v3-0001-Simplify-abbreviated-key-hashing-using-murmurhash.patch

From 3cd625d2d42554111b34d70d0820f68c7ec5db11 Mon Sep 17 00:00:00 2001
From: Aleksander Alekseev <aleksander@tigerdata.com>
Date: Tue, 13 Jan 2026 14:51:21 +0300
Subject: [PATCH v3 1/2] Simplify abbreviated key hashing using murmurhash64()

Now when all Datums are 64-bit values we can simplify the code by using
murmurhash64() in *_abbrev_convert() functions. Also replace hash_uint32()
with murmurhash32() in a few other places for consistency.

Author: Aleksander Alekseev <aleksander@tigerdata.com>
Suggested-by: John Naylor <johncnaylorls@gmail.com>
Reviewed-by: John Naylor <johncnaylorls@gmail.com>
Discussion: https://postgr.es/m/CAJ7c6TMPhDRQMmkUHPv8oOK97B1mR8NRS61DgjpdaZUPAwaeZQ%40mail.gmail.com
---
 src/backend/commands/async.c    |  6 +++---
 src/backend/utils/adt/bytea.c   |  9 ++-------
 src/backend/utils/adt/mac.c     | 11 +++--------
 src/backend/utils/adt/network.c |  6 +-----
 src/backend/utils/adt/numeric.c |  5 +----
 src/backend/utils/adt/uuid.c    |  6 +-----
 src/backend/utils/adt/varlena.c |  9 ++-------
 7 files changed, 13 insertions(+), 39 deletions(-)

diff --git a/src/backend/commands/async.c b/src/backend/commands/async.c
index 657c591618d..315270ddb11 100644
--- a/src/backend/commands/async.c
+++ b/src/backend/commands/async.c
@@ -651,9 +651,9 @@ globalChannelTableHash(const void *key, size_t size, void *arg)
 	const GlobalChannelKey *k = (const GlobalChannelKey *) key;
 	dshash_hash h;
 
-	h = DatumGetUInt32(hash_uint32(k->dboid));
-	h ^= DatumGetUInt32(hash_any((const unsigned char *) k->channel,
-								 strnlen(k->channel, NAMEDATALEN)));
+	h = murmurhash32(k->dboid);
+	h ^= hash_any((const unsigned char *) k->channel,
+				  strnlen(k->channel, NAMEDATALEN));
 
 	return h;
 }
diff --git a/src/backend/utils/adt/bytea.c b/src/backend/utils/adt/bytea.c
index fd7662d41ee..f32bd23d03c 100644
--- a/src/backend/utils/adt/bytea.c
+++ b/src/backend/utils/adt/bytea.c
@@ -1110,17 +1110,12 @@ bytea_abbrev_convert(Datum original, SortSupport ssup)
 								   Min(len, PG_CACHE_LINE_SIZE)));
 
 	if (len > PG_CACHE_LINE_SIZE)
-		hash ^= DatumGetUInt32(hash_uint32((uint32) len));
+		hash ^= murmurhash32((uint32) len);
 
 	addHyperLogLog(&bss->full_card, hash);
 
 	/* Hash abbreviated key */
-	{
-		uint32		tmp;
-
-		tmp = DatumGetUInt32(res) ^ (uint32) (DatumGetUInt64(res) >> 32);
-		hash = DatumGetUInt32(hash_uint32(tmp));
-	}
+	hash = (uint32) murmurhash64(DatumGetUInt64(res));
 
 	addHyperLogLog(&bss->abbr_card, hash);
 
diff --git a/src/backend/utils/adt/mac.c b/src/backend/utils/adt/mac.c
index f14675dea40..0658846f274 100644
--- a/src/backend/utils/adt/mac.c
+++ b/src/backend/utils/adt/mac.c
@@ -492,17 +492,12 @@ macaddr_abbrev_convert(Datum original, SortSupport ssup)
 	uss->input_count += 1;
 
