Improve sys/catcache performance.

The following are the individual improvements:
1) Avoidance of FunctionCallInfo based function calls, replaced by
   more efficient functions with a native C argument interface.
2) Don't extract columns from a cache entry's tuple whenever matching
   entries - instead store them as a Datum array. This also allows to
   get rid of having to build dummy tuples for negative & list
   entries, and of a hack for dealing with cstring vs. text weirdness.
3) Reorder members of catcache.h struct, so imortant entries are more
   likely to be on one cacheline.
4) Allowing the compiler to specialize critical SearchCatCache for a
   specific number of attributes allows to unroll loops and avoid
   other nkeys dependant initialization.
5) Only initializing the ScanKey when necessary, i.e. catcache misses,
   greatly reduces cache unnecessary cpu cache misses.
6) Split of the cache-miss case from the hash lookup, reducing stack
   allocations etc in the common case.
7) CatCTup and their corresponding heaptuple are allocated in one
   piece.

This results in making cache lookups themselves roughly three times as
fast - full-system benchmarks obviously improve less than that.

I've also evaluated further techniques:
- replace open coded hash with simplehash - the list walk right now
  shows up in profiles. Unfortunately it's not easy to do so safely as
  an entry's memory location can change at various times, which
  doesn't work well with the refcounting and cache invalidation.
- Cacheline-aligning CatCTup entries - helps some with performance,
  but the win isn't big and the code for it is ugly, because the
  tuples have to be freed as well.
- add more proper functions, rather than macros for
  SearchSysCacheCopyN etc., but right now they don't show up in
  profiles.

The reason the macro wrapper for syscache.c/h have to be changed,
rather than just catcache, is that doing otherwise would require
exposing the SysCache array to the outside.  That might be a good idea
anyway, but it's for another day.

Author: Andres Freund
Reviewed-By: Robert Haas
Discussion: https://postgr.es/m/20170914061207.zxotvyopetm7lrrp@alap3.anarazel.de

src/backend/utils/cache/catcache.c

@@ -30,7 +30,9 @@
 #endif
 #include "storage/lmgr.h"
 #include "utils/builtins.h"
+#include "utils/datum.h"
 #include "utils/fmgroids.h"
+#include "utils/hashutils.h"
 #include "utils/inval.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
@@ -72,11 +74,25 @@
 /* Cache management header --- pointer is NULL until created */
 static CatCacheHeader *CacheHdr = NULL;
 
+static inline HeapTuple SearchCatCacheInternal(CatCache *cache,
+					   int nkeys,
+					   Datum v1, Datum v2,
+					   Datum v3, Datum v4);
+
+static pg_noinline HeapTuple SearchCatCacheMiss(CatCache *cache,
+				   int nkeys,
+				   uint32 hashValue,
+				   Index hashIndex,
+				   Datum v1, Datum v2,
+				   Datum v3, Datum v4);
 
 static uint32 CatalogCacheComputeHashValue(CatCache *cache, int nkeys,
-							 ScanKey cur_skey);
-static uint32 CatalogCacheComputeTupleHashValue(CatCache *cache,
+							 Datum v1, Datum v2, Datum v3, Datum v4);
+static uint32 CatalogCacheComputeTupleHashValue(CatCache *cache, int nkeys,
 								  HeapTuple tuple);
+static inline bool CatalogCacheCompareTuple(const CatCache *cache, int nkeys,
+						 const Datum *cachekeys,
+						 const Datum *searchkeys);
 
 #ifdef CATCACHE_STATS
 static void CatCachePrintStats(int code, Datum arg);
@@ -85,9 +101,14 @@ static void CatCacheRemoveCTup(CatCache *cache, CatCTup *ct);
 static void CatCacheRemoveCList(CatCache *cache, CatCList *cl);
 static void CatalogCacheInitializeCache(CatCache *cache);
 static CatCTup *CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp,
+						Datum *arguments,
 						uint32 hashValue, Index hashIndex,
 						bool negative);
-static HeapTuple build_dummy_tuple(CatCache *cache, int nkeys, ScanKey skeys);
+
+static void CatCacheFreeKeys(TupleDesc tupdesc, int nkeys, int *attnos,
+				 Datum *keys);
+static void CatCacheCopyKeys(TupleDesc tupdesc, int nkeys, int *attnos,
+				 Datum *srckeys, Datum *dstkeys);
 
 
 /*
@@ -95,45 +116,126 @@ static HeapTuple build_dummy_tuple(CatCache *cache, int nkeys, ScanKey skeys);
  */
 
