Improve performance of git status --ignored
Improve the performance of the directory listing logic when it wants to list non-empty ignored directories. In order to show non-empty ignored directories, the existing logic will recursively iterate through all contents of an ignored directory. This change introduces the optimization to stop iterating through the contents once it finds the first file. This can have a significant improvement in 'git status --ignored' performance in repositories with a large number of files in ignored directories. For an example of the performance difference on an example repository with 196,000 files in 400 ignored directories: | Command | Time (s) | | -------------------------- | --------- | | git status | 1.2 | | git status --ignored (old) | 3.9 | | git status --ignored (new) | 1.4 | Signed-off-by: Jameson Miller <jamill@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Jameson Miller committed
Sep 18, 2017 at 13:24 UTC
5aaa7fd39aafb83fdb30a6af4685eda5fc1cd382
1 file changed
+41
-6
dir.c
+41
-6
@@ -49,7 +49,7 @@ struct cached_dir {
49
static enum path_treatment read_directory_recursive(struct dir_struct *dir,
50
struct index_state *istate, const char *path, int len,
51
struct untracked_cache_dir *untracked,
52
- int check_only, const struct pathspec *pathspec);
52
+ int check_only, int stop_at_first_file, const struct pathspec *pathspec);
53
static int get_dtype(struct dirent *de, struct index_state *istate,
54
const char *path, int len);
55
@@ -1404,8 +1404,13 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
1404
1405
untracked = lookup_untracked(dir->untracked, untracked,
1406
dirname + baselen, len - baselen);
1407
+
1408
+ /*
1409
+ * If this is an excluded directory, then we only need to check if
1410
+ * the directory contains any files.
1411
+ */
1412
return read_directory_recursive(dir, istate, dirname, len,
1408
- untracked, 1, pathspec);
1413
+ untracked, 1, exclude, pathspec);
1414
}
1415
1416
/*
@@ -1633,7 +1638,7 @@ static enum path_treatment treat_path_fast(struct dir_struct *dir,
1638
* with check_only set.
1639
*/
1640
return read_directory_recursive(dir, istate, path->buf, path->len,
1636
- cdir->ucd, 1, pathspec);
1641
+ cdir->ucd, 1, 0, pathspec);
1642
/*
1643
* We get path_recurse in the first run when
1644
* directory_exists_in_index() returns index_nonexistent. We
@@ -1793,12 +1798,20 @@ static void close_cached_dir(struct cached_dir *cdir)
1798
* Also, we ignore the name ".git" (even if it is not a directory).
1799
* That likely will not change.
1800
*
1801
+ * If 'stop_at_first_file' is specified, 'path_excluded' is returned
1802
+ * to signal that a file was found. This is the least significant value that
1803
+ * indicates that a file was encountered that does not depend on the order of
1804
+ * whether an untracked or exluded path was encountered first.
1805
+ *
1806
* Returns the most significant path_treatment value encountered in the scan.
1807
+ * If 'stop_at_first_file' is specified, `path_excluded` is the most
1808
+ * significant path_treatment value that will be returned.
1809
*/
1810
+
1811
static enum path_treatment read_directory_recursive(struct dir_struct *dir,
1812
struct index_state *istate, const char *base, int baselen,
1813
struct untracked_cache_dir *untracked, int check_only,
1801
- const struct pathspec *pathspec)
1814
+ int stop_at_first_file, const struct pathspec *pathspec)
1815
{
1816
struct cached_dir cdir;
1817
enum path_treatment state, subdir_state, dir_state = path_none;
@@ -1832,12 +1845,34 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
1845
subdir_state =
1846
read_directory_recursive(dir, istate, path.buf,
1847
path.len, ud,
1835
- check_only, pathspec);
1848
+ check_only, stop_at_first_file, pathspec);
1849
if (subdir_state > dir_state)
1850
dir_state = subdir_state;
1851
}
1852
1853
if (check_only) {
1854
+ if (stop_at_first_file) {
1855
+ /*
1856
+ * If stopping at first file, then
1857
+ * signal that a file was found by
1858
+ * returning `path_excluded`. This is
1859
+ * to return a consistent value
1860
+ * regardless of whether an ignored or
1861
+ * excluded file happened to be
1862
+ * encountered 1st.
1863
+ *
1864
+ * In current usage, the
1865
+ * `stop_at_first_file` is passed when
1866
+ * an ancestor directory has matched
1867
+ * an exclude pattern, so any found
1868
+ * files will be excluded.
1869
+ */
1870
+ if (dir_state >= path_excluded) {
1871
+ dir_state = path_excluded;
1872
+ break;
1873
+ }
1874
+ }
1875
+
1876
/* abort early if maximum state has been reached */
1877
if (dir_state == path_untracked) {
1878
if (cdir.fdir)
@@ -2108,7 +2143,7 @@ int read_directory(struct dir_struct *dir, struct index_state *istate,
2143
*/
2144
dir->untracked = NULL;
2145
if (!len || treat_leading_path(dir, istate, path, len, pathspec))
2111
- read_directory_recursive(dir, istate, path, len, untracked, 0, pathspec);
2146
+ read_directory_recursive(dir, istate, path, len, untracked, 0, 0, pathspec);
2147
QSORT(dir->entries, dir->nr, cmp_dir_entry);
2148
QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);
2149