Merge branch 'jk/ref-cache-non-repository-optim'

The underlying machinery used by "ls-files -o" and other commands
have been taught not to create empty submodule ref cache for a
directory that is not a submodule.  This removes a ton of wasted
CPU cycles.

* jk/ref-cache-non-repository-optim:
  resolve_gitlink_ref: ignore non-repository paths
  clean: make is_git_repository a public function

6 files changed, 80 insertions, 40 deletions

diff --git a/builtin/clean.c b/builtin/clean.c
index cc5f972..7b08237 100644
--- a/builtin/clean.c
+++ b/builtin/clean.c
@@ -147,30 +147,6 @@ static int exclude_cb(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
-/*
- * Return 1 if the given path is the root of a git repository or
- * submodule else 0. Will not return 1 for bare repositories with the
- * exception of creating a bare repository in "foo/.git" and calling
- * is_git_repository("foo").
- */
-static int is_git_repository(struct strbuf *path)
-{
-	int ret = 0;
-	int gitfile_error;
-	size_t orig_path_len = path->len;
-	assert(orig_path_len != 0);
-	strbuf_complete(path, '/');
-	strbuf_addstr(path, ".git");
-	if (read_gitfile_gently(path->buf, &gitfile_error) || is_git_directory(path->buf))
-		ret = 1;
-	if (gitfile_error == READ_GITFILE_ERR_OPEN_FAILED ||
-	    gitfile_error == READ_GITFILE_ERR_READ_FAILED)
-		ret = 1;  /* This could be a real .git file, take the
-			   * safe option and avoid cleaning */
-	strbuf_setlen(path, orig_path_len);
-	return ret;
-}
-
 static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag,
 		int dry_run, int quiet, int *dir_gone)
 {
@@ -182,7 +158,7 @@ static int remove_dirs(struct strbuf *path, const char *prefix, int force_flag,
 
 	*dir_gone = 1;
 
-	if ((force_flag & REMOVE_DIR_KEEP_NESTED_GIT) && is_git_repository(path)) {
+	if ((force_flag & REMOVE_DIR_KEEP_NESTED_GIT) && is_nonbare_repository_dir(path)) {
 		if (!quiet) {
 			quote_path_relative(path->buf, prefix, &quoted);
 			printf(dry_run ?  _(msg_would_skip_git_dir) : _(msg_skip_git_dir),
diff --git a/cache.h b/cache.h
index dfc459c..553b04b 100644
--- a/cache.h
+++ b/cache.h
@@ -458,7 +458,6 @@ extern char *git_work_tree_cfg;
 extern int is_inside_work_tree(void);
 extern const char *get_git_dir(void);
 extern const char *get_git_common_dir(void);
-extern int is_git_directory(const char *path);
 extern char *get_object_directory(void);
 extern char *get_index_file(void);
 extern char *get_graft_file(void);
@@ -469,6 +468,25 @@ extern const char *get_git_namespace(void);
 extern const char *strip_namespace(const char *namespaced_ref);
 extern const char *get_git_work_tree(void);
 
+/*
+ * Return true if the given path is a git directory; note that this _just_
+ * looks at the directory itself. If you want to know whether "foo/.git"
+ * is a repository, you must feed that path, not just "foo".
+ */
+extern int is_git_directory(const char *path);
+
+/*
+ * Return 1 if the given path is the root of a git repository or
+ * submodule, else 0. Will not return 1 for bare repositories with the
+ * exception of creating a bare repository in "foo/.git" and calling
+ * is_git_repository("foo").
+ *
+ * If we run into read errors, we err on the side of saying "yes, it is",
+ * as we usually consider sub-repos precious, and would prefer to err on the
+ * side of not disrupting or deleting them.
+ */
+extern int is_nonbare_repository_dir(struct strbuf *path);
+
 #define READ_GITFILE_ERR_STAT_FAILED 1
 #define READ_GITFILE_ERR_NOT_A_FILE 2
 #define READ_GITFILE_ERR_OPEN_FAILED 3
diff --git a/refs/files-backend.c b/refs/files-backend.c
index 81c92b4..b569762 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -933,6 +933,10 @@ static void clear_loose_ref_cache(struct ref_cache *refs)
 	}
 }
 
+/*
+ * Create a new submodule ref cache and add it to the internal
+ * set of caches.
+ */
 static struct ref_cache *create_ref_cache(const char *submodule)
 {
 	int len;
@@ -942,16 +946,12 @@ static struct ref_cache *create_ref_cache(const char *submodule)
 	len = strlen(submodule) + 1;
 	refs = xcalloc(1, sizeof(struct ref_cache) + len);
 	memcpy(refs->name, submodule, len);
+	refs->next = submodule_ref_caches;
+	submodule_ref_caches = refs;
 	return refs;
 }
 