 	/*
-	 * Cardinality estimation. The estimate uses uint32, so XOR the two 32-bit
-	 * halves together to produce slightly more entropy. The two zeroed bytes
-	 * won't have any practical impact on this operation.
+	 * Cardinality estimation. The estimate uses uint32, so we hash the full
+	 * 64-bit value and take the lower 32 bits of the result.
 	 */
 	if (uss->estimating)
 	{
-		uint32		tmp;
-
-		tmp = DatumGetUInt32(res) ^ (uint32) (DatumGetUInt64(res) >> 32);
-
-		addHyperLogLog(&uss->abbr_card, DatumGetUInt32(hash_uint32(tmp)));
+		addHyperLogLog(&uss->abbr_card, (uint32) murmurhash64(DatumGetUInt64(res)));
 	}
 
 	/*
diff --git a/src/backend/utils/adt/network.c b/src/backend/utils/adt/network.c
index 3a2002097dd..c226af5ca80 100644
--- a/src/backend/utils/adt/network.c
+++ b/src/backend/utils/adt/network.c
@@ -739,11 +739,7 @@ network_abbrev_convert(Datum original, SortSupport ssup)
 	/* Hash abbreviated key */
 	if (uss->estimating)
 	{
-		uint32		tmp;
-
-		tmp = DatumGetUInt32(res) ^ (uint32) (DatumGetUInt64(res) >> 32);
-
-		addHyperLogLog(&uss->abbr_card, DatumGetUInt32(hash_uint32(tmp)));
+		addHyperLogLog(&uss->abbr_card, (uint32) murmurhash64(DatumGetUInt64(res)));
 	}
 
 	return res;
diff --git a/src/backend/utils/adt/numeric.c b/src/backend/utils/adt/numeric.c
index d25b8ad505d..bbe2581f0b7 100644
--- a/src/backend/utils/adt/numeric.c
+++ b/src/backend/utils/adt/numeric.c
@@ -2397,10 +2397,7 @@ numeric_abbrev_convert_var(const NumericVar *var, NumericSortSupport *nss)
 
 	if (nss->estimating)
 	{
-		uint32		tmp = ((uint32) result
-						   ^ (uint32) ((uint64) result >> 32));
-
-		addHyperLogLog(&nss->abbr_card, DatumGetUInt32(hash_uint32(tmp)));
+		addHyperLogLog(&nss->abbr_card, (uint32) murmurhash64(result));
 	}
 
 	return NumericAbbrevGetDatum(result);
diff --git a/src/backend/utils/adt/uuid.c b/src/backend/utils/adt/uuid.c
index 6ee3752ac78..888802c3012 100644
--- a/src/backend/utils/adt/uuid.c
+++ b/src/backend/utils/adt/uuid.c
@@ -396,11 +396,7 @@ uuid_abbrev_convert(Datum original, SortSupport ssup)
 
 	if (uss->estimating)
 	{
-		uint32		tmp;
-
-		tmp = DatumGetUInt32(res) ^ (uint32) (DatumGetUInt64(res) >> 32);
-
-		addHyperLogLog(&uss->abbr_card, DatumGetUInt32(hash_uint32(tmp)));
+		addHyperLogLog(&uss->abbr_card, (uint32) murmurhash64(DatumGetUInt64(res)));
 	}
 
 	/*
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 7caf700fd61..ea3d4dcf18b 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -2155,17 +2155,12 @@ varstr_abbrev_convert(Datum original, SortSupport ssup)
 								   Min(len, PG_CACHE_LINE_SIZE)));
 
 	if (len > PG_CACHE_LINE_SIZE)
-		hash ^= DatumGetUInt32(hash_uint32((uint32) len));
+		hash ^= murmurhash32((uint32) len);
 
 	addHyperLogLog(&sss->full_card, hash);
 
 	/* Hash abbreviated key */
-	{
-		uint32		tmp;
-
-		tmp = DatumGetUInt32(res) ^ (uint32) (DatumGetUInt64(res) >> 32);
-		hash = DatumGetUInt32(hash_uint32(tmp));
-	}
+	hash = (uint32) murmurhash64(DatumGetUInt64(res));
 
 	addHyperLogLog(&sss->abbr_card, hash);
 
-- 
2.43.0