@matheusbsbs / matheus-bagliano / commits / 2cdb796101

files-backend.c: avoid stat in 'loose_fill_ref_dir'

Modify the 'readdir' loop in 'loose_fill_ref_dir' to, rather than 'stat' a file to determine whether it is a directory or not, use 'get_dtype'. Currently, the loop uses 'stat' to determine whether each dirent is a directory itself or not in order to construct the appropriate ref cache entry. If 'stat' fails (returning a negative value), the dirent is silently skipped; otherwise, 'S_ISDIR(st.st_mode)' is used to check whether the entry is a directory. On platforms that include an entry's d_type in in the 'dirent' struct, this extra 'stat' check is redundant. We can use the 'get_dtype' method to extract this information on platforms that support it (i.e. where NO_D_TYPE_IN_DIRENT is unset), and derive it with 'stat' on platforms that don't. Because 'stat' is an expensive call, this confers a modest-but-noticeable performance improvement when iterating over large numbers of refs (approximately 20% speedup in 'git for-each-ref' in a 30k ref repo). Unlike other existing usage of 'get_dtype', the 'follow_symlinks' arg is set to 1 to replicate the existing handling of symlink dirents. This unfortunately requires calling 'stat' on the associated entry regardless of platform, but symlinks in the loose ref store are highly unlikely since they'd need to be created manually by a user. Note that this patch also changes the condition for skipping creation of a ref entry from "when 'stat' fails" to "when the d_type is anything other than DT_REG or DT_DIR". If a dirent's d_type is DT_UNKNOWN (either because the platform doesn't support d_type in dirents or some other reason) or DT_LNK, 'get_dtype' will try to derive the underlying type with 'stat'. If the 'stat' fails, the d_type will remain 'DT_UNKNOWN' and dirent will be skipped. However, it will also be skipped if it is any other valid d_type (e.g. DT_FIFO for named pipes, DT_LNK for a nested symlink). Git does not handle these properly anyway, so we can safely constrain accepted types to directories and regular files. Signed-off-by: Victoria Dye <vdye@github.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Victoria Dye committed Oct 9, 2023 at 21:58 UTC 2cdb796101be2feb47a57760b3b0057ad71402bf

1 file changed +5 -9

refs/files-backend.c

+5 -9

@@ -246,10 +246,8 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,

246 int dirnamelen = strlen(dirname);

247 struct strbuf refname;

248 struct strbuf path = STRBUF_INIT;

249 - size_t path_baselen;

249

250 files_ref_path(refs, &path, dirname);

252 - path_baselen = path.len;

251

252 d = opendir(path.buf);

253 if (!d) {

@@ -262,23 +260,22 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,

260

261 while ((de = readdir(d)) != NULL) {

262 struct object_id oid;

265 - struct stat st;

263 int flag;

264 + unsigned char dtype;

265

266 if (de->d_name[0] == '.')

267 continue;

268 if (ends_with(de->d_name, ".lock"))

269 continue;

270 strbuf_addstr(&refname, de->d_name);

273 - strbuf_addstr(&path, de->d_name);

274 - if (stat(path.buf, &st) < 0) {

275 - ; /* silently ignore */

276 - } else if (S_ISDIR(st.st_mode)) {

271 +

272 + dtype = get_dtype(de, &path, 1);

273 + if (dtype == DT_DIR) {

274 strbuf_addch(&refname, '/');

275 add_entry_to_dir(dir,

276 create_dir_entry(dir->cache, refname.buf,

277 refname.len));

281 - } else {

278 + } else if (dtype == DT_REG) {

279 if (!refs_resolve_ref_unsafe(&refs->base,

280 refname.buf,

281 RESOLVE_REF_READING,

@@ -308,7 +305,6 @@ static void loose_fill_ref_dir(struct ref_store *ref_store,

305 create_ref_entry(refname.buf, &oid, flag));

306 }

307 strbuf_setlen(&refname, dirnamelen);

311 - strbuf_setlen(&path, path_baselen);

308 }

309 strbuf_release(&refname);

310 strbuf_release(&path);