midx: use `strset` for retained MIDX files
Both `clear_midx_files_ext()` and `clear_incremental_midx_files_ext()` build a list of filenames to keep while pruning stale MIDX files. Today they hand-roll an array instead of using a `strset`, thus requiring us to pass an additional length parameter, and makes lookups linear. Replace the bare array with a `strset` which can be passed around as a single parameter. Though it improves lookup performance, the difference is likely immeasurable given how small the keep_hashes array typically is. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Taylor Blau committed
May 19, 2026 at 11:57 UTC
ddaa7a6fb79038a30b59341ed3f0f2097014ccbf
1 file changed
+27
-30
midx.c
+27
-30
@@ -758,8 +758,7 @@ int midx_checksum_valid(struct multi_pack_index *m)
758
}
759
760
struct clear_midx_data {
761
- char **keep;
762
- uint32_t keep_nr;
761
+ struct strset keep;
762
const char *ext;
763
};
764
@@ -767,15 +766,12 @@ static void clear_midx_file_ext(const char *full_path, size_t full_path_len UNUS
766
const char *file_name, void *_data)
767
{
768
struct clear_midx_data *data = _data;
770
- uint32_t i;
769
770
if (!(starts_with(file_name, "multi-pack-index-") &&
771
ends_with(file_name, data->ext)))
772
return;
775
- for (i = 0; i < data->keep_nr; i++) {
776
- if (!strcmp(data->keep[i], file_name))
777
- return;
778
- }
773
+ if (strset_contains(&data->keep, file_name))
774
+ return;
775
if (unlink(full_path))
776
die_errno(_("failed to remove %s"), full_path);
777
}
@@ -783,48 +779,49 @@ static void clear_midx_file_ext(const char *full_path, size_t full_path_len UNUS
779
void clear_midx_files_ext(struct odb_source *source, const char *ext,
780
const char *keep_hash)
781
{
786
- struct clear_midx_data data;
787
- memset(&data, 0, sizeof(struct clear_midx_data));
782
+ struct clear_midx_data data = {
783
+ .keep = STRSET_INIT,
784
+ .ext = ext,
785
+ };
786
787
if (keep_hash) {
790
- ALLOC_ARRAY(data.keep, 1);
788
+ struct strbuf buf = STRBUF_INIT;
789
+ strbuf_addf(&buf, "multi-pack-index-%s.%s", keep_hash, ext);
790
+
791
+ strset_add(&data.keep, buf.buf);
792
792
- data.keep[0] = xstrfmt("multi-pack-index-%s.%s", keep_hash, ext);
793
- data.keep_nr = 1;
793
+ strbuf_release(&buf);
794
}
795
- data.ext = ext;
795
797
- for_each_file_in_pack_dir(source->path,
798
- clear_midx_file_ext,
799
- &data);
796
+ for_each_file_in_pack_dir(source->path, clear_midx_file_ext, &data);
797
801
- if (keep_hash)
802
- free(data.keep[0]);
803
- free(data.keep);
798
+ strset_clear(&data.keep);
799
}
800
801
void clear_incremental_midx_files_ext(struct odb_source *source, const char *ext,
802
char **keep_hashes,
803
uint32_t hashes_nr)
804
{
810
- struct clear_midx_data data;
805
+ struct clear_midx_data data = {
806
+ .keep = STRSET_INIT,
807
+ .ext = ext,
808
+ };
809
+ struct strbuf buf = STRBUF_INIT;
810
uint32_t i;
811
813
- memset(&data, 0, sizeof(struct clear_midx_data));
812
+ for (i = 0; i < hashes_nr; i++) {
813
+ strbuf_reset(&buf);
814
+ strbuf_addf(&buf, "multi-pack-index-%s.%s", keep_hashes[i],
815
+ ext);
816
815
- ALLOC_ARRAY(data.keep, hashes_nr);
816
- for (i = 0; i < hashes_nr; i++)
817
- data.keep[i] = xstrfmt("multi-pack-index-%s.%s", keep_hashes[i],
818
- ext);
819
- data.keep_nr = hashes_nr;
820
- data.ext = ext;
817
+ strset_add(&data.keep, buf.buf);
818
+ }
819
820
for_each_file_in_pack_subdir(source->path, "multi-pack-index.d",
821
clear_midx_file_ext, &data);
822
825
- for (i = 0; i < hashes_nr; i++)
826
- free(data.keep[i]);
827
- free(data.keep);
823
+ strbuf_release(&buf);
824
+ strset_clear(&data.keep);
825
}
826
827
void clear_midx_file(struct repository *r)