From 94cd775a6c52a99caeb1278c3d8044ee109e2d3e Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:17:35 -0400
Subject: pack-mtimes: support reading .mtimes files

To store the individual mtimes of objects in a cruft pack, introduce a
new `.mtimes` format that can optionally accompany a single pack in the
repository.

The format is defined in Documentation/technical/pack-format.txt, and
stores a 4-byte network order timestamp for each object in name (index)
order.

This patch prepares for cruft packs by defining the `.mtimes` format,
and introducing a basic API that callers can use to read out individual
mtimes.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/repack.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'builtin')

diff --git a/builtin/repack.c b/builtin/repack.c
index d1a563d5b6..e7a3920c6d 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -217,6 +217,7 @@ static struct {
 } exts[] = {
 	{".pack"},
 	{".rev", 1},
+	{".mtimes", 1},
 	{".bitmap", 1},
 	{".promisor", 1},
 	{".idx"},
-- 
cgit v1.3-5-g9baa


From 1c573cdd7219db5600fb2b5249f7c8835c8d416d Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:17:38 -0400
Subject: pack-write: pass 'struct packing_data' to 'stage_tmp_packfiles'

This structure will be used to communicate the per-object mtimes when
writing a cruft pack. Here, we need the full packing_data structure
because the mtime information is stored in an array there, not on the
individual object_entry's themselves (to avoid paying the overhead in
structure width for operations which do not generate a cruft pack).

We haven't passed this information down before because one of the two
callers (in bulk-checkin.c) does not have a packing_data structure at
all. In that case (where no cruft pack will be generated), NULL is
passed instead.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/pack-objects.c | 3 ++-
 bulk-checkin.c         | 2 +-
 pack-write.c           | 1 +
 pack.h                 | 3 +++
 4 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'builtin')

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 014dcd4bc9..6ac927047c 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -1262,7 +1262,8 @@ static void write_pack_file(void)
 
 			stage_tmp_packfiles(&tmpname, pack_tmp_name,
 					    written_list, nr_written,
-					    &pack_idx_opts, hash, &idx_tmp_name);
+					    &to_pack, &pack_idx_opts, hash,
+					    &idx_tmp_name);
 
 			if (write_bitmap_index) {
 				size_t tmpname_len = tmpname.len;
diff --git a/bulk-checkin.c b/bulk-checkin.c
index 6d6c37171c..e988a388b6 100644
--- a/bulk-checkin.c
+++ b/bulk-checkin.c
@@ -33,7 +33,7 @@ static void finish_tmp_packfile(struct strbuf *basename,
 	char *idx_tmp_name = NULL;
 
 	stage_tmp_packfiles(basename, pack_tmp_name, written_list, nr_written,
-			    pack_idx_opts, hash, &idx_tmp_name);
+			    NULL, pack_idx_opts, hash, &idx_tmp_name);
 	rename_tmp_packfile_idx(basename, &idx_tmp_name);
 
 	free(idx_tmp_name);
diff --git a/pack-write.c b/pack-write.c
index 51812cb129..a2adc565f4 100644
--- a/pack-write.c
+++ b/pack-write.c
@@ -484,6 +484,7 @@ void stage_tmp_packfiles(struct strbuf *name_buffer,
 			 const char *pack_tmp_name,
 			 struct pack_idx_entry **written_list,
 			 uint32_t nr_written,
+			 struct packing_data *to_pack,
 			 struct pack_idx_option *pack_idx_opts,
 			 unsigned char hash[],
 			 char **idx_tmp_name)
diff --git a/pack.h b/pack.h
index b22bfc4a18..fd27cfdfd7 100644
--- a/pack.h
+++ b/pack.h
@@ -109,11 +109,14 @@ int encode_in_pack_object_header(unsigned char *hdr, int hdr_len,
 #define PH_ERROR_PROTOCOL	(-3)
 int read_pack_header(int fd, struct pack_header *);
 
+struct packing_data;
+
 struct hashfile *create_tmp_packfile(char **pack_tmp_name);
 void stage_tmp_packfiles(struct strbuf *name_buffer,
 			 const char *pack_tmp_name,
 			 struct pack_idx_entry **written_list,
 			 uint32_t nr_written,
+			 struct packing_data *to_pack,
 			 struct pack_idx_option *pack_idx_opts,
 			 unsigned char hash[],
 			 char **idx_tmp_name);
-- 
cgit v1.3-5-g9baa


From fa23090b0c5cc27d0720535e27236fef9b409efb Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:17:49 -0400
Subject: builtin/pack-objects.c: return from create_object_entry()

A new caller in the next commit will want to immediately modify the
object_entry structure created by create_object_entry(). Instead of
forcing that caller to wastefully look-up the entry we just created,
return it from create_object_entry() instead.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/pack-objects.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'builtin')

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 6ac927047c..c6d16872ee 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -1516,13 +1516,13 @@ static int want_object_in_pack(const struct object_id *oid,
 	return 1;
 }
 
-static void create_object_entry(const struct object_id *oid,
-				enum object_type type,
-				uint32_t hash,
-				int exclude,
-				int no_try_delta,
-				struct packed_git *found_pack,
-				off_t found_offset)
+static struct object_entry *create_object_entry(const struct object_id *oid,
+						enum object_type type,
+						uint32_t hash,
+						int exclude,
+						int no_try_delta,
+						struct packed_git *found_pack,
+						off_t found_offset)
 {
 	struct object_entry *entry;
 
@@ -1539,6 +1539,8 @@ static void create_object_entry(const struct object_id *oid,
 	}
 
 	entry->no_try_delta = no_try_delta;
+
+	return entry;
 }
 
 static const char no_closure_warning[] = N_(
-- 
cgit v1.3-5-g9baa


From b757353676d6ffe1ac275366fa8b5b42b5d9727d Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:17:52 -0400
Subject: builtin/pack-objects.c: --cruft without expiration

Teach `pack-objects` how to generate a cruft pack when no objects are
dropped (i.e., `--cruft-expiration=never`). Later patches will teach
`pack-objects` how to generate a cruft pack that prunes objects.

When generating a cruft pack which does not prune objects, we want to
collect all unreachable objects into a single pack (noting and updating
their mtimes as we accumulate them). Ordinary use will pass the result
of a `git repack -A` as a kept pack, so when this patch says "kept
pack", readers should think "reachable objects".

Generating a non-expiring cruft packs works as follows:

  - Callers provide a list of every pack they know about, and indicate
    which packs are about to be removed.

  - All packs which are going to be removed (we'll call these the
    redundant ones) are marked as kept in-core.

    Any packs the caller did not mention (but are known to the
    `pack-objects` process) are also marked as kept in-core. Packs not
    mentioned by the caller are assumed to be unknown to them, i.e.,
    they entered the repository after the caller decided which packs
    should be kept and which should be discarded.

    Since we do not want to include objects in these "unknown" packs
    (because we don't know which of their objects are or aren't
    reachable), these are also marked as kept in-core.

  - Then, we enumerate all objects in the repository, and add them to
    our packing list if they do not appear in an in-core kept pack.

This results in a new cruft pack which contains all known objects that
aren't included in the kept packs. When the kept pack is the result of
`git repack -A`, the resulting pack contains all unreachable objects.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/git-pack-objects.txt |  30 +++++
 builtin/pack-objects.c             | 201 +++++++++++++++++++++++++++++++++-
 object-file.c                      |   2 +-
 object-store.h                     |   2 +
 t/t5329-pack-objects-cruft.sh      | 218 +++++++++++++++++++++++++++++++++++++
 5 files changed, 448 insertions(+), 5 deletions(-)
 create mode 100755 t/t5329-pack-objects-cruft.sh

(limited to 'builtin')

diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt
index f8344e1e5b..a9995a932c 100644
--- a/Documentation/git-pack-objects.txt
+++ b/Documentation/git-pack-objects.txt
@@ -13,6 +13,7 @@ SYNOPSIS
 	[--no-reuse-delta] [--delta-base-offset] [--non-empty]
 	[--local] [--incremental] [--window=<n>] [--depth=<n>]
 	[--revs [--unpacked | --all]] [--keep-pack=<pack-name>]
+	[--cruft] [--cruft-expiration=<time>]
 	[--stdout [--filter=<filter-spec>] | <base-name>]
 	[--shallow] [--keep-true-parents] [--[no-]sparse] < <object-list>
 
@@ -95,6 +96,35 @@ base-name::
 Incompatible with `--revs`, or options that imply `--revs` (such as
 `--all`), with the exception of `--unpacked`, which is compatible.
 
