[PATCH v2 2/2] multi-pack-index: respect repack.packKeptObjects=false

["Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>]

From: Derrick Stolee <dstolee@microsoft.com>

When selecting a batch of pack-files to repack in the "git
multi-pack-index repack" command, Git should respect the
repack.packKeptObjects config option. When false, this option says that
the pack-files with an associated ".keep" file should not be repacked.
This config value is "false" by default.

There are two cases for selecting a batch of objects. The first is the
case where the input batch-size is zero, which specifies "repack
everything". The second is with a non-zero batch size, which selects
pack-files using a greedy selection criteria. Both of these cases are
updated and tested.

Reported-by: Son Luong Ngoc <sluongng@gmail.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 Documentation/git-multi-pack-index.txt |  3 +++
 midx.c                                 | 26 +++++++++++++++++++++-----
 t/t5319-multi-pack-index.sh            | 26 ++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 5 deletions(-)

diff --git a/Documentation/git-multi-pack-index.txt b/Documentation/git-multi-pack-index.txt
index 642d9ac5b72..0c6619493c1 100644
--- a/Documentation/git-multi-pack-index.txt
+++ b/Documentation/git-multi-pack-index.txt
@@ -56,6 +56,9 @@ repack::
 	file is created, rewrite the multi-pack-index to reference the
 	new pack-file. A later run of 'git multi-pack-index expire' will
 	delete the pack-files that were part of this batch.
++
+If `repack.packKeptObjects` is `false`, then any pack-files with an
+associated `.keep` file will not be selected for the batch to repack.
 
 
 EXAMPLES
diff --git a/midx.c b/midx.c
index 3348f8e569b..b8a52740832 100644
--- a/midx.c
+++ b/midx.c
@@ -1293,15 +1293,26 @@ static int compare_by_mtime(const void *a_, const void *b_)
 	return 0;
 }
 
-static int fill_included_packs_all(struct multi_pack_index *m,
+static int fill_included_packs_all(struct repository *r,
+				   struct multi_pack_index *m,
 				   unsigned char *include_pack)
 {
-	uint32_t i;
+	uint32_t i, count = 0;
+	int pack_kept_objects = 0;
+
+	repo_config_get_bool(r, "repack.packkeptobjects", &pack_kept_objects);
+
+	for (i = 0; i < m->num_packs; i++) {
+		if (prepare_midx_pack(r, m, i))
+			continue;
+		if (!pack_kept_objects && m->packs[i]->pack_keep)
+			continue;
 
-	for (i = 0; i < m->num_packs; i++)
 		include_pack[i] = 1;
+		count++;
+	}
 
-	return m->num_packs < 2;
+	return count < 2;
 }
 
 static int fill_included_packs_batch(struct repository *r,
@@ -1312,6 +1323,9 @@ static int fill_included_packs_batch(struct repository *r,
 	uint32_t i, packs_to_repack;
 	size_t total_size;
 	struct repack_info *pack_info = xcalloc(m->num_packs, sizeof(struct repack_info));
+	int pack_kept_objects = 0;
+
+	repo_config_get_bool(r, "repack.packkeptobjects", &pack_kept_objects);
 
 	for (i = 0; i < m->num_packs; i++) {
 		pack_info[i].pack_int_id = i;
@@ -1338,6 +1352,8 @@ static int fill_included_packs_batch(struct repository *r,
 
 		if (!p)
 			continue;
+		if (!pack_kept_objects && p->pack_keep)
+			continue;
 		if (open_pack_index(p) || !p->num_objects)
 			continue;
 
@@ -1380,7 +1396,7 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size,
 	if (batch_size) {
 		if (fill_included_packs_batch(r, m, include_pack, batch_size))
 			goto cleanup;
-	} else if (fill_included_packs_all(m, include_pack))
+	} else if (fill_included_packs_all(r, m, include_pack))
 		goto cleanup;
 
 	repo_config_get_bool(r, "repack.usedeltabaseoffset", &delta_base_offset);
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index 030a7222b2a..67afe1bb8d9 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -538,6 +538,32 @@ test_expect_success 'repack with minimum size does not alter existing packs' '
 	)
 '
 
+test_expect_success 'repack respects repack.packKeptObjects=false' '
+	test_when_finished rm -f dup/.git/objects/pack/*keep &&
+	(
+		cd dup &&
+		ls .git/objects/pack/*idx >idx-list &&
+		test_line_count = 5 idx-list &&
+		ls .git/objects/pack/*.pack | sed "s/\.pack/.keep/" >keep-list &&
+		for keep in $(cat keep-list)
+		do
+			touch $keep || return 1
+		done &&
+		git multi-pack-index repack --batch-size=0 &&
+		ls .git/objects/pack/*idx >idx-list &&
+		test_line_count = 5 idx-list &&
+		test-tool read-midx .git/objects | grep idx >midx-list &&
+		test_line_count = 5 midx-list &&
+		THIRD_SMALLEST_SIZE=$(test-tool path-utils file-size .git/objects/pack/*pack | sort -n | head -n 3 | tail -n 1) &&
+		BATCH_SIZE=$(($THIRD_SMALLEST_SIZE + 1)) &&
+		git multi-pack-index repack --batch-size=$BATCH_SIZE &&
+		ls .git/objects/pack/*idx >idx-list &&
+		test_line_count = 5 idx-list &&
+		test-tool read-midx .git/objects | grep idx >midx-list &&
+		test_line_count = 5 midx-list
+	)
+'
+
 test_expect_success 'repack creates a new pack' '
 	(
 		cd dup &&
-- 
gitgitgadget