gc: do not explode objects which will be immediately pruned
When we pack everything into one big pack with "git repack -Ad", any unreferenced objects in to-be-deleted packs are exploded into loose objects, with the intent that they will be examined and possibly cleaned up by the next run of "git prune". Since the exploded objects will receive the mtime of the pack from which they come, if the source pack is old, those loose objects will end up pruned immediately. In that case, it is much more efficient to skip the exploding step entirely for these objects. This patch teaches pack-objects to receive the expiration information and avoid writing these objects out. It also teaches "git gc" to pass the value of gc.pruneexpire to repack (which in turn learns to pass it along to pack-objects) so that this optimization happens automatically during "git gc" and "git gc --auto". Signed-off-by: Jeff King <peff@peff.net> Acked-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Jeff King committed
Apr 7, 2012 at 06:30 UTC
7e52f5660e542cf801e8fc6902a30cc572c13736
4 files changed
+61
-11
builtin/gc.c
+15
-8
@@ -144,6 +144,19 @@ static int too_many_packs(void)
144
return gc_auto_pack_limit <= cnt;
145
}
146
147
+static void add_repack_all_option(void)
148
+{
149
+ if (prune_expire && !strcmp(prune_expire, "now"))
150
+ append_option(argv_repack, "-a", MAX_ADD);
151
+ else {
152
+ append_option(argv_repack, "-A", MAX_ADD);
153
+ if (prune_expire) {
154
+ append_option(argv_repack, "--unpack-unreachable", MAX_ADD);
155
+ append_option(argv_repack, prune_expire, MAX_ADD);
156
+ }
157
+ }
158
+}
159
+
160
static int need_to_gc(void)
161
{
162
/*
@@ -160,10 +173,7 @@ static int need_to_gc(void)
173
* there is no need.
174
*/
175
if (too_many_packs())
163
- append_option(argv_repack,
164
- prune_expire && !strcmp(prune_expire, "now") ?
165
- "-a" : "-A",
166
- MAX_ADD);
176
+ add_repack_all_option();
177
else if (!too_many_loose_objects())
178
return 0;
179
@@ -227,10 +237,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
237
"run \"git gc\" manually. See "
238
"\"git help gc\" for more information.\n"));
239
} else
230
- append_option(argv_repack,
231
- prune_expire && !strcmp(prune_expire, "now")
232
- ? "-a" : "-A",
233
- MAX_ADD);
240
+ add_repack_all_option();
241
242
if (pack_refs && run_command_v_opt(argv_pack_refs, RUN_GIT_CMD))
243
return error(FAILED_RUN, argv_pack_refs[0]);
builtin/pack-objects.c
+23
-2
@@ -63,6 +63,7 @@ static uint32_t nr_objects, nr_alloc, nr_result, nr_written;
63
static int non_empty;
64
static int reuse_delta = 1, reuse_object = 1;
65
static int keep_unreachable, unpack_unreachable, include_tag;
66
+static unsigned long unpack_unreachable_expiration;
67
static int local;
68
static int incremental;
69
static int ignore_packed_keep;
@@ -2249,6 +2250,10 @@ static void loosen_unused_packed_objects(struct rev_info *revs)
2250
if (!p->pack_local || p->pack_keep)
2251
continue;
2252
2253
+ if (unpack_unreachable_expiration &&
2254
+ p->mtime < unpack_unreachable_expiration)
2255
+ continue;
2256
+
2257
if (open_pack_index(p))
2258
die("cannot open pack index");
2259
@@ -2315,6 +2320,21 @@ static int option_parse_index_version(const struct option *opt,
2320
return 0;
2321
}
2322
2323
+static int option_parse_unpack_unreachable(const struct option *opt,
2324
+ const char *arg, int unset)
2325
+{
2326
+ if (unset) {
2327
+ unpack_unreachable = 0;
2328
+ unpack_unreachable_expiration = 0;
2329
+ }
2330
+ else {
2331
+ unpack_unreachable = 1;
2332
+ if (arg)
2333
+ unpack_unreachable_expiration = approxidate(arg);
2334
+ }
2335
+ return 0;
2336
+}
2337
+
2338
static int option_parse_ulong(const struct option *opt,
2339
const char *arg, int unset)
2340
{
@@ -2392,8 +2412,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
2412
"include tag objects that refer to objects to be packed"),
2413
OPT_BOOL(0, "keep-unreachable", &keep_unreachable,
2414
"keep unreachable objects"),
2395
- OPT_BOOL(0, "unpack-unreachable", &unpack_unreachable,
2396
- "unpack unreachable objects"),
2415
+ { OPTION_CALLBACK, 0, "unpack-unreachable", NULL, "time",
2416
+ "unpack unreachable objects newer than <time>",
2417
+ PARSE_OPT_OPTARG, option_parse_unpack_unreachable },
2418
OPT_BOOL(0, "thin", &thin,
2419
"create thin packs"),
2420
OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep,
git-repack.sh
+9
-1
@@ -15,6 +15,7 @@ F pass --no-reuse-object to git-pack-objects
15
n do not run git-update-server-info
16
q,quiet be quiet
17
l pass --local to git-pack-objects
18
+unpack-unreachable= with -A, do not loosen objects older than this
19
Packing constraints
20
window= size of the window used for delta compression
21
window-memory= same as the above, but limit memory size instead of entries count
@@ -33,6 +34,8 @@ do
34
-a) all_into_one=t ;;
35
-A) all_into_one=t
36
unpack_unreachable=--unpack-unreachable ;;
37
+ --unpack-unreachable)
38
+ unpack_unreachable="--unpack-unreachable=$2"; shift ;;
39
-d) remove_redundant=t ;;
40
-q) GIT_QUIET=t ;;
41
-f) no_reuse=--no-reuse-delta ;;
@@ -76,7 +79,12 @@ case ",$all_into_one," in
79
if test -n "$existing" -a -n "$unpack_unreachable" -a \
80
-n "$remove_redundant"
81
then
79
- args="$args $unpack_unreachable"
82
+ # This may have arbitrary user arguments, so we
83
+ # have to protect it against whitespace splitting
84
+ # when it gets run as "pack-objects $args" later.
85
+ # Fortunately, we know it's an approxidate, so we
86
+ # can just use dots instead.
87
+ args="$args $(echo "$unpack_unreachable" | tr ' ' .)"
88
fi
89
fi
90
;;
t/t7701-repack-unpack-unreachable.sh
+14
@@ -95,4 +95,18 @@ test_expect_success 'unpacked objects receive timestamp of pack file' '
95
compare_mtimes < mtimes
96
'
97
98
+test_expect_success 'do not bother loosening old objects' '
99
+ obj1=$(echo one | git hash-object -w --stdin) &&
100
+ obj2=$(echo two | git hash-object -w --stdin) &&
101
+ pack1=$(echo $obj1 | git pack-objects .git/objects/pack/pack) &&
102
+ pack2=$(echo $obj2 | git pack-objects .git/objects/pack/pack) &&
103
+ git prune-packed &&
104
+ git cat-file -p $obj1 &&
105
+ git cat-file -p $obj2 &&
106
+ test-chmtime =-86400 .git/objects/pack/pack-$pack2.pack &&
107
+ git repack -A -d --unpack-unreachable=1.hour.ago &&
108
+ git cat-file -p $obj1 &&
109
+ test_must_fail git cat-file -p $obj2
110
+'
111
+
112
test_done