+--cruft::
+	Packs unreachable objects into a separate "cruft" pack, denoted
+	by the existence of a `.mtimes` file. Typically used by `git
+	repack --cruft`. Callers provide a list of pack names and
+	indicate which packs will remain in the repository, along with
+	which packs will be deleted (indicated by the `-` prefix). The
+	contents of the cruft pack are all objects not contained in the
+	surviving packs which have not exceeded the grace period (see
+	`--cruft-expiration` below), or which have exceeded the grace
+	period, but are reachable from an other object which hasn't.
++
+When the input lists a pack containing all reachable objects (and lists
+all other packs as pending deletion), the corresponding cruft pack will
+contain all unreachable objects (with mtime newer than the
+`--cruft-expiration`) along with any unreachable objects whose mtime is
+older than the `--cruft-expiration`, but are reachable from an
+unreachable object whose mtime is newer than the `--cruft-expiration`).
++
+Incompatible with `--unpack-unreachable`, `--keep-unreachable`,
+`--pack-loose-unreachable`, `--stdin-packs`, as well as any other
+options which imply `--revs`. Also incompatible with `--max-pack-size`;
+when this option is set, the maximum pack size is not inferred from
+`pack.packSizeLimit`.
+
+--cruft-expiration=<approxidate>::
+	If specified, objects are eliminated from the cruft pack if they
+	have an mtime older than `<approxidate>`. If unspecified (and
+	given `--cruft`), then no objects are eliminated.
+
 --window=<n>::
 --depth=<n>::
 	These two options affect how the objects contained in
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index c6d16872ee..9cf89be673 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -36,6 +36,7 @@
 #include "trace2.h"
 #include "shallow.h"
 #include "promisor-remote.h"
+#include "pack-mtimes.h"
 
 /*
  * Objects we are going to pack are collected in the `to_pack` structure.
@@ -194,6 +195,8 @@ static int reuse_delta = 1, reuse_object = 1;
 static int keep_unreachable, unpack_unreachable, include_tag;
 static timestamp_t unpack_unreachable_expiration;
 static int pack_loose_unreachable;
+static int cruft;
+static timestamp_t cruft_expiration;
 static int local;
 static int have_non_local_packs;
 static int incremental;
@@ -1260,6 +1263,9 @@ static void write_pack_file(void)
 					&to_pack, written_list, nr_written);
 			}
 
+			if (cruft)
+				pack_idx_opts.flags |= WRITE_MTIMES;
+
 			stage_tmp_packfiles(&tmpname, pack_tmp_name,
 					    written_list, nr_written,
 					    &to_pack, &pack_idx_opts, hash,
@@ -3397,6 +3403,135 @@ static void read_packs_list_from_stdin(void)
 	string_list_clear(&exclude_packs, 0);
 }
 
+static void add_cruft_object_entry(const struct object_id *oid, enum object_type type,
+				   struct packed_git *pack, off_t offset,
+				   const char *name, uint32_t mtime)
+{
+	struct object_entry *entry;
+
+	display_progress(progress_state, ++nr_seen);
+
+	entry = packlist_find(&to_pack, oid);
+	if (entry) {
+		if (name) {
+			entry->hash = pack_name_hash(name);
+			entry->no_try_delta = no_try_delta(name);
+		}
+	} else {
+		if (!want_object_in_pack(oid, 0, &pack, &offset))
+			return;
+		if (!pack && type == OBJ_BLOB && !has_loose_object(oid)) {
+			/*
+			 * If a traversed tree has a missing blob then we want
+			 * to avoid adding that missing object to our pack.
+			 *
+			 * This only applies to missing blobs, not trees,
+			 * because the traversal needs to parse sub-trees but
+			 * not blobs.
+			 *
+			 * Note we only perform this check when we couldn't
+			 * already find the object in a pack, so we're really
+			 * limited to "ensure non-tip blobs which don't exist in
+			 * packs do exist via loose objects". Confused?
+			 */
+			return;
+		}
+
+		entry = create_object_entry(oid, type, pack_name_hash(name),
+					    0, name && no_try_delta(name),
+					    pack, offset);
+	}
+
+	if (mtime > oe_cruft_mtime(&to_pack, entry))
+		oe_set_cruft_mtime(&to_pack, entry, mtime);
+	return;
+}
+
+static void mark_pack_kept_in_core(struct string_list *packs, unsigned keep)
+{
+	struct string_list_item *item = NULL;
+	for_each_string_list_item(item, packs) {
+		struct packed_git *p = item->util;
+		if (!p)
+			die(_("could not find pack '%s'"), item->string);
+		p->pack_keep_in_core = keep;
+	}
+}
+
+static void add_unreachable_loose_objects(void);
+static void add_objects_in_unpacked_packs(void);
+
+static void enumerate_cruft_objects(void)
+{
+	if (progress)
+		progress_state = start_progress(_("Enumerating cruft objects"), 0);
+
+	add_objects_in_unpacked_packs();
+	add_unreachable_loose_objects();
+
+	stop_progress(&progress_state);
+}
+
+static void read_cruft_objects(void)
+{
+	struct strbuf buf = STRBUF_INIT;
+	struct string_list discard_packs = STRING_LIST_INIT_DUP;
+	struct string_list fresh_packs = STRING_LIST_INIT_DUP;
+	struct packed_git *p;
+
+	ignore_packed_keep_in_core = 1;
+
+	while (strbuf_getline(&buf, stdin) != EOF) {
+		if (!buf.len)
+			continue;
+
+		if (*buf.buf == '-')
+			string_list_append(&discard_packs, buf.buf + 1);
+		else
+			string_list_append(&fresh_packs, buf.buf);
+		strbuf_reset(&buf);
+	}
+
+	string_list_sort(&discard_packs);
+	string_list_sort(&fresh_packs);
+
+	for (p = get_all_packs(the_repository); p; p = p->next) {
+		const char *pack_name = pack_basename(p);
+		struct string_list_item *item;
+
+		item = string_list_lookup(&fresh_packs, pack_name);
+		if (!item)
+			item = string_list_lookup(&discard_packs, pack_name);
+
+		if (item) {
+			item->util = p;
+		} else {
+			/*
+			 * This pack wasn't mentioned in either the "fresh" or
+			 * "discard" list, so the caller didn't know about it.
+			 *
+			 * Mark it as kept so that its objects are ignored by
+			 * add_unseen_recent_objects_to_traversal(). We'll
+			 * unmark it before starting the traversal so it doesn't
+			 * halt the traversal early.
+			 */
+			p->pack_keep_in_core = 1;
+		}
+	}
+
+	mark_pack_kept_in_core(&fresh_packs, 1);
+	mark_pack_kept_in_core(&discard_packs, 0);
+
+	if (cruft_expiration)
+		die("--cruft-expiration not yet implemented");
+	else
+		enumerate_cruft_objects();
+
+	strbuf_release(&buf);
+	string_list_clear(&discard_packs, 0);
+	string_list_clear(&fresh_packs, 0);
+}
+
 static void read_object_list_from_stdin(void)
 {
 	char line[GIT_MAX_HEXSZ + 1 + PATH_MAX + 2];
@@ -3529,7 +3664,24 @@ static int add_object_in_unpacked_pack(const struct object_id *oid,
 				       uint32_t pos,
 				       void *_data)
 {
-	add_object_entry(oid, OBJ_NONE, "", 0);
+	if (cruft) {
+		off_t offset;
+		time_t mtime;
+
+		if (pack->is_cruft) {
+			if (load_pack_mtimes(pack) < 0)
+				die(_("could not load cruft pack .mtimes"));
+			mtime = nth_packed_mtime(pack, pos);
+		} else {
+			mtime = pack->mtime;
+		}
+		offset = nth_packed_object_offset(pack, pos);
+
+		add_cruft_object_entry(oid, OBJ_NONE, pack, offset,
+				       NULL, mtime);
+	} else {
+		add_object_entry(oid, OBJ_NONE, "", 0);
+	}
 	return 0;
 }
 
