agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 3/8] Improve performance of SendRowDescriptionMessage.
51+ messages / 5 participants
[nested] [flat]

* [PATCH 3/8] Improve performance of SendRowDescriptionMessage.
@ 2017-09-14 01:41  Andres Freund <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Andres Freund @ 2017-09-14 01:41 UTC (permalink / raw)

Using the new pqformat functions yields performance for statements
with a noticeable number of rows. The function itself is more than
twice as fast.
---
 src/backend/access/common/printtup.c | 156 ++++++++++++++++++++++++++---------
 1 file changed, 118 insertions(+), 38 deletions(-)

diff --git a/src/backend/access/common/printtup.c b/src/backend/access/common/printtup.c
index 20d20e623e..894f89b63c 100644
--- a/src/backend/access/common/printtup.c
+++ b/src/backend/access/common/printtup.c
@@ -32,6 +32,8 @@ static bool printtup_internal_20(TupleTableSlot *slot, DestReceiver *self);
 static void printtup_shutdown(DestReceiver *self);
 static void printtup_destroy(DestReceiver *self);
 
+static void SendRowDescriptionCols_2(StringInfo buf, TupleDesc typeinfo, List *targetlist, int16 *formats);
+static void SendRowDescriptionCols_3(StringInfo buf, TupleDesc typeinfo, List *targetlist, int16 *formats);
 
 /* ----------------------------------------------------------------
  *		printtup / debugtup support
@@ -189,12 +191,118 @@ SendRowDescriptionMessage(TupleDesc typeinfo, List *targetlist, int16 *formats)
 {
 	int			natts = typeinfo->natts;
 	int			proto = PG_PROTOCOL_MAJOR(FrontendProtocol);
+	static StringInfo rowDescriptionBuf = NULL;
+
+	/*
+	 * As this routine is executed for every single query, it can be a
+	 * pq_sendstring_prebottleneck. To avoid unnecessary allocator overhead
+	 * reuse a single buffer. That means we'll never shrink below the largest
+	 * row-description sent, but that seems acceptable given the limited size.
+	 */
+	if (unlikely(!rowDescriptionBuf))
+	{
+		MemoryContext oldContext = MemoryContextSwitchTo(TopMemoryContext);
+		rowDescriptionBuf = makeStringInfo();
+		MemoryContextSwitchTo(oldContext);
+	}
+
+	/* tuple descriptor message type */
+	pq_beginmessage_pre(rowDescriptionBuf, 'T');
+	/* # of attrs in tuples */
+	pq_sendint(rowDescriptionBuf, natts, 2);
+
+	if (proto >= 3)
+		SendRowDescriptionCols_3(rowDescriptionBuf, typeinfo, targetlist,
+								 formats);
+	else
+		SendRowDescriptionCols_2(rowDescriptionBuf, typeinfo, targetlist,
+								 formats);
+
+	pq_endmessage_keep(rowDescriptionBuf);
+}
+
+/*
+ * Send description for each column when using v3+ protocol
+ */
+static void
+SendRowDescriptionCols_3(StringInfo buf, TupleDesc typeinfo, List *targetlist, int16 *formats)
+{
+	int			natts = typeinfo->natts;
 	int			i;
-	StringInfoData buf;
 	ListCell   *tlist_item = list_head(targetlist);
 
