Merge branch 'vd/loose-ref-iteration-optimization'

The code to iterate over loose references have been optimized to
reduce the number of lstat() system calls.

* vd/loose-ref-iteration-optimization:
  files-backend.c: avoid stat in 'loose_fill_ref_dir'
  dir.[ch]: add 'follow_symlink' arg to 'get_dtype'
  dir.[ch]: expose 'get_dtype'
  ref-cache.c: fix prefix matching in ref iteration

Author: gitster

diagnose.c

@@ -71,42 +71,6 @@ static int dir_file_stats(struct object_directory *object_dir, void *data)
 	return 0;
 }
 
-/*
- * Get the d_type of a dirent. If the d_type is unknown, derive it from
- * stat.st_mode.
- *
- * Note that 'path' is assumed to have a trailing slash. It is also modified
- * in-place during the execution of the function, but is then reverted to its
- * original value before returning.
- */
-static unsigned char get_dtype(struct dirent *e, struct strbuf *path)
-{
-	struct stat st;
-	unsigned char dtype = DTYPE(e);
-	size_t base_path_len;
-
-	if (dtype != DT_UNKNOWN)
-		return dtype;
-
-	/* d_type unknown in dirent, try to fall back on lstat results */
-	base_path_len = path->len;
-	strbuf_addstr(path, e->d_name);
-	if (lstat(path->buf, &st))
-		goto cleanup;
-
-	/* determine d_type from st_mode */
-	if (S_ISREG(st.st_mode))
-		dtype = DT_REG;
-	else if (S_ISDIR(st.st_mode))
-		dtype = DT_DIR;
-	else if (S_ISLNK(st.st_mode))
-		dtype = DT_LNK;
-
-cleanup:
-	strbuf_setlen(path, base_path_len);
-	return dtype;
-}
-
 static int count_files(struct strbuf *path)
 {
 	DIR *dir = opendir(path->buf);
@@ -117,7 +81,7 @@ static int count_files(struct strbuf *path)
 		return 0;
 
 	while ((e = readdir_skip_dot_and_dotdot(dir)) != NULL)
-		if (get_dtype(e, path) == DT_REG)
+		if (get_dtype(e, path, 0) == DT_REG)
 			count++;
 
 	closedir(dir);
@@ -146,7 +110,7 @@ static void loose_objs_stats(struct strbuf *buf, const char *path)
 	base_path_len = count_path.len;
 
 	while ((e = readdir_skip_dot_and_dotdot(dir)) != NULL)
-		if (get_dtype(e, &count_path) == DT_DIR &&
+		if (get_dtype(e, &count_path, 0) == DT_DIR &&
 		    strlen(e->d_name) == 2 &&
 		    !hex_to_bytes(&c, e->d_name, 1)) {
 			strbuf_setlen(&count_path, base_path_len);
@@ -191,7 +155,7 @@ static int add_directory_to_archiver(struct strvec *archiver_args,
 
 		strbuf_add_absolute_path(&abspath, at_root ? "." : path);
 		strbuf_addch(&abspath, '/');
-		dtype = get_dtype(e, &abspath);
+		dtype = get_dtype(e, &abspath, 0);
 
 		strbuf_setlen(&buf, len);
 		strbuf_addstr(&buf, e->d_name);

dir.c

@@ -2235,6 +2235,39 @@ static int get_index_dtype(struct index_state *istate,
 	return DT_UNKNOWN;
 }
 
+unsigned char get_dtype(struct dirent *e, struct strbuf *path,
+			int follow_symlink)
+{
+	struct stat st;
+	unsigned char dtype = DTYPE(e);
+	size_t base_path_len;
+
+	if (dtype != DT_UNKNOWN && !(follow_symlink && dtype == DT_LNK))
+		return dtype;
+
+	/*
+	 * d_type unknown or unfollowed symlink, try to fall back on [l]stat
+	 * results. If [l]stat fails, explicitly set DT_UNKNOWN.
+	 */
+	base_path_len = path->len;
+	strbuf_addstr(path, e->d_name);
+	if ((follow_symlink && stat(path->buf, &st)) ||
+	    (!follow_symlink && lstat(path->buf, &st)))
+		goto cleanup;
+
+	/* determine d_type from st_mode */
+	if (S_ISREG(st.st_mode))
+		dtype = DT_REG;
+	else if (S_ISDIR(st.st_mode))
+		dtype = DT_DIR;
+	else if (S_ISLNK(st.st_mode))
+		dtype = DT_LNK;
+
+cleanup:
+	strbuf_setlen(path, base_path_len);
+	return dtype;
+}
+
 static int resolve_dtype(int dtype, struct index_state *istate,
 			 const char *path, int len)
 {

dir.h

@@ -363,6 +363,22 @@ struct dir_struct {
 
 struct dirent *readdir_skip_dot_and_dotdot(DIR *dirp);
 
