checkout: avoid unnecessary match_pathspec calls

In checkout_paths() we do this

 - for all updated items, call match_pathspec
 - for all items, call match_pathspec (inside unmerge_cache)
 - for all items, call match_pathspec (for showing "path .. is unmerged)
 - for updated items, call match_pathspec and update paths

That's a lot of duplicate match_pathspec(s) and the function is not
exactly cheap to be called so many times, especially on large indexes.
This patch makes it call match_pathspec once per updated index entry,
save the result in ce_flags and reuse the results in the following
loops.

The changes in 0a1283b (checkout $tree $path: do not clobber local
changes in $path not in $tree - 2011-09-30) limit the affected paths
to ones we read from $tree. We do not do anything to other modified
entries in this case, so the "for all items" above could be modified
to "for all updated items". But..

The command's behavior now is modified slightly: unmerged entries that
match $path, but not updated by $tree, are now NOT touched.  Although
this should be considered a bug fix, not a regression. A new test is
added for this change.

And while at there, free ps_matched after use.

The following command is tested on webkit, 215k entries. The pattern
is chosen mainly to make match_pathspec sweat:

git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*"

        before      after
real    0m3.493s    0m2.737s
user    0m2.239s    0m1.586s
sys     0m1.252s    0m1.151s

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 36 insertions, 7 deletions

diff --git a/builtin/checkout.c b/builtin/checkout.c
index a9c1b5a95f..f8033f446e 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -271,24 +271,55 @@ static int checkout_paths(const struct checkout_opts *opts,
 		;
 	ps_matched = xcalloc(1, pos);
 
+	/*
+	 * Make sure all pathspecs participated in locating the paths
+	 * to be checked out.
+	 */
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
+		ce->ce_flags &= ~CE_MATCHED;
 		if (opts->source_tree && !(ce->ce_flags & CE_UPDATE))
+			/*
+			 * "git checkout tree-ish -- path", but this entry
+			 * is in the original index; it will not be checked
+			 * out to the working tree and it does not matter
+			 * if pathspec matched this entry.  We will not do
+			 * anything to this entry at all.
+			 */
 			continue;
-		match_pathspec(opts->pathspec, ce->name, ce_namelen(ce), 0, ps_matched);
+		/*
+		 * Either this entry came from the tree-ish we are
+		 * checking the paths out of, or we are checking out
+		 * of the index.
+		 *
+		 * If it comes from the tree-ish, we already know it
+		 * matches the pathspec and could just stamp
+		 * CE_MATCHED to it from update_some(). But we still
+		 * need ps_matched and read_tree_recursive (and
+		 * eventually tree_entry_interesting) cannot fill
+		 * ps_matched yet. Once it can, we can avoid calling
+		 * match_pathspec() for _all_ entries when
+		 * opts->source_tree != NULL.
+		 */
+		if (match_pathspec(opts->pathspec, ce->name, ce_namelen(ce),
+				   0, ps_matched))
+			ce->ce_flags |= CE_MATCHED;
 	}
 
-	if (report_path_error(ps_matched, opts->pathspec, opts->prefix))
+	if (report_path_error(ps_matched, opts->pathspec, opts->prefix)) {
+		free(ps_matched);
 		return 1;
+	}
+	free(ps_matched);
 
 	/* "checkout -m path" to recreate conflicted state */
 	if (opts->merge)
-		unmerge_cache(opts->pathspec);
+		unmerge_marked_index(&the_index);
 
 	/* Any unmerged paths? */
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		if (match_pathspec(opts->pathspec, ce->name, ce_namelen(ce), 0, NULL)) {
+		if (ce->ce_flags & CE_MATCHED) {
 			if (!ce_stage(ce))
 				continue;
 			if (opts->force) {
@@ -313,9 +344,7 @@ static int checkout_paths(const struct checkout_opts *opts,
 	state.refresh_cache = 1;
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		if (opts->source_tree && !(ce->ce_flags & CE_UPDATE))
-			continue;
-		if (match_pathspec(opts->pathspec, ce->name, ce_namelen(ce), 0, NULL)) {
+		if (ce->ce_flags & CE_MATCHED) {
 			if (!ce_stage(ce)) {
 				errs |= checkout_entry(ce, &state, NULL);
 				continue;