From 0cd306ebc8c7a9faeced0a2fa7bddeea434bf285 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 5 Jan 2026 14:16:41 +0100 Subject: builtin/pack-objects: exclude promisor objects with "--stdin-packs" It is currently not possible to combine "--exclude-promisor-objects" with "--stdin-packs" because both flags want to set up a revision walk to enumerate the objects to pack. In a subsequent commit though we want to extend geometric repacks to support promisor objects, and for that we need to handle the combination of both flags. There are two cases we have to think about here: - "--stdin-packs" asks us to pack exactly the objects part of the specified packfiles. It is somewhat questionable what to do in the case where the user asks us to exclude promisor objects, but at the same time explicitly passes a promisor pack to us. For now, we simply abort the request as it is self-contradicting. As we have also been dying before this commit there is no regression here. - "--stdin-packs=follow" does the same as the first flag, but it also asks us to include all objects transitively reachable from any object in the packs we are about to repack. This is done by doing the revision walk mentioned further up. Luckily, fixing this case is trivial: we only need to modify the revision walk to also set the `exclude_promisor_objects` field. Note that we do not support the "--exclude-promisor-objects-best-effort" flag for now as we don't need it to support geometric repacking with promisor objects. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- builtin/pack-objects.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'builtin') diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index ca44b7894f..c53e0c91b9 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -3857,8 +3857,11 @@ static void read_packs_list_from_stdin(struct rev_info *revs) repo_for_each_pack(the_repository, p) { const char *pack_name = pack_basename(p); - if ((item = string_list_lookup(&include_packs, pack_name))) + if ((item = string_list_lookup(&include_packs, pack_name))) { + if (exclude_promisor_objects && p->pack_promisor) + die(_("packfile %s is a promisor but --exclude-promisor-objects was given"), p->pack_name); item->util = p; + } if ((item = string_list_lookup(&exclude_packs, pack_name))) item->util = p; } @@ -3936,6 +3939,7 @@ static void read_stdin_packs(enum stdin_packs_mode mode, int rev_list_unpacked) revs.tree_objects = 1; revs.tag_objects = 1; revs.ignore_missing_links = 1; + revs.exclude_promisor_objects = exclude_promisor_objects; /* avoids adding objects in excluded packs */ ignore_packed_keep_in_core = 1; @@ -5092,9 +5096,13 @@ int cmd_pack_objects(int argc, exclude_promisor_objects_best_effort, "--exclude-promisor-objects-best-effort"); if (exclude_promisor_objects) { - use_internal_rev_list = 1; fetch_if_missing = 0; - strvec_push(&rp, "--exclude-promisor-objects"); + + /* --stdin-packs handles promisor objects separately. */ + if (!stdin_packs) { + use_internal_rev_list = 1; + strvec_push(&rp, "--exclude-promisor-objects"); + } } else if (exclude_promisor_objects_best_effort) { use_internal_rev_list = 1; fetch_if_missing = 0; -- cgit v1.3-6-g1900 From dcc9c7ef47d8755f1448116cdf0a421129999cd4 Mon Sep 17 00:00:00 2001 From: Patrick Steinhardt Date: Mon, 5 Jan 2026 14:16:45 +0100 Subject: builtin/repack: handle promisor packs with geometric repacking When performing a fetch with an object filter, we mark the resulting packfile as a promisor pack. An object part of such a pack may miss any of its referenced objects, and Git knows to handle this case by fetching any such missing objects from the promisor remote. The "promisor" property needs to be retained going forward. So every time we pack a promisor object, the resulting pack must be marked as a promisor pack. git-repack(1) does this already: when