 /*
- * Look up the hash and equality functions for system types that are used
- * as cache key fields.
- *
- * XXX this should be replaced by catalog lookups,
- * but that seems to pose considerable risk of circularity...
+ * Hash and equality functions for system types that are used as cache key
+ * fields.  In some cases, we just call the regular SQL-callable functions for
+ * the appropriate data type, but that tends to be a little slow, and the
+ * speed of these functions is performance-critical.  Therefore, for data
+ * types that frequently occur as catcache keys, we hard-code the logic here.
+ * Avoiding the overhead of DirectFunctionCallN(...) is a substantial win, and
+ * in certain cases (like int4) we can adopt a faster hash algorithm as well.
  */
+
+static bool
+chareqfast(Datum a, Datum b)
+{
+	return DatumGetChar(a) == DatumGetChar(b);
+}
+
+static uint32
+charhashfast(Datum datum)
+{
+	return murmurhash32((int32) DatumGetChar(datum));
+}
+
+static bool
+nameeqfast(Datum a, Datum b)
+{
+	char	   *ca = NameStr(*DatumGetName(a));
+	char	   *cb = NameStr(*DatumGetName(b));
+
+	return strncmp(ca, cb, NAMEDATALEN) == 0;
+}
+
+static uint32
+namehashfast(Datum datum)
+{
+	char	   *key = NameStr(*DatumGetName(datum));
+
+	return hash_any((unsigned char *) key, strlen(key));
+}
+
+static bool
+int2eqfast(Datum a, Datum b)
+{
+	return DatumGetInt16(a) == DatumGetInt16(b);
+}
+
+static uint32
+int2hashfast(Datum datum)
+{
+	return murmurhash32((int32) DatumGetInt16(datum));
+}
+
+static bool
+int4eqfast(Datum a, Datum b)
+{
+	return DatumGetInt32(a) == DatumGetInt32(b);
+}
+
+static uint32
+int4hashfast(Datum datum)
+{
+	return murmurhash32((int32) DatumGetInt32(datum));
+}
+
+static bool
+texteqfast(Datum a, Datum b)
+{
+	return DatumGetBool(DirectFunctionCall2(texteq, a, b));
+}
+
+static uint32
+texthashfast(Datum datum)
+{
+	return DatumGetInt32(DirectFunctionCall1(hashtext, datum));
+}
+
+static bool
+oidvectoreqfast(Datum a, Datum b)
+{
+	return DatumGetBool(DirectFunctionCall2(oidvectoreq, a, b));
+}
+
+static uint32
+oidvectorhashfast(Datum datum)
+{
+	return DatumGetInt32(DirectFunctionCall1(hashoidvector, datum));
+}
+
+/* Lookup support functions for a type. */
 static void
-GetCCHashEqFuncs(Oid keytype, PGFunction *hashfunc, RegProcedure *eqfunc)
+GetCCHashEqFuncs(Oid keytype, CCHashFN *hashfunc, RegProcedure *eqfunc, CCFastEqualFN *fasteqfunc)
 {
 	switch (keytype)
 	{
 		case BOOLOID:
-			*hashfunc = hashchar;
-
+			*hashfunc = charhashfast;
+			*fasteqfunc = chareqfast;
 			*eqfunc = F_BOOLEQ;
 			break;
 		case CHAROID:
-			*hashfunc = hashchar;
-
+			*hashfunc = charhashfast;
+			*fasteqfunc = chareqfast;
 			*eqfunc = F_CHAREQ;
 			break;
 		case NAMEOID:
-			*hashfunc = hashname;
-
+			*hashfunc = namehashfast;
+			*fasteqfunc = nameeqfast;
 			*eqfunc = F_NAMEEQ;
 			break;
 		case INT2OID:
-			*hashfunc = hashint2;
-
+			*hashfunc = int2hashfast;
+			*fasteqfunc = int2eqfast;
 			*eqfunc = F_INT2EQ;
 			break;
 		case INT4OID:
-			*hashfunc = hashint4;
-
+			*hashfunc = int4hashfast;
+			*fasteqfunc = int4eqfast;
 			*eqfunc = F_INT4EQ;
 			break;
 		case TEXTOID:
-			*hashfunc = hashtext;
-
+			*hashfunc = texthashfast;
+			*fasteqfunc = texteqfast;
 			*eqfunc = F_TEXTEQ;
 			break;
 		case OIDOID:
@@ -147,13 +249,13 @@ GetCCHashEqFuncs(Oid keytype, PGFunction *hashfunc, RegProcedure *eqfunc)
 		case REGDICTIONARYOID:
 		case REGROLEOID:
 		case REGNAMESPACEOID:
-			*hashfunc = hashoid;
-
+			*hashfunc = int4hashfast;
+			*fasteqfunc = int4eqfast;
 			*eqfunc = F_OIDEQ;
 			break;
 		case OIDVECTOROID:
-			*hashfunc = hashoidvector;
-
+			*hashfunc = oidvectorhashfast;
+			*fasteqfunc = oidvectoreqfast;
 			*eqfunc = F_OIDVECTOREQ;
 			break;
 		default:
@@ -171,10 +273,12 @@ GetCCHashEqFuncs(Oid keytype, PGFunction *hashfunc, RegProcedure *eqfunc)
  * Compute the hash value associated with a given set of lookup keys
  */
 static uint32
-CatalogCacheComputeHashValue(CatCache *cache, int nkeys, ScanKey cur_skey)
+CatalogCacheComputeHashValue(CatCache *cache, int nkeys,
+							 Datum v1, Datum v2, Datum v3, Datum v4)
 {
 	uint32		hashValue = 0;
 	uint32		oneHash;
+	CCHashFN   *cc_hashfunc = cache->cc_hashfunc;
 
 	CACHE4_elog(DEBUG2, "CatalogCacheComputeHashValue %s %d %p",
 				cache->cc_relname,
@@ -184,30 +288,26 @@ CatalogCacheComputeHashValue(CatCache *cache, int nkeys, ScanKey cur_skey)
 	switch (nkeys)
 	{
 		case 4:
-			oneHash =
-				DatumGetUInt32(DirectFunctionCall1(cache->cc_hashfunc[3],
-												   cur_skey[3].sk_argument));
+			oneHash = (cc_hashfunc[3]) (v4);
+
 			hashValue ^= oneHash << 24;
 			hashValue ^= oneHash >> 8;
 			/* FALLTHROUGH */
 		case 3:
-			oneHash =
-				DatumGetUInt32(DirectFunctionCall1(cache->cc_hashfunc[2],
-												   cur_skey[2].sk_argument));
+			oneHash = (cc_hashfunc[2]) (v3);
+
 			hashValue ^= oneHash << 16;
 			hashValue ^= oneHash >> 16;
 			/* FALLTHROUGH */
 		case 2:
-			oneHash =
-				DatumGetUInt32(DirectFunctionCall1(cache->cc_hashfunc[1],
-												   cur_skey[1].sk_argument));
+			oneHash = (cc_hashfunc[1]) (v2);
+
 			hashValue ^= oneHash << 8;
 			hashValue ^= oneHash >> 24;
 			/* FALLTHROUGH */
 		case 1:
-			oneHash =
-				DatumGetUInt32(DirectFunctionCall1(cache->cc_hashfunc[0],
-												   cur_skey[0].sk_argument));
+			oneHash = (cc_hashfunc[0]) (v1);
+
 			hashValue ^= oneHash;
 			break;
 		default:
@@ -224,63 +324,82 @@ CatalogCacheComputeHashValue(CatCache *cache, int nkeys, ScanKey cur_skey)
  * Compute the hash value associated with a given tuple to be cached
  */
 static uint32
-CatalogCacheComputeTupleHashValue(CatCache *cache, HeapTuple tuple)
+CatalogCacheComputeTupleHashValue(CatCache *cache, int nkeys, HeapTuple tuple)
 {
-	ScanKeyData cur_skey[CATCACHE_MAXKEYS];
+	Datum		v1 = 0,
+				v2 = 0,
+				v3 = 0,
+				v4 = 0;
 	bool		isNull = false;
-
-	/* Copy pre-initialized overhead data for scankey */
-	memcpy(cur_skey, cache->cc_skey, sizeof(cur_skey));
+	int		   *cc_keyno = cache->cc_keyno;
+	TupleDesc	cc_tupdesc = cache->cc_tupdesc;
 
 	/* Now extract key fields from tuple, insert into scankey */
-	switch (cache->cc_nkeys)
+	switch (nkeys)
 	{
 		case 4:
-			cur_skey[3].sk_argument =
-				(cache->cc_key[3] == ObjectIdAttributeNumber)
+			v4 = (cc_keyno[3] == ObjectIdAttributeNumber)
 				? ObjectIdGetDatum(HeapTupleGetOid(tuple))
 				: fastgetattr(tuple,
-							  cache->cc_key[3],
-							  cache->cc_tupdesc,
+							  cc_keyno[3],
+							  cc_tupdesc,
 							  &isNull);
 			Assert(!isNull);
 			/* FALLTHROUGH */
 		case 3:
-			cur_skey[2].sk_argument =
-				(cache->cc_key[2] == ObjectIdAttributeNumber)
+			v3 = (cc_keyno[2] == ObjectIdAttributeNumber)
 				? ObjectIdGetDatum(HeapTupleGetOid(tuple))
 				: fastgetattr(tuple,
-							  cache->cc_key[2],
-							  cache->cc_tupdesc,
+							  cc_keyno[2],
+							  cc_tupdesc,
 							  &isNull);
 			Assert(!isNull);
 			/* FALLTHROUGH */
 		case 2:
-			cur_skey[1].sk_argument =
-				(cache->cc_key[1] == ObjectIdAttributeNumber)
+			v2 = (cc_keyno[1] == ObjectIdAttributeNumber)
 				? ObjectIdGetDatum(HeapTupleGetOid(tuple))
 				: fastgetattr(tuple,
-							  cache->cc_key[1],
-							  cache->cc_tupdesc,
+							  cc_keyno[1],
+							  cc_tupdesc,
 							  &isNull);
 			Assert(!isNull);
 			/* FALLTHROUGH */
 		case 1:
-			cur_skey[0].sk_argument =
-				(cache->cc_key[0] == ObjectIdAttributeNumber)
+			v1 = (cc_keyno[0] == ObjectIdAttributeNumber)
 				? ObjectIdGetDatum(HeapTupleGetOid(tuple))
 				: fastgetattr(tuple,
-							  cache->cc_key[0],
-							  cache->cc_tupdesc,
+							  cc_keyno[0],
+							  cc_tupdesc,
 							  &isNull);
 			Assert(!isNull);
 			break;
 		default:
-			elog(FATAL, "wrong number of hash keys: %d", cache->cc_nkeys);
+			elog(FATAL, "wrong number of hash keys: %d", nkeys);
 			break;
 	}
 
