Merge branch 'ew/many-alternate-optim'

Optimization for repositories with many alternate object store.

* ew/many-alternate-optim:
  oidtree: a crit-bit tree for odb_loose_cache
  oidcpy_with_padding: constify `src' arg
  make object_directory.loose_objects_subdir_seen a bitmap
  avoid strlen via strbuf_addstr in link_alt_odb_entry
  speed up alt_odb_usable() with many alternates

1 files changed, 45 insertions, 30 deletions

diff --git a/object-file.c b/object-file.c
index ecca5a8..3d27dc8 100644
--- a/object-file.c
+++ b/object-file.c
@@ -517,9 +517,9 @@ const char *loose_object_path(struct repository *r, struct strbuf *buf,
  */
 static int alt_odb_usable(struct raw_object_store *o,
 			  struct strbuf *path,
-			  const char *normalized_objdir)
+			  const char *normalized_objdir, khiter_t *pos)
 {
-	struct object_directory *odb;
+	int r;
 
 	/* Detect cases where alternate disappeared */
 	if (!is_directory(path->buf)) {
@@ -533,14 +533,20 @@ static int alt_odb_usable(struct raw_object_store *o,
 	 * Prevent the common mistake of listing the same
 	 * thing twice, or object directory itself.
 	 */
-	for (odb = o->odb; odb; odb = odb->next) {
-		if (!fspathcmp(path->buf, odb->path))
-			return 0;
+	if (!o->odb_by_path) {
+		khiter_t p;
+
+		o->odb_by_path = kh_init_odb_path_map();
+		assert(!o->odb->next);
+		p = kh_put_odb_path_map(o->odb_by_path, o->odb->path, &r);
+		assert(r == 1); /* never used */
+		kh_value(o->odb_by_path, p) = o->odb;
 	}
-	if (!fspathcmp(path->buf, normalized_objdir))
+	if (fspatheq(path->buf, normalized_objdir))
 		return 0;
-
-	return 1;
+	*pos = kh_put_odb_path_map(o->odb_by_path, path->buf, &r);
+	/* r: 0 = exists, 1 = never used, 2 = deleted */
+	return r == 0 ? 0 : 1;
 }
 
 /*
@@ -561,17 +567,18 @@ static int alt_odb_usable(struct raw_object_store *o,
 static void read_info_alternates(struct repository *r,
 				 const char *relative_base,
 				 int depth);
-static int link_alt_odb_entry(struct repository *r, const char *entry,
+static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry,
 	const char *relative_base, int depth, const char *normalized_objdir)
 {
 	struct object_directory *ent;
 	struct strbuf pathbuf = STRBUF_INIT;
+	khiter_t pos;
 
-	if (!is_absolute_path(entry) && relative_base) {
+	if (!is_absolute_path(entry->buf) && relative_base) {
 		strbuf_realpath(&pathbuf, relative_base, 1);
 		strbuf_addch(&pathbuf, '/');
 	}
-	strbuf_addstr(&pathbuf, entry);
+	strbuf_addbuf(&pathbuf, entry);
 
 	if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) {
 		error(_("unable to normalize alternate object path: %s"),
@@ -587,23 +594,25 @@ static int link_alt_odb_entry(struct repository *r, const char *entry,
 	while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/')
 		strbuf_setlen(&pathbuf, pathbuf.len - 1);
 
-	if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir)) {
+	if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos)) {
 		strbuf_release(&pathbuf);
 		return -1;
 	}
 
 	CALLOC_ARRAY(ent, 1);
-	ent->path = xstrdup(pathbuf.buf);
+	/* pathbuf.buf is already in r->objects->odb_by_path */
+	ent->path = strbuf_detach(&pathbuf, NULL);
 
 	/* add the alternate entry */
 	*r->objects->odb_tail = ent;
 	r->objects->odb_tail = &(ent->next);
 	ent->next = NULL;
+	assert(r->objects->odb_by_path);
+	kh_value(r->objects->odb_by_path, pos) = ent;
 
 	/* recursively add alternates */
-	read_info_alternates(r, pathbuf.buf, depth + 1);
+	read_info_alternates(r, ent->path, depth + 1);
 
-	strbuf_release(&pathbuf);
 	return 0;
 }
 
@@ -660,7 +669,7 @@ static void link_alt_odb_entries(struct repository *r, const char *alt,
 		alt = parse_alt_odb_entry(alt, sep, &entry);
 		if (!entry.len)
 			continue;
-		link_alt_odb_entry(r, entry.buf,
+		link_alt_odb_entry(r, &entry,
 				   relative_base, depth, objdirbuf.buf);
 	}
 	strbuf_release(&entry);
@@ -1178,7 +1187,7 @@ static int quick_has_loose(struct repository *r,
 
 	prepare_alt_odb(r);
 	for (odb = r->objects->odb; odb; odb = odb->next) {
-		if (oid_array_lookup(odb_loose_cache(odb, oid), oid) >= 0)
+		if (oidtree_contains(odb_loose_cache(odb, oid), oid))
 			return 1;
 	}
 	return 0;
@@ -2454,39 +2463,45 @@ int for_each_loose_object(each_loose_object_fn cb, void *data,
 static int append_loose_object(const struct object_id *oid, const char *path,
 			       void *data)
 {
-	oid_array_append(data, oid);
+	oidtree_insert(data, oid);
 	return 0;
 }
 
-struct oid_array *odb_loose_cache(struct object_directory *odb,
+struct oidtree *odb_loose_cache(struct object_directory *odb,
 				  const struct object_id *oid)
 {
 	int subdir_nr = oid->hash[0];
 	struct strbuf buf = STRBUF_INIT;
+	size_t word_bits = bitsizeof(odb->loose_objects_subdir_seen[0]);
+	size_t word_index = subdir_nr / word_bits;
+	size_t mask = 1 << (subdir_nr % word_bits);
+	uint32_t *bitmap;
 
 	if (subdir_nr < 0 ||
-	    subdir_nr >= ARRAY_SIZE(odb->loose_objects_subdir_seen))
+	    subdir_nr >= bitsizeof(odb->loose_objects_subdir_seen))
 		BUG("subdir_nr out of range");
 
-	if (odb->loose_objects_subdir_seen[subdir_nr])
-		return &odb->loose_objects_cache[subdir_nr];
-
+	bitmap = &odb->loose_objects_subdir_seen[word_index];
+	if (*bitmap & mask)
+		return odb->loose_objects_cache;
+	if (!odb->loose_objects_cache) {
+		ALLOC_ARRAY(odb->loose_objects_cache, 1);
+		oidtree_init(odb->loose_objects_cache);
+	}
 	strbuf_addstr(&buf, odb->path);
 	for_each_file_in_obj_subdir(subdir_nr, &buf,
 				    append_loose_object,
 				    NULL, NULL,
-				    &odb->loose_objects_cache[subdir_nr]);
-	odb->loose_objects_subdir_seen[subdir_nr] = 1;
+				    odb->loose_objects_cache);
+	*bitmap |= mask;
 	strbuf_release(&buf);
-	return &odb->loose_objects_cache[subdir_nr];
+	return odb->loose_objects_cache;
 }
 
 void odb_clear_loose_cache(struct object_directory *odb)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(odb->loose_objects_cache); i++)
-		oid_array_clear(&odb->loose_objects_cache[i]);
+	oidtree_clear(odb->loose_objects_cache);
+	FREE_AND_NULL(odb->loose_objects_cache);
 	memset(&odb->loose_objects_subdir_seen, 0,
 	       sizeof(odb->loose_objects_subdir_seen));
 }