-	pq_beginmessage(&buf, 'T'); /* tuple descriptor message type */
-	pq_sendint(&buf, natts, 2); /* # of attrs in tuples */
+	/*
+	 * Prealloc memory for the entire message to be sent. That allows to use
+	 * the significantly faster inline pqformat.h functions and to avoid
+	 * reallocations. Have to overestimate the size of the column-names, to
+	 * account for character set overhead.
+	 */
+	enlargeStringInfo(buf, (NAMEDATALEN * MAX_CONVERSION_GROWTH /* attname */
+							+ sizeof(int32) /* attlen */
+							+ sizeof(int32) /* resorigtbl */
+							+ sizeof(int16) /* resorigcol */
+							+ sizeof(Oid) /* atttypid */
+							+ sizeof(int16) /* attlen */
+							+ sizeof(int32) /* attypmod */
+						  ) * natts);
+
+	for (i = 0; i < natts; ++i)
+	{
+		Form_pg_attribute att = TupleDescAttr(typeinfo, i);
+		Oid			atttypid = att->atttypid;
+		int32		atttypmod = att->atttypmod;
+		int32		resorigtbl;
+		int32		resorigcol;
+		int16		format;
+
+		/*
+		 * If column is a domain, send the base type and typmod
+		 * instead. Lookup before sending any ints, for efficiency.
+		 */
+		atttypid = getBaseTypeAndTypmod(atttypid, &atttypmod);
+
+		/* Do we have a non-resjunk tlist item? */
+		while (tlist_item &&
+			   ((TargetEntry *) lfirst(tlist_item))->resjunk)
+			tlist_item = lnext(tlist_item);
+		if (tlist_item)
+		{
+			TargetEntry *tle = (TargetEntry *) lfirst(tlist_item);
+
+			resorigtbl = tle->resorigtbl;
+			resorigcol = tle->resorigcol;
+			tlist_item = lnext(tlist_item);
+		}
+		else
+		{
+			/* No info available, so send zeroes */
+			resorigtbl = 0;
+			resorigcol = 0;
+		}
+
+		if (formats)
+			format = formats[i];
+		else
+			format = 0;
+
+		pq_sendstring_pre(buf, NameStr(att->attname));
+		pq_sendint32_pre(buf, resorigtbl);
+		pq_sendint16_pre(buf, resorigcol);
+		pq_sendint32_pre(buf, atttypid);
+		pq_sendint16_pre(buf, att->attlen);
+		pq_sendint32_pre(buf, atttypmod);
+		pq_sendint16_pre(buf, format);
+	}
+}
+
+/*
+ * Send description for each column when using v2 protocol
+ */
+static void
+SendRowDescriptionCols_2(StringInfo buf, TupleDesc typeinfo, List *targetlist, int16 *formats)
+{
+	int			natts = typeinfo->natts;
+	int			i;
 
 	for (i = 0; i < natts; ++i)
 	{
@@ -202,44 +310,16 @@ SendRowDescriptionMessage(TupleDesc typeinfo, List *targetlist, int16 *formats)
 		Oid			atttypid = att->atttypid;
 		int32		atttypmod = att->atttypmod;
 
-		pq_sendstring(&buf, NameStr(att->attname));
-		/* column ID info appears in protocol 3.0 and up */
-		if (proto >= 3)
-		{
-			/* Do we have a non-resjunk tlist item? */
-			while (tlist_item &&
-				   ((TargetEntry *) lfirst(tlist_item))->resjunk)
-				tlist_item = lnext(tlist_item);
-			if (tlist_item)
-			{
-				TargetEntry *tle = (TargetEntry *) lfirst(tlist_item);
-
-				pq_sendint(&buf, tle->resorigtbl, 4);
-				pq_sendint(&buf, tle->resorigcol, 2);
-				tlist_item = lnext(tlist_item);
-			}
-			else
-			{
-				/* No info available, so send zeroes */
-				pq_sendint(&buf, 0, 4);
-				pq_sendint(&buf, 0, 2);
-			}
-		}
 		/* If column is a domain, send the base type and typmod instead */
 		atttypid = getBaseTypeAndTypmod(atttypid, &atttypmod);
-		pq_sendint(&buf, (int) atttypid, sizeof(atttypid));
-		pq_sendint(&buf, att->attlen, sizeof(att->attlen));
-		pq_sendint(&buf, atttypmod, sizeof(atttypmod));
-		/* format info appears in protocol 3.0 and up */
-		if (proto >= 3)
-		{
-			if (formats)
-				pq_sendint(&buf, formats[i], 2);
-			else
-				pq_sendint(&buf, 0, 2);
-		}
+
+		pq_sendstring(buf, NameStr(att->attname));
+		/* column ID only info appears in protocol 3.0 and up */
+		pq_sendint(buf, (int) atttypid, sizeof(atttypid));
+		pq_sendint(buf, att->attlen, sizeof(att->attlen));
+		pq_sendint(buf, atttypmod, sizeof(atttypmod));
+		/* format info only appears in protocol 3.0 and up */
 	}
-	pq_endmessage(&buf);
 }
 
 /*
-- 
2.14.1.536.g6867272d5b.dirty


--o6fgx62zvq657xjz
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
 filename="0004-Add-inline-murmurhash32-int32-functionv1.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v8 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.2


--------------846F221A8A016B7AA8E567B3--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v7 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index d62b1495dd3..6189d051072 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.1


--------------C6A03312D0F99F9183A0DF46--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v6 3/3] Optimize hash function
@ 2021-01-20 22:06  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-01-20 22:06 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 1db1e7cf14b..72e4d8a784c 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -163,15 +163,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own. But some resources store plain integers (Files
+	 * and Buffers as of this writing), so we want to incorporate the 'kind'
+	 * in the hash too, otherwise those resources will collide a lot. But
+	 * because there are only a few resource kinds like that - and only a few
+	 * resource kinds to begin with - we don't need to work too hard to mix
+	 * 'kind' into the hash. Just add it with hash_combine(), it perturbs the
+	 * result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 static void
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.29.2