-	return CatalogCacheComputeHashValue(cache, cache->cc_nkeys, cur_skey);
+	return CatalogCacheComputeHashValue(cache, nkeys, v1, v2, v3, v4);
+}
+
+/*
+ *		CatalogCacheCompareTuple
+ *
+ * Compare a tuple to the passed arguments.
+ */
+static inline bool
+CatalogCacheCompareTuple(const CatCache *cache, int nkeys,
+						 const Datum *cachekeys,
+						 const Datum *searchkeys)
+{
+	const CCFastEqualFN *cc_fastequal = cache->cc_fastequal;
+	int			i;
+
+	for (i = 0; i < nkeys; i++)
+	{
+		if (!(cc_fastequal[i]) (cachekeys[i], searchkeys[i]))
+			return false;
+	}
+	return true;
 }
 
 
@@ -371,9 +490,14 @@ CatCacheRemoveCTup(CatCache *cache, CatCTup *ct)
 	/* delink from linked list */
 	dlist_delete(&ct->cache_elem);
 
-	/* free associated tuple data */
-	if (ct->tuple.t_data != NULL)
-		pfree(ct->tuple.t_data);
+	/*
+	 * Free keys when we're dealing with a negative entry, normal entries just
+	 * point into tuple, allocated together with the CatCTup.
+	 */
+	if (ct->negative)
+		CatCacheFreeKeys(cache->cc_tupdesc, cache->cc_nkeys,
+						 cache->cc_keyno, ct->keys);
+
 	pfree(ct);
 
 	--cache->cc_ntup;
@@ -414,9 +538,10 @@ CatCacheRemoveCList(CatCache *cache, CatCList *cl)
 	/* delink from linked list */
 	dlist_delete(&cl->cache_elem);
 
-	/* free associated tuple data */
-	if (cl->tuple.t_data != NULL)
-		pfree(cl->tuple.t_data);
+	/* free associated column data */
+	CatCacheFreeKeys(cache->cc_tupdesc, cl->nkeys,
+					 cache->cc_keyno, cl->keys);
+
 	pfree(cl);
 }
 
@@ -660,6 +785,7 @@ InitCatCache(int id,
 {
 	CatCache   *cp;
 	MemoryContext oldcxt;
+	size_t		sz;
 	int			i;
 
 	/*
@@ -699,11 +825,12 @@ InitCatCache(int id,
 	}
 
 	/*
-	 * allocate a new cache structure
+	 * Allocate a new cache structure, aligning to a cacheline boundary
 	 *
 	 * Note: we rely on zeroing to initialize all the dlist headers correctly
 	 */
-	cp = (CatCache *) palloc0(sizeof(CatCache));
+	sz = sizeof(CatCache) + PG_CACHE_LINE_SIZE;
+	cp = (CatCache *) CACHELINEALIGN(palloc0(sz));
 	cp->cc_bucket = palloc0(nbuckets * sizeof(dlist_head));
 
 	/*
@@ -721,7 +848,7 @@ InitCatCache(int id,
 	cp->cc_nbuckets = nbuckets;
 	cp->cc_nkeys = nkeys;
 	for (i = 0; i < nkeys; ++i)
-		cp->cc_key[i] = key[i];
+		cp->cc_keyno[i] = key[i];
 
 	/*
 	 * new cache is initialized as far as we can go for now. print some
@@ -794,13 +921,13 @@ RehashCatCache(CatCache *cp)
 
 #define CatalogCacheInitializeCache_DEBUG2 \
 do { \
-		if (cache->cc_key[i] > 0) { \
+		if (cache->cc_keyno[i] > 0) { \
 			elog(DEBUG2, "CatalogCacheInitializeCache: load %d/%d w/%d, %u", \
-				i+1, cache->cc_nkeys, cache->cc_key[i], \
-				 TupleDescAttr(tupdesc, cache->cc_key[i] - 1)->atttypid); \
+				i+1, cache->cc_nkeys, cache->cc_keyno[i], \
+				 TupleDescAttr(tupdesc, cache->cc_keyno[i] - 1)->atttypid); \
 		} else { \
 			elog(DEBUG2, "CatalogCacheInitializeCache: load %d/%d w/%d", \
-				i+1, cache->cc_nkeys, cache->cc_key[i]); \
+				i+1, cache->cc_nkeys, cache->cc_keyno[i]); \
 		} \
 } while(0)
 #else
@@ -860,10 +987,10 @@ CatalogCacheInitializeCache(CatCache *cache)
 
 		CatalogCacheInitializeCache_DEBUG2;
 
-		if (cache->cc_key[i] > 0)
+		if (cache->cc_keyno[i] > 0)
 		{
 			Form_pg_attribute attr = TupleDescAttr(tupdesc,
-												   cache->cc_key[i] - 1);
+												   cache->cc_keyno[i] - 1);
 
 			keytype = attr->atttypid;
 			/* cache key columns should always be NOT NULL */
@@ -871,16 +998,15 @@ CatalogCacheInitializeCache(CatCache *cache)
 		}
 		else
 		{
-			if (cache->cc_key[i] != ObjectIdAttributeNumber)
+			if (cache->cc_keyno[i] != ObjectIdAttributeNumber)
 				elog(FATAL, "only sys attr supported in caches is OID");
 			keytype = OIDOID;
 		}
 
 		GetCCHashEqFuncs(keytype,
 						 &cache->cc_hashfunc[i],
-						 &eqfunc);
-
-		cache->cc_isname[i] = (keytype == NAMEOID);
+						 &eqfunc,
+						 &cache->cc_fastequal[i]);
 
 		/*
 		 * Do equality-function lookup (we assume this won't need a catalog
@@ -891,7 +1017,7 @@ CatalogCacheInitializeCache(CatCache *cache)
 					  CacheMemoryContext);
 
 		/* Initialize sk_attno suitably for HeapKeyTest() and heap scans */
-		cache->cc_skey[i].sk_attno = cache->cc_key[i];
+		cache->cc_skey[i].sk_attno = cache->cc_keyno[i];
 