a repository has a promisor remote, it knows to pass "--exclude-promisor-objects" to the git-pack-objects(1) child process. Promisor packs are written separately when doing an all-into-one repack via `repack_promisor_objects()`. But we don't support promisor objects when doing a geometric repack yet. Promisor packs do not get any special treatment there, as we simply merge promisor and non-promisor packs. The resulting pack is not even marked as a promisor pack, which essentially corrupts the repository. This corruption couldn't happen in the real world though: we pass both "--exclude-promisor-objects" and "--stdin-packs" to git-pack-objects(1) if a repository has a promisor remote, but as those options are mutually exclusive we always end up dying. And while we made those flags compatible with one another in a preceding commit, we still end up dying in case git-pack-objects(1) is asked to repack a promisor pack. There's multiple ways to fix this: - We can exclude promisor packs from the geometric progression altogether. This would have the consequence that we never repack promisor packs at all. But in a partial clone it is quite likely that the user generates a bunch of promisor packs over time, as every backfill fetch would create another one. So this doesn't really feel like a sensible option. - We can adapt git-pack-objects(1) to support repacking promisor packs and include them in the normal geometric progression. But this would mean that the set of promisor objects expands over time as the packs are merged with normal packs. - We can use a separate geometric progression to repack promisor packs. The first two options both have significant downsides, so they aren't really feasible. But the third option fixes both of these downsides: we make sure that promisor packs get merged, and at the same time we never expand the set of promisor objects beyond the set of objects that are already marked as promisor objects. Implement this strategy so that geometric repacking works in partial clones. Signed-off-by: Patrick Steinhardt Signed-off-by: Junio C Hamano --- builtin/repack.c | 3 +++ repack-geometry.c | 28 ++++++++++++++++----- repack-promisor.c | 28 +++++++++++++++++++++ repack.h | 10 ++++++++ t/t7703-repack-geometric.sh | 61 +++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 124 insertions(+), 6 deletions(-) (limited to 'builtin') diff --git a/builtin/repack.c b/builtin/repack.c index d9012141f6..f6bb04bef7 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -332,6 +332,9 @@ int cmd_repack(int argc, !(pack_everything & PACK_CRUFT)) strvec_push(&cmd.args, "--pack-loose-unreachable"); } else if (geometry.split_factor) { + pack_geometry_repack_promisors(repo, &po_args, &geometry, + &names, packtmp); + if (midx_must_contain_cruft) strvec_push(&cmd.args, "--stdin-packs"); else diff --git a/repack-geometry.c b/repack-geometry.c index 0daf545a81..7cebd0cb45 100644 --- a/repack-geometry.c +++ b/repack-geometry.c @@ -66,15 +66,25 @@ void pack_geometry_init(struct pack_geometry *geometry, if (p->is_cruft) continue; - ALLOC_GROW(geometry->pack, - geometry->pack_nr + 1, - geometry->pack_alloc); - - geometry->pack[geometry->pack_nr] = p; - geometry->pack_nr++; + if (p->pack_promisor) { + ALLOC_GROW(geometry->promisor_pack, + geometry->promisor_pack_nr + 1, + geometry->promisor_pack_alloc); + + geometry->promisor_pack[geometry->promisor_pack_nr] = p; + geometry->promisor_pack_nr++; + } else { + ALLOC_GROW(geometry->pack, + geometry->pack_nr + 1, + geometry->pack_alloc); + + geometry->pack[geometry->pack_nr] = p; + geometry->pack_nr++; + } } QSORT(geometry->pack, geometry->pack_nr, pack_geometry_cmp); + QSORT(geometry->promisor_pack, geometry->promisor_pack_nr, pack_geometry_cmp); strbuf_release(&buf); } @@ -160,6 +170,9 @@ void pack_geometry_split(struct pack_geometry *geometry) { geometry->split = compute_pack_geometry_split(geometry->pack, geometry->pack_nr, geometry->split_factor); + geometry->promisor_split = compute_pack_geometry_split(geometry->promisor_pack, + geometry->promisor_pack_nr, + geometry->split_factor); } struct packed_git *pack_geometry_preferred_pack(struct pack_geometry *geometry) @@ -234,6 +247,8 @@ void pack_geometry_remove_redundant(struct pack_geometry *geometry, { remove_redundant_packs(geometry->pack, geometry->split, names, existing, packdir); + remove_redundant_packs(geometry->promisor_pack, geometry->promisor_split, + names, existing, packdir); } void pack_geometry_release(struct pack_geometry *geometry) @@ -242,4 +257,5 @@ void pack_geometry_release(struct pack_geometry *geometry) return; free(geometry->pack); + free(geometry->promisor_pack); } diff --git a/repack-promisor.c b/repack-promisor.c index 125038d92e..73af57bce3 100644 --- a/repack-promisor.c +++ b/repack-promisor.c @@ -109,3 +109,31 @@ void repack_promisor_objects(struct repository *repo, finish_repacking_promisor_objects(repo, &cmd, names, packtmp); } + +void pack_geometry_repack_promisors(struct repository *repo, + const struct pack_objects_args *args, + const struct pack_geometry *geometry, + struct string_list *names, + const char *packtmp) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + FILE *in; + + if (!geometry->promisor_split) + return; + + prepare_pack_objects(&cmd, args, packtmp); + strvec_push(&cmd.args, "--stdin-packs"); + cmd.in = -1; + if (start_command(&cmd)) + die(_("could not start pack-objects to repack promisor packs")); + + in = xfdopen(cmd.in, "w"); + for (size_t i = 0; i < geometry->promisor_split; i++) + fprintf(in, "%s\n", pack_basename(geometry->promisor_pack[i])); + for (size_t i = geometry->promisor_split; i < geometry->promisor_pack_nr; i++) + fprintf(in, "^%s\n", pack_basename(geometry->promisor_pack[i])); + fclose(in); + + finish_repacking_promisor_objects(repo, &cmd, names, packtmp); +} diff --git a/repack.h b/repack.h index 3a688a12ee..bc9f2e1a5d 100644 --- a/repack.h +++ b/repack.h @@ -103,9 +103,19 @@ struct pack_geometry { uint32_t pack_nr, pack_alloc; uint32_t split; + struct packed_git **promisor_pack; + uint32_t promisor_pack_nr, promisor_pack_alloc; + uint32_t promisor_split; + int split_factor; }; +void pack_geometry_repack_promisors(struct repository *repo, + const struct pack_objects_args *args, + const struct pack_geometry *geometry, + struct string_list *names, + const char *packtmp); + void pack_geometry_init(struct pack_geometry *geometry, struct existing_packs *existing, const struct pack_objects_args *args); diff --git a/t/t7703-repack-geometric.sh b/t/t7703-repack-geometric.sh index 98806cdb6f..04d5d8fc33 100755 --- a/t/t7703-repack-geometric.sh +++ b/t/t7703-repack-geometric.sh @@ -480,4 +480,65 @@ test_expect_success '--geometric -l disables writing bitmaps with non-local pack test_path_is_file member/.git/objects/pack/multi-pack-index-*.bitmap ' +write_packfile () { + NR="$1" + PREFIX="$2" + + printf "blob\ndata <objects-expect && + + ls .git/objects/pack/*.pack >packs-before && + test_line_count = 8 packs-before && + git repack --geometric=2 -d && + ls .git/objects/pack/*.pack >packs-after && + test_line_count = 5 packs-after && + test_grep ! "$NORMAL_A" packs-after && + test_grep ! "$NORMAL_B" packs-after && + test_grep "$NORMAL_C" packs-after && + test_grep ! "$PROMISOR_A" packs-after && + test_grep ! "$PROMISOR_B" packs-after && + test_grep ! "$PROMISOR_C" packs-after && + test_grep "$PROMISOR_D" packs-after && + test_grep "$PROMISOR_E" packs-after && + + ls .git/objects/pack/*.promisor >promisors && + test_line_count = 3 promisors && + + git cat-file --batch-all-objects --batch-check="%(objectname)" >objects-actual && + test_cmp objects-expect objects-actual + ) +' + test_done -- cgit v1.3-6-g1900