Remove 'additional' pointer from TupleHashEntryData.

Reduces memory required for hash aggregation by avoiding an allocation
and a pointer in the TupleHashEntryData structure. That structure is
used for all buckets, whether occupied or not, so the savings is
substantial.

Discussion: https://postgr.es/m/AApHDvpN4v3t_sdz4dvrv1Fx_ZPw=twSnxuTEytRYP7LFz5K9A@mail.gmail.com
Reviewed-by: David Rowley <[email protected]>

3 files changed, 16 insertions, 7 deletions

diff --git a/src/backend/executor/execGrouping.c b/src/backend/executor/execGrouping.c
index a9d212aaec6..255bd795361 100644
--- a/src/backend/executor/execGrouping.c
+++ b/src/backend/executor/execGrouping.c
@@ -485,11 +485,18 @@ LookupTupleHashEntry_internal(TupleHashTable hashtable, TupleTableSlot *slot,
 
 			MemoryContextSwitchTo(hashtable->tablecxt);
 
-			entry->firstTuple = ExecCopySlotMinimalTuple(slot);
-			if (hashtable->additionalsize > 0)
-				entry->additional = palloc0(hashtable->additionalsize);
-			else
-				entry->additional = NULL;
+			/*
+			 * Copy the first tuple into the table context, and request
+			 * additionalsize extra bytes before the allocation.
+			 *
+			 * The caller can get a pointer to the additional data with
+			 * TupleHashEntryGetAdditional(), and store arbitrary data there.
+			 * Placing both the tuple and additional data in the same
+			 * allocation avoids the need to store an extra pointer in
+			 * TupleHashEntryData or allocate an additional chunk.
+			 */
+			entry->firstTuple = ExecCopySlotMinimalTupleExtra(slot,
+															  hashtable->additionalsize);
 		}
 	}
 	else
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 69396a9d7f8..6a1fec88928 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -188,7 +188,10 @@ TupleHashEntryGetTuple(TupleHashEntry entry)
 static inline void *
 TupleHashEntryGetAdditional(TupleHashTable hashtable, TupleHashEntry entry)
 {
-	return entry->additional;
+	if (hashtable->additionalsize > 0)
+		return (char *) entry->firstTuple - hashtable->additionalsize;
+	else
+		return NULL;
 }
 #endif
 
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 7df25d7e64f..e42f9f9f957 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -840,7 +840,6 @@ typedef struct TupleHashTableData *TupleHashTable;
 typedef struct TupleHashEntryData
 {
 	MinimalTuple firstTuple;	/* copy of first tuple in this group */
-	void	   *additional;		/* user data */
 	uint32		status;			/* hash status */
 	uint32		hash;			/* hash value (cached) */
 } TupleHashEntryData;