 		/* Fill in sk_strategy as well --- always standard equality */
 		cache->cc_skey[i].sk_strategy = BTEqualStrategyNumber;
@@ -1020,7 +1146,7 @@ IndexScanOK(CatCache *cache, ScanKey cur_skey)
 }
 
 /*
- *	SearchCatCache
+ *	SearchCatCacheInternal
  *
  *		This call searches a system cache for a tuple, opening the relation
  *		if necessary (on the first access to a particular cache).
@@ -1042,42 +1168,90 @@ SearchCatCache(CatCache *cache,
 			   Datum v3,
 			   Datum v4)
 {
-	ScanKeyData cur_skey[CATCACHE_MAXKEYS];
+	return SearchCatCacheInternal(cache, cache->cc_nkeys, v1, v2, v3, v4);
+}
+
+
+/*
+ * SearchCatCacheN() are SearchCatCache() versions for a specific number of
+ * arguments. The compiler can inline the body and unroll loops, making them a
+ * bit faster than SearchCatCache().
+ */
+
+HeapTuple
+SearchCatCache1(CatCache *cache,
+				Datum v1)
+{
+	return SearchCatCacheInternal(cache, 1, v1, 0, 0, 0);
+}
+
+
+HeapTuple
+SearchCatCache2(CatCache *cache,
+				Datum v1, Datum v2)
+{
+	return SearchCatCacheInternal(cache, 2, v1, v2, 0, 0);
+}
+
+
+HeapTuple
+SearchCatCache3(CatCache *cache,
+				Datum v1, Datum v2, Datum v3)
+{
+	return SearchCatCacheInternal(cache, 3, v1, v2, v3, 0);
+}
+
+
+HeapTuple
+SearchCatCache4(CatCache *cache,
+				Datum v1, Datum v2, Datum v3, Datum v4)
+{
+	return SearchCatCacheInternal(cache, 4, v1, v2, v3, v4);
+}
+
+/*
+ * Work-horse for SearchCatCache/SearchCatCacheN.
+ */
+static inline HeapTuple
+SearchCatCacheInternal(CatCache *cache,
+					   int nkeys,
+					   Datum v1,
+					   Datum v2,
+					   Datum v3,
+					   Datum v4)
+{
+	Datum		arguments[CATCACHE_MAXKEYS];
 	uint32		hashValue;
 	Index		hashIndex;
 	dlist_iter	iter;
 	dlist_head *bucket;
 	CatCTup    *ct;
-	Relation	relation;
-	SysScanDesc scandesc;
-	HeapTuple	ntp;
 
 	/* Make sure we're in an xact, even if this ends up being a cache hit */
 	Assert(IsTransactionState());
 
+	Assert(cache->cc_nkeys == nkeys);
+
 	/*
 	 * one-time startup overhead for each cache
 	 */
-	if (cache->cc_tupdesc == NULL)
+	if (unlikely(cache->cc_tupdesc == NULL))
 		CatalogCacheInitializeCache(cache);
 
 #ifdef CATCACHE_STATS
 	cache->cc_searches++;
 #endif
 
-	/*
-	 * initialize the search key information
-	 */
-	memcpy(cur_skey, cache->cc_skey, sizeof(cur_skey));
-	cur_skey[0].sk_argument = v1;
-	cur_skey[1].sk_argument = v2;
-	cur_skey[2].sk_argument = v3;
-	cur_skey[3].sk_argument = v4;
+	/* Initialize local parameter array */
+	arguments[0] = v1;
+	arguments[1] = v2;
+	arguments[2] = v3;
+	arguments[3] = v4;
 
 	/*
 	 * find the hash bucket in which to look for the tuple
 	 */
-	hashValue = CatalogCacheComputeHashValue(cache, cache->cc_nkeys, cur_skey);
+	hashValue = CatalogCacheComputeHashValue(cache, nkeys, v1, v2, v3, v4);
 	hashIndex = HASH_INDEX(hashValue, cache->cc_nbuckets);
 
 	/*
@@ -1089,8 +1263,6 @@ SearchCatCache(CatCache *cache,
 	bucket = &cache->cc_bucket[hashIndex];
 	dlist_foreach(iter, bucket)
 	{
-		bool		res;
-
 		ct = dlist_container(CatCTup, cache_elem, iter.cur);
 
 		if (ct->dead)
@@ -1099,15 +1271,7 @@ SearchCatCache(CatCache *cache,
 		if (ct->hash_value != hashValue)
 			continue;			/* quickly skip entry if wrong hash val */
 
-		/*
-		 * see if the cached tuple matches our key.
-		 */
-		HeapKeyTest(&ct->tuple,
-					cache->cc_tupdesc,
-					cache->cc_nkeys,
-					cur_skey,
-					res);
-		if (!res)
+		if (!CatalogCacheCompareTuple(cache, nkeys, ct->keys, arguments))
 			continue;
 
 		/*
@@ -1150,6 +1314,49 @@ SearchCatCache(CatCache *cache,
 		}
 	}
 
+	return SearchCatCacheMiss(cache, nkeys, hashValue, hashIndex, v1, v2, v3, v4);
+}
+
+/*
+ * Search the actual catalogs, rather than the cache.
+ *
+ * This is kept separate from SearchCatCacheInternal() to keep the fast-path
+ * as small as possible.  To avoid that effort being undone by a helpful
+ * compiler, try to explicitly forbid inlining.
+ */
+static pg_noinline HeapTuple
+SearchCatCacheMiss(CatCache *cache,
+				   int nkeys,
+				   uint32 hashValue,
+				   Index hashIndex,
+				   Datum v1,
+				   Datum v2,
+				   Datum v3,
+				   Datum v4)
+{
+	ScanKeyData cur_skey[CATCACHE_MAXKEYS];
+	Relation	relation;
+	SysScanDesc scandesc;
+	HeapTuple	ntp;
+	CatCTup    *ct;
+	Datum		arguments[CATCACHE_MAXKEYS];
+
+	/* Initialize local parameter array */
+	arguments[0] = v1;
+	arguments[1] = v2;
+	arguments[2] = v3;
+	arguments[3] = v4;
+
+	/*
+	 * Ok, need to make a lookup in the relation, copy the scankey and fill
+	 * out any per-call fields.
+	 */
+	memcpy(cur_skey, cache->cc_skey, sizeof(ScanKeyData) * nkeys);
+	cur_skey[0].sk_argument = v1;
+	cur_skey[1].sk_argument = v2;
+	cur_skey[2].sk_argument = v3;
+	cur_skey[3].sk_argument = v4;
+
 	/*
 	 * Tuple was not found in cache, so we have to try to retrieve it directly
 	 * from the relation.  If found, we will add it to the cache; if not
@@ -1171,14 +1378,14 @@ SearchCatCache(CatCache *cache,
 								  cache->cc_indexoid,
 								  IndexScanOK(cache, cur_skey),
 								  NULL,
-								  cache->cc_nkeys,
+								  nkeys,
 								  cur_skey);
 
 	ct = NULL;
 
 	while (HeapTupleIsValid(ntp = systable_getnext(scandesc)))
 	{
-		ct = CatalogCacheCreateEntry(cache, ntp,
+		ct = CatalogCacheCreateEntry(cache, ntp, arguments,
 									 hashValue, hashIndex,
 									 false);
 		/* immediately set the refcount to 1 */
@@ -1207,11 +1414,9 @@ SearchCatCache(CatCache *cache,
 		if (IsBootstrapProcessingMode())
 			return NULL;
 