@@ -3553,7 +3705,19 @@ static int add_loose_object(const struct object_id *oid, const char *path,
 		return 0;
 	}
 
-	add_object_entry(oid, type, "", 0);
+	if (cruft) {
+		struct stat st;
+		if (stat(path, &st) < 0) {
+			if (errno == ENOENT)
+				return 0;
+			return error_errno("unable to stat %s", oid_to_hex(oid));
+		}
+
+		add_cruft_object_entry(oid, type, NULL, 0, NULL,
+				       st.st_mtime);
+	} else {
+		add_object_entry(oid, type, "", 0);
+	}
 	return 0;
 }
 
@@ -3870,6 +4034,20 @@ static int option_parse_unpack_unreachable(const struct option *opt,
 	return 0;
 }
 
+static int option_parse_cruft_expiration(const struct option *opt,
+					 const char *arg, int unset)
+{
+	if (unset) {
+		cruft = 0;
+		cruft_expiration = 0;
+	} else {
+		cruft = 1;
+		if (arg)
+			cruft_expiration = approxidate(arg);
+	}
+	return 0;
+}
+
 struct po_filter_data {
 	unsigned have_revs:1;
 	struct rev_info revs;
@@ -3959,6 +4137,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		OPT_CALLBACK_F(0, "unpack-unreachable", NULL, N_("time"),
 		  N_("unpack unreachable objects newer than <time>"),
 		  PARSE_OPT_OPTARG, option_parse_unpack_unreachable),
+		OPT_BOOL(0, "cruft", &cruft, N_("create a cruft pack")),
+		OPT_CALLBACK_F(0, "cruft-expiration", NULL, N_("time"),
+		  N_("expire cruft objects older than <time>"),
+		  PARSE_OPT_OPTARG, option_parse_cruft_expiration),
 		OPT_BOOL(0, "sparse", &sparse,
 			 N_("use the sparse reachability algorithm")),
 		OPT_BOOL(0, "thin", &thin,
@@ -4085,7 +4267,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 
 	if (!HAVE_THREADS && delta_search_threads != 1)
 		warning(_("no threads support, ignoring --threads"));
-	if (!pack_to_stdout && !pack_size_limit)
+	if (!pack_to_stdout && !pack_size_limit && !cruft)
 		pack_size_limit = pack_size_limit_cfg;
 	if (pack_to_stdout && pack_size_limit)
 		die(_("--max-pack-size cannot be used to build a pack for transfer"));
@@ -4112,6 +4294,15 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (stdin_packs && use_internal_rev_list)
 		die(_("cannot use internal rev list with --stdin-packs"));
 
+	if (cruft) {
+		if (use_internal_rev_list)
+			die(_("cannot use internal rev list with --cruft"));
+		if (stdin_packs)
+			die(_("cannot use --stdin-packs with --cruft"));
+		if (pack_size_limit)
+			die(_("cannot use --max-pack-size with --cruft"));
+	}
+
 	/*
 	 * "soft" reasons not to use bitmaps - for on-disk repack by default we want
 	 *
@@ -4168,7 +4359,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 			    the_repository);
 	prepare_packing_data(the_repository, &to_pack);
 
-	if (progress)
+	if (progress && !cruft)
 		progress_state = start_progress(_("Enumerating objects"), 0);
 	if (stdin_packs) {
 		/* avoids adding objects in excluded packs */
@@ -4176,6 +4367,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		read_packs_list_from_stdin();
 		if (rev_list_unpacked)
 			add_unreachable_loose_objects();
+	} else if (cruft) {
+		read_cruft_objects();
 	} else if (!use_internal_rev_list) {
 		read_object_list_from_stdin();
 	} else if (pfd.have_revs) {
diff --git a/object-file.c b/object-file.c
index 5ffbf3d4fd..ff0cffe68e 100644
--- a/object-file.c
+++ b/object-file.c
@@ -997,7 +997,7 @@ int has_loose_object_nonlocal(const struct object_id *oid)
 	return check_and_freshen_nonlocal(oid, 0);
 }
 
-static int has_loose_object(const struct object_id *oid)
+int has_loose_object(const struct object_id *oid)
 {
 	return check_and_freshen(oid, 0);
 }
diff --git a/object-store.h b/object-store.h
index 3c98028ce6..1c58d25355 100644
--- a/object-store.h
+++ b/object-store.h
@@ -339,6 +339,8 @@ int repo_has_object_file_with_flags(struct repository *r,
  */
 int has_loose_object_nonlocal(const struct object_id *);
 
