[PATCH 03/10] builtin/gc.c: ignore cruft packs with `--keep-largest-pack`

From

Taylor Blau <me@ttaylorr.com>

Date

Apr 17, 2023, 20:54 UTC

Message-ID

<796df920ad6af0ee9101a0f3f80edbc793987336.1681764848.git.me@ttaylorr.com>

In-Reply-To

<cover.1681764848.git.me@ttaylorr.com>

  - Running `git gc --keep-largest-pack` in a repository where the
    largest pack is the cruft pack itself will make it impossible for
    `git gc` to prune objects, since the cruft pack itself is kept.

  - The same is true for `gc.bigPackThreshold`, if the size of the cruft
    pack exceeds the limit set by the caller.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 Documentation/config/gc.txt | 10 ++++-----
 Documentation/git-gc.txt    |  7 +++---
 builtin/gc.c                |  2 +-
 t/t6500-gc.sh               | 43 +++++++++++++++++++++++++++++++++++++
 4 files changed, 53 insertions(+), 9 deletions(-)

diff --git a/Documentation/config/gc.txt b/Documentation/config/gc.txt
index 38fea076a2..8d5353e9e0 100644
--- a/Documentation/config/gc.txt
+++ b/Documentation/config/gc.txt
@@ -43,11 +43,11 @@ gc.autoDetach::
 	if the system supports it. Default is true.
 
 gc.bigPackThreshold::
-	If non-zero, all packs larger than this limit are kept when
-	`git gc` is run. This is very similar to `--keep-largest-pack`
-	except that all packs that meet the threshold are kept, not
-	just the largest pack. Defaults to zero. Common unit suffixes of
-	'k', 'm', or 'g' are supported.
+	If non-zero, all non-cruft packs larger than this limit are kept
+	when `git gc` is run. This is very similar to
+	`--keep-largest-pack` except that all non-cruft packs that meet
+	the threshold are kept, not just the largest pack. Defaults to
+	zero. Common unit suffixes of 'k', 'm', or 'g' are supported.
 +
 Note that if the number of kept packs is more than gc.autoPackLimit,
 this configuration variable is ignored, all packs except the base pack
diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index a65c9aa62d..2427478314 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -77,9 +77,10 @@ be performed as well.
 	instance running on this repository.
 
 --keep-largest-pack::
-	All packs except the largest pack and those marked with a
-	`.keep` files are consolidated into a single pack. When this
-	option is used, `gc.bigPackThreshold` is ignored.
+	All packs except the largest pack, any packs marked with a
+	`.keep` file, and any cruft pack(s) are consolidated into a
+	single pack. When this option is used, `gc.bigPackThreshold` is
+	ignored.
 
 AGGRESSIVE
 ----------
diff --git a/builtin/gc.c b/builtin/gc.c
index edd98d35a5..53ef137e1d 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -219,7 +219,7 @@ static struct packed_git *find_base_packs(struct string_list *packs,
 	struct packed_git *p, *base = NULL;
 
 	for (p = get_all_packs(the_repository); p; p = p->next) {
-		if (!p->pack_local)
+		if (!p->pack_local || p->is_cruft)
 			continue;
 		if (limit) {
 			if (p->pack_size >= limit)
diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh
index d9acb63951..df6f2e6e52 100755
--- a/t/t6500-gc.sh
+++ b/t/t6500-gc.sh
@@ -298,6 +298,49 @@ test_expect_success 'feature.experimental=false avoids cruft packs by default' '
 	)
 '
 
+test_expect_success '--keep-largest-pack ignores cruft packs' '
+	test_when_finished "rm -fr repo" &&
+	git init repo &&
+	(
+		cd repo &&
+
+		# Generate a pack for reachable objects (of which there
+		# are 3), and one for unreachable objects (of which
+		# there are 6).
+		prepare_cruft_history &&
+		git gc --cruft &&
+
+		mtimes="$(find .git/objects/pack -type f -name "pack-*.mtimes")" &&
+		sz="$(test_file_size "${mtimes%.mtimes}.pack")" &&
+
+		# Ensure that the cruft pack gets removed (due to
+		# `--prune=now`) despite it being the largest pack.
+		git -c gc.bigPackThreshold=$sz gc --cruft --prune=now &&
+
+		assert_no_cruft_packs
+	)
+'
+
+test_expect_success 'gc.bigPackThreshold ignores cruft packs' '
+	test_when_finished "rm -fr repo" &&
+	git init repo &&
+	(
+		cd repo &&
+
+		# Generate a pack for reachable objects (of which there
+		# are 3), and one for unreachable objects (of which
+		# there are 6).
+		prepare_cruft_history &&
+		git gc --cruft &&
+
+		# Ensure that the cruft pack gets removed (due to
+		# `--prune=now`) despite it being the largest pack.
+		git gc --cruft --prune=now --keep-largest-pack &&
+
+		assert_no_cruft_packs
+	)
+'
+
 run_and_wait_for_auto_gc () {
 	# We read stdout from gc for the side effect of waiting until the
 	# background gc process exits, closing its fd 9.  Furthermore, the

-- 
2.38.1