Introduce 64-bit hash functions with a 64-bit seed.

This will be useful for hash partitioning, which needs a way to seed
the hash functions to avoid problems such as a hash index on a hash
partitioned table clumping all values into a small portion of the
bucket space; it's also useful for anything that wants a 64-bit hash
value rather than a 32-bit hash value.

Just in case somebody wants a 64-bit hash value that is compatible
with the existing 32-bit hash values, make the low 32-bits of the
64-bit hash value match the 32-bit hash value when the seed is 0.

Robert Haas and Amul Sul

Discussion: http://postgr.es/m/CA+Tgmoafx2yoJuhCQQOL5CocEi-w_uG4S2xT0EtgiJnPGcHW3g@mail.gmail.com

2 files changed, 58 insertions, 8 deletions

diff --git a/src/backend/utils/cache/lsyscache.c b/src/backend/utils/cache/lsyscache.c
index 82763f8013d..b7a14dc87e1 100644
--- a/src/backend/utils/cache/lsyscache.c
+++ b/src/backend/utils/cache/lsyscache.c
@@ -490,8 +490,8 @@ get_compatible_hash_operators(Oid opno,
 
 /*
  * get_op_hash_functions
- *		Get the OID(s) of hash support function(s) compatible with the given
- *		operator, operating on its LHS and/or RHS datatype as required.
+ *		Get the OID(s) of the standard hash support function(s) compatible with
+ *		the given operator, operating on its LHS and/or RHS datatype as required.
  *
  * A function for the LHS type is sought and returned into *lhs_procno if
  * lhs_procno isn't NULL.  Similarly, a function for the RHS type is sought
@@ -542,7 +542,7 @@ get_op_hash_functions(Oid opno,
 				*lhs_procno = get_opfamily_proc(aform->amopfamily,
 												aform->amoplefttype,
 												aform->amoplefttype,
-												HASHPROC);
+												HASHSTANDARD_PROC);
 				if (!OidIsValid(*lhs_procno))
 					continue;
 				/* Matching LHS found, done if caller doesn't want RHS */
@@ -564,7 +564,7 @@ get_op_hash_functions(Oid opno,
 				*rhs_procno = get_opfamily_proc(aform->amopfamily,
 												aform->amoprighttype,
 												aform->amoprighttype,
-												HASHPROC);
+												HASHSTANDARD_PROC);
 				if (!OidIsValid(*rhs_procno))
 				{
 					/* Forget any LHS function from this opfamily */
diff --git a/src/backend/utils/cache/typcache.c b/src/backend/utils/cache/typcache.c
index 691d4987b16..2e633f08c51 100644
--- a/src/backend/utils/cache/typcache.c
+++ b/src/backend/utils/cache/typcache.c
@@ -90,6 +90,7 @@ static TypeCacheEntry *firstDomainTypeEntry = NULL;
 #define TCFLAGS_HAVE_FIELD_EQUALITY			0x1000
 #define TCFLAGS_HAVE_FIELD_COMPARE			0x2000
 #define TCFLAGS_CHECKED_DOMAIN_CONSTRAINTS	0x4000
+#define TCFLAGS_CHECKED_HASH_EXTENDED_PROC	0x8000
 
 /*
  * Data stored about a domain type's constraints.  Note that we do not create
@@ -307,6 +308,8 @@ lookup_type_cache(Oid type_id, int flags)
 		flags |= TYPECACHE_HASH_OPFAMILY;
 
 	if ((flags & (TYPECACHE_HASH_PROC | TYPECACHE_HASH_PROC_FINFO |
+				  TYPECACHE_HASH_EXTENDED_PROC |
+				  TYPECACHE_HASH_EXTENDED_PROC_FINFO |
 				  TYPECACHE_HASH_OPFAMILY)) &&
 		!(typentry->flags & TCFLAGS_CHECKED_HASH_OPCLASS))
 	{
@@ -329,6 +332,7 @@ lookup_type_cache(Oid type_id, int flags)
 		 * decision is still good.
 		 */
 		typentry->flags &= ~(TCFLAGS_CHECKED_HASH_PROC);
+		typentry->flags &= ~(TCFLAGS_CHECKED_HASH_EXTENDED_PROC);
 		typentry->flags |= TCFLAGS_CHECKED_HASH_OPCLASS;
 	}
 