+int has_loose_object(const struct object_id *);
+
 /**
  * format_object_header() is a thin wrapper around s xsnprintf() that
  * writes the initial "<type> <obj-len>" part of the loose object
diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh
new file mode 100755
index 0000000000..003ca7344e
--- /dev/null
+++ b/t/t5329-pack-objects-cruft.sh
@@ -0,0 +1,218 @@
+#!/bin/sh
+
+test_description='cruft pack related pack-objects tests'
+. ./test-lib.sh
+
+objdir=.git/objects
+packdir=$objdir/pack
+
+basic_cruft_pack_tests () {
+	expire="$1"
+
+	test_expect_success "unreachable loose objects are packed (expire $expire)" '
+		git init repo &&
+		test_when_finished "rm -fr repo" &&
+		(
+			cd repo &&
+
+			test_commit base &&
+			git repack -Ad &&
+			test_commit loose &&
+
+			test-tool chmtime +2000 "$objdir/$(test_oid_to_path \
+				$(git rev-parse loose:loose.t))" &&
+			test-tool chmtime +1000 "$objdir/$(test_oid_to_path \
+				$(git rev-parse loose^{tree}))" &&
+
+			(
+				git rev-list --objects --no-object-names base..loose |
+				while read oid
+				do
+					path="$objdir/$(test_oid_to_path "$oid")" &&
+					printf "%s %d\n" "$oid" "$(test-tool chmtime --get "$path")"
+				done |
+				sort -k1
+			) >expect &&
+
+			keep="$(basename "$(ls $packdir/pack-*.pack)")" &&
+			cruft="$(echo $keep | git pack-objects --cruft \
+				--cruft-expiration="$expire" $packdir/pack)" &&
+			test-tool pack-mtimes "pack-$cruft.mtimes" >actual &&
+
+			test_cmp expect actual
+		)
+	'
+
+	test_expect_success "unreachable packed objects are packed (expire $expire)" '
+		git init repo &&
+		test_when_finished "rm -fr repo" &&
+		(
+			cd repo &&
+
+			test_commit packed &&
+			git repack -Ad &&
+			test_commit other &&
+
+			git rev-list --objects --no-object-names packed.. >objects &&
+			keep="$(basename "$(ls $packdir/pack-*.pack)")" &&
+			other="$(git pack-objects --delta-base-offset \
+				$packdir/pack <objects)" &&
+			git prune-packed &&
+
+			test-tool chmtime --get -100 "$packdir/pack-$other.pack" >expect &&
+
+			cruft="$(git pack-objects --cruft --cruft-expiration="$expire" $packdir/pack <<-EOF
+			$keep
+			-pack-$other.pack
+			EOF
+			)" &&
+			test-tool pack-mtimes "pack-$cruft.mtimes" >actual.raw &&
+
+			cut -d" " -f2 <actual.raw | sort -u >actual &&
+
+			test_cmp expect actual
+		)
+	'
+
+	test_expect_success "unreachable cruft objects are repacked (expire $expire)" '
+		git init repo &&
+		test_when_finished "rm -fr repo" &&
+		(
+			cd repo &&
+
+			test_commit packed &&
+			git repack -Ad &&
+			test_commit other &&
+
+			git rev-list --objects --no-object-names packed.. >objects &&
+			keep="$(basename "$(ls $packdir/pack-*.pack)")" &&
+
+			cruft_a="$(echo $keep | git pack-objects --cruft --cruft-expiration="$expire" $packdir/pack)" &&
+			git prune-packed &&
+			cruft_b="$(git pack-objects --cruft --cruft-expiration="$expire" $packdir/pack <<-EOF
+			$keep
+			-pack-$cruft_a.pack
+			EOF
+			)" &&
+
+			test-tool pack-mtimes "pack-$cruft_a.mtimes" >expect.raw &&
+			test-tool pack-mtimes "pack-$cruft_b.mtimes" >actual.raw &&
+
+			sort <expect.raw >expect &&
+			sort <actual.raw >actual &&
+
+			test_cmp expect actual
+		)
+	'
+
+	test_expect_success "multiple cruft packs (expire $expire)" '
+		git init repo &&
+		test_when_finished "rm -fr repo" &&
+		(
+			cd repo &&
+
+			test_commit reachable &&
+			git repack -Ad &&
+			keep="$(basename "$(ls $packdir/pack-*.pack)")" &&
+
+			test_commit cruft &&
+			loose="$objdir/$(test_oid_to_path $(git rev-parse cruft))" &&
+
+			# generate three copies of the cruft object in different
+			# cruft packs, each with a unique mtime:
+			#   - one expired (1000 seconds ago)
+			#   - two non-expired (one 1000 seconds in the future,
+			#     one 1500 seconds in the future)
+			test-tool chmtime =-1000 "$loose" &&
+			git pack-objects --cruft $packdir/pack-A <<-EOF &&
+			$keep
+			EOF
+			test-tool chmtime =+1000 "$loose" &&
+			git pack-objects --cruft $packdir/pack-B <<-EOF &&
+			$keep
+			-$(basename $(ls $packdir/pack-A-*.pack))
+			EOF
+			test-tool chmtime =+1500 "$loose" &&
+			git pack-objects --cruft $packdir/pack-C <<-EOF &&
+			$keep
+			-$(basename $(ls $packdir/pack-A-*.pack))
+			-$(basename $(ls $packdir/pack-B-*.pack))
+			EOF
+
+			# ensure the resulting cruft pack takes the most recent
+			# mtime among all copies
+			cruft="$(git pack-objects --cruft \
+				--cruft-expiration="$expire" \
+				$packdir/pack <<-EOF
+			$keep
+			-$(basename $(ls $packdir/pack-A-*.pack))
+			-$(basename $(ls $packdir/pack-B-*.pack))
+			-$(basename $(ls $packdir/pack-C-*.pack))
+			EOF
+			)" &&
+
+			test-tool pack-mtimes "$(basename $(ls $packdir/pack-C-*.mtimes))" >expect.raw &&
+			test-tool pack-mtimes "pack-$cruft.mtimes" >actual.raw &&
+
+			sort expect.raw >expect &&
+			sort actual.raw >actual &&
+			test_cmp expect actual
+		)
+	'
+
+	test_expect_success "cruft packs tolerate missing trees (expire $expire)" '
+		git init repo &&
+		test_when_finished "rm -fr repo" &&
+		(
+			cd repo &&
+
+			test_commit reachable &&
+			test_commit cruft &&
+
+			tree="$(git rev-parse cruft^{tree})" &&
+
+			git reset --hard reachable &&
+			git tag -d cruft &&
+			git reflog expire --all --expire=all &&
+
+			# remove the unreachable tree, but leave the commit
+			# which has it as its root tree intact
+			rm -fr "$objdir/$(test_oid_to_path "$tree")" &&
+
+			git repack -Ad &&
+			basename $(ls $packdir/pack-*.pack) >in &&
+			git pack-objects --cruft --cruft-expiration="$expire" \
+				$packdir/pack <in
+		)
+	'
+
+	test_expect_success "cruft packs tolerate missing blobs (expire $expire)" '
+		git init repo &&
+		test_when_finished "rm -fr repo" &&
+		(
+			cd repo &&
+
+			test_commit reachable &&
+			test_commit cruft &&
+
+			blob="$(git rev-parse cruft:cruft.t)" &&
+
+			git reset --hard reachable &&
+			git tag -d cruft &&
+			git reflog expire --all --expire=all &&
+
+			# remove the unreachable blob, but leave the commit (and
+			# the root tree of that commit) intact
+			rm -fr "$objdir/$(test_oid_to_path "$blob")" &&
+
+			git repack -Ad &&
+			basename $(ls $packdir/pack-*.pack) >in &&
+			git pack-objects --cruft --cruft-expiration="$expire" \
+				$packdir/pack <in
+		)
+	'
+}
+
+basic_cruft_pack_tests never
+
+test_done
-- 
cgit v1.3-5-g9baa


From 2fb90409b8133803bae89773ac9a9db629443dc6 Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:17:54 -0400
Subject: reachable: add options to add_unseen_recent_objects_to_traversal

This function behaves very similarly to what we will need in
pack-objects in order to implement cruft packs with expiration. But it
is lacking a couple of things. Namely, it needs:

  - a mechanism to communicate the timestamps of individual recent
    objects to some external caller

  - and, in the case of packed objects, our future caller will also want
    to know the originating pack, as well as the offset within that pack
    at which the object can be found

  - finally, it needs a way to skip over packs which are marked as kept
    in-core.

To address the first two, add a callback interface in this patch which
reports the time of each recent object, as well as a (packed_git,
off_t) pair for packed objects.

Likewise, add a new option to the packed object iterators to skip over
packs which are marked as kept in core. This option will become
implicitly tested in a future patch.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/pack-objects.c |  2 +-
 reachable.c            | 51 ++++++++++++++++++++++++++++++++++++++++++--------
 reachable.h            |  9 ++++++++-
 3 files changed, 52 insertions(+), 10 deletions(-)

(limited to 'builtin')

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 9cf89be673..3b8bf6a3dd 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -3957,7 +3957,7 @@ static void get_object_list(struct rev_info *revs, int ac, const char **av)
 	if (unpack_unreachable_expiration) {
 		revs->ignore_missing_links = 1;
 		if (add_unseen_recent_objects_to_traversal(revs,
-				unpack_unreachable_expiration))
+				unpack_unreachable_expiration, NULL, 0))
 			die(_("unable to add recent objects"));
 		if (prepare_revision_walk(revs))
 			die(_("revision walk setup failed"));
diff --git a/reachable.c b/reachable.c
index b9f4ad886e..d4507c4270 100644
--- a/reachable.c
+++ b/reachable.c
@@ -60,9 +60,13 @@ static void mark_commit(struct commit *c, void *data)
 struct recent_data {
 	struct rev_info *revs;
 	timestamp_t timestamp;
+	report_recent_object_fn *cb;
+	int ignore_in_core_kept_packs;
 };
 
 static void add_recent_object(const struct object_id *oid,
+			      struct packed_git *pack,
+			      off_t offset,
 			      timestamp_t mtime,
 			      struct recent_data *data)
 {
@@ -103,13 +107,29 @@ static void add_recent_object(const struct object_id *oid,
 		die("unable to lookup %s", oid_to_hex(oid));
 
 	add_pending_object(data->revs, obj, "");
+	if (data->cb)
+		data->cb(obj, pack, offset, mtime);
+}
+
+static int want_recent_object(struct recent_data *data,
+			      const struct object_id *oid)
+{
+	if (data->ignore_in_core_kept_packs &&
+	    has_object_kept_pack(oid, IN_CORE_KEEP_PACKS))
+		return 0;
+	return 1;
 }
 
 static int add_recent_loose(const struct object_id *oid,
 			    const char *path, void *data)
 {
 	struct stat st;
-	struct object *obj = lookup_object(the_repository, oid);
+	struct object *obj;
+
+	if (!want_recent_object(data, oid))
+		return 0;
+
+	obj = lookup_object(the_repository, oid);
 
 	if (obj && obj->flags & SEEN)
 		return 0;
@@ -126,7 +146,7 @@ static int add_recent_loose(const struct object_id *oid,
 		return error_errno("unable to stat %s", oid_to_hex(oid));
 	}
 
-	add_recent_object(oid, st.st_mtime, data);
+	add_recent_object(oid, NULL, 0, st.st_mtime, data);
 	return 0;
 }
 
