Merge branch 'rs/name-rev-memsave'

Memory footprint and performance of "git name-rev" has been
improved.

* rs/name-rev-memsave:
  name-rev: sort tip names before applying
  name-rev: release unused name strings
  name-rev: generate name strings only if they are better
  name-rev: pre-size buffer in get_parent_name()
  name-rev: factor out get_parent_name()
  name-rev: put struct rev_name into commit slab
  name-rev: don't _peek() in create_or_update_name()
  name-rev: don't leak path copy in name_ref()
  name-rev: respect const qualifier
  name-rev: remove unused typedef
  name-rev: rewrite create_or_update_name()

builtin/name-rev.c

@@ -16,15 +16,15 @@
  */
 #define CUTOFF_DATE_SLOP 86400
 
-typedef struct rev_name {
+struct rev_name {
-	const char *tip_name;
+	char *tip_name;
 	timestamp_t taggerdate;
 	int generation;
 	int distance;
 	int from_tag;
-} rev_name;
+};
 
-define_commit_slab(commit_rev_name, struct rev_name *);
+define_commit_slab(commit_rev_name, struct rev_name);
 
 static timestamp_t cutoff = TIME_MAX;
 static struct commit_rev_name rev_names;
@@ -32,16 +32,16 @@ static struct commit_rev_name rev_names;
 /* How many generations are maximally preferred over _one_ merge traversal? */
 #define MERGE_TRAVERSAL_WEIGHT 65535
 
-static struct rev_name *get_commit_rev_name(struct commit *commit)
+static int is_valid_rev_name(const struct rev_name *name)
 {
-	struct rev_name **slot = commit_rev_name_peek(&rev_names, commit);
+	return name && (name->generation || name->tip_name);
-
-	return slot ? *slot : NULL;
 }
 
-static void set_commit_rev_name(struct commit *commit, struct rev_name *name)
+static struct rev_name *get_commit_rev_name(const struct commit *commit)
 {
-	*commit_rev_name_at(&rev_names, commit) = name;
+	struct rev_name *name = commit_rev_name_peek(&rev_names, commit);
+
+	return is_valid_rev_name(name) ? name : NULL;
 }
 
 static int is_better_name(struct rev_name *name,
@@ -81,28 +81,54 @@ static int is_better_name(struct rev_name *name,
 }
 
 static struct rev_name *create_or_update_name(struct commit *commit,
-					      const char *tip_name,
 					      timestamp_t taggerdate,
 					      int generation, int distance,
 					      int from_tag)
 {
-	struct rev_name *name = get_commit_rev_name(commit);
+	struct rev_name *name = commit_rev_name_at(&rev_names, commit);
 
-	if (name == NULL) {
+	if (is_valid_rev_name(name)) {
-		name = xmalloc(sizeof(*name));
+		if (!is_better_name(name, taggerdate, distance, from_tag))
-		set_commit_rev_name(commit, name);
+			return NULL;
-		goto copy_data;
-	} else if (is_better_name(name, taggerdate, distance, from_tag)) {
-copy_data:
-		name->tip_name = tip_name;
-		name->taggerdate = taggerdate;
-		name->generation = generation;
-		name->distance = distance;
-		name->from_tag = from_tag;
 
-		return name;
+		/*
-	} else
+		 * This string might still be shared with ancestors
-		return NULL;
+		 * (generation > 0).  We can release it here regardless,
+		 * because the new name that has just won will be better
+		 * for them as well, so name_rev() will replace these
+		 * stale pointers when it processes the parents.
+		 */
+		if (!name->generation)
+			free(name->tip_name);
+	}
+
+	name->taggerdate = taggerdate;
+	name->generation = generation;
+	name->distance = distance;
+	name->from_tag = from_tag;
+
+	return name;
+}
+
+static char *get_parent_name(const struct rev_name *name, int parent_number)
+{
+	struct strbuf sb = STRBUF_INIT;
+	size_t len;
+
+	strip_suffix(name->tip_name, "^0", &len);
+	if (name->generation > 0) {
+		strbuf_grow(&sb, len +
+			    1 + decimal_width(name->generation) +
+			    1 + decimal_width(parent_number));
+		strbuf_addf(&sb, "%.*s~%d^%d", (int)len, name->tip_name,
+			    name->generation, parent_number);
+	} else {
+		strbuf_grow(&sb, len +
+			    1 + decimal_width(parent_number));
+		strbuf_addf(&sb, "%.*s^%d", (int)len, name->tip_name,
+			    parent_number);
+	}
+	return strbuf_detach(&sb, NULL);
 }
 
