Refactor hash_agg_entry_size().

jeff-davis · jeff-davis · commit 7d4395d0a115 · 2020-02-06T11:49:56.000-08:00
Consolidate the calculations for hash table size estimation. This will
help with upcoming Hash Aggregation work that will add additional call
sites.
diff --git a/src/backend/executor/nodeAgg.c b/src/backend/executor/nodeAgg.c
@@ -1422,24 +1422,17 @@ find_hash_columns(AggState *aggstate)
 }
 
 /*
- * Estimate per-hash-table-entry overhead for the planner.
- *
- * Note that the estimate does not include space for pass-by-reference
- * transition data values, nor for the representative tuple of each group.
- * Nor does this account of the target fill-factor and growth policy of the
- * hash table.
+ * Estimate per-hash-table-entry overhead.
  */
 Size
-hash_agg_entry_size(int numAggs)
+hash_agg_entry_size(int numAggs, Size tupleWidth, Size transitionSpace)
 {
-	Size		entrysize;
-
-	/* This must match build_hash_table */
-	entrysize = sizeof(TupleHashEntryData) +
-		numAggs * sizeof(AggStatePerGroupData);
-	entrysize = MAXALIGN(entrysize);
-
-	return entrysize;
+	return
+		MAXALIGN(SizeofMinimalTupleHeader) +
+		MAXALIGN(tupleWidth) +
+		MAXALIGN(sizeof(TupleHashEntryData) +
+				 numAggs * sizeof(AggStatePerGroupData)) +
+		transitionSpace;
 }
 
 /*
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
@@ -4867,13 +4867,8 @@ create_distinct_paths(PlannerInfo *root,
 		allow_hash = false;		/* policy-based decision not to hash */
 	else
 	{
-		Size		hashentrysize;
-
-		/* Estimate per-hash-entry space at tuple width... */
-		hashentrysize = MAXALIGN(cheapest_input_path->pathtarget->width) +
-			MAXALIGN(SizeofMinimalTupleHeader);
-		/* plus the per-hash-entry overhead */
-		hashentrysize += hash_agg_entry_size(0);
+		Size		hashentrysize = hash_agg_entry_size(
+			0, cheapest_input_path->pathtarget->width, 0);
 
 		/* Allow hashing only if hashtable is predicted to fit in work_mem */
 		allow_hash = (hashentrysize * numDistinctRows <= work_mem * 1024L);
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
@@ -3526,16 +3526,8 @@ double
 estimate_hashagg_tablesize(Path *path, const AggClauseCosts *agg_costs,
 						   double dNumGroups)
 {
-	Size		hashentrysize;
-
-	/* Estimate per-hash-entry space at tuple width... */
-	hashentrysize = MAXALIGN(path->pathtarget->width) +
-		MAXALIGN(SizeofMinimalTupleHeader);
-
-	/* plus space for pass-by-ref transition values... */
-	hashentrysize += agg_costs->transitionSpace;
-	/* plus the per-hash-entry overhead */
-	hashentrysize += hash_agg_entry_size(agg_costs->numAggs);
+	Size		hashentrysize = hash_agg_entry_size(
+		agg_costs->numAggs, path->pathtarget->width, agg_costs->transitionSpace);
 
 	/*
 	 * Note that this disregards the effect of fill-factor and growth policy
diff --git a/src/include/executor/nodeAgg.h b/src/include/executor/nodeAgg.h
@@ -309,6 +309,7 @@ extern AggState *ExecInitAgg(Agg *node, EState *estate, int eflags);
 extern void ExecEndAgg(AggState *node);
 extern void ExecReScanAgg(AggState *node);
 
-extern Size hash_agg_entry_size(int numAggs);
+extern Size hash_agg_entry_size(int numAggs, Size tupleWidth,
+								Size transitionSpace);
 
 #endif							/* NODEAGG_H */
