Convert uses of hash_string_pointer to fasthash equivalent

j-naylor · j-naylor · commit f956ecd0353b · 2024-04-06T12:20:40.000+07:00
Remove duplicate hash_string_pointer() function definitions by creating a new inline function hash_string() for this purpose. This has the added advantage of avoiding strlen() calls when doing hash lookup. It's not clear how many of these are perfomance-sensitive enough to benefit from that, but the simplification is worth it on its own. Reviewed by Jeff Davis Discussion: https://postgr.es/m/CANWCAZbg_XeSeY0a_PqWmWqeRATvzTzUNYRLeT%2Bbzs%2BYQdC92g%40mail.gmail.com
diff --git a/src/bin/pg_combinebackup/load_manifest.c b/src/bin/pg_combinebackup/load_manifest.c
@@ -15,7 +15,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 
-#include "common/hashfn.h"
+#include "common/hashfn_unstable.h"
 #include "common/logging.h"
 #include "common/parse_manifest.h"
 #include "load_manifest.h"
@@ -44,12 +44,11 @@
  * Define a hash table which we can use to store information about the files
  * mentioned in the backup manifest.
  */
-static uint32 hash_string_pointer(char *s);
 #define SH_PREFIX		manifest_files
 #define SH_ELEMENT_TYPE	manifest_file
 #define SH_KEY_TYPE		char *
 #define	SH_KEY			pathname
-#define SH_HASH_KEY(tb, key)	hash_string_pointer(key)
+#define SH_HASH_KEY(tb, key)	hash_string(key)
 #define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
 #define	SH_SCOPE		extern
 #define SH_RAW_ALLOCATOR	pg_malloc0
@@ -311,14 +310,3 @@ combinebackup_per_wal_range_cb(JsonManifestParseContext *context,
 		manifest->last_wal_range->next = range;
 	manifest->last_wal_range = range;
 }
-
-/*
- * Helper function for manifest_files hash table.
- */
-static uint32
-hash_string_pointer(char *s)
-{
-	unsigned char *ss = (unsigned char *) s;
-
-	return hash_bytes(ss, strlen(s));
-}
diff --git a/src/bin/pg_dump/pg_dumpall.c b/src/bin/pg_dump/pg_dumpall.c
@@ -21,7 +21,7 @@
 #include "catalog/pg_authid_d.h"
 #include "common/connect.h"
 #include "common/file_utils.h"
-#include "common/hashfn.h"
+#include "common/hashfn_unstable.h"
 #include "common/logging.h"
 #include "common/string.h"
 #include "dumputils.h"
@@ -33,8 +33,6 @@
 /* version string we expect back from pg_dump */
 #define PGDUMP_VERSIONSTR "pg_dump (PostgreSQL) " PG_VERSION "\n"
 
-static uint32 hash_string_pointer(char *s);
-
 typedef struct
 {
 	uint32		status;
@@ -46,7 +44,7 @@ typedef struct
 #define SH_ELEMENT_TYPE	RoleNameEntry
 #define SH_KEY_TYPE	char *
 #define SH_KEY		rolename
-#define SH_HASH_KEY(tb, key)	hash_string_pointer(key)
+#define SH_HASH_KEY(tb, key)	hash_string(key)
 #define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
 #define SH_STORE_HASH
 #define SH_GET_HASH(tb, a)		(a)->hashval
@@ -1938,17 +1936,6 @@ dumpTimestamp(const char *msg)
 		fprintf(OPF, "-- %s %s\n\n", msg, buf);
 }
 
-/*
- * Helper function for rolename_hash hash table.
- */
-static uint32
-hash_string_pointer(char *s)
-{
-	unsigned char *ss = (unsigned char *) s;
-
-	return hash_bytes(ss, strlen(s));
-}
-
 /*
  * read_dumpall_filters - retrieve database identifier patterns from file
  *
diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c
@@ -28,7 +28,7 @@
 
 #include "catalog/pg_tablespace_d.h"
 #include "common/file_utils.h"
-#include "common/hashfn.h"
+#include "common/hashfn_unstable.h"
 #include "common/string.h"
 #include "datapagemap.h"
 #include "filemap.h"
@@ -38,12 +38,11 @@
  * Define a hash table which we can use to store information about the files
  * appearing in source and target systems.
  */
-static uint32 hash_string_pointer(const char *s);
 #define SH_PREFIX		filehash
 #define SH_ELEMENT_TYPE	file_entry_t
 #define SH_KEY_TYPE		const char *
 #define	SH_KEY			path
-#define SH_HASH_KEY(tb, key)	hash_string_pointer(key)
+#define SH_HASH_KEY(tb, key)	hash_string(key)
 #define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
 #define	SH_SCOPE		static inline
 #define SH_RAW_ALLOCATOR	pg_malloc0
@@ -821,15 +820,3 @@ decide_file_actions(void)
 
 	return filemap;
 }
-
-
-/*
- * Helper function for filemap hash table.
- */
-static uint32
-hash_string_pointer(const char *s)
-{
-	unsigned char *ss = (unsigned char *) s;
-
-	return hash_bytes(ss, strlen(s));
-}
diff --git a/src/bin/pg_verifybackup/pg_verifybackup.c b/src/bin/pg_verifybackup/pg_verifybackup.c
@@ -19,7 +19,7 @@
 #include <time.h>
 
 #include "common/controldata_utils.h"
-#include "common/hashfn.h"
+#include "common/hashfn_unstable.h"
 #include "common/logging.h"
 #include "common/parse_manifest.h"
 #include "fe_utils/simple_list.h"
@@ -68,12 +68,11 @@ typedef struct manifest_file
  * Define a hash table which we can use to store information about the files
  * mentioned in the backup manifest.
  */
-static uint32 hash_string_pointer(char *s);
 #define SH_PREFIX		manifest_files
 #define SH_ELEMENT_TYPE	manifest_file
 #define SH_KEY_TYPE		char *
 #define	SH_KEY			pathname
-#define SH_HASH_KEY(tb, key)	hash_string_pointer(key)
+#define SH_HASH_KEY(tb, key)	hash_string(key)
 #define SH_EQUAL(tb, a, b)		(strcmp(a, b) == 0)
 #define	SH_SCOPE		static inline
 #define SH_RAW_ALLOCATOR	pg_malloc0
@@ -1028,17 +1027,6 @@ should_ignore_relpath(verifier_context *context, char *relpath)
 	return false;
 }
 
-/*
- * Helper function for manifest_files hash table.
- */
-static uint32
-hash_string_pointer(char *s)
-{
-	unsigned char *ss = (unsigned char *) s;
-
-	return hash_bytes(ss, strlen(s));
-}
-
 /*
  * Print a progress report based on the global variables.
  *
diff --git a/src/include/common/hashfn_unstable.h b/src/include/common/hashfn_unstable.h
@@ -370,4 +370,24 @@ fasthash32(const char *k, size_t len, uint64 seed)
 	return fasthash_reduce32(fasthash64(k, len, seed));
 }
 
+/*
+ * Convenience function for hashing NUL-terminated strings
+ */
+static inline uint32
+hash_string(const char *s)
+{
+	fasthash_state hs;
+	size_t		s_len;
+
+	fasthash_init(&hs, 0);
+
+	/*
+	 * Combine string into the hash and save the length for tweaking the final
+	 * mix.
+	 */
+	s_len = fasthash_accum_cstring(&hs, s);
+
+	return fasthash_final32(&hs, s_len);
+}
+
 #endif							/* HASHFN_UNSTABLE_H */