-		ntp = build_dummy_tuple(cache, cache->cc_nkeys, cur_skey);
-		ct = CatalogCacheCreateEntry(cache, ntp,
+		ct = CatalogCacheCreateEntry(cache, NULL, arguments,
 									 hashValue, hashIndex,
 									 true);
-		heap_freetuple(ntp);
 
 		CACHE4_elog(DEBUG2, "SearchCatCache(%s): Contains %d/%d tuples",
 					cache->cc_relname, cache->cc_ntup, CacheHdr->ch_ntup);
@@ -1288,27 +1493,16 @@ GetCatCacheHashValue(CatCache *cache,
 					 Datum v3,
 					 Datum v4)
 {
-	ScanKeyData cur_skey[CATCACHE_MAXKEYS];
-
 	/*
 	 * one-time startup overhead for each cache
 	 */
 	if (cache->cc_tupdesc == NULL)
 		CatalogCacheInitializeCache(cache);
 
-	/*
-	 * initialize the search key information
-	 */
-	memcpy(cur_skey, cache->cc_skey, sizeof(cur_skey));
-	cur_skey[0].sk_argument = v1;
-	cur_skey[1].sk_argument = v2;
-	cur_skey[2].sk_argument = v3;
-	cur_skey[3].sk_argument = v4;
-
 	/*
 	 * calculate the hash value
 	 */
-	return CatalogCacheComputeHashValue(cache, cache->cc_nkeys, cur_skey);
+	return CatalogCacheComputeHashValue(cache, cache->cc_nkeys, v1, v2, v3, v4);
 }
 
 
@@ -1329,7 +1523,7 @@ SearchCatCacheList(CatCache *cache,
 				   Datum v3,
 				   Datum v4)
 {
-	ScanKeyData cur_skey[CATCACHE_MAXKEYS];
+	Datum		arguments[CATCACHE_MAXKEYS];
 	uint32		lHashValue;
 	dlist_iter	iter;
 	CatCList   *cl;
@@ -1354,21 +1548,18 @@ SearchCatCacheList(CatCache *cache,
 	cache->cc_lsearches++;
 #endif
 
-	/*
-	 * initialize the search key information
-	 */
-	memcpy(cur_skey, cache->cc_skey, sizeof(cur_skey));
-	cur_skey[0].sk_argument = v1;
-	cur_skey[1].sk_argument = v2;
-	cur_skey[2].sk_argument = v3;
-	cur_skey[3].sk_argument = v4;
+	/* Initialize local parameter array */
+	arguments[0] = v1;
+	arguments[1] = v2;
+	arguments[2] = v3;
+	arguments[3] = v4;
 
 	/*
 	 * compute a hash value of the given keys for faster search.  We don't
 	 * presently divide the CatCList items into buckets, but this still lets
 	 * us skip non-matching items quickly most of the time.
 	 */
-	lHashValue = CatalogCacheComputeHashValue(cache, nkeys, cur_skey);
+	lHashValue = CatalogCacheComputeHashValue(cache, nkeys, v1, v2, v3, v4);
 
 	/*
 	 * scan the items until we find a match or exhaust our list
@@ -1378,8 +1569,6 @@ SearchCatCacheList(CatCache *cache,
 	 */
 	dlist_foreach(iter, &cache->cc_lists)
 	{
-		bool		res;
-
 		cl = dlist_container(CatCList, cache_elem, iter.cur);
 
 		if (cl->dead)
@@ -1393,12 +1582,8 @@ SearchCatCacheList(CatCache *cache,
 		 */
 		if (cl->nkeys != nkeys)
 			continue;
-		HeapKeyTest(&cl->tuple,
-					cache->cc_tupdesc,
-					nkeys,
-					cur_skey,
-					res);
-		if (!res)
+
+		if (!CatalogCacheCompareTuple(cache, nkeys, cl->keys, arguments))
 			continue;
 
 		/*
@@ -1441,9 +1626,20 @@ SearchCatCacheList(CatCache *cache,
 
 	PG_TRY();
 	{
+		ScanKeyData cur_skey[CATCACHE_MAXKEYS];
 		Relation	relation;
 		SysScanDesc scandesc;
 
+		/*
+		 * Ok, need to make a lookup in the relation, copy the scankey and
+		 * fill out any per-call fields.
+		 */
+		memcpy(cur_skey, cache->cc_skey, sizeof(ScanKeyData) * cache->cc_nkeys);
+		cur_skey[0].sk_argument = v1;
+		cur_skey[1].sk_argument = v2;
+		cur_skey[2].sk_argument = v3;
+		cur_skey[3].sk_argument = v4;
+
 		relation = heap_open(cache->cc_reloid, AccessShareLock);
 
 		scandesc = systable_beginscan(relation,
@@ -1467,7 +1663,7 @@ SearchCatCacheList(CatCache *cache,
 			 * See if there's an entry for this tuple already.
 			 */
 			ct = NULL;
-			hashValue = CatalogCacheComputeTupleHashValue(cache, ntp);
+			hashValue = CatalogCacheComputeTupleHashValue(cache, cache->cc_nkeys, ntp);
 			hashIndex = HASH_INDEX(hashValue, cache->cc_nbuckets);
 
 			bucket = &cache->cc_bucket[hashIndex];
@@ -1498,7 +1694,7 @@ SearchCatCacheList(CatCache *cache,
 			if (!found)
 			{
 				/* We didn't find a usable entry, so make a new one */
-				ct = CatalogCacheCreateEntry(cache, ntp,
+				ct = CatalogCacheCreateEntry(cache, ntp, arguments,
 											 hashValue, hashIndex,
 											 false);
 			}
@@ -1513,18 +1709,16 @@ SearchCatCacheList(CatCache *cache,
 
 		heap_close(relation, AccessShareLock);
 
-		/*
-		 * Now we can build the CatCList entry.  First we need a dummy tuple
-		 * containing the key values...
-		 */
-		ntp = build_dummy_tuple(cache, nkeys, cur_skey);
+		/* Now we can build the CatCList entry. */
 		oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
 		nmembers = list_length(ctlist);
 		cl = (CatCList *)
 			palloc(offsetof(CatCList, members) + nmembers * sizeof(CatCTup *));
-		heap_copytuple_with_tuple(ntp, &cl->tuple);
+
+		/* Extract key values */
+		CatCacheCopyKeys(cache->cc_tupdesc, nkeys, cache->cc_keyno,
+						 arguments, cl->keys);
 		MemoryContextSwitchTo(oldcxt);
-		heap_freetuple(ntp);
 