 static void name_rev(struct commit *start_commit,
@@ -113,20 +139,20 @@ static void name_rev(struct commit *start_commit,
 	struct commit *commit;
 	struct commit **parents_to_queue = NULL;
 	size_t parents_to_queue_nr, parents_to_queue_alloc = 0;
-	char *to_free = NULL;
+	struct rev_name *start_name;
 
 	parse_commit(start_commit);
 	if (start_commit->date < cutoff)
 		return;
 
-	if (deref)
+	start_name = create_or_update_name(start_commit, taggerdate, 0, 0,
-		tip_name = to_free = xstrfmt("%s^0", tip_name);
+					   from_tag);
-
+	if (!start_name)
-	if (!create_or_update_name(start_commit, tip_name, taggerdate, 0, 0,
-				   from_tag)) {
-		free(to_free);
 		return;
-	}
+	if (deref)
+		start_name->tip_name = xstrfmt("%s^0", tip_name);
+	else
+		start_name->tip_name = xstrdup(tip_name);
 
 	memset(&queue, 0, sizeof(queue)); /* Use the prio_queue as LIFO */
 	prio_queue_put(&queue, start_commit);
@@ -142,7 +168,7 @@ static void name_rev(struct commit *start_commit,
 				parents;
 				parents = parents->next, parent_number++) {
 			struct commit *parent = parents->item;
-			const char *new_name;
+			struct rev_name *parent_name;
 			int generation, distance;
 
 			parse_commit(parent);
@@ -150,30 +176,23 @@ static void name_rev(struct commit *start_commit,
 				continue;
 
 			if (parent_number > 1) {
-				size_t len;
-
-				strip_suffix(name->tip_name, "^0", &len);
-				if (name->generation > 0)
-					new_name = xstrfmt("%.*s~%d^%d",
-							   (int)len,
-							   name->tip_name,
-							   name->generation,
-							   parent_number);
-				else
-					new_name = xstrfmt("%.*s^%d", (int)len,
-							   name->tip_name,
-							   parent_number);
 				generation = 0;
 				distance = name->distance + MERGE_TRAVERSAL_WEIGHT;
 			} else {
-				new_name = name->tip_name;
 				generation = name->generation + 1;
 				distance = name->distance + 1;
 			}
 
-			if (create_or_update_name(parent, new_name, taggerdate,
+			parent_name = create_or_update_name(parent, taggerdate,
-						  generation, distance,
+							    generation,
-						  from_tag)) {
+							    distance, from_tag);
+			if (parent_name) {
+				if (parent_number > 1)
+					parent_name->tip_name =
+						get_parent_name(name,
+								parent_number);
+				else
+					parent_name->tip_name = name->tip_name;
 				ALLOC_GROW(parents_to_queue,
 					   parents_to_queue_nr + 1,
 					   parents_to_queue_alloc);
@@ -228,6 +247,10 @@ static struct tip_table {
 	struct tip_table_entry {
 		struct object_id oid;
 		const char *refname;
+		struct commit *commit;
+		timestamp_t taggerdate;
+		unsigned int from_tag:1;
+		unsigned int deref:1;
 	} *table;
 	int nr;
 	int alloc;
@@ -235,13 +258,18 @@ static struct tip_table {
 } tip_table;
 
 static void add_to_tip_table(const struct object_id *oid, const char *refname,
-			     int shorten_unambiguous)
+			     int shorten_unambiguous, struct commit *commit,
+			     timestamp_t taggerdate, int from_tag, int deref)
 {
 	refname = name_ref_abbrev(refname, shorten_unambiguous);
 