-/*
- * Return a pointer to a ref_cache for the specified submodule. For
- * the main repository, use submodule==NULL. The returned structure
- * will be allocated and initialized but not necessarily populated; it
- * should not be freed.
- */
-static struct ref_cache *get_ref_cache(const char *submodule)
+static struct ref_cache *lookup_ref_cache(const char *submodule)
 {
 	struct ref_cache *refs;
 
@@ -961,10 +961,20 @@ static struct ref_cache *get_ref_cache(const char *submodule)
 	for (refs = submodule_ref_caches; refs; refs = refs->next)
 		if (!strcmp(submodule, refs->name))
 			return refs;
+	return NULL;
+}
 
-	refs = create_ref_cache(submodule);
-	refs->next = submodule_ref_caches;
-	submodule_ref_caches = refs;
+/*
+ * Return a pointer to a ref_cache for the specified submodule. For
+ * the main repository, use submodule==NULL. The returned structure
+ * will be allocated and initialized but not necessarily populated; it
+ * should not be freed.
+ */
+static struct ref_cache *get_ref_cache(const char *submodule)
+{
+	struct ref_cache *refs = lookup_ref_cache(submodule);
+	if (!refs)
+		refs = create_ref_cache(submodule);
 	return refs;
 }
 
@@ -1336,16 +1346,24 @@ static int resolve_gitlink_ref_recursive(struct ref_cache *refs,
 int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *sha1)
 {
 	int len = strlen(path), retval;
-	char *submodule;
+	struct strbuf submodule = STRBUF_INIT;
 	struct ref_cache *refs;
 
 	while (len && path[len-1] == '/')
 		len--;
 	if (!len)
 		return -1;
-	submodule = xstrndup(path, len);
-	refs = get_ref_cache(submodule);
-	free(submodule);
+
+	strbuf_add(&submodule, path, len);
+	refs = lookup_ref_cache(submodule.buf);
+	if (!refs) {
+		if (!is_nonbare_repository_dir(&submodule)) {
+			strbuf_release(&submodule);
+			return -1;
+		}
+		refs = create_ref_cache(submodule.buf);
+	}
+	strbuf_release(&submodule);
 
 	retval = resolve_gitlink_ref_recursive(refs, refname, sha1, 0);
 	return retval;
diff --git a/setup.c b/setup.c
index d343725..2c4b22c 100644
--- a/setup.c
+++ b/setup.c
@@ -312,6 +312,23 @@ done:
 	return ret;
 }
 
+int is_nonbare_repository_dir(struct strbuf *path)
+{
+	int ret = 0;
+	int gitfile_error;
+	size_t orig_path_len = path->len;
+	assert(orig_path_len != 0);
+	strbuf_complete(path, '/');
+	strbuf_addstr(path, ".git");
+	if (read_gitfile_gently(path->buf, &gitfile_error) || is_git_directory(path->buf))
+		ret = 1;
+	if (gitfile_error == READ_GITFILE_ERR_OPEN_FAILED ||
+	    gitfile_error == READ_GITFILE_ERR_READ_FAILED)
+		ret = 1;
+	strbuf_setlen(path, orig_path_len);
+	return ret;
+}
+
 int is_inside_git_dir(void)
 {
 	if (inside_git_dir < 0)
diff --git a/t/perf/p7300-clean.sh b/t/perf/p7300-clean.sh
index ec94cdd..7c1888a 100755
--- a/t/perf/p7300-clean.sh
+++ b/t/perf/p7300-clean.sh
@@ -28,4 +28,8 @@ test_perf 'clean many untracked sub dirs, ignore nested git' '
 	git clean -n -q -f -f -d 100000_sub_dirs/
 '
 
+test_perf 'ls-files -o' '
+	git ls-files -o
+'
+
 test_done
diff --git a/t/t3000-ls-files-others.sh b/t/t3000-ls-files-others.sh
index 88be904..c525656 100755
--- a/t/t3000-ls-files-others.sh
+++ b/t/t3000-ls-files-others.sh
@@ -65,6 +65,13 @@ test_expect_success '--no-empty-directory hides empty directory' '
 	test_cmp expected3 output
 '
 
+test_expect_success 'ls-files --others handles non-submodule .git' '
+	mkdir not-a-submodule &&
+	echo foo >not-a-submodule/.git &&
+	git ls-files -o >output &&
+	test_cmp expected1 output
+'
+
 test_expect_success SYMLINKS 'ls-files --others with symlinked submodule' '
 	git init super &&
 	git init sub &&