@@ -134,29 +154,43 @@ static int add_recent_packed(const struct object_id *oid,
 			     struct packed_git *p, uint32_t pos,
 			     void *data)
 {
-	struct object *obj = lookup_object(the_repository, oid);
+	struct object *obj;
+
+	if (!want_recent_object(data, oid))
+		return 0;
+
+	obj = lookup_object(the_repository, oid);
 
 	if (obj && obj->flags & SEEN)
 		return 0;
-	add_recent_object(oid, p->mtime, data);
+	add_recent_object(oid, p, nth_packed_object_offset(p, pos), p->mtime, data);
 	return 0;
 }
 
 int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
-					   timestamp_t timestamp)
+					   timestamp_t timestamp,
+					   report_recent_object_fn *cb,
+					   int ignore_in_core_kept_packs)
 {
 	struct recent_data data;
+	enum for_each_object_flags flags;
 	int r;
 
 	data.revs = revs;
 	data.timestamp = timestamp;
+	data.cb = cb;
+	data.ignore_in_core_kept_packs = ignore_in_core_kept_packs;
 
 	r = for_each_loose_object(add_recent_loose, &data,
 				  FOR_EACH_OBJECT_LOCAL_ONLY);
 	if (r)
 		return r;
-	return for_each_packed_object(add_recent_packed, &data,
-				      FOR_EACH_OBJECT_LOCAL_ONLY);
+
+	flags = FOR_EACH_OBJECT_LOCAL_ONLY | FOR_EACH_OBJECT_PACK_ORDER;
+	if (ignore_in_core_kept_packs)
+		flags |= FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS;
+
+	return for_each_packed_object(add_recent_packed, &data, flags);
 }
 
 static int mark_object_seen(const struct object_id *oid,
@@ -217,7 +251,8 @@ void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 
 	if (mark_recent) {
 		revs->ignore_missing_links = 1;
-		if (add_unseen_recent_objects_to_traversal(revs, mark_recent))
+		if (add_unseen_recent_objects_to_traversal(revs, mark_recent,
+							   NULL, 0))
 			die("unable to mark recent objects");
 		if (prepare_revision_walk(revs))
 			die("revision walk setup failed");
diff --git a/reachable.h b/reachable.h
index 5df932ad8f..b776761baa 100644
--- a/reachable.h
+++ b/reachable.h
@@ -1,11 +1,18 @@
 #ifndef REACHEABLE_H
 #define REACHEABLE_H
 
+#include "object.h"
+
 struct progress;
 struct rev_info;
 
+typedef void report_recent_object_fn(const struct object *, struct packed_git *,
+				     off_t, time_t);
+
 int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
-					   timestamp_t timestamp);
+					   timestamp_t timestamp,
+					   report_recent_object_fn cb,
+					   int ignore_in_core_kept_packs);
 void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 			    timestamp_t mark_recent, struct progress *);
 
-- 
cgit v1.3-5-g9baa


From a7d493833fe615211fd329183e59cec08496fb90 Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:18:00 -0400
Subject: builtin/pack-objects.c: --cruft with expiration

In a previous patch, pack-objects learned how to generate a cruft pack
so long as no objects are dropped.

This patch teaches pack-objects to handle the case where a non-never
`--cruft-expiration` value is passed. This case is slightly more
complicated than before, because we want pack-objects to save
unreachable objects which would have been pruned when there is another
recent (i.e., non-prunable) unreachable object which reaches the other.
We'll call these objects "unreachable but reachable-from-recent".

Here is how pack-objects handles `--cruft-expiration`:

  - Instead of adding all objects outside of the kept pack(s) into the
    packing list, only handle the ones whose mtime is within the grace
    period.

  - Construct a reachability traversal whose tips are the
    unreachable-but-recent objects.

  - Then, walk along that traversal, stopping if we reach an object in
    the kept pack. At each step along the traversal, we add the object
    we are visiting to the packing list.

In the majority of these cases, any object we visit in this traversal
will already be in our packing list. But we will sometimes encounter
reachable-from-recent cruft objects, which we want to retain even if
they aged out of the grace period.

The most subtle point of this process is that we actually don't need to
bother to update the rescued object's mtime. Even though we will write
an .mtimes file with a value that is older than the expiration window,
it will continue to survive cruft repacks so long as any objects which
reach it haven't aged out.

That is, a future repack will also exclude that object from the initial
packing list, only to discover it later on when doing the reachability
traversal.

Finally, stopping early once an object is found in a kept pack is safe
to do because the kept packs ordinarily represent which packs will
survive after repacking. Assuming that it _isn't_ safe to halt a
traversal early would mean that there is some ancestor object which is
missing, which implies repository corruption (i.e., the complete set of
reachable objects isn't present).

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/pack-objects.c        |  84 ++++++++++++++++++++++++-
 reachable.h                   |   4 +-
 t/t5329-pack-objects-cruft.sh | 143 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 228 insertions(+), 3 deletions(-)

(limited to 'builtin')

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
-- 
cgit v1.3-5-g9baa


From f9825d1cf752b8d04a3e9193ff6fdb54d09e28a3 Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:18:03 -0400
Subject: 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>
---
 Documentation/git-repack.txt            |  11 ++
 Documentation/technical/cruft-packs.txt |   2 +-
 builtin/repack.c                        | 105 +++++++++++++++-
 t/t5329-pack-objects-cruft.sh           | 207 ++++++++++++++++++++++++++++++++
 4 files changed, 319 insertions(+), 6 deletions(-)

(limited to 'builtin')

diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
index ee30edc178..0bf13893d8 100644
--- a/Documentation/git-repack.txt
+++ b/Documentation/git-repack.txt
@@ -63,6 +63,17 @@ to the new separate pack will be written.
 	Also run  'git prune-packed' to remove redundant
 	loose object files.
 
+--cruft::
+	Same as `-a`, unless `-d` is used. Then any unreachable objects
+	are packed into a separate cruft pack. Unreachable objects can
+	be pruned using the normal expiry rules with the next `git gc`
+	invocation (see linkgit:git-gc[1]). Incompatible with `-k`.
+
+--cruft-expiration=<approxidate>::
+	Expire unreachable objects older than `<approxidate>`
+	immediately instead of waiting for the next `git gc` invocation.
+	Only useful with `--cruft -d`.
+
 -l::
 	Pass the `--local` option to 'git pack-objects'. See
 	linkgit:git-pack-objects[1].
diff --git a/Documentation/technical/cruft-packs.txt b/Documentation/technical/cruft-packs.txt
index c0f583cd48..d81f3a8982 100644
--- a/Documentation/technical/cruft-packs.txt
+++ b/Documentation/technical/cruft-packs.txt
@@ -17,7 +17,7 @@ pruned according to normal expiry rules with the next 'git gc' invocation.
 
 Unreachable objects aren't removed immediately, since doing so could race with
 an incoming push which may reference an object which is about to be deleted.
-Instead, those unreachable objects are stored as loose object and stay that way
+Instead, those unreachable objects are stored as loose objects and stay that way
 until they are older than the expiration window, at which point they are removed
 by linkgit:git-prune[1].
 
diff --git a/builtin/repack.c b/builtin/repack.c
index e7a3920c6d..593c18d4e8 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -18,12 +18,18 @@
 #include "pack-bitmap.h"
 #include "refs.h"
 
+#define ALL_INTO_ONE 1
+#define LOOSEN_UNREACHABLE 2
+#define PACK_CRUFT 4
+
+static int pack_everything;
 static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
 static int write_bitmaps = -1;
 static int use_delta_islands;
 static int run_update_server_info = 1;
 static char *packdir, *packtmp_name, *packtmp;
+static char *cruft_expiration;
 
 static const char *const git_repack_usage[] = {
 	N_("git repack [<options>]"),
@@ -305,9 +311,6 @@ static void repack_promisor_objects(const struct pack_objects_args *args,
 		die(_("could not finish pack-objects to repack promisor objects"));
 }
 
-#define ALL_INTO_ONE 1
-#define LOOSEN_UNREACHABLE 2
-
 struct pack_geometry {
 	struct packed_git **pack;
 	uint32_t pack_nr, pack_alloc;
@@ -344,6 +347,8 @@ static void init_pack_geometry(struct pack_geometry **geometry_p)
 	for (p = get_all_packs(the_repository); p; p = p->next) {
 		if (!pack_kept_objects && p->pack_keep)
 			continue;
+		if (p->is_cruft)
+			continue;
 
 		ALLOC_GROW(geometry->pack,
 			   geometry->pack_nr + 1,
@@ -605,6 +610,67 @@ static int write_midx_included_packs(struct string_list *include,
 	return finish_command(&cmd);
 }
 
