summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNguyễn Thái Ngọc Duy <pclouds@gmail.com>2018-01-24 16:30:21 +0700
committerJunio C Hamano <gitster@pobox.com>2018-01-24 12:40:14 -0800
commitb640313110ab5117b3c45b3445da4ce28967a386 (patch)
tree6eeb1244bfa942068f2e55a0d8e6ffa0fe64c051
parent2523c4be855af84460e70ab5c8375534f8cefed5 (diff)
downloadgit-b640313110ab5117b3c45b3445da4ce28967a386.tar.gz
dir.c: fix missing dir invalidation in untracked code
Let's start with how create a new directory cache after the last one becomes invalid (e.g. because its dir mtime has changed...). In open_cached_dir(): 1. We start out with valid_cached_dir() returning false, which should call invalidate_directory() to put a directory state back to initial state, no untracked entries (untracked_nr zero), no sub directory traversal (dirs[].recurse zero). 2. Since the cache cannot be used, we go the slow path opendir() and go through items one by one via readdir(). All the directories on disk will be added back to the cache (if not already exist in dirs[]) and its flag "recurse" gets changed to one to note that it's part of the cached dir travesal next time. 3. By the time we reach close_cached_dir() we should have a good subdir list in dirs[]. Those with "recurse" flag set are the ones present in the on-disk directory. The directory is now marked "valid". Next time read_directory() is called, since the directory is marked valid, it will skip readdir(), go fast path and traverse through dirs[] array instead. Steps one and two need some tight cooperation. If a subdir is removed, readdir() will not find it and of course we cannot examine/invalidate it. To make sure removed directories on disk are gone from the cache, step one must make sure recurse flag of all subdirs are zero. But that's not true. If "valid" flag is already false, there is a chance we go straight to the end of valid_cached_dir() without calling invalidate_directory(). Or we fail to meet the "if (untracked-valid)" condition and skip over the invalidate_directory(). After step 3, we mark the cache valid. Any stale subdir with incorrect recurse flag becomes a real subdir next time we traverse the directory using dirs[] array. We could avoid this by making sure invalidate_directory() is always called (therefore dirs[].recurse cleared) at the beginning of open_cached_dir(). Which is what this patch does. As to how we get into this situation, the key in the test is this command git checkout master where "one/file" is replaced with "one" in the index. This index update triggers untracked_cache_invalidate_path(), which clears valid flag of the root directory while keeping "recurse" flag on the subdir "one" on. On the next git-status, we go through steps 1-3 above and save an incorrect cache on disk. The second git-status blindly follows the bad cache data and shows the problem. This is arguably because of a bad design where "recurse" flag plays double roles: whether a directory should be saved on disk, and whether it is part of a directory traversal. We need to keep recurse flag set at "checkout master" because of the first role: we need to keep subdir caches (dir "two" for example has not been touched at all, no reason to throw its cache away). As long as we make sure to ignore/reset "recurse" flag at the beginning of a directory traversal, we're good. But maybe eventually we should separate these two roles. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--dir.c22
-rwxr-xr-xt/t7063-status-untracked-cache.sh4
2 files changed, 16 insertions, 10 deletions
diff --git a/dir.c b/dir.c
index ee1605f004..44b4dd2ec8 100644
--- a/dir.c
+++ b/dir.c
@@ -733,7 +733,16 @@ static void invalidate_directory(struct untracked_cache *uc,
struct untracked_cache_dir *dir)
{
int i;
- uc->dir_invalidated++;
+
+ /*
+ * Invalidation increment here is just roughly correct. If
+ * untracked_nr or any of dirs[].recurse is non-zero, we
+ * should increment dir_invalidated too. But that's more
+ * expensive to do.
+ */
+ if (dir->valid)
+ uc->dir_invalidated++;
+
dir->valid = 0;
dir->untracked_nr = 0;
for (i = 0; i < dir->dirs_nr; i++)
@@ -1740,23 +1749,18 @@ static int valid_cached_dir(struct dir_struct *dir,
refresh_fsmonitor(istate);
if (!(dir->untracked->use_fsmonitor && untracked->valid)) {
if (lstat(path->len ? path->buf : ".", &st)) {
- invalidate_directory(dir->untracked, untracked);
memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
return 0;
}
if (!untracked->valid ||
match_stat_data_racy(istate, &untracked->stat_data, &st)) {
- if (untracked->valid)
- invalidate_directory(dir->untracked, untracked);
fill_stat_data(&untracked->stat_data, &st);
return 0;
}
}
- if (untracked->check_only != !!check_only) {
- invalidate_directory(dir->untracked, untracked);
+ if (untracked->check_only != !!check_only)
return 0;
- }
/*
* prep_exclude will be called eventually on this directory,
@@ -1788,8 +1792,10 @@ static int open_cached_dir(struct cached_dir *cdir,
if (valid_cached_dir(dir, untracked, istate, path, check_only))
return 0;
cdir->fdir = opendir(path->len ? path->buf : ".");
- if (dir->untracked)
+ if (dir->untracked) {
+ invalidate_directory(dir->untracked, untracked);
dir->untracked->dir_opened++;
+ }
if (!cdir->fdir)
return -1;
return 0;
diff --git a/t/t7063-status-untracked-cache.sh b/t/t7063-status-untracked-cache.sh
index dba7f50bbb..46b947824f 100755
--- a/t/t7063-status-untracked-cache.sh
+++ b/t/t7063-status-untracked-cache.sh
@@ -707,7 +707,7 @@ test_expect_success SYMLINKS 'setup worktree for symlink test' '
git commit -m"second commit"
'
-test_expect_failure SYMLINKS '"status" after symlink replacement should be clean with UC=true' '
+test_expect_success SYMLINKS '"status" after symlink replacement should be clean with UC=true' '
git checkout HEAD~ &&
status_is_clean &&
status_is_clean &&
@@ -742,7 +742,7 @@ test_expect_success 'setup worktree for non-symlink test' '
git commit -m"second commit"
'
-test_expect_failure '"status" after file replacement should be clean with UC=true' '
+test_expect_success '"status" after file replacement should be clean with UC=true' '
git checkout HEAD~ &&
status_is_clean &&
status_is_clean &&