--------------F30A5443A5D524A5CBC51AE7
Content-Type: text/x-patch; charset=UTF-8;
 name="v2-0001-resownerbench.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="v2-0001-resownerbench.patch"



^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* [PATCH v10 3/3] Optimize hash function
@ 2021-10-18 10:59  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 51+ messages in thread

From: Heikki Linnakangas @ 2021-10-18 10:59 UTC (permalink / raw)

---
 src/backend/utils/resowner/resowner.c | 24 ++++++++++++++++++------
 src/include/common/hashfn.h           | 15 +++++++++++++++
 2 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c
index 35e824d4534..118bd2b34c9 100644
--- a/src/backend/utils/resowner/resowner.c
+++ b/src/backend/utils/resowner/resowner.c
@@ -169,15 +169,27 @@ static void ReleaseAuxProcessResourcesCallback(int code, Datum arg);
  *	  INTERNAL ROUTINES														 *
  *****************************************************************************/
 
+/*
+ * Hash function for value+kind combination.
+ */
 static inline uint32
 hash_resource_elem(Datum value, ResourceOwnerFuncs *kind)
 {
-	Datum		data[2];
-
-	data[0] = value;
-	data[1] = PointerGetDatum(kind);
-
-	return hash_bytes((unsigned char *) &data, 2 * SIZEOF_DATUM);
+	/*
+	 * Most resources types store a pointer in 'value', and pointers are
+	 * unique all on their own.  But some resources store plain integers
+	 * (Files and Buffers as of this writing), so we want to incorporate the
+	 * 'kind' in the hash too, otherwise those resources will collide a lot.
+	 * But because there are only a few resource kinds like that - and only a
+	 * few resource kinds to begin with - we don't need to work too hard to
+	 * mix 'kind' into the hash.  Just add it with hash_combine(), it perturbs
+	 * the result enough for our purposes.
+	 */
+#if SIZEOF_DATUM == 8
+	return hash_combine64(murmurhash64((uint64) value), (uint64) kind);
+#else
+	return hash_combine(murmurhash32((uint32) value), (uint32) kind);
+#endif
 }
 
 /*
diff --git a/src/include/common/hashfn.h b/src/include/common/hashfn.h
index c634cc067a1..009ffbbdd38 100644
--- a/src/include/common/hashfn.h
+++ b/src/include/common/hashfn.h
@@ -101,4 +101,19 @@ murmurhash32(uint32 data)
 	return h;
 }
 
+/* 64-bit variant */
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+
 #endif							/* HASHFN_H */
-- 
2.30.2


--------------AF226508B1039DE40796DE51--





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* Re: Transaction timeout
@ 2023-09-06 08:16  Fujii Masao <[email protected]>
  0 siblings, 2 replies; 51+ messages in thread

From: Fujii Masao @ 2023-09-06 08:16 UTC (permalink / raw)
  To: Andrey Borodin <[email protected]>; Andres Freund <[email protected]>; +Cc: Michael Paquier <[email protected]>; Nikolay Samokhvalov <[email protected]>; pgsql-hackers



On 2022/12/19 5:53, Andrey Borodin wrote:
> On Wed, Dec 7, 2022 at 1:30 PM Andrey Borodin <[email protected]> wrote:
>> I hope to address other feedback on the weekend.

Thanks for implementing this feature!

While testing v4 patch, I noticed it doesn't handle the COMMIT AND CHAIN case correctly.
When COMMIT AND CHAIN is executed, I believe the transaction timeout counter should reset
and start from zero with the next transaction. However, it appears that the current
v4 patch doesn't reset the counter in this scenario. Can you confirm this?

With the v4 patch, I found that timeout errors no longer occur during the idle in
transaction phase. Instead, they occur when the next statement is executed. Is this
the intended behavior? I thought some users might want to use the transaction timeout
feature to prevent prolonged transactions and promptly release resources (e.g., locks)
in case of a timeout, similar to idle_in_transaction_session_timeout.

Regards,

-- 
Fujii Masao
Advanced Computing Technology Center
Research and Development Headquarters
NTT DATA CORPORATION






^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* Re: Transaction timeout
@ 2023-09-06 11:32  Andrey M. Borodin <[email protected]>
  parent: Fujii Masao <[email protected]>
  1 sibling, 0 replies; 51+ messages in thread

From: Andrey M. Borodin @ 2023-09-06 11:32 UTC (permalink / raw)
  To: Fujii Masao <[email protected]>; +Cc: Andrey Borodin <[email protected]>; Andres Freund <[email protected]>; Michael Paquier <[email protected]>; Nikolay Samokhvalov <[email protected]>; pgsql-hackers

Thanks for looking into this!

