diff options
| -rw-r--r-- | builtin/pack-objects.c | 84 | ||||
| -rw-r--r-- | reachable.h | 4 | ||||
| -rwxr-xr-x | t/t5329-pack-objects-cruft.sh | 143 |
3 files changed, 228 insertions, 3 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 3b8bf6a3dd..8decc9dc0c 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -3447,6 +3447,44 @@ static void add_cruft_object_entry(const struct object_id *oid, enum object_type return; } +static void show_cruft_object(struct object *obj, const char *name, void *data) +{ + /* + * if we did not record it earlier, it's at least as old as our + * expiration value. Rather than find it exactly, just use that + * value. This may bump it forward from its real mtime, but it + * will still be "too old" next time we run with the same + * expiration. + * + * if obj does appear in the packing list, this call is a noop (or may + * set the namehash). + */ + add_cruft_object_entry(&obj->oid, obj->type, NULL, 0, name, cruft_expiration); +} + +static void show_cruft_commit(struct commit *commit, void *data) +{ + show_cruft_object((struct object*)commit, NULL, data); +} + +static int cruft_include_check_obj(struct object *obj, void *data) +{ + return !has_object_kept_pack(&obj->oid, IN_CORE_KEEP_PACKS); +} + +static int cruft_include_check(struct commit *commit, void *data) +{ + return cruft_include_check_obj((struct object*)commit, data); +} + +static void set_cruft_mtime(const struct object *object, + struct packed_git *pack, + off_t offset, time_t mtime) +{ + add_cruft_object_entry(&object->oid, object->type, pack, offset, NULL, + mtime); +} + static void mark_pack_kept_in_core(struct string_list *packs, unsigned keep) { struct string_list_item *item = NULL; @@ -3472,6 +3510,50 @@ static void enumerate_cruft_objects(void) stop_progress(&progress_state); } +static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs) +{ + struct packed_git *p; + struct rev_info revs; + int ret; + + repo_init_revisions(the_repository, &revs, NULL); + + revs.tag_objects = 1; + revs.tree_objects = 1; + revs.blob_objects = 1; + + revs.include_check = cruft_include_check; + revs.include_check_obj = cruft_include_check_obj; + + revs.ignore_missing_links = 1; + + if (progress) + progress_state = start_progress(_("Enumerating cruft objects"), 0); + ret = add_unseen_recent_objects_to_traversal(&revs, cruft_expiration, + set_cruft_mtime, 1); + stop_progress(&progress_state); + + if (ret) + die(_("unable to add cruft objects")); + + /* + * Re-mark only the fresh packs as kept so that objects in + * unknown packs do not halt the reachability traversal early. + */ + for (p = get_all_packs(the_repository); p; p = p->next) + p->pack_keep_in_core = 0; + mark_pack_kept_in_core(fresh_packs, 1); + + if (prepare_revision_walk(&revs)) + die(_("revision walk setup failed")); + if (progress) + progress_state = start_progress(_("Traversing cruft objects"), 0); + nr_seen = 0; + traverse_commit_list(&revs, show_cruft_commit, show_cruft_object, NULL); + + stop_progress(&progress_state); +} + static void read_cruft_objects(void) { struct strbuf buf = STRBUF_INIT; @@ -3523,7 +3605,7 @@ static void read_cruft_objects(void) mark_pack_kept_in_core(&discard_packs, 0); if (cruft_expiration) - die("--cruft-expiration not yet implemented"); + enumerate_and_traverse_cruft_objects(&fresh_packs); else enumerate_cruft_objects(); diff --git a/reachable.h b/reachable.h index b776761baa..020a887b99 100644 --- a/reachable.h +++ b/reachable.h @@ -1,10 +1,10 @@ #ifndef REACHEABLE_H #define REACHEABLE_H -#include "object.h" - struct progress; struct rev_info; +struct object; +struct packed_git; typedef void report_recent_object_fn(const struct object *, struct packed_git *, off_t, time_t); diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh index 003ca7344e..939cdc297a 100755 --- a/t/t5329-pack-objects-cruft.sh +++ b/t/t5329-pack-objects-cruft.sh @@ -214,5 +214,148 @@ basic_cruft_pack_tests () { } basic_cruft_pack_tests never +basic_cruft_pack_tests 2.weeks.ago + +test_expect_success 'cruft tags rescue tagged objects' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + + test_commit packed && + git repack -Ad && + + test_commit tagged && + git tag -a annotated -m tag && + + git rev-list --objects --no-object-names packed.. >objects && + while read oid + do + test-tool chmtime -1000 \ + "$objdir/$(test_oid_to_path $oid)" + done <objects && + + test-tool chmtime -500 \ + "$objdir/$(test_oid_to_path $(git rev-parse annotated))" && + + keep="$(basename "$(ls $packdir/pack-*.pack)")" && + cruft="$(echo $keep | git pack-objects --cruft \ + --cruft-expiration=750.seconds.ago \ + $packdir/pack)" && + test-tool pack-mtimes "pack-$cruft.mtimes" >actual.raw && + cut -f1 -d" " <actual.raw | sort >actual && + + ( + cat objects && + git rev-parse annotated + ) >expect.raw && + sort <expect.raw >expect && + + test_cmp expect actual && + cat actual + ) +' + +test_expect_success 'cruft commits rescue parents, trees' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + + test_commit packed && + git repack -Ad && + + test_commit old && + test_commit new && + + git rev-list --objects --no-object-names packed..new >objects && + while read object + do + test-tool chmtime -1000 \ + "$objdir/$(test_oid_to_path $object)" + done <objects && + test-tool chmtime +500 "$objdir/$(test_oid_to_path \ + $(git rev-parse HEAD))" && + + keep="$(basename "$(ls $packdir/pack-*.pack)")" && + cruft="$(echo $keep | git pack-objects --cruft \ + --cruft-expiration=750.seconds.ago \ + $packdir/pack)" && + test-tool pack-mtimes "pack-$cruft.mtimes" >actual.raw && + + cut -d" " -f1 <actual.raw | sort >actual && + sort <objects >expect && + + test_cmp expect actual + ) +' + +test_expect_success 'cruft trees rescue sub-trees, blobs' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + + test_commit packed && + git repack -Ad && + + mkdir -p dir/sub && + echo foo >foo && + echo bar >dir/bar && + echo baz >dir/sub/baz && + + test_tick && + git add . && + git commit -m "pruned" && + + test-tool chmtime -1000 "$objdir/$(test_oid_to_path $(git rev-parse HEAD))" && + test-tool chmtime -1000 "$objdir/$(test_oid_to_path $(git rev-parse HEAD^{tree}))" && + test-tool chmtime -1000 "$objdir/$(test_oid_to_path $(git rev-parse HEAD:foo))" && + test-tool chmtime -500 "$objdir/$(test_oid_to_path $(git rev-parse HEAD:dir))" && + test-tool chmtime -1000 "$objdir/$(test_oid_to_path $(git rev-parse HEAD:dir/bar))" && + test-tool chmtime -1000 "$objdir/$(test_oid_to_path $(git rev-parse HEAD:dir/sub))" && + test-tool chmtime -1000 "$objdir/$(test_oid_to_path $(git rev-parse HEAD:dir/sub/baz))" && + + keep="$(basename "$(ls $packdir/pack-*.pack)")" && + cruft="$(echo $keep | git pack-objects --cruft \ + --cruft-expiration=750.seconds.ago \ + $packdir/pack)" && + test-tool pack-mtimes "pack-$cruft.mtimes" >actual.raw && + cut -f1 -d" " <actual.raw | sort >actual && + + git rev-parse HEAD:dir HEAD:dir/bar HEAD:dir/sub HEAD:dir/sub/baz >expect.raw && + sort <expect.raw >expect && + + test_cmp expect actual + ) +' + +test_expect_success 'expired objects are pruned' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + + test_commit packed && + git repack -Ad && + + test_commit pruned && + + git rev-list --objects --no-object-names packed..pruned >objects && + while read object + do + test-tool chmtime -1000 \ + "$objdir/$(test_oid_to_path $object)" + done <objects && + + keep="$(basename "$(ls $packdir/pack-*.pack)")" && + cruft="$(echo $keep | git pack-objects --cruft \ + --cruft-expiration=750.seconds.ago \ + $packdir/pack)" && + + test-tool pack-mtimes "pack-$cruft.mtimes" >actual && + test_must_be_empty actual + ) +' test_done |