builtin/repack.c: support generating a cruft pack

Expose a way to split the contents of a repository into a main and cruft
pack when doing an all-into-one repack with `git repack --cruft -d`, and
a complementary configuration variable.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 207 insertions, 0 deletions

diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh
index 939cdc2..067c50a 100755
--- a/t/t5329-pack-objects-cruft.sh
+++ b/t/t5329-pack-objects-cruft.sh
@@ -358,4 +358,211 @@ test_expect_success 'expired objects are pruned' '
 	)
 '
 
+test_expect_success 'repack --cruft generates a cruft pack' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit reachable &&
+		git branch -M main &&
+		git checkout --orphan other &&
+		test_commit unreachable &&
+
+		git checkout main &&
+		git branch -D other &&
+		git tag -d unreachable &&
+		# objects are not cruft if they are contained in the reflogs
+		git reflog expire --all --expire=all &&
+
+		git rev-list --objects --all --no-object-names >reachable.raw &&
+		git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
+		sort <reachable.raw >reachable &&
+		comm -13 reachable objects >unreachable &&
+
+		git repack --cruft -d &&
+
+		cruft=$(basename $(ls $packdir/pack-*.mtimes) .mtimes) &&
+		pack=$(basename $(ls $packdir/pack-*.pack | grep -v $cruft) .pack) &&
+
+		git show-index <$packdir/$pack.idx >actual.raw &&
+		cut -f2 -d" " actual.raw | sort >actual &&
+		test_cmp reachable actual &&
+
+		git show-index <$packdir/$cruft.idx >actual.raw &&
+		cut -f2 -d" " actual.raw | sort >actual &&
+		test_cmp unreachable actual
+	)
+'
+
+test_expect_success 'loose objects mtimes upsert others' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit reachable &&
+		git repack -Ad &&
+		git branch -M main &&
+
+		git checkout --orphan other &&
+		test_commit cruft &&
+		# incremental repack, leaving existing objects loose (so
+		# they can be "freshened")
+		git repack &&
+
+		tip="$(git rev-parse cruft)" &&
+		path="$objdir/$(test_oid_to_path "$tip")" &&
+		test-tool chmtime --get +1000 "$path" >expect &&
+
+		git checkout main &&
+		git branch -D other &&
+		git tag -d cruft &&
+		git reflog expire --all --expire=all &&
+
+		git repack --cruft -d &&
+
+		mtimes="$(basename $(ls $packdir/pack-*.mtimes))" &&
+		test-tool pack-mtimes "$mtimes" >actual.raw &&
+		grep "$tip" actual.raw | cut -d" " -f2 >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'cruft packs are not included in geometric repack' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit reachable &&
+		git repack -Ad &&
+		git branch -M main &&
+
+		git checkout --orphan other &&
+		test_commit cruft &&
+		git repack -d &&
+
+		git checkout main &&
+		git branch -D other &&
+		git tag -d cruft &&
+		git reflog expire --all --expire=all &&
+
+		git repack --cruft &&
+
+		find $packdir -type f | sort >before &&
+		git repack --geometric=2 -d &&
+		find $packdir -type f | sort >after &&
+
+		test_cmp before after
+	)
+'
+
+test_expect_success 'repack --geometric collects once-cruft objects' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit reachable &&
+		git repack -Ad &&
+		git branch -M main &&
+
+		git checkout --orphan other &&
+		git rm -rf . &&
+		test_commit --no-tag cruft &&
+		cruft="$(git rev-parse HEAD)" &&
+
+		git checkout main &&
+		git branch -D other &&
+		git reflog expire --all --expire=all &&
+
+		# Pack the objects created in the previous step into a cruft
+		# pack. Intentionally leave loose copies of those objects
+		# around so we can pick them up in a subsequent --geometric
+		# reapack.
+		git repack --cruft &&
+
+		# Now make those objects reachable, and ensure that they are
+		# packed into the new pack created via a --geometric repack.
+		git update-ref refs/heads/other $cruft &&
+
+		# Without this object, the set of unpacked objects is exactly
+		# the set of objects already in the cruft pack. Tweak that set
+		# to ensure we do not overwrite the cruft pack entirely.
+		test_commit reachable2 &&
+
+		find $packdir -name "pack-*.idx" | sort >before &&
+		git repack --geometric=2 -d &&
+		find $packdir -name "pack-*.idx" | sort >after &&
+
+		{
+			git rev-list --objects --no-object-names $cruft &&
+			git rev-list --objects --no-object-names reachable..reachable2
+		} >want.raw &&
+		sort want.raw >want &&
+
+		pack=$(comm -13 before after) &&
+		git show-index <$pack >objects.raw &&
+
+		cut -d" " -f2 objects.raw | sort >got &&
+
+		test_cmp want got
+	)
+'
+
+test_expect_success 'cruft repack with no reachable objects' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+		git repack -ad &&
+
+		base="$(git rev-parse base)" &&
+
+		git for-each-ref --format="delete %(refname)" >in &&
+		git update-ref --stdin <in &&
+		git reflog expire --all --expire=all &&
+		rm -fr .git/index &&
+
+		git repack --cruft -d &&
+
+		git cat-file -t $base
+	)
+'
+
+test_expect_success 'cruft repack ignores --max-pack-size' '
+	git init max-pack-size &&
+	(
+		cd max-pack-size &&
+		test_commit base &&
+		# two cruft objects which exceed the maximum pack size
+		test-tool genrandom foo 1048576 | git hash-object --stdin -w &&
+		test-tool genrandom bar 1048576 | git hash-object --stdin -w &&
+		git repack --cruft --max-pack-size=1M &&
+		find $packdir -name "*.mtimes" >cruft &&
+		test_line_count = 1 cruft &&
+		test-tool pack-mtimes "$(basename "$(cat cruft)")" >objects &&
+		test_line_count = 2 objects
+	)
+'
+
+test_expect_success 'cruft repack ignores pack.packSizeLimit' '
+	(
+		cd max-pack-size &&
+		# repack everything back together to remove the existing cruft
+		# pack (but to keep its objects)
+		git repack -adk &&
+		git -c pack.packSizeLimit=1M repack --cruft &&
+		# ensure the same post condition is met when --max-pack-size
+		# would otherwise be inferred from the configuration
+		find $packdir -name "*.mtimes" >cruft &&
+		test_line_count = 1 cruft &&
+		test-tool pack-mtimes "$(basename "$(cat cruft)")" >objects &&
+		test_line_count = 2 objects
+	)
+'
+
 test_done