 		/*
 		 * We are now past the last thing that could trigger an elog before we
@@ -1621,36 +1815,81 @@ ReleaseCatCacheList(CatCList *list)
  *		supplied data into it.  The new entry initially has refcount 0.
  */
 static CatCTup *
-CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp,
-						uint32 hashValue, Index hashIndex, bool negative)
+CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp, Datum *arguments,
+						uint32 hashValue, Index hashIndex,
+						bool negative)
 {
 	CatCTup    *ct;
 	HeapTuple	dtp;
 	MemoryContext oldcxt;
 
+	/* negative entries have no tuple associated */
+	if (ntp)
+	{
+		int			i;
+
+		Assert(!negative);
+
 		/*
-	 * If there are any out-of-line toasted fields in the tuple, expand them
-	 * in-line.  This saves cycles during later use of the catcache entry, and
-	 * also protects us against the possibility of the toast tuples being
-	 * freed before we attempt to fetch them, in case of something using a
-	 * slightly stale catcache entry.
+		 * If there are any out-of-line toasted fields in the tuple, expand
+		 * them in-line.  This saves cycles during later use of the catcache
+		 * entry, and also protects us against the possibility of the toast
+		 * tuples being freed before we attempt to fetch them, in case of
+		 * something using a slightly stale catcache entry.
 		 */
 		if (HeapTupleHasExternal(ntp))
 			dtp = toast_flatten_tuple(ntp, cache->cc_tupdesc);
 		else
 			dtp = ntp;
 
-	/*
-	 * Allocate CatCTup header in cache memory, and copy the tuple there too.
-	 */
+		/* Allocate memory for CatCTup and the cached tuple in one go */
 		oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
-	ct = (CatCTup *) palloc(sizeof(CatCTup));
-	heap_copytuple_with_tuple(dtp, &ct->tuple);
+
+		ct = (CatCTup *) palloc(sizeof(CatCTup) +
+								MAXIMUM_ALIGNOF + dtp->t_len);
+		ct->tuple.t_len = dtp->t_len;
+		ct->tuple.t_self = dtp->t_self;
+		ct->tuple.t_tableOid = dtp->t_tableOid;
+		ct->tuple.t_data = (HeapTupleHeader)
+			MAXALIGN(((char *) ct) + sizeof(CatCTup));
+		/* copy tuple contents */
+		memcpy((char *) ct->tuple.t_data,
+			   (const char *) dtp->t_data,
+			   dtp->t_len);
 		MemoryContextSwitchTo(oldcxt);
 
 		if (dtp != ntp)
 			heap_freetuple(dtp);
 
+		/* extract keys - they'll point into the tuple if not by-value */
+		for (i = 0; i < cache->cc_nkeys; i++)
+		{
+			Datum		atp;
+			bool		isnull;
+
+			atp = heap_getattr(&ct->tuple,
+							   cache->cc_keyno[i],
+							   cache->cc_tupdesc,
+							   &isnull);
+			Assert(!isnull);
+			ct->keys[i] = atp;
+		}
+	}
+	else
+	{
+		Assert(negative);
+		oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
+		ct = (CatCTup *) palloc(sizeof(CatCTup));
+
+		/*
+		 * Store keys - they'll point into separately allocated memory if not
+		 * by-value.
+		 */
+		CatCacheCopyKeys(cache->cc_tupdesc, cache->cc_nkeys, cache->cc_keyno,
+						 arguments, ct->keys);
+		MemoryContextSwitchTo(oldcxt);
+	}
+
 	/*
 	 * Finish initializing the CatCTup header, and add it to the cache's
 	 * linked list and counts.
@@ -1679,71 +1918,80 @@ CatalogCacheCreateEntry(CatCache *cache, HeapTuple ntp,
 }
 
 /*
- * build_dummy_tuple
- *		Generate a palloc'd HeapTuple that contains the specified key
- *		columns, and NULLs for other columns.
- *
- * This is used to store the keys for negative cache entries and CatCList
- * entries, which don't have real tuples associated with them.
+ * Helper routine that frees keys stored in the keys array.
  */
-static HeapTuple
-build_dummy_tuple(CatCache *cache, int nkeys, ScanKey skeys)
+static void
+CatCacheFreeKeys(TupleDesc tupdesc, int nkeys, int *attnos, Datum *keys)
 {
-	HeapTuple	ntp;
-	TupleDesc	tupDesc = cache->cc_tupdesc;
-	Datum	   *values;
-	bool	   *nulls;
-	Oid			tupOid = InvalidOid;
-	NameData	tempNames[4];
 	int			i;
 
-	values = (Datum *) palloc(tupDesc->natts * sizeof(Datum));
-	nulls = (bool *) palloc(tupDesc->natts * sizeof(bool));
-
-	memset(values, 0, tupDesc->natts * sizeof(Datum));
-	memset(nulls, true, tupDesc->natts * sizeof(bool));
-
 	for (i = 0; i < nkeys; i++)
 	{
-		int			attindex = cache->cc_key[i];
-		Datum		keyval = skeys[i].sk_argument;
+		int			attnum = attnos[i];
+		Form_pg_attribute att;
+
+		/* only valid system attribute is the oid, which is by value */
+		if (attnum == ObjectIdAttributeNumber)
+			continue;
+		Assert(attnum > 0);
+
+		att = TupleDescAttr(tupdesc, attnum - 1);
+
+		if (!att->attbyval)
+			pfree(DatumGetPointer(keys[i]));
+	}
+}
+
+/*
+ * Helper routine that copies the keys in the srckeys array into the dstkeys
+ * one, guaranteeing that the datums are fully allocated in the current memory
+ * context.
+ */
+static void
+CatCacheCopyKeys(TupleDesc tupdesc, int nkeys, int *attnos,
+				 Datum *srckeys, Datum *dstkeys)
+{
+	int			i;
 
-		if (attindex > 0)
-		{
 	/*
-			 * Here we must be careful in case the caller passed a C string
-			 * where a NAME is wanted: convert the given argument to a
-			 * correctly padded NAME.  Otherwise the memcpy() done in
-			 * heap_form_tuple could fall off the end of memory.
+	 * XXX: memory and lookup performance could possibly be improved by
+	 * storing all keys in one allocation.
 	 */
-			if (cache->cc_isname[i])
+
+	for (i = 0; i < nkeys; i++)
 	{
-				Name		newval = &tempNames[i];
+		int			attnum = attnos[i];
 
-				namestrcpy(newval, DatumGetCString(keyval));
-				keyval = NameGetDatum(newval);
-			}
-			values[attindex - 1] = keyval;
-			nulls[attindex - 1] = false;
+		if (attnum == ObjectIdAttributeNumber)
+		{
+			dstkeys[i] = srckeys[i];
 		}
 		else
 		{
-			Assert(attindex == ObjectIdAttributeNumber);
-			tupOid = DatumGetObjectId(keyval);
-		}
-	}
+			Form_pg_attribute att = TupleDescAttr(tupdesc, attnum - 1);
+			Datum		src = srckeys[i];
+			NameData	srcname;
 