 	ALLOC_GROW(tip_table.table, tip_table.nr + 1, tip_table.alloc);
 	oidcpy(&tip_table.table[tip_table.nr].oid, oid);
 	tip_table.table[tip_table.nr].refname = xstrdup(refname);
+	tip_table.table[tip_table.nr].commit = commit;
+	tip_table.table[tip_table.nr].taggerdate = taggerdate;
+	tip_table.table[tip_table.nr].from_tag = from_tag;
+	tip_table.table[tip_table.nr].deref = deref;
 	tip_table.nr++;
 	tip_table.sorted = 0;
 }
@@ -252,12 +280,30 @@ static int tipcmp(const void *a_, const void *b_)
 	return oidcmp(&a->oid, &b->oid);
 }
 
+static int cmp_by_tag_and_age(const void *a_, const void *b_)
+{
+	const struct tip_table_entry *a = a_, *b = b_;
+	int cmp;
+
+	/* Prefer tags. */
+	cmp = b->from_tag - a->from_tag;
+	if (cmp)
+		return cmp;
+
+	/* Older is better. */
+	if (a->taggerdate < b->taggerdate)
+		return -1;
+	return a->taggerdate != b->taggerdate;
+}
+
 static int name_ref(const char *path, const struct object_id *oid, int flags, void *cb_data)
 {
 	struct object *o = parse_object(the_repository, oid);
 	struct name_ref_data *data = cb_data;
 	int can_abbreviate_output = data->tags_only && data->name_only;
 	int deref = 0;
+	int from_tag = 0;
+	struct commit *commit = NULL;
 	timestamp_t taggerdate = TIME_MAX;
 
 	if (data->tags_only && !starts_with(path, "refs/tags/"))
@@ -306,8 +352,6 @@ static int name_ref(const char *path, const struct object_id *oid, int flags, vo
 			return 0;
 	}
 
-	add_to_tip_table(oid, path, can_abbreviate_output);
-
 	while (o && o->type == OBJ_TAG) {
 		struct tag *t = (struct tag *) o;
 		if (!t->tagged)
@@ -317,17 +361,35 @@ static int name_ref(const char *path, const struct object_id *oid, int flags, vo
 		taggerdate = t->date;
 	}
 	if (o && o->type == OBJ_COMMIT) {
-		struct commit *commit = (struct commit *)o;
+		commit = (struct commit *)o;
-		int from_tag = starts_with(path, "refs/tags/");
+		from_tag = starts_with(path, "refs/tags/");
-
 		if (taggerdate == TIME_MAX)
 			taggerdate = commit->date;
-		path = name_ref_abbrev(path, can_abbreviate_output);
-		name_rev(commit, xstrdup(path), taggerdate, from_tag, deref);
 	}
+
+	add_to_tip_table(oid, path, can_abbreviate_output, commit, taggerdate,
+			 from_tag, deref);
 	return 0;
 }
 
+static void name_tips(void)
+{
+	int i;
+
+	/*
+	 * Try to set better names first, so that worse ones spread
+	 * less.
+	 */
+	QSORT(tip_table.table, tip_table.nr, cmp_by_tag_and_age);
+	for (i = 0; i < tip_table.nr; i++) {
+		struct tip_table_entry *e = &tip_table.table[i];
+		if (e->commit) {
+			name_rev(e->commit, e->refname, e->taggerdate,
+				 e->from_tag, e->deref);
+		}
+	}
+}
+
 static const unsigned char *nth_tip_table_ent(size_t ix, void *table_)
 {
 	struct tip_table_entry *table = table_;
@@ -357,11 +419,11 @@ static const char *get_exact_ref_match(const struct object *o)
 static const char *get_rev_name(const struct object *o, struct strbuf *buf)
 {
 	struct rev_name *n;
-	struct commit *c;
+	const struct commit *c;
 
 	if (o->type != OBJ_COMMIT)
 		return get_exact_ref_match(o);
-	c = (struct commit *) o;
+	c = (const struct commit *) o;
 	n = get_commit_rev_name(c);
 	if (!n)
 		return NULL;
@@ -540,6 +602,7 @@ int cmd_name_rev(int argc, const char **argv, const char *prefix)
 			cutoff = TIME_MIN;
 	}
 	for_each_ref(name_ref, &data);
+	name_tips();
 
 	if (transform_stdin) {
 		char buffer[2048];