list-objects: support for skipping tree traversal

matvore · gitster · commit 8b10a206f090 · 2018-10-18T12:49:18.000+09:00
The tree:0 filter does not need to traverse the trees that it has
filtered out, so optimize list-objects and list-objects-filter to skip
traversing the trees entirely. Before this patch, we iterated over all
children of the tree, and did nothing for all of them, which was
wasteful.

Signed-off-by: Matthew DeVore &lt;matvore@google.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/list-objects-filter.c b/list-objects-filter.c
@@ -102,9 +102,16 @@ static enum list_objects_filter_result filter_trees_none(
 
 	case LOFS_BEGIN_TREE:
 	case LOFS_BLOB:
-		if (filter_data->omits)
+		if (filter_data->omits) {
 			oidset_insert(filter_data->omits, &obj->oid);
-		return LOFR_MARK_SEEN; /* but not LOFR_DO_SHOW (hard omit) */
+			/* _MARK_SEEN but not _DO_SHOW (hard omit) */
+			return LOFR_MARK_SEEN;
+		} else {
+			/*
+			 * Not collecting omits so no need to to traverse tree.
+			 */
+			return LOFR_SKIP_TREE | LOFR_MARK_SEEN;
+		}
 
 	case LOFS_END_TREE:
 		assert(obj->type == OBJ_TREE);
diff --git a/list-objects-filter.h b/list-objects-filter.h
@@ -20,6 +20,11 @@
  *              In general, objects should only be shown once, but
  *              this result DOES NOT imply that we mark it SEEN.
  *
+ * _SKIP_TREE : Used in LOFS_BEGIN_TREE situation - indicates that
+ *              the tree's children should not be iterated over. This
+ *              is used as an optimization when all children will
+ *              definitely be ignored.
+ *
  * Most of the time, you want the combination (_MARK_SEEN | _DO_SHOW)
  * but they can be used independently, such as when sparse-checkout
  * pattern matching is being applied.
@@ -41,6 +46,7 @@ enum list_objects_filter_result {
 	LOFR_ZERO      = 0,
 	LOFR_MARK_SEEN = 1<<0,
 	LOFR_DO_SHOW   = 1<<1,
+	LOFR_SKIP_TREE = 1<<2,
 };
 
 enum list_objects_filter_situation {
diff --git a/list-objects.c b/list-objects.c
@@ -11,6 +11,7 @@
 #include "list-objects-filter-options.h"
 #include "packfile.h"
 #include "object-store.h"
+#include "trace.h"
 
 struct traversal_context {
 	struct rev_info *revs;
@@ -184,7 +185,9 @@ static void process_tree(struct traversal_context *ctx,
 	if (base->len)
 		strbuf_addch(base, '/');
 
-	if (!failed_parse)
+	if (r & LOFR_SKIP_TREE)
+		trace_printf("Skipping contents of tree %s...\n", base->buf);
+	else if (!failed_parse)
 		process_tree_contents(ctx, tree, base);
 
 	if ((obj->flags & NOT_USER_GIVEN) && ctx->filter_fn) {
diff --git a/t/t6112-rev-list-filters-objects.sh b/t/t6112-rev-list-filters-objects.sh
@@ -245,6 +245,19 @@ test_expect_success 'verify tree:0 includes trees in "filtered" output' '
 	test_cmp expected filtered_types
 '
 
+# Make sure tree:0 does not iterate through any trees.
+
+test_expect_success 'filter a GIANT tree through tree:0' '
+	GIT_TRACE=1 git -C r3 rev-list \
+		--objects --filter=tree:0 HEAD 2>filter_trace &&
+	grep "Skipping contents of tree [.][.][.]" filter_trace >actual &&
+	# One line for each commit traversed.
+	test_line_count = 2 actual &&
+
+	# Make sure no other trees were considered besides the root.
+	! grep "Skipping contents of tree [^.]" filter_trace
+'
+
 # Delete some loose objects and use rev-list, but WITHOUT any filtering.
 # This models previously omitted objects that we did not receive.
 