-	ntp = heap_form_tuple(tupDesc, values, nulls);
-	if (tupOid != InvalidOid)
-		HeapTupleSetOid(ntp, tupOid);
+			/*
+			 * Must be careful in case the caller passed a C string where a
+			 * NAME is wanted: convert the given argument to a correctly
+			 * padded NAME.  Otherwise the memcpy() done by datumCopy() could
+			 * fall off the end of memory.
+			 */
+			if (att->atttypid == NAMEOID)
+			{
+				namestrcpy(&srcname, DatumGetCString(src));
+				src = NameGetDatum(&srcname);
+			}
 
-	pfree(values);
-	pfree(nulls);
+			dstkeys[i] = datumCopy(src,
+								   att->attbyval,
+								   att->attlen);
+		}
+	}
 
-	return ntp;
 }
 
-
 /*
  *	PrepareToInvalidateCacheTuple()
  *
@@ -1820,7 +2068,7 @@ PrepareToInvalidateCacheTuple(Relation relation,
 		if (ccp->cc_tupdesc == NULL)
 			CatalogCacheInitializeCache(ccp);
 
-		hashvalue = CatalogCacheComputeTupleHashValue(ccp, tuple);
+		hashvalue = CatalogCacheComputeTupleHashValue(ccp, ccp->cc_nkeys, tuple);
 		dbid = ccp->cc_relisshared ? (Oid) 0 : MyDatabaseId;
 
 		(*function) (ccp->id, hashvalue, dbid);
@@ -1829,7 +2077,7 @@ PrepareToInvalidateCacheTuple(Relation relation,
 		{
 			uint32		newhashvalue;
 
-			newhashvalue = CatalogCacheComputeTupleHashValue(ccp, newtuple);
+			newhashvalue = CatalogCacheComputeTupleHashValue(ccp, ccp->cc_nkeys, newtuple);
 
 			if (newhashvalue != hashvalue)
 				(*function) (ccp->id, newhashvalue, dbid);

src/backend/utils/cache/syscache.c

@@ -1102,13 +1102,56 @@ SearchSysCache(int cacheId,
 			   Datum key3,
 			   Datum key4)
 {
-	if (cacheId < 0 || cacheId >= SysCacheSize ||
-		!PointerIsValid(SysCache[cacheId]))
-		elog(ERROR, "invalid cache ID: %d", cacheId);
+	Assert(cacheId >= 0 && cacheId < SysCacheSize &&
+		   PointerIsValid(SysCache[cacheId]));
 
 	return SearchCatCache(SysCache[cacheId], key1, key2, key3, key4);
 }
 
+HeapTuple
+SearchSysCache1(int cacheId,
+				Datum key1)
+{
+	Assert(cacheId >= 0 && cacheId < SysCacheSize &&
+		   PointerIsValid(SysCache[cacheId]));
+	Assert(SysCache[cacheId]->cc_nkeys == 1);
+
+	return SearchCatCache1(SysCache[cacheId], key1);
+}
+
+HeapTuple
+SearchSysCache2(int cacheId,
+				Datum key1, Datum key2)
+{
+	Assert(cacheId >= 0 && cacheId < SysCacheSize &&
+		   PointerIsValid(SysCache[cacheId]));
+	Assert(SysCache[cacheId]->cc_nkeys == 2);
+
+	return SearchCatCache2(SysCache[cacheId], key1, key2);
+}
+
+HeapTuple
+SearchSysCache3(int cacheId,
+				Datum key1, Datum key2, Datum key3)
+{
+	Assert(cacheId >= 0 && cacheId < SysCacheSize &&
+		   PointerIsValid(SysCache[cacheId]));
+	Assert(SysCache[cacheId]->cc_nkeys == 3);
+
+	return SearchCatCache3(SysCache[cacheId], key1, key2, key3);
+}
+
+HeapTuple
+SearchSysCache4(int cacheId,
+				Datum key1, Datum key2, Datum key3, Datum key4)
+{
+	Assert(cacheId >= 0 && cacheId < SysCacheSize &&
+		   PointerIsValid(SysCache[cacheId]));
+	Assert(SysCache[cacheId]->cc_nkeys == 4);
+
+	return SearchCatCache4(SysCache[cacheId], key1, key2, key3, key4);
+}
+
 /*
  * ReleaseSysCache
  *		Release previously grabbed reference count on a tuple

src/include/utils/catcache.h

@@ -34,25 +34,33 @@
 
 #define CATCACHE_MAXKEYS		4
 
+
+/* function computing a datum's hash */
+typedef uint32 (*CCHashFN) (Datum datum);
+
+/* function computing equality of two datums */
+typedef bool (*CCFastEqualFN) (Datum a, Datum b);
+
 typedef struct catcache
 {
 	int			id;				/* cache identifier --- see syscache.h */
-	slist_node	cc_next;		/* list link */
+	int			cc_nbuckets;	/* # of hash buckets in this cache */
+	TupleDesc	cc_tupdesc;		/* tuple descriptor (copied from reldesc) */
+	dlist_head *cc_bucket;		/* hash buckets */
+	CCHashFN	cc_hashfunc[CATCACHE_MAXKEYS];	/* hash function for each key */
+	CCFastEqualFN cc_fastequal[CATCACHE_MAXKEYS];	/* fast equal function for
+													 * each key */
+	int			cc_keyno[CATCACHE_MAXKEYS]; /* AttrNumber of each key */
+	dlist_head	cc_lists;		/* list of CatCList structs */
+	int			cc_ntup;		/* # of tuples currently in this cache */
+	int			cc_nkeys;		/* # of keys (1..CATCACHE_MAXKEYS) */
 	const char *cc_relname;		/* name of relation the tuples come from */
 	Oid			cc_reloid;		/* OID of relation the tuples come from */
 	Oid			cc_indexoid;	/* OID of index matching cache keys */
 	bool		cc_relisshared; /* is relation shared across databases? */
-	TupleDesc	cc_tupdesc;		/* tuple descriptor (copied from reldesc) */
-	int			cc_ntup;		/* # of tuples currently in this cache */
-	int			cc_nbuckets;	/* # of hash buckets in this cache */
-	int			cc_nkeys;		/* # of keys (1..CATCACHE_MAXKEYS) */
-	int			cc_key[CATCACHE_MAXKEYS];	/* AttrNumber of each key */
-	PGFunction	cc_hashfunc[CATCACHE_MAXKEYS];	/* hash function for each key */
+	slist_node	cc_next;		/* list link */
 	ScanKeyData cc_skey[CATCACHE_MAXKEYS];	/* precomputed key info for heap
 											 * scans */
-	bool		cc_isname[CATCACHE_MAXKEYS];	/* flag "name" key columns */
-	dlist_head	cc_lists;		/* list of CatCList structs */
-	dlist_head *cc_bucket;		/* hash buckets */
 
 	/*
 	 * Keep these at the end, so that compiling catcache.c with CATCACHE_STATS
@@ -79,7 +87,14 @@ typedef struct catctup
 {
 	int			ct_magic;		/* for identifying CatCTup entries */
 #define CT_MAGIC   0x57261502
-	CatCache   *my_cache;		/* link to owning catcache */
+
+	uint32		hash_value;		/* hash value for this tuple's keys */
+
+	/*
+	 * Lookup keys for the entry. By-reference datums point into the tuple for
+	 * positive cache entries, and are separately allocated for negative ones.
+	 */
+	Datum		keys[CATCACHE_MAXKEYS];
 