+/*
+ * Get the d_type of a dirent. If the d_type is unknown, derive it from
+ * stat.st_mode using the path to the dirent's containing directory (path) and
+ * the name of the dirent itself.
+ *
+ * If 'follow_symlink' is 1, this function will attempt to follow DT_LNK types
+ * using 'stat'. Links are *not* followed recursively, so a symlink pointing
+ * to another symlink will still resolve to 'DT_LNK'.
+ *
+ * Note that 'path' is assumed to have a trailing slash. It is also modified
+ * in-place during the execution of the function, but is then reverted to its
+ * original value before returning.
+ */
+unsigned char get_dtype(struct dirent *e, struct strbuf *path,
+			int follow_symlink);
+
 /*Count the number of slashes for string s*/
 int count_slashes(const char *s);
 

refs/files-backend.c

@@ -246,10 +246,8 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,
 	int dirnamelen = strlen(dirname);
 	struct strbuf refname;
 	struct strbuf path = STRBUF_INIT;
-	size_t path_baselen;
 
 	files_ref_path(refs, &path, dirname);
-	path_baselen = path.len;
 
 	d = opendir(path.buf);
 	if (!d) {
@@ -262,23 +260,22 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,
 
 	while ((de = readdir(d)) != NULL) {
 		struct object_id oid;
-		struct stat st;
 		int flag;
+		unsigned char dtype;
 
 		if (de->d_name[0] == '.')
 			continue;
 		if (ends_with(de->d_name, ".lock"))
 			continue;
 		strbuf_addstr(&refname, de->d_name);
-		strbuf_addstr(&path, de->d_name);
-		if (stat(path.buf, &st) < 0) {
-			; /* silently ignore */
-		} else if (S_ISDIR(st.st_mode)) {
+
+		dtype = get_dtype(de, &path, 1);
+		if (dtype == DT_DIR) {
 			strbuf_addch(&refname, '/');
 			add_entry_to_dir(dir,
 					 create_dir_entry(dir->cache, refname.buf,
 							  refname.len));
-		} else {
+		} else if (dtype == DT_REG) {
 			if (!refs_resolve_ref_unsafe(&refs->base,
 						     refname.buf,
 						     RESOLVE_REF_READING,
@@ -308,7 +305,6 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,
 					 create_ref_entry(refname.buf, &oid, flag));
 		}
 		strbuf_setlen(&refname, dirnamelen);
-		strbuf_setlen(&path, path_baselen);
 	}
 	strbuf_release(&refname);
 	strbuf_release(&path);

refs/ref-cache.c

@@ -412,7 +412,8 @@ static int cache_ref_iterator_advance(struct ref_iterator *ref_iterator)
 
 		if (level->prefix_state == PREFIX_WITHIN_DIR) {
 			entry_prefix_state = overlaps_prefix(entry->name, iter->prefix);
-			if (entry_prefix_state == PREFIX_EXCLUDES_DIR)
+			if (entry_prefix_state == PREFIX_EXCLUDES_DIR ||
+			    (entry_prefix_state == PREFIX_WITHIN_DIR && !(entry->flag & REF_DIR)))
 				continue;
 		} else {
 			entry_prefix_state = level->prefix_state;

t/t1500-rev-parse.sh

@@ -264,4 +264,27 @@ test_expect_success 'rev-parse --since= unsqueezed ordering' '
 	test_cmp expect actual
 '
 
+test_expect_success 'rev-parse --bisect includes bad, excludes good' '
+	test_commit_bulk 6 &&
+
+	git update-ref refs/bisect/bad-1 HEAD~1 &&
+	git update-ref refs/bisect/b HEAD~2 &&
+	git update-ref refs/bisect/bad-3 HEAD~3 &&
+	git update-ref refs/bisect/good-3 HEAD~3 &&
+	git update-ref refs/bisect/bad-4 HEAD~4 &&
+	git update-ref refs/bisect/go HEAD~4 &&
+
+	# Note: refs/bisect/b and refs/bisect/go should be ignored because they
+	# do not match the refs/bisect/bad or refs/bisect/good prefixes.
+	cat >expect <<-EOF &&
+	refs/bisect/bad-1
+	refs/bisect/bad-3
+	refs/bisect/bad-4
+	^refs/bisect/good-3
+	EOF
+
+	git rev-parse --symbolic-full-name --bisect >actual &&
+	test_cmp expect actual
+'
+
 test_done

t/t4205-log-pretty-formats.sh

@@ -956,6 +956,36 @@ test_expect_success '%S in git log --format works with other placeholders (part
 	test_cmp expect actual
 '
 
+test_expect_success 'setup more commits for %S with --bisect' '
+	test_commit four &&
+	test_commit five &&
+
+	head1=$(git rev-parse --verify HEAD~0) &&
+	head2=$(git rev-parse --verify HEAD~1) &&
+	head3=$(git rev-parse --verify HEAD~2) &&
+	head4=$(git rev-parse --verify HEAD~3)
+'
+
+test_expect_success '%S with --bisect labels commits with refs/bisect/bad ref' '
+	git update-ref refs/bisect/bad-$head1 $head1 &&
+	git update-ref refs/bisect/go $head1 &&
+	git update-ref refs/bisect/bad-$head2 $head2 &&
+	git update-ref refs/bisect/b $head3 &&
+	git update-ref refs/bisect/bad-$head4 $head4 &&
+	git update-ref refs/bisect/good-$head4 $head4 &&
+
+	# We expect to see the range of commits betwee refs/bisect/good-$head4
+	# and refs/bisect/bad-$head1. The "source" ref is the nearest bisect ref
+	# from which the commit is reachable.
+	cat >expect <<-EOF &&
+	$head1 refs/bisect/bad-$head1
+	$head2 refs/bisect/bad-$head2
+	$head3 refs/bisect/bad-$head2
+	EOF
+	git log --bisect --format="%H %S" >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success 'log --pretty=reference' '
 	git log --pretty="tformat:%h (%s, %as)" >expect &&
 	git log --pretty=reference >actual &&