lstat_cache(): introduce has_symlink_or_noent_leading_path() function

In some cases, especially inside the unpack-trees.c file, and inside
the verify_absent() function, we can avoid some unnecessary calls to
lstat(), if the lstat_cache() function can also be told to keep track
of non-existing directories.

So we update the lstat_cache() function to handle this new fact,
introduce a new wrapper function, and the result is that we save lots
of lstat() calls for a removed directory which previously contained
lots of files, when we call this new wrapper of lstat_cache() instead
of the old one.

We do similar changes inside the unlink_entry() function, since if we
can already say that the leading directory component of a pathname
does not exist, it is not necessary to try to remove a pathname below
it!

Thanks to Junio C Hamano, Linus Torvalds and Rene Scharfe for valuable
comments to this patch!

Signed-off-by: Kjetil Barvik <barvik@broadpark.no>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

cache.h

@@ -720,6 +720,7 @@ struct checkout {
 
 extern int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath);
 extern int has_symlink_leading_path(int len, const char *name);
+extern int has_symlink_or_noent_leading_path(int len, const char *name);
 
 extern struct alternate_object_database {
 	struct alternate_object_database *next;

symlinks.c

@@ -4,6 +4,7 @@ static struct cache_def {
 	char path[PATH_MAX];
 	int len;
 	int flags;
+	int track_flags;
 } cache;
 
 /*
@@ -30,21 +31,23 @@ static inline int longest_match_lstat_cache(int len, const char *name)
 	return match_len;
 }
 
-static inline void reset_lstat_cache(void)
+static inline void reset_lstat_cache(int track_flags)
 {
 	cache.path[0] = '\0';
 	cache.len = 0;
 	cache.flags = 0;
+	cache.track_flags = track_flags;
 }
 
 #define FL_DIR      (1 << 0)
-#define FL_SYMLINK  (1 << 1)
+#define FL_NOENT    (1 << 1)
-#define FL_LSTATERR (1 << 2)
+#define FL_SYMLINK  (1 << 2)
-#define FL_ERR      (1 << 3)
+#define FL_LSTATERR (1 << 3)
+#define FL_ERR      (1 << 4)
 
 /*
  * Check if name 'name' of length 'len' has a symlink leading
- * component, or if the directory exists and is real.
+ * component, or if the directory exists and is real, or not.
  *
  * To speed up the check, some information is allowed to be cached.
  * This can be indicated by the 'track_flags' argument.
@@ -56,25 +59,35 @@ static int lstat_cache(int len, const char *name,
 	int match_flags, ret_flags, save_flags, max_len;
 	struct stat st;
 
-	/*
+	if (cache.track_flags != track_flags) {
-	 * Check to see if we have a match from the cache for the
+		/*
-	 * symlink path type.
+		 * As a safeguard we clear the cache if the value of
-	 */
+		 * track_flags does not match with the last supplied
-	match_len = last_slash = longest_match_lstat_cache(len, name);
+		 * value.
-	match_flags = cache.flags & track_flags & FL_SYMLINK;
+		 */
-	if (match_flags && match_len == cache.len)
+		reset_lstat_cache(track_flags);
-		return match_flags;
+		match_len = last_slash = 0;
-	/*
+	} else {
-	 * If we now have match_len > 0, we would know that the
+		/*
-	 * matched part will always be a directory.
+		 * Check to see if we have a match from the cache for
-	 *
+		 * the 2 "excluding" path types.
-	 * Also, if we are tracking directories and 'name' is a
+		 */
-	 * substring of the cache on a path component basis, we can
+		match_len = last_slash = longest_match_lstat_cache(len, name);
-	 * return immediately.
+		match_flags = cache.flags & track_flags & (FL_NOENT|FL_SYMLINK);
-	 */
+		if (match_flags && match_len == cache.len)
-	match_flags = track_flags & FL_DIR;
+			return match_flags;
-	if (match_flags && len == match_len)
+		/*
-		return match_flags;
+		 * If we now have match_len > 0, we would know that
+		 * the matched part will always be a directory.
+		 *
+		 * Also, if we are tracking directories and 'name' is
+		 * a substring of the cache on a path component basis,
+		 * we can return immediately.
+		 */
+		match_flags = track_flags & FL_DIR;
+		if (match_flags && len == match_len)
+			return match_flags;
+	}
 
