Merge pull request #1344 from jeffhostetler/perf_add_excludes_with_fscache

dir.c: make add_excludes aware of fscache during status

Author: dscho

compat/win32/fscache.c

@@ -260,7 +260,7 @@ static void fscache_clear(void)
 /*
  * Checks if the cache is enabled for the given path.
  */
-static inline int fscache_enabled(const char *path)
+int fscache_enabled(const char *path)
 {
 	return enabled > 0 && !is_absolute_path(path);
 }

compat/win32/fscache.h

@@ -4,6 +4,9 @@
 int fscache_enable(int enable);
 #define enable_fscache(x) fscache_enable(x)
 
+int fscache_enabled(const char *path);
+#define is_fscache_enabled(path) fscache_enabled(path)
+
 DIR *fscache_opendir(const char *dir);
 int fscache_lstat(const char *file_name, struct stat *buf);
 

dir.c

@@ -1054,12 +1054,55 @@ static int add_patterns(const char *fname, const char *base, int baselen,
 	size_t size = 0;
 	char *buf;
 
-	fd = open(fname, O_RDONLY);
-	if (fd < 0 || fstat(fd, &st) < 0) {
-		if (fd < 0)
-			warn_on_fopen_errors(fname);
-		else
-			close(fd);
+	/*
+	 * A performance optimization for status.
+	 *
+	 * During a status scan, git looks in each directory for a .gitignore
+	 * file before scanning the directory.  Since .gitignore files are not
+	 * that common, we can waste a lot of time looking for files that are
+	 * not there.  Fortunately, the fscache already knows if the directory
+	 * contains a .gitignore file, since it has already read the directory
+	 * and it already has the stat-data.
+	 *
+	 * If the fscache is enabled, use the fscache-lstat() interlude to see
+	 * if the file exists (in the fscache hash maps) before trying to open()
+	 * it.
+	 *
+	 * This causes problem when the .gitignore file is a symlink, because
+	 * we call lstat() rather than stat() on the symlnk and the resulting
+	 * stat-data is for the symlink itself rather than the target file.
+	 * We CANNOT use stat() here because the fscache DOES NOT install an
+	 * interlude for stat() and mingw_stat() always calls "open-fstat-close"
+	 * on the file and defeats the purpose of the optimization here.  Since
+	 * symlinks are even more rare than .gitignore files, we force a fstat()
+	 * after our open() to get stat-data for the target file.
+	 */
+	if (is_fscache_enabled(fname)) {
+		if (lstat(fname, &st) < 0) {
+			fd = -1;
+		} else {
+			fd = open(fname, O_RDONLY);
+			if (fd < 0)
+				warn_on_fopen_errors(fname);
+			else if (S_ISLNK(st.st_mode) && fstat(fd, &st) < 0) {
+				warn_on_fopen_errors(fname);
+				close(fd);
+				fd = -1;
+			}
+		}
+	} else {
+		fd = open(fname, O_RDONLY);
+		if (fd < 0 || fstat(fd, &st) < 0) {
+			if (fd < 0)
+				warn_on_fopen_errors(fname);
+			else {
+				close(fd);
+				fd = -1;
+			}
+		}
+	}
+
+	if (fd < 0) {
 		if (!istate)
 			return -1;
 		r = read_skip_worktree_file_from_index(istate, fname,

git-compat-util.h

@@ -1304,6 +1304,10 @@ static inline int is_missing_file_error(int errno_)
 #define enable_fscache(x) /* noop */
 #endif
 
+#ifndef is_fscache_enabled
+#define is_fscache_enabled(path) (0)
+#endif
+
 int cmd_main(int, const char **);
 
 /*