@@ -372,11 +376,12 @@ lookup_type_cache(Oid type_id, int flags)
 		typentry->eq_opr = eq_opr;
 
 		/*
-		 * Reset info about hash function whenever we pick up new info about
-		 * equality operator.  This is so we can ensure that the hash function
-		 * matches the operator.
+		 * Reset info about hash functions whenever we pick up new info about
+		 * equality operator.  This is so we can ensure that the hash functions
+		 * match the operator.
 		 */
 		typentry->flags &= ~(TCFLAGS_CHECKED_HASH_PROC);
+		typentry->flags &= ~(TCFLAGS_CHECKED_HASH_EXTENDED_PROC);
 		typentry->flags |= TCFLAGS_CHECKED_EQ_OPR;
 	}
 	if ((flags & TYPECACHE_LT_OPR) &&
@@ -467,7 +472,7 @@ lookup_type_cache(Oid type_id, int flags)
 			hash_proc = get_opfamily_proc(typentry->hash_opf,
 										  typentry->hash_opintype,
 										  typentry->hash_opintype,
-										  HASHPROC);
+										  HASHSTANDARD_PROC);
 
 		/*
 		 * As above, make sure hash_array will succeed.  We don't currently
@@ -485,6 +490,43 @@ lookup_type_cache(Oid type_id, int flags)
 		typentry->hash_proc = hash_proc;
 		typentry->flags |= TCFLAGS_CHECKED_HASH_PROC;
 	}
+	if ((flags & (TYPECACHE_HASH_EXTENDED_PROC |
+				  TYPECACHE_HASH_EXTENDED_PROC_FINFO)) &&
+		!(typentry->flags & TCFLAGS_CHECKED_HASH_EXTENDED_PROC))
+	{
+		Oid			hash_extended_proc = InvalidOid;
+
+		/*
+		 * We insist that the eq_opr, if one has been determined, match the
+		 * hash opclass; else report there is no hash function.
+		 */
+		if (typentry->hash_opf != InvalidOid &&
+			(!OidIsValid(typentry->eq_opr) ||
+			 typentry->eq_opr == get_opfamily_member(typentry->hash_opf,
+													 typentry->hash_opintype,
+													 typentry->hash_opintype,
+													 HTEqualStrategyNumber)))
+			hash_extended_proc = get_opfamily_proc(typentry->hash_opf,
+												   typentry->hash_opintype,
+												   typentry->hash_opintype,
+												   HASHEXTENDED_PROC);
+
+		/*
+		 * As above, make sure hash_array_extended will succeed.  We don't
+		 * currently support hashing for composite types, but when we do,
+		 * we'll need more logic here to check that case too.
+		 */
+		if (hash_extended_proc == F_HASH_ARRAY_EXTENDED &&
+			!array_element_has_hashing(typentry))
+			hash_extended_proc = InvalidOid;
+
+		/* Force update of hash_proc_finfo only if we're changing state */
+		if (typentry->hash_extended_proc != hash_extended_proc)
+			typentry->hash_extended_proc_finfo.fn_oid = InvalidOid;
+
+		typentry->hash_extended_proc = hash_extended_proc;
+		typentry->flags |= TCFLAGS_CHECKED_HASH_EXTENDED_PROC;
+	}
 
 	/*
 	 * Set up fmgr lookup info as requested
@@ -523,6 +565,14 @@ lookup_type_cache(Oid type_id, int flags)
 		fmgr_info_cxt(typentry->hash_proc, &typentry->hash_proc_finfo,
 					  CacheMemoryContext);
 	}
+	if ((flags & TYPECACHE_HASH_EXTENDED_PROC_FINFO) &&
+		typentry->hash_extended_proc_finfo.fn_oid == InvalidOid &&
+		typentry->hash_extended_proc != InvalidOid)
+	{
+		fmgr_info_cxt(typentry->hash_extended_proc,
+					  &typentry->hash_extended_proc_finfo,
+					  CacheMemoryContext);
+	}
 
 	/*
 	 * If it's a composite type (row type), get tupdesc if requested