 	/*
 	 * Okay, no match from the cache so far, so now we have to
@@ -95,6 +108,8 @@ static int lstat_cache(int len, const char *name,
 
 		if (lstat(cache.path, &st)) {
 			ret_flags = FL_LSTATERR;
+			if (errno == ENOENT)
+				ret_flags |= FL_NOENT;
 		} else if (S_ISDIR(st.st_mode)) {
 			last_slash_dir = last_slash;
 			continue;
@@ -107,11 +122,11 @@ static int lstat_cache(int len, const char *name,
 	}
 
 	/*
-	 * At the end update the cache.  Note that max 2 different
+	 * At the end update the cache.  Note that max 3 different
-	 * path types, FL_SYMLINK and FL_DIR, can be cached for the
+	 * path types, FL_NOENT, FL_SYMLINK and FL_DIR, can be cached
-	 * moment!
+	 * for the moment!
 	 */
-	save_flags = ret_flags & track_flags & FL_SYMLINK;
+	save_flags = ret_flags & track_flags & (FL_NOENT|FL_SYMLINK);
 	if (save_flags && last_slash > 0 && last_slash < PATH_MAX) {
 		cache.path[last_slash] = '\0';
 		cache.len = last_slash;
@@ -120,20 +135,20 @@ static int lstat_cache(int len, const char *name,
 		   last_slash_dir > 0 && last_slash_dir < PATH_MAX) {
 		/*
 		 * We have a separate test for the directory case,
-		 * since it could be that we have found a symlink and
+		 * since it could be that we have found a symlink or a
-		 * the track_flags says that we cannot cache this
+		 * non-existing directory and the track_flags says
-		 * fact, so the cache would then have been left empty
+		 * that we cannot cache this fact, so the cache would
-		 * in this case.
+		 * then have been left empty in this case.
 		 *
 		 * But if we are allowed to track real directories, we
 		 * can still cache the path components before the last
-		 * one (the found symlink component).
+		 * one (the found symlink or non-existing component).
 		 */
 		cache.path[last_slash_dir] = '\0';
 		cache.len = last_slash_dir;
 		cache.flags = FL_DIR;
 	} else {
-		reset_lstat_cache();
+		reset_lstat_cache(track_flags);
 	}
 	return ret_flags;
 }
@@ -147,3 +162,14 @@ int has_symlink_leading_path(int len, const char *name)
 			   FL_SYMLINK|FL_DIR) &
 		FL_SYMLINK;
 }
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component or
+ * if some leading path component does not exists.
+ */
+int has_symlink_or_noent_leading_path(int len, const char *name)
+{
+	return lstat_cache(len, name,
+			   FL_SYMLINK|FL_NOENT|FL_DIR) &
+		(FL_SYMLINK|FL_NOENT);
+}

unpack-trees.c

@@ -61,7 +61,7 @@ static void unlink_entry(struct cache_entry *ce)
 	char *cp, *prev;
 	char *name = ce->name;
 
-	if (has_symlink_leading_path(ce_namelen(ce), ce->name))
+	if (has_symlink_or_noent_leading_path(ce_namelen(ce), ce->name))
 		return;
 	if (unlink(name))
 		return;
@@ -584,7 +584,7 @@ static int verify_absent(struct cache_entry *ce, const char *action,
 	if (o->index_only || o->reset || !o->update)
 		return 0;
 
-	if (has_symlink_leading_path(ce_namelen(ce), ce->name))
+	if (has_symlink_or_noent_leading_path(ce_namelen(ce), ce->name))
 		return 0;
 
 	if (!lstat(ce->name, &st)) {