From 4eaea3db150af56aa2e40efe91997fd25f3b6d73 Mon Sep 17 00:00:00 2001
From: Jeff Davis <jdavis@postgresql.org>
Date: Thu, 6 Feb 2020 19:39:47 -0800
Subject: [PATCH] Introduce TupleHashTableHash() and
 LookupTupleHashEntryHash().

Expose two new entry points: one for only calculating the hash value
of a tuple, and another for looking up a hash entry when the hash
value is already known. This will be useful for disk-based Hash
Aggregation to avoid recomputing the hash value for the same tuple
after saving and restoring it from disk.

Discussion: https://postgr.es/m/37091115219dd522fd9ed67333ee8ed1b7e09443.camel%40j-davis.com
---
 src/backend/executor/execGrouping.c | 108 ++++++++++++++++++++--------
 src/include/executor/executor.h     |   5 ++
 2 files changed, 83 insertions(+), 30 deletions(-)

diff --git a/src/backend/executor/execGrouping.c b/src/backend/executor/execGrouping.c
index 3603c58b63e..f0737fecca8 100644
--- a/src/backend/executor/execGrouping.c
+++ b/src/backend/executor/execGrouping.c
@@ -25,8 +25,9 @@
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 
-static uint32 TupleHashTableHash(struct tuplehash_hash *tb, const MinimalTuple tuple);
 static int	TupleHashTableMatch(struct tuplehash_hash *tb, const MinimalTuple tuple1, const MinimalTuple tuple2);
+static TupleHashEntry LookupTupleHashEntry_internal(
+	TupleHashTable hashtable, TupleTableSlot *slot, bool *isnew, uint32 hash);
 
 /*
  * Define parameters for tuple hash table code generation. The interface is
@@ -300,10 +301,9 @@ TupleHashEntry
 LookupTupleHashEntry(TupleHashTable hashtable, TupleTableSlot *slot,
 					 bool *isnew)
 {
-	TupleHashEntryData *entry;
-	MemoryContext oldContext;
-	bool		found;
-	MinimalTuple key;
+	TupleHashEntry	entry;
+	MemoryContext	oldContext;
+	uint32			hash;
 
 	/* Need to run the hash functions in short-lived context */
 	oldContext = MemoryContextSwitchTo(hashtable->tempcxt);
@@ -313,32 +313,34 @@ LookupTupleHashEntry(TupleHashTable hashtable, TupleTableSlot *slot,
 	hashtable->in_hash_funcs = hashtable->tab_hash_funcs;
 	hashtable->cur_eq_func = hashtable->tab_eq_func;
 
-	key = NULL;					/* flag to reference inputslot */
+	hash = TupleHashTableHash(hashtable->hashtab, NULL);
+	entry = LookupTupleHashEntry_internal(hashtable, slot, isnew, hash);
 
-	if (isnew)
-	{
-		entry = tuplehash_insert(hashtable->hashtab, key, &found);
+	MemoryContextSwitchTo(oldContext);
 
-		if (found)
-		{
-			/* found pre-existing entry */
-			*isnew = false;
-		}
-		else
-		{
-			/* created new entry */
-			*isnew = true;
-			/* zero caller data */
-			entry->additional = NULL;
-			MemoryContextSwitchTo(hashtable->tablecxt);
-			/* Copy the first tuple into the table context */
-			entry->firstTuple = ExecCopySlotMinimalTuple(slot);
-		}
-	}
-	else
-	{
-		entry = tuplehash_lookup(hashtable->hashtab, key);
-	}
+	return entry;
+}
+
+/*
+ * A variant of LookupTupleHashEntry for callers that have already computed
+ * the hash value.
+ */
+TupleHashEntry
+LookupTupleHashEntryHash(TupleHashTable hashtable, TupleTableSlot *slot,
+						 bool *isnew, uint32 hash)
+{
+	TupleHashEntry	entry;
+	MemoryContext	oldContext;
+
+	/* Need to run the hash functions in short-lived context */
+	oldContext = MemoryContextSwitchTo(hashtable->tempcxt);
+
+	/* set up data needed by hash and match functions */
+	hashtable->inputslot = slot;
+	hashtable->in_hash_funcs = hashtable->tab_hash_funcs;
+	hashtable->cur_eq_func = hashtable->tab_eq_func;
+
+	entry = LookupTupleHashEntry_internal(hashtable, slot, isnew, hash);
 
 	MemoryContextSwitchTo(oldContext);
 
@@ -389,7 +391,7 @@ FindTupleHashEntry(TupleHashTable hashtable, TupleTableSlot *slot,
  * Also, the caller must select an appropriate memory context for running
  * the hash functions. (dynahash.c doesn't change CurrentMemoryContext.)
  */
-static uint32
+uint32
 TupleHashTableHash(struct tuplehash_hash *tb, const MinimalTuple tuple)
 {
 	TupleHashTable hashtable = (TupleHashTable) tb->private_data;
@@ -450,6 +452,52 @@ TupleHashTableHash(struct tuplehash_hash *tb, const MinimalTuple tuple)
 	return murmurhash32(hashkey);
 }
 
+/*
+ * Does the work of LookupTupleHashEntry and LookupTupleHashEntryHash. Useful
+ * so that we can avoid switching the memory context multiple times for
+ * LookupTupleHashEntry.
+ *
+ * NB: This function may or may not change the memory context. Caller is
+ * expected to change it back.
+ */
+static TupleHashEntry
+LookupTupleHashEntry_internal(TupleHashTable hashtable, TupleTableSlot *slot,
+							  bool *isnew, uint32 hash)
+{
+	TupleHashEntryData *entry;
+	bool		found;
+	MinimalTuple key;
+
+	key = NULL;					/* flag to reference inputslot */
+
+	if (isnew)
+	{
+		entry = tuplehash_insert_hash(hashtable->hashtab, key, hash, &found);
+
+		if (found)
+		{
+			/* found pre-existing entry */
+			*isnew = false;
+		}
+		else
+		{
+			/* created new entry */
+			*isnew = true;
+			/* zero caller data */
+			entry->additional = NULL;
+			MemoryContextSwitchTo(hashtable->tablecxt);
+			/* Copy the first tuple into the table context */
+			entry->firstTuple = ExecCopySlotMinimalTuple(slot);
+		}
+	}
+	else
+	{
+		entry = tuplehash_lookup_hash(hashtable->hashtab, key, hash);
+	}
+
+	return entry;
+}
+
 /*
  * See whether two tuples (presumably of the same hash value) match
  */
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 6ef3e1fe069..e49cb110461 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -140,6 +140,11 @@ extern TupleHashTable BuildTupleHashTableExt(PlanState *parent,
 extern TupleHashEntry LookupTupleHashEntry(TupleHashTable hashtable,
 										   TupleTableSlot *slot,
 										   bool *isnew);
+extern uint32 TupleHashTableHash(struct tuplehash_hash *tb,
+								 const MinimalTuple tuple);
+extern TupleHashEntry LookupTupleHashEntryHash(TupleHashTable hashtable,
+											   TupleTableSlot *slot,
+											   bool *isnew, uint32 hash);
 extern TupleHashEntry FindTupleHashEntry(TupleHashTable hashtable,
 										 TupleTableSlot *slot,
 										 ExprState *eqcomp,