[PATCH v2 12/14] dir.c: git-status: avoid is_excluded checks for tracked files

From: Karsten Blees <karsten.blees@gmail.com>
Date: Apr 15, 2013, 19:13 UTC
Message-ID: <516C515F.1070206@gmail.com>
In-Reply-To: <516C4F27.30203@gmail.com>

Checking if a file is in the index is much faster (hashtable lookup) than checking if the file is excluded (linear search over exclude patterns).

Skip is_excluded checks for files: move the cache_name_exists check from treat_file to treat_one_path and return early if the file is tracked.

This can safely be done as all other code paths also return path_ignored for tracked files, and dir_add_ignored skips tracked files as well.

There's just one line left in treat_file, so move this to treat_one_path as well.

Here's some performance data for git-status from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true):

       |    status      | status --ignored
       | linux | WebKit | linux | WebKit
-------+-------+--------+-------+---------
before | 0.218 |  1.583 | 0.321 |  2.579
after  | 0.156 |  0.988 | 0.202 |  1.279
gain   | 1.397 |  1.602 | 1.589 |  2.016

Signed-off-by: Karsten Blees <blees@dcon.de>
---
 dir.c | 38 +++++++++++---------------------------
 1 file changed, 11 insertions(+), 27 deletions(-)

diff --git a/dir.c b/dir.c
index 67313bd..5ae5722 100644
--- a/dir.c
+++ b/dir.c
@@ -1023,28 +1023,6 @@ static enum directory_treatment treat_directory(struct dir_struct *dir,
 }
 
 /*
- * Decide what to do when we find a file while traversing the
- * filesystem. Mostly two cases:
- *
- *  1. We are looking for ignored files
- *   (a) File is ignored, include it
- *   (b) File is in ignored path, include it
- *   (c) File is not ignored, exclude it
- *
- *  2. Other scenarios, include the file if not excluded
- *
- * Return 1 for exclude, 0 for include.
- */
-static int treat_file(struct dir_struct *dir, struct strbuf *path, int exclude)
-{
-	/* Always exclude indexed files */
-	if (index_name_exists(&the_index, path->buf, path->len, ignore_case))
-		return 1;
-
-	return exclude == !(dir->flags & DIR_SHOW_IGNORED);
-}
-
-/*
  * This is an inexact early pruning of any recursive directory
  * reading - if the path cannot possibly be in the pathspec,
  * return true, and we'll skip it early.
@@ -1167,7 +1145,16 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 					  const struct path_simplify *simplify,
 					  int dtype, struct dirent *de)
 {
-	int exclude = is_excluded(dir, path->buf, &dtype);
+	int exclude;
+	if (dtype == DT_UNKNOWN)
+		dtype = get_dtype(de, path->buf, path->len);
+
+	/* Always exclude indexed files */
+	if (dtype != DT_DIR &&
+	    cache_name_exists(path->buf, path->len, ignore_case))
+		return path_ignored;
+
+	exclude = is_excluded(dir, path->buf, &dtype);
 	if (exclude && (dir->flags & DIR_COLLECT_IGNORED)
 	    && exclude_matches_pathspec(path->buf, path->len, simplify))
 		dir_add_ignored(dir, path->buf, path->len);
@@ -1179,9 +1166,6 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 	if (exclude && !(dir->flags & DIR_SHOW_IGNORED))
 		return path_ignored;
 
-	if (dtype == DT_UNKNOWN)
-		dtype = get_dtype(de, path->buf, path->len);
-
 	switch (dtype) {
 	default:
 		return path_ignored;
@@ -1198,7 +1182,7 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 		break;
 	case DT_REG:
 	case DT_LNK:
-		if (treat_file(dir, path, exclude))
+		if (exclude == !(dir->flags & DIR_SHOW_IGNORED))
 			return path_ignored;
 		break;
 	}

-- 
1.8.1.2.8026.g2b66448.dirty