From ddee3703b36e96056f11ddc4621707b6054bab48 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 20 May 2022 19:18:11 -0400 Subject: [PATCH] builtin/repack.c: add cruft packs to MIDX during geometric repack When using cruft packs, the following race can occur when a geometric repack that writes a MIDX bitmap takes place afterwords: - First, create an unreachable object and do an all-into-one cruft repack which stores that object in the repository's cruft pack. - Then make that object reachable. - Finally, do a geometric repack and write a MIDX bitmap. Assuming that we are sufficiently unlucky as to select a commit from the MIDX which reaches that object for bitmapping, then the `git multi-pack-index` process will complain that that object is missing. The reason is because we don't include cruft packs in the MIDX when doing a geometric repack. Since the "make that object reachable" doesn't necessarily mean that we'll create a new copy of that object in one of the packs that will get rolled up as part of a geometric repack, it's possible that the MIDX won't see any copies of that now-reachable object. Of course, it's desirable to avoid including cruft packs in the MIDX because it causes the MIDX to store a bunch of objects which are likely to get thrown away. But excluding that pack does open us up to the above race. This patch demonstrates the bug, and resolves it by including cruft packs in the MIDX even when doing a geometric repack. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- builtin/repack.c | 23 ++++++++++++++++++++--- t/t5329-pack-objects-cruft.sh | 26 ++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 3 deletions(-) diff --git a/builtin/repack.c b/builtin/repack.c index 36d1f03671..15071fadbe 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -23,6 +23,7 @@ #define PACK_CRUFT 4 #define DELETE_PACK 1 +#define CRUFT_PACK 2 static int pack_everything; static int delta_base_offset = 1; @@ -159,10 +160,15 @@ static void collect_pack_filenames(struct string_list *fname_nonkept_list, fname = xmemdupz(e->d_name, len); if ((extra_keep->nr > 0 && i < extra_keep->nr) || - (file_exists(mkpath("%s/%s.keep", packdir, fname)))) + (file_exists(mkpath("%s/%s.keep", packdir, fname)))) { string_list_append_nodup(fname_kept_list, fname); - else - string_list_append_nodup(fname_nonkept_list, fname); + } else { + struct string_list_item *item; + item = string_list_append_nodup(fname_nonkept_list, + fname); + if (file_exists(mkpath("%s/%s.mtimes", packdir, fname))) + item->util = (void*)(uintptr_t)CRUFT_PACK; + } } closedir(dir); } @@ -564,6 +570,17 @@ static void midx_included_packs(struct string_list *include, string_list_insert(include, strbuf_detach(&buf, NULL)); } + + for_each_string_list_item(item, existing_nonkept_packs) { + if (!((uintptr_t)item->util & CRUFT_PACK)) { + /* + * no need to check DELETE_PACK, since we're not + * doing an ALL_INTO_ONE repack + */ + continue; + } + string_list_insert(include, xstrfmt("%s.idx", item->string)); + } } else { for_each_string_list_item(item, existing_nonkept_packs) { if ((uintptr_t)item->util & DELETE_PACK) diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh index c82f973b41..8de87afce2 100755 --- a/t/t5329-pack-objects-cruft.sh +++ b/t/t5329-pack-objects-cruft.sh @@ -648,4 +648,30 @@ test_expect_success 'cruft --local drops unreachable objects' ' ) ' +test_expect_success 'MIDX bitmaps tolerate reachable cruft objects' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + + test_commit reachable && + test_commit cruft && + unreachable="$(git rev-parse cruft)" && + + git reset --hard $unreachable^ && + git tag -d cruft && + git reflog expire --all --expire=all && + + git repack --cruft -d && + + # resurrect the unreachable object via a new commit. the + # new commit will get selected for a bitmap, but be + # missing one of its parents from the selected packs. + git reset --hard $unreachable && + test_commit resurrect && + + git repack --write-midx --write-bitmap-index --geometric=2 -d + ) +' + test_done