+static int write_cruft_pack(const struct pack_objects_args *args,
+			    const char *pack_prefix,
+			    struct string_list *names,
+			    struct string_list *existing_packs,
+			    struct string_list *existing_kept_packs)
+{
+	struct child_process cmd = CHILD_PROCESS_INIT;
+	struct strbuf line = STRBUF_INIT;
+	struct string_list_item *item;
+	FILE *in, *out;
+	int ret;
+
+	prepare_pack_objects(&cmd, args);
+
+	strvec_push(&cmd.args, "--cruft");
+	if (cruft_expiration)
+		strvec_pushf(&cmd.args, "--cruft-expiration=%s",
+			     cruft_expiration);
+
+	strvec_push(&cmd.args, "--honor-pack-keep");
+	strvec_push(&cmd.args, "--non-empty");
+	strvec_push(&cmd.args, "--max-pack-size=0");
+
+	cmd.in = -1;
+
+	ret = start_command(&cmd);
+	if (ret)
+		return ret;
+
+	/*
+	 * names has a confusing double use: it both provides the list
+	 * of just-written new packs, and accepts the name of the cruft
+	 * pack we are writing.
+	 *
+	 * By the time it is read here, it contains only the pack(s)
+	 * that were just written, which is exactly the set of packs we
+	 * want to consider kept.
+	 */
+	in = xfdopen(cmd.in, "w");
+	for_each_string_list_item(item, names)
+		fprintf(in, "%s-%s.pack\n", pack_prefix, item->string);
+	for_each_string_list_item(item, existing_packs)
+		fprintf(in, "-%s.pack\n", item->string);
+	for_each_string_list_item(item, existing_kept_packs)
+		fprintf(in, "%s.pack\n", item->string);
+	fclose(in);
+
+	out = xfdopen(cmd.out, "r");
+	while (strbuf_getline_lf(&line, out) != EOF) {
+		if (line.len != the_hash_algo->hexsz)
+			die(_("repack: Expecting full hex object ID lines only "
+			      "from pack-objects."));
+		string_list_append(names, line.buf);
+	}
+	fclose(out);
+
+	strbuf_release(&line);
+
+	return finish_command(&cmd);
+}
+
 int cmd_repack(int argc, const char **argv, const char *prefix)
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
@@ -621,7 +687,6 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int show_progress;
 
 	/* variables to be filled by option parsing */
-	int pack_everything = 0;
 	int delete_redundant = 0;
 	const char *unpack_unreachable = NULL;
 	int keep_unreachable = 0;
@@ -636,6 +701,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		OPT_BIT('A', NULL, &pack_everything,
 				N_("same as -a, and turn unreachable objects loose"),
 				   LOOSEN_UNREACHABLE | ALL_INTO_ONE),
+		OPT_BIT(0, "cruft", &pack_everything,
+				N_("same as -a, pack unreachable cruft objects separately"),
+				   PACK_CRUFT),
+		OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"),
+				N_("with -C, expire objects older than this")),
 		OPT_BOOL('d', NULL, &delete_redundant,
 				N_("remove redundant packs, and run git-prune-packed")),
 		OPT_BOOL('f', NULL, &po_args.no_reuse_delta,
@@ -688,6 +758,15 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	    (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)))
 		die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "-A");
 
+	if (pack_everything & PACK_CRUFT) {
+		pack_everything |= ALL_INTO_ONE;
+
+		if (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE))
+			die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-A");
+		if (keep_unreachable)
+			die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-k");
+	}
+
 	if (write_bitmaps < 0) {
 		if (!write_midx &&
 		    (!(pack_everything & ALL_INTO_ONE) || !is_bare_repository()))
@@ -771,7 +850,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (pack_everything & ALL_INTO_ONE) {
 		repack_promisor_objects(&po_args, &names);
 
-		if (existing_nonkept_packs.nr && delete_redundant) {
+		if (existing_nonkept_packs.nr && delete_redundant &&
+		    !(pack_everything & PACK_CRUFT)) {
 			for_each_string_list_item(item, &names) {
 				strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack",
 					     packtmp_name, item->string);
@@ -833,6 +913,21 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (!names.nr && !po_args.quiet)
 		printf_ln(_("Nothing new to pack."));
 
+	if (pack_everything & PACK_CRUFT) {
+		const char *pack_prefix;
+		if (!skip_prefix(packtmp, packdir, &pack_prefix))
+			die(_("pack prefix %s does not begin with objdir %s"),
+			    packtmp, packdir);
+		if (*pack_prefix == '/')
+			pack_prefix++;
+
+		ret = write_cruft_pack(&po_args, pack_prefix, &names,
+				       &existing_nonkept_packs,
+				       &existing_kept_packs);
+		if (ret)
+			return ret;
+	}
+
 	for_each_string_list_item(item, &names) {
 		item->util = (void *)(uintptr_t)populate_pack_exts(item->string);
 	}
diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh
index 939cdc297a..067c50af38 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
-- 
cgit v1.3-5-g9baa


From 4571324b99fcf7bd9e58fce677801fbf72b0e0a5 Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:18:06 -0400
Subject: builtin/repack.c: allow configuring cruft pack generation

In servers which set the pack.window configuration to a large value, we
can wind up spending quite a lot of time finding new bases when breaking
delta chains between reachable and unreachable objects while generating
a cruft pack.

Introduce a handful of `repack.cruft*` configuration variables to
control the parameters used by pack-objects when generating a cruft
pack.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/config/repack.txt |  9 +++++
 builtin/repack.c                | 49 +++++++++++++++++-------
 t/t5329-pack-objects-cruft.sh   | 83 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+), 14 deletions(-)

(limited to 'builtin')

diff --git a/Documentation/config/repack.txt b/Documentation/config/repack.txt
index 41ac6953c8..c79af6d7b8 100644
--- a/Documentation/config/repack.txt
+++ b/Documentation/config/repack.txt
@@ -30,3 +30,12 @@ repack.updateServerInfo::
 	If set to false, linkgit:git-repack[1] will not run
 	linkgit:git-update-server-info[1]. Defaults to true. Can be overridden
 	when true by the `-n` option of linkgit:git-repack[1].
+
+repack.cruftWindow::
+repack.cruftWindowMemory::
+repack.cruftDepth::
+repack.cruftThreads::
+	Parameters used by linkgit:git-pack-objects[1] when generating
+	a cruft pack and the respective parameters are not given over
+	the command line. See similarly named `pack.*` configuration
+	variables for defaults and meaning.
diff --git a/builtin/repack.c b/builtin/repack.c
index 593c18d4e8..b85483a148 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -41,9 +41,21 @@ static const char incremental_bitmap_conflict_error[] = N_(
 "--no-write-bitmap-index or disable the pack.writebitmaps configuration."
 );
 
+struct pack_objects_args {
+	const char *window;
+	const char *window_memory;
+	const char *depth;
+	const char *threads;
+	const char *max_pack_size;
+	int no_reuse_delta;
+	int no_reuse_object;
+	int quiet;
+	int local;
+};
 
 static int repack_config(const char *var, const char *value, void *cb)
 {
+	struct pack_objects_args *cruft_po_args = cb;
 	if (!strcmp(var, "repack.usedeltabaseoffset")) {
 		delta_base_offset = git_config_bool(var, value);
 		return 0;
@@ -65,6 +77,14 @@ static int repack_config(const char *var, const char *value, void *cb)
 		run_update_server_info = git_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "repack.cruftwindow"))
+		return git_config_string(&cruft_po_args->window, var, value);
+	if (!strcmp(var, "repack.cruftwindowmemory"))
+		return git_config_string(&cruft_po_args->window_memory, var, value);
+	if (!strcmp(var, "repack.cruftdepth"))
+		return git_config_string(&cruft_po_args->depth, var, value);
+	if (!strcmp(var, "repack.cruftthreads"))
+		return git_config_string(&cruft_po_args->threads, var, value);
 	return git_default_config(var, value, cb);
 }
 
@@ -157,18 +177,6 @@ static void remove_redundant_pack(const char *dir_name, const char *base_name)
 	strbuf_release(&buf);
 }
 
-struct pack_objects_args {
-	const char *window;
-	const char *window_memory;
-	const char *depth;
-	const char *threads;
-	const char *max_pack_size;
-	int no_reuse_delta;
-	int no_reuse_object;
-	int quiet;
-	int local;
-};
-
 static void prepare_pack_objects(struct child_process *cmd,
 				 const struct pack_objects_args *args)
 {
@@ -692,6 +700,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int keep_unreachable = 0;
 	struct string_list keep_pack_list = STRING_LIST_INIT_NODUP;
 	struct pack_objects_args po_args = {NULL};
+	struct pack_objects_args cruft_po_args = {NULL};
 	int geometric_factor = 0;
 	int write_midx = 0;
 
@@ -746,7 +755,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		OPT_END()
 	};
 
-	git_config(repack_config, NULL);
+	git_config(repack_config, &cruft_po_args);
 
 	argc = parse_options(argc, argv, prefix, builtin_repack_options,
 				git_repack_usage, 0);
@@ -921,7 +930,19 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		if (*pack_prefix == '/')
 			pack_prefix++;
 
-		ret = write_cruft_pack(&po_args, pack_prefix, &names,
+		if (!cruft_po_args.window)
+			cruft_po_args.window = po_args.window;
+		if (!cruft_po_args.window_memory)
+			cruft_po_args.window_memory = po_args.window_memory;
+		if (!cruft_po_args.depth)
+			cruft_po_args.depth = po_args.depth;
+		if (!cruft_po_args.threads)
+			cruft_po_args.threads = po_args.threads;
+
+		cruft_po_args.local = po_args.local;
+		cruft_po_args.quiet = po_args.quiet;
+
+		ret = write_cruft_pack(&cruft_po_args, pack_prefix, &names,
 				       &existing_nonkept_packs,
 				       &existing_kept_packs);
 		if (ret)
diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh
index 067c50af38..c82f973b41 100755
--- a/t/t5329-pack-objects-cruft.sh
+++ b/t/t5329-pack-objects-cruft.sh
@@ -565,4 +565,87 @@ test_expect_success 'cruft repack ignores pack.packSizeLimit' '
 	)
 '
 
+test_expect_success 'cruft repack respects repack.cruftWindow' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+
+		GIT_TRACE2_EVENT=$(pwd)/event.trace \
+		git -c pack.window=1 -c repack.cruftWindow=2 repack \
+		       --cruft --window=3 &&
+
+		grep "pack-objects.*--window=2.*--cruft" event.trace
+	)
+'
+
+test_expect_success 'cruft repack respects --window by default' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+
+		GIT_TRACE2_EVENT=$(pwd)/event.trace \
+		git -c pack.window=2 repack --cruft --window=3 &&
+
+		grep "pack-objects.*--window=3.*--cruft" event.trace
+	)
+'
+
+test_expect_success 'cruft repack respects --quiet' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+		GIT_PROGRESS_DELAY=0 git repack --cruft --quiet 2>err &&
+		test_must_be_empty err
+	)
+'
+
+test_expect_success 'cruft --local drops unreachable objects' '
+	git init alternate &&
+	git init repo &&
+	test_when_finished "rm -fr alternate repo" &&
+
+	test_commit -C alternate base &&
+	# Pack all objects in alterate so that the cruft repack in "repo" sees
+	# the object it dropped due to `--local` as packed. Otherwise this
+	# object would not appear packed anywhere (since it is not packed in
+	# alternate and likewise not part of the cruft pack in the other repo
+	# because of `--local`).
+	git -C alternate repack -ad &&
+
+	(
+		cd repo &&
+
+		object="$(git -C ../alternate rev-parse HEAD:base.t)" &&
+		git -C ../alternate cat-file -p $object >contents &&
+
+		# Write some reachable objects and two unreachable ones: one
+		# that the alternate has and another that is unique.
+		test_commit other &&
+		git hash-object -w -t blob contents &&
+		cruft="$(echo cruft | git hash-object -w -t blob --stdin)" &&
+
+		( cd ../alternate/.git/objects && pwd ) \
+		       >.git/objects/info/alternates &&
+
+		test_path_is_file $objdir/$(test_oid_to_path $cruft) &&
+		test_path_is_file $objdir/$(test_oid_to_path $object) &&
+
+		git repack -d --cruft --local &&
+
+		test-tool pack-mtimes "$(basename $(ls $packdir/pack-*.mtimes))" \
+		       >objects &&
+		! grep $object objects &&
+		grep $cruft objects
+	)
+'
+
 test_done
-- 
cgit v1.3-5-g9baa


From 72263ffc322d0b6c8646a4f096981a0b4bad17ba Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:18:08 -0400
Subject: builtin/repack.c: use named flags for existing_packs

We use the `util` pointer for items in the `existing_packs` string list
to indicate which packs are going to be deleted. Since that has so far
been the only use of that `util` pointer, we just set it to 0 or 1.

But we're going to add an additional state to this field in the next
patch, so prepare for that by adding a #define for the first bit so we
can more expressively inspect the flags state.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/repack.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'builtin')

diff --git a/builtin/repack.c b/builtin/repack.c
index b85483a148..36d1f03671 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -22,6 +22,8 @@
 #define LOOSEN_UNREACHABLE 2
 #define PACK_CRUFT 4
 
+#define DELETE_PACK 1
+
 static int pack_everything;
 static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
@@ -564,7 +566,7 @@ static void midx_included_packs(struct string_list *include,
 		}
 	} else {
 		for_each_string_list_item(item, existing_nonkept_packs) {
-			if (item->util)
+			if ((uintptr_t)item->util & DELETE_PACK)
 				continue;
 			string_list_insert(include, xstrfmt("%s.idx", item->string));
 		}
@@ -1002,7 +1004,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			 * was given) and that we will actually delete this pack
 			 * (if `-d` was given).
 			 */
-			item->util = (void*)(intptr_t)!string_list_has_string(&names, sha1);
+			if (!string_list_has_string(&names, sha1))
+				item->util = (void*)(uintptr_t)((size_t)item->util | DELETE_PACK);
 		}
 	}
 
@@ -1026,7 +1029,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (delete_redundant) {
 		int opts = 0;
 		for_each_string_list_item(item, &existing_nonkept_packs) {
-			if (!item->util)
+			if (!((uintptr_t)item->util & DELETE_PACK))
 				continue;
 			remove_redundant_pack(packdir, item->string);
 		}
-- 
cgit v1.3-5-g9baa


From ddee3703b36e96056f11ddc4621707b6054bab48 Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:18:11 -0400
Subject: builtin/repack.c: add cruft packs to MIDX during geometric repack

When using cruft packs, the following race can occur when a geometric
repack that writes a MIDX bitmap takes place afterwords:

  - First, create an unreachable object and do an all-into-one cruft
    repack which stores that object in the repository's cruft pack.
  - Then make that object reachable.
  - Finally, do a geometric repack and write a MIDX bitmap.

Assuming that we are sufficiently unlucky as to select a commit from the
MIDX which reaches that object for bitmapping, then the `git
multi-pack-index` process will complain that that object is missing.

The reason is because we don't include cruft packs in the MIDX when
doing a geometric repack. Since the "make that object reachable" doesn't
necessarily mean that we'll create a new copy of that object in one of
the packs that will get rolled up as part of a geometric repack, it's
possible that the MIDX won't see any copies of that now-reachable
object.

Of course, it's desirable to avoid including cruft packs in the MIDX
because it causes the MIDX to store a bunch of objects which are likely
to get thrown away. But excluding that pack does open us up to the above
race.

This patch demonstrates the bug, and resolves it by including cruft
packs in the MIDX even when doing a geometric repack.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/repack.c              | 23 ++++++++++++++++++++---
 t/t5329-pack-objects-cruft.sh | 26 ++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 3 deletions(-)

(limited to 'builtin')

diff --git a/builtin/repack.c b/builtin/repack.c
index 36d1f03671..15071fadbe 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -23,6 +23,7 @@
 #define PACK_CRUFT 4
 
 #define DELETE_PACK 1
+#define CRUFT_PACK 2
 
 static int pack_everything;
 static int delta_base_offset = 1;
@@ -159,10 +160,15 @@ static void collect_pack_filenames(struct string_list *fname_nonkept_list,
 		fname = xmemdupz(e->d_name, len);
 
 		if ((extra_keep->nr > 0 && i < extra_keep->nr) ||
-		    (file_exists(mkpath("%s/%s.keep", packdir, fname))))
+		    (file_exists(mkpath("%s/%s.keep", packdir, fname)))) {
 			string_list_append_nodup(fname_kept_list, fname);
-		else
-			string_list_append_nodup(fname_nonkept_list, fname);
+		} else {
+			struct string_list_item *item;
+			item = string_list_append_nodup(fname_nonkept_list,
+							fname);
+			if (file_exists(mkpath("%s/%s.mtimes", packdir, fname)))
+				item->util = (void*)(uintptr_t)CRUFT_PACK;
+		}
 	}
 	closedir(dir);
 }
@@ -564,6 +570,17 @@ static void midx_included_packs(struct string_list *include,
 
 			string_list_insert(include, strbuf_detach(&buf, NULL));
 		}
+
+		for_each_string_list_item(item, existing_nonkept_packs) {
+			if (!((uintptr_t)item->util & CRUFT_PACK)) {
+				/*
+				 * no need to check DELETE_PACK, since we're not
+				 * doing an ALL_INTO_ONE repack
+				 */
+				continue;
+			}
+			string_list_insert(include, xstrfmt("%s.idx", item->string));
+		}
 	} else {
 		for_each_string_list_item(item, existing_nonkept_packs) {
 			if ((uintptr_t)item->util & DELETE_PACK)
diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh
index c82f973b41..8de87afce2 100755
--- a/t/t5329-pack-objects-cruft.sh
+++ b/t/t5329-pack-objects-cruft.sh
@@ -648,4 +648,30 @@ test_expect_success 'cruft --local drops unreachable objects' '
 	)
 '
 
+test_expect_success 'MIDX bitmaps tolerate reachable cruft objects' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit reachable &&
+		test_commit cruft &&
+		unreachable="$(git rev-parse cruft)" &&
+
+		git reset --hard $unreachable^ &&
+		git tag -d cruft &&
+		git reflog expire --all --expire=all &&
+
+		git repack --cruft -d &&
+
+		# resurrect the unreachable object via a new commit. the
+		# new commit will get selected for a bitmap, but be
+		# missing one of its parents from the selected packs.
+		git reset --hard $unreachable &&
+		test_commit resurrect &&
+
+		git repack --write-midx --write-bitmap-index --geometric=2 -d
+	)
+'
+
 test_done
-- 
cgit v1.3-5-g9baa


From 5b92477f896f147d02bd2e9168a780940b57cfc5 Mon Sep 17 00:00:00 2001
From: Taylor Blau <me@ttaylorr.com>
Date: Fri, 20 May 2022 19:18:14 -0400
Subject: builtin/gc.c: conditionally avoid pruning objects via loose

Expose the new `git repack --cruft` mode from `git gc` via a new opt-in
flag. When invoked like `git gc --cruft`, `git gc` will avoid exploding
unreachable objects as loose ones, and instead create a cruft pack and
`.mtimes` file.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 Documentation/config/gc.txt   | 21 ++++++++++++++-------
 Documentation/git-gc.txt      |  5 +++++
 builtin/gc.c                  | 10 +++++++++-
 t/t5329-pack-objects-cruft.sh | 37 +++++++++++++++++++++++++++++++++++++
 4 files changed, 65 insertions(+), 8 deletions(-)

(limited to 'builtin')

diff --git a/Documentation/config/gc.txt b/Documentation/config/gc.txt
index c834e07991..38fea076a2 100644
--- a/Documentation/config/gc.txt
+++ b/Documentation/config/gc.txt
@@ -81,14 +81,21 @@ gc.packRefs::
 	to enable it within all non-bare repos or it can be set to a
 	boolean value.  The default is `true`.
 
+gc.cruftPacks::
+	Store unreachable objects in a cruft pack (see
+	linkgit:git-repack[1]) instead of as loose objects. The default
+	is `false`.
+
 gc.pruneExpire::
-	When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'.
-	Override the grace period with this config variable.  The value
-	"now" may be used to disable this grace period and always prune
-	unreachable objects immediately, or "never" may be used to
-	suppress pruning.  This feature helps prevent corruption when
-	'git gc' runs concurrently with another process writing to the
-	repository; see the "NOTES" section of linkgit:git-gc[1].
+	When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'
+	(and 'repack --cruft --cruft-expiration 2.weeks.ago' if using
+	cruft packs via `gc.cruftPacks` or `--cruft`).  Override the
+	grace period with this config variable.  The value "now" may be
+	used to disable this grace period and always prune unreachable
+	objects immediately, or "never" may be used to suppress pruning.
+	This feature helps prevent corruption when 'git gc' runs
+	concurrently with another process writing to the repository; see
+	the "NOTES" section of linkgit:git-gc[1].
 
 gc.worktreePruneExpire::
 	When 'git gc' is run, it calls
diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 853967dea0..ba4e67700e 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -54,6 +54,11 @@ other housekeeping tasks (e.g. rerere, working trees, reflog...) will
 be performed as well.
 
 
+--cruft::
+	When expiring unreachable objects, pack them separately into a
+	cruft pack instead of storing the loose objects as loose
+	objects.
+
 --prune=<date>::
 	Prune loose objects older than date (default is 2 weeks ago,
 	overridable by the config variable `gc.pruneExpire`).
diff --git a/builtin/gc.c b/builtin/gc.c
index b335cffa33..4d995e85e9 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -42,6 +42,7 @@ static const char * const builtin_gc_usage[] = {
 
 static int pack_refs = 1;
 static int prune_reflogs = 1;
+static int cruft_packs = 0;
 static int aggressive_depth = 50;
 static int aggressive_window = 250;
 static int gc_auto_threshold = 6700;
@@ -152,6 +153,7 @@ static void gc_config(void)
 	git_config_get_int("gc.auto", &gc_auto_threshold);
 	git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
 	git_config_get_bool("gc.autodetach", &detach_auto);
+	git_config_get_bool("gc.cruftpacks", &cruft_packs);
 	git_config_get_expiry("gc.pruneexpire", &prune_expire);
 	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
 	git_config_get_expiry("gc.logexpiry", &gc_log_expire);
@@ -331,7 +333,11 @@ static void add_repack_all_option(struct string_list *keep_pack)
 {
 	if (prune_expire && !strcmp(prune_expire, "now"))
 		strvec_push(&repack, "-a");
-	else {
+	else if (cruft_packs) {
+		strvec_push(&repack, "--cruft");
+		if (prune_expire)
+			strvec_pushf(&repack, "--cruft-expiration=%s", prune_expire);
+	} else {
 		strvec_push(&repack, "-A");
 		if (prune_expire)
 			strvec_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
@@ -551,6 +557,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		{ OPTION_STRING, 0, "prune", &prune_expire, N_("date"),
 			N_("prune unreferenced objects"),
 			PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
+		OPT_BOOL(0, "cruft", &cruft_packs, N_("pack unreferenced objects separately")),
 		OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
 		OPT_BOOL_F(0, "auto", &auto_gc, N_("enable auto-gc mode"),
 			   PARSE_OPT_NOCOMPLETE),
@@ -670,6 +677,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 			die(FAILED_RUN, repack.v[0]);
 
 		if (prune_expire) {
+			/* run `git prune` even if using cruft packs */
 			strvec_push(&prune, prune_expire);
 			if (quiet)
 				strvec_push(&prune, "--no-progress");
diff --git a/t/t5329-pack-objects-cruft.sh b/t/t5329-pack-objects-cruft.sh
index 8de87afce2..70a6a9553c 100755
--- a/t/t5329-pack-objects-cruft.sh
+++ b/t/t5329-pack-objects-cruft.sh
@@ -429,6 +429,43 @@ test_expect_success 'loose objects mtimes upsert others' '
 	)
 '
 
+test_expect_success 'expiring cruft objects with git gc' '
+	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 &&
+
+		mtimes=$(ls .git/objects/pack/pack-*.mtimes) &&
+		test_path_is_file $mtimes &&
+
+		git gc --cruft --prune=now &&
+
+		git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
+
+		comm -23 unreachable objects >removed &&
+		test_cmp unreachable removed &&
+		test_path_is_missing $mtimes
+	)
+'
+
 test_expect_success 'cruft packs are not included in geometric repack' '
 	git init repo &&
 	test_when_finished "rm -fr repo" &&
-- 
cgit v1.3-5-g9baa