPlan *subplan, Plan *plan);
 extern void cost_qual_eval(QualCost *cost, List *quals, PlannerInfo *root);
 extern void cost_qual_eval_node(QualCost *cost, Node *qual, PlannerInfo *root);
diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h
index d1eb22f27a4..1744ff058e8 100644
--- a/src/include/optimizer/pathnode.h
+++ b/src/include/optimizer/pathnode.h
@@ -74,7 +74,8 @@ extern MaterialPath *create_material_path(RelOptInfo *rel, Path *subpath);
 extern UniquePath *create_unique_path(PlannerInfo *root, RelOptInfo *rel,
 				   Path *subpath, SpecialJoinInfo *sjinfo);
 extern GatherPath *create_gather_path(PlannerInfo *root,
-				   RelOptInfo *rel, Path *subpath, Relids required_outer);
+				   RelOptInfo *rel, Path *subpath, PathTarget *target,
+				   Relids required_outer, double *rows);
 extern SubqueryScanPath *create_subqueryscan_path(PlannerInfo *root,
 						 RelOptInfo *rel, Path *subpath,
 						 List *pathkeys, Relids required_outer);
@@ -168,7 +169,9 @@ extern AggPath *create_agg_path(PlannerInfo *root,
 				List *groupClause,
 				List *qual,
 				const AggClauseCosts *aggcosts,
-				double numGroups);
+				double numGroups,
+				bool combineStates,
+				bool finalizeAggs);
 extern GroupingSetsPath *create_groupingsets_path(PlannerInfo *root,
 						 RelOptInfo *rel,
 						 Path *subpath,
diff --git a/src/include/optimizer/tlist.h b/src/include/optimizer/tlist.h
index 0d745a08914..de58db1db2a 100644
--- a/src/include/optimizer/tlist.h
+++ b/src/include/optimizer/tlist.h
@@ -61,6 +61,7 @@ extern void add_column_to_pathtarget(PathTarget *target,
 extern void add_new_column_to_pathtarget(PathTarget *target, Expr *expr);
 extern void add_new_columns_to_pathtarget(PathTarget *target, List *exprs);
 extern void apply_pathtarget_labeling_to_tlist(List *tlist, PathTarget *target);
+extern void apply_partialaggref_adjustment(PathTarget *target);
 
 /* Convenience macro to get a PathTarget with valid cost/width fields */
 #define create_pathtarget(root, tlist) \