> On 6 Sep 2023, at 13:16, Fujii Masao <[email protected]> wrote:
> 
> While testing v4 patch, I noticed it doesn't handle the COMMIT AND CHAIN case correctly.
> When COMMIT AND CHAIN is executed, I believe the transaction timeout counter should reset
> and start from zero with the next transaction. However, it appears that the current
> v4 patch doesn't reset the counter in this scenario. Can you confirm this?
Yes, I was not aware of this feature. I'll test and fix this.

> With the v4 patch, I found that timeout errors no longer occur during the idle in
> transaction phase. Instead, they occur when the next statement is executed. Is this
> the intended behavior?
AFAIR I had been testing that behaviour of "idle in transaction" was intact. I'll check that again.

> I thought some users might want to use the transaction timeout
> feature to prevent prolonged transactions and promptly release resources (e.g., locks)
> in case of a timeout, similar to idle_in_transaction_session_timeout.
Yes, this is exactly how I was expecting the feature to behave: empty up max_connections slots for long-hanging transactions.

Thanks for your findings, I'll check and post new version!


Best regards, Andrey Borodin.





^ permalink  raw  reply  [nested|flat] 51+ messages in thread

* Re: Transaction timeout
@ 2023-10-10 21:07  Nikolay Samokhvalov <[email protected]>
  parent: Fujii Masao <[email protected]>
  1 sibling, 0 replies; 51+ messages in thread

From: Nikolay Samokhvalov @ 2023-10-10 21:07 UTC (permalink / raw)
  To: Fujii Masao <[email protected]>; +Cc: Andrey Borodin <[email protected]>; Andres Freund <[email protected]>; Michael Paquier <[email protected]>; pgsql-hackers

On Wed, Sep 6, 2023 at 1:16 AM Fujii Masao <[email protected]> wrote:
> With the v4 patch, I found that timeout errors no longer occur during the idle in
> transaction phase. Instead, they occur when the next statement is executed. Is this
> the intended behavior? I thought some users might want to use the transaction timeout
> feature to prevent prolonged transactions and promptly release resources (e.g., locks)
> in case of a timeout, similar to idle_in_transaction_session_timeout.

I agree – it seems reasonable to interrupt transaction immediately
when the timeout occurs. This was the idea – to determine the maximum
possible time for all transactions that is allowed on a server, to
avoid too long-lasting locking and not progressing xmin horizon.

That being said, I also think this wording in the docs:

+        Setting <varname>transaction_timeout</varname> in
+        <filename>postgresql.conf</filename> is not recommended
because it would
+        affect all sessions.

It was inherited from statement_timeout, where I also find this
wording too one-sided. There are certain situations where we do want
global setting to be set – actually, any large OLTP case (to be on
lower risk side; those users who need longer timeout, can set it when
needed, but by default we do need very restrictive timeouts, usually <
1 minute, like we do in HTTP or application servers). I propose this:
> Setting transaction_timeout in postgresql.conf should be done with caution because it affects all sessions.

Looking at the v4 of the patch, a couple of more comments that might
be helpful for v5 (which is planned, as I understand):

1)  it might be beneficial to add tests for more complex scenarios,
e.g., subtransactions

2) In the error message:

+ errmsg("canceling statement due to %s%s%s%s%s", lock_reason, comma1,
+ stmt_reason, comma2, tx_reason)));

– it seems we can have excessive commas here

3) Perhaps, we should say that we cancel the transaction, not
statement (especially in the case when it is happening in the
idle-in-transaction state).

Thanks for working on this feature!






^ permalink  raw  reply  [nested|flat] 51+ messages in thread

end of thread, other threads:[~2023-10-10 21:07 UTC | newest]

Thread overview: 51+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2017-09-14 01:41 [PATCH 3/8] Improve performance of SendRowDescriptionMessage. Andres Freund <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v8 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v6 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-01-20 22:06 [PATCH v7 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2021-10-18 10:59 [PATCH v10 3/3] Optimize hash function Heikki Linnakangas <[email protected]>
2023-09-06 08:16 Re: Transaction timeout Fujii Masao <[email protected]>
2023-09-06 11:32 ` Re: Transaction timeout Andrey M. Borodin <[email protected]>
2023-10-10 21:07 ` Re: Transaction timeout Nikolay Samokhvalov <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox