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>
Taylor Blau committed
May 20, 2022 at 19:18 UTC
5b92477f896f147d02bd2e9168a780940b57cfc5
4 files changed
+65
-8
Documentation/config/gc.txt
+14
-7
@@ -81,14 +81,21 @@ gc.packRefs::
81
to enable it within all non-bare repos or it can be set to a
82
boolean value. The default is `true`.
83
84
+gc.cruftPacks::
85
+ Store unreachable objects in a cruft pack (see
86
+ linkgit:git-repack[1]) instead of as loose objects. The default
87
+ is `false`.
88
+
89
gc.pruneExpire::
85
- When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'.
86
- Override the grace period with this config variable. The value
87
- "now" may be used to disable this grace period and always prune
88
- unreachable objects immediately, or "never" may be used to
89
- suppress pruning. This feature helps prevent corruption when
90
- 'git gc' runs concurrently with another process writing to the
91
- repository; see the "NOTES" section of linkgit:git-gc[1].
90
+ When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'
91
+ (and 'repack --cruft --cruft-expiration 2.weeks.ago' if using
92
+ cruft packs via `gc.cruftPacks` or `--cruft`). Override the
93
+ grace period with this config variable. The value "now" may be
94
+ used to disable this grace period and always prune unreachable
95
+ objects immediately, or "never" may be used to suppress pruning.
96
+ This feature helps prevent corruption when 'git gc' runs
97
+ concurrently with another process writing to the repository; see
98
+ the "NOTES" section of linkgit:git-gc[1].
99
100
gc.worktreePruneExpire::
101
When 'git gc' is run, it calls
Documentation/git-gc.txt
+5
@@ -54,6 +54,11 @@ other housekeeping tasks (e.g. rerere, working trees, reflog...) will
54
be performed as well.
55
56
57
+--cruft::
58
+ When expiring unreachable objects, pack them separately into a
59
+ cruft pack instead of storing the loose objects as loose
60
+ objects.
61
+
62
--prune=<date>::
63
Prune loose objects older than date (default is 2 weeks ago,
64
overridable by the config variable `gc.pruneExpire`).
builtin/gc.c
+9
-1
@@ -42,6 +42,7 @@ static const char * const builtin_gc_usage[] = {
42
43
static int pack_refs = 1;
44
static int prune_reflogs = 1;
45
+static int cruft_packs = 0;
46
static int aggressive_depth = 50;
47
static int aggressive_window = 250;
48
static int gc_auto_threshold = 6700;
@@ -152,6 +153,7 @@ static void gc_config(void)
153
git_config_get_int("gc.auto", &gc_auto_threshold);
154
git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
155
git_config_get_bool("gc.autodetach", &detach_auto);
156
+ git_config_get_bool("gc.cruftpacks", &cruft_packs);
157
git_config_get_expiry("gc.pruneexpire", &prune_expire);
158
git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
159
git_config_get_expiry("gc.logexpiry", &gc_log_expire);
@@ -331,7 +333,11 @@ static void add_repack_all_option(struct string_list *keep_pack)
333
{
334
if (prune_expire && !strcmp(prune_expire, "now"))
335
strvec_push(&repack, "-a");
334
- else {
336
+ else if (cruft_packs) {
337
+ strvec_push(&repack, "--cruft");
338
+ if (prune_expire)
339
+ strvec_pushf(&repack, "--cruft-expiration=%s", prune_expire);
340
+ } else {
341
strvec_push(&repack, "-A");
342
if (prune_expire)
343
strvec_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
@@ -551,6 +557,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
557
{ OPTION_STRING, 0, "prune", &prune_expire, N_("date"),
558
N_("prune unreferenced objects"),
559
PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
560
+ OPT_BOOL(0, "cruft", &cruft_packs, N_("pack unreferenced objects separately")),
561
OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
562
OPT_BOOL_F(0, "auto", &auto_gc, N_("enable auto-gc mode"),
563
PARSE_OPT_NOCOMPLETE),
@@ -670,6 +677,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
677
die(FAILED_RUN, repack.v[0]);
678
679
if (prune_expire) {
680
+ /* run `git prune` even if using cruft packs */
681
strvec_push(&prune, prune_expire);
682
if (quiet)
683
strvec_push(&prune, "--no-progress");
t/t5329-pack-objects-cruft.sh
+37
@@ -429,6 +429,43 @@ test_expect_success 'loose objects mtimes upsert others' '
429
)
430
'
431
432
+test_expect_success 'expiring cruft objects with git gc' '
433
+ git init repo &&
434
+ test_when_finished "rm -fr repo" &&
435
+ (
436
+ cd repo &&
437
+
438
+ test_commit reachable &&
439
+ git branch -M main &&
440
+ git checkout --orphan other &&
441
+ test_commit unreachable &&
442
+
443
+ git checkout main &&
444
+ git branch -D other &&
445
+ git tag -d unreachable &&
446
+ # objects are not cruft if they are contained in the reflogs
447
+ git reflog expire --all --expire=all &&
448
+
449
+ git rev-list --objects --all --no-object-names >reachable.raw &&
450
+ git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
451
+ sort <reachable.raw >reachable &&
452
+ comm -13 reachable objects >unreachable &&
453
+
454
+ git repack --cruft -d &&
455
+
456
+ mtimes=$(ls .git/objects/pack/pack-*.mtimes) &&
457
+ test_path_is_file $mtimes &&
458
+
459
+ git gc --cruft --prune=now &&
460
+
461
+ git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
462
+
463
+ comm -23 unreachable objects >removed &&
464
+ test_cmp unreachable removed &&
465
+ test_path_is_missing $mtimes
466
+ )
467
+'
468
+
469
test_expect_success 'cruft packs are not included in geometric repack' '
470
git init repo &&
471
test_when_finished "rm -fr repo" &&