 	/*
 	 * Each tuple in a cache is a member of a dlist that stores the elements
@@ -88,15 +103,6 @@ typedef struct catctup
 	 */
 	dlist_node	cache_elem;		/* list member of per-bucket list */
 
-	/*
-	 * The tuple may also be a member of at most one CatCList.  (If a single
-	 * catcache is list-searched with varying numbers of keys, we may have to
-	 * make multiple entries for the same tuple because of this restriction.
-	 * Currently, that's not expected to be common, so we accept the potential
-	 * inefficiency.)
-	 */
-	struct catclist *c_list;	/* containing CatCList, or NULL if none */
-
 	/*
 	 * A tuple marked "dead" must not be returned by subsequent searches.
 	 * However, it won't be physically deleted from the cache until its
@@ -112,24 +118,28 @@ typedef struct catctup
 	int			refcount;		/* number of active references */
 	bool		dead;			/* dead but not yet removed? */
 	bool		negative;		/* negative cache entry? */
-	uint32		hash_value;		/* hash value for this tuple's keys */
 	HeapTupleData tuple;		/* tuple management header */
-} CatCTup;
 
+	/*
+	 * The tuple may also be a member of at most one CatCList.  (If a single
+	 * catcache is list-searched with varying numbers of keys, we may have to
+	 * make multiple entries for the same tuple because of this restriction.
+	 * Currently, that's not expected to be common, so we accept the potential
+	 * inefficiency.)
+	 */
+	struct catclist *c_list;	/* containing CatCList, or NULL if none */
 
-typedef struct catclist
-{
-	int			cl_magic;		/* for identifying CatCList entries */
-#define CL_MAGIC   0x52765103
 	CatCache   *my_cache;		/* link to owning catcache */
+	/* properly aligned tuple data follows, unless a negative entry */
+} CatCTup;
 
-	/*
+
+/*
  * A CatCList describes the result of a partial search, ie, a search using
-	 * only the first K key columns of an N-key cache.  We form the keys used
-	 * into a tuple (with other attributes NULL) to represent the stored key
-	 * set.  The CatCList object contains links to cache entries for all the
-	 * table rows satisfying the partial key.  (Note: none of these will be
-	 * negative cache entries.)
+ * only the first K key columns of an N-key cache.  We store the keys used
+ * into the keys attribute to represent the stored key set.  The CatCList
+ * object contains links to cache entries for all the table rows satisfying
+ * the partial key.  (Note: none of these will be negative cache entries.)
  *
  * A CatCList is only a member of a per-cache list; we do not currently
  * divide them into hash buckets.
@@ -144,14 +154,27 @@ typedef struct catclist
  * might not be true during bootstrap or recovery operations. (namespace.c
  * is able to save some cycles when it is true.)
  */
+typedef struct catclist
+{
+	int			cl_magic;		/* for identifying CatCList entries */
+#define CL_MAGIC   0x52765103
+
+	uint32		hash_value;		/* hash value for lookup keys */
+
 	dlist_node	cache_elem;		/* list member of per-catcache list */
+
+	/*
+	 * Lookup keys for the entry, with the first nkeys elements being valid.
+	 * All by-reference are separately allocated.
+	 */
+	Datum		keys[CATCACHE_MAXKEYS];
+
 	int			refcount;		/* number of active references */
 	bool		dead;			/* dead but not yet removed? */
 	bool		ordered;		/* members listed in index order? */
 	short		nkeys;			/* number of lookup keys specified */
-	uint32		hash_value;		/* hash value for lookup keys */
-	HeapTupleData tuple;		/* header for tuple holding keys */
 	int			n_members;		/* number of member tuples */
+	CatCache   *my_cache;		/* link to owning catcache */
 	CatCTup    *members[FLEXIBLE_ARRAY_MEMBER]; /* members */
 } CatCList;
 
@@ -174,8 +197,15 @@ extern CatCache *InitCatCache(int id, Oid reloid, Oid indexoid,
 extern void InitCatCachePhase2(CatCache *cache, bool touch_index);
 
 extern HeapTuple SearchCatCache(CatCache *cache,
-			   Datum v1, Datum v2,
-			   Datum v3, Datum v4);
+			   Datum v1, Datum v2, Datum v3, Datum v4);
+extern HeapTuple SearchCatCache1(CatCache *cache,
+				Datum v1);
+extern HeapTuple SearchCatCache2(CatCache *cache,
+				Datum v1, Datum v2);
+extern HeapTuple SearchCatCache3(CatCache *cache,
+				Datum v1, Datum v2, Datum v3);
+extern HeapTuple SearchCatCache4(CatCache *cache,
+				Datum v1, Datum v2, Datum v3, Datum v4);
 extern void ReleaseCatCache(HeapTuple tuple);
 
 extern uint32 GetCatCacheHashValue(CatCache *cache,

src/include/utils/syscache.h

@@ -117,6 +117,20 @@ extern void InitCatalogCachePhase2(void);
 
 extern HeapTuple SearchSysCache(int cacheId,
 			   Datum key1, Datum key2, Datum key3, Datum key4);
+
+/*
+ * The use of argument specific numbers is encouraged. They're faster, and
+ * insulates the caller from changes in the maximum number of keys.
+ */
+extern HeapTuple SearchSysCache1(int cacheId,
+				Datum key1);
+extern HeapTuple SearchSysCache2(int cacheId,
+				Datum key1, Datum key2);
+extern HeapTuple SearchSysCache3(int cacheId,
+				Datum key1, Datum key2, Datum key3);
+extern HeapTuple SearchSysCache4(int cacheId,
+				Datum key1, Datum key2, Datum key3, Datum key4);
+
 extern void ReleaseSysCache(HeapTuple tuple);
 
 /* convenience routines */
@@ -156,15 +170,6 @@ extern bool RelationSupportsSysCache(Oid relid);
  * functions is encouraged, as it insulates the caller from changes in the
  * maximum number of keys.
  */
-#define SearchSysCache1(cacheId, key1) \
-	SearchSysCache(cacheId, key1, 0, 0, 0)
-#define SearchSysCache2(cacheId, key1, key2) \
-	SearchSysCache(cacheId, key1, key2, 0, 0)
-#define SearchSysCache3(cacheId, key1, key2, key3) \
-	SearchSysCache(cacheId, key1, key2, key3, 0)
-#define SearchSysCache4(cacheId, key1, key2, key3, key4) \
-	SearchSysCache(cacheId, key1, key2, key3, key4)
-
 #define SearchSysCacheCopy1(cacheId, key1) \
 	SearchSysCacheCopy(cacheId, key1, 0, 0, 0)
 #define SearchSysCacheCopy2(cacheId, key1, key2) \

src/tools/pgindent/typedefs.list

@@ -302,6 +302,8 @@ CatCache
 CatCacheHeader
 CatalogId
 CatalogIndexState
+CCHashFN
+CCFastEqualFN
 ChangeVarNodes_context
 CheckPoint
 CheckPointStmt