[thirdparty/git.git] / builtin / gc.c

/*
 * git gc builtin command
 *
 * Cleanup unreachable files and optimize the repository.
 *
 * Copyright (c) 2007 James Bowes
 *
 * Based on git-gc.sh, which is
 *
 * Copyright (c) 2006 Shawn O. Pearce
 */

#include "builtin.h"
#include "cache.h"
#include "parse-options.h"
#include "run-command.h"
#include "argv-array.h"

#define FAILED_RUN "failed to run %s"

static const char * const builtin_gc_usage[] = {
	N_("git gc [options]"),
	NULL
};

static int pack_refs = 1;
static int aggressive_window = 250;
static int gc_auto_threshold = 6700;
static int gc_auto_pack_limit = 50;
static const char *prune_expire = "2.weeks.ago";

static struct argv_array pack_refs_cmd = ARGV_ARRAY_INIT;
static struct argv_array reflog = ARGV_ARRAY_INIT;
static struct argv_array repack = ARGV_ARRAY_INIT;
static struct argv_array prune = ARGV_ARRAY_INIT;
static struct argv_array rerere = ARGV_ARRAY_INIT;

static int gc_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "gc.packrefs")) {
		if (value && !strcmp(value, "notbare"))
			pack_refs = -1;
		else
			pack_refs = git_config_bool(var, value);
		return 0;
	}
	if (!strcmp(var, "gc.aggressivewindow")) {
		aggressive_window = git_config_int(var, value);
		return 0;
	}
	if (!strcmp(var, "gc.auto")) {
		gc_auto_threshold = git_config_int(var, value);
		return 0;
	}
	if (!strcmp(var, "gc.autopacklimit")) {
		gc_auto_pack_limit = git_config_int(var, value);
		return 0;
	}
	if (!strcmp(var, "gc.pruneexpire")) {
		if (value && strcmp(value, "now")) {
			unsigned long now = approxidate("now");
			if (approxidate(value) >= now)
				return error(_("Invalid %s: '%s'"), var, value);
		}
		return git_config_string(&prune_expire, var, value);
	}
	return git_default_config(var, value, cb);
}

static int too_many_loose_objects(void)
{
	/*
	 * Quickly check if a "gc" is needed, by estimating how
	 * many loose objects there are.  Because SHA-1 is evenly
	 * distributed, we can check only one and get a reasonable
	 * estimate.
	 */
	char path[PATH_MAX];
	const char *objdir = get_object_directory();
	DIR *dir;
	struct dirent *ent;
	int auto_threshold;
	int num_loose = 0;
	int needed = 0;

	if (gc_auto_threshold <= 0)
		return 0;

	if (sizeof(path) <= snprintf(path, sizeof(path), "%s/17", objdir)) {
		warning(_("insanely long object directory %.*s"), 50, objdir);
		return 0;
	}
	dir = opendir(path);
	if (!dir)
		return 0;

	auto_threshold = (gc_auto_threshold + 255) / 256;
	while ((ent = readdir(dir)) != NULL) {
		if (strspn(ent->d_name, "0123456789abcdef") != 38 ||
		    ent->d_name[38] != '\0')
			continue;
		if (++num_loose > auto_threshold) {
			needed = 1;
			break;
		}
	}
	closedir(dir);
	return needed;
}

static int too_many_packs(void)
{
	struct packed_git *p;
	int cnt;

	if (gc_auto_pack_limit <= 0)
		return 0;

	prepare_packed_git();
	for (cnt = 0, p = packed_git; p; p = p->next) {
		if (!p->pack_local)
			continue;
		if (p->pack_keep)
			continue;
		/*
		 * Perhaps check the size of the pack and count only
		 * very small ones here?
		 */
		cnt++;
	}
	return gc_auto_pack_limit <= cnt;
}

static void add_repack_all_option(void)
{
	if (prune_expire && !strcmp(prune_expire, "now"))
		argv_array_push(&repack, "-a");
	else {
		argv_array_push(&repack, "-A");
		if (prune_expire)
			argv_array_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
	}
}

static int need_to_gc(void)
{
	/*
	 * Setting gc.auto to 0 or negative can disable the
	 * automatic gc.
	 */
	if (gc_auto_threshold <= 0)
		return 0;

	/*
	 * If there are too many loose objects, but not too many
	 * packs, we run "repack -d -l".  If there are too many packs,
	 * we run "repack -A -d -l".  Otherwise we tell the caller
	 * there is no need.
	 */
	if (too_many_packs())
		add_repack_all_option();
	else if (!too_many_loose_objects())
		return 0;

	if (run_hook(NULL, "pre-auto-gc", NULL))
		return 0;
	return 1;
}

int cmd_gc(int argc, const char **argv, const char *prefix)
{
	int aggressive = 0;
	int auto_gc = 0;
	int quiet = 0;

	struct option builtin_gc_options[] = {
		OPT__QUIET(&quiet, N_("suppress progress reporting")),
		{ OPTION_STRING, 0, "prune", &prune_expire, N_("date"),
			N_("prune unreferenced objects"),
			PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
		OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
		OPT_BOOL(0, "auto", &auto_gc, N_("enable auto-gc mode")),
		OPT_END()
	};

	if (argc == 2 && !strcmp(argv[1], "-h"))
		usage_with_options(builtin_gc_usage, builtin_gc_options);

	argv_array_pushl(&pack_refs_cmd, "pack-refs", "--all", "--prune", NULL);
	argv_array_pushl(&reflog, "reflog", "expire", "--all", NULL);
	argv_array_pushl(&repack, "repack", "-d", "-l", NULL);
	argv_array_pushl(&prune, "prune", "--expire", NULL );
	argv_array_pushl(&rerere, "rerere", "gc", NULL);

	git_config(gc_config, NULL);

	if (pack_refs < 0)
		pack_refs = !is_bare_repository();

	argc = parse_options(argc, argv, prefix, builtin_gc_options,
			     builtin_gc_usage, 0);
	if (argc > 0)
		usage_with_options(builtin_gc_usage, builtin_gc_options);

	if (aggressive) {
		argv_array_push(&repack, "-f");
		argv_array_push(&repack, "--depth=250");
		if (aggressive_window > 0)
			argv_array_pushf(&repack, "--window=%d", aggressive_window);
	}
	if (quiet)
		argv_array_push(&repack, "-q");

	if (auto_gc) {
		/*
		 * Auto-gc should be least intrusive as possible.
		 */
		if (!need_to_gc())
			return 0;
		if (!quiet)
			fprintf(stderr,
					_("Auto packing the repository for optimum performance. You may also\n"
					"run \"git gc\" manually. See "
					"\"git help gc\" for more information.\n"));
	} else
		add_repack_all_option();

	if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD))
		return error(FAILED_RUN, pack_refs_cmd.argv[0]);

	if (run_command_v_opt(reflog.argv, RUN_GIT_CMD))
		return error(FAILED_RUN, reflog.argv[0]);

	if (run_command_v_opt(repack.argv, RUN_GIT_CMD))
		return error(FAILED_RUN, repack.argv[0]);

	if (prune_expire) {
		argv_array_push(&prune, prune_expire);
		if (quiet)
			argv_array_push(&prune, "--no-progress");
		if (run_command_v_opt(prune.argv, RUN_GIT_CMD))
			return error(FAILED_RUN, prune.argv[0]);
	}

	if (run_command_v_opt(rerere.argv, RUN_GIT_CMD))
		return error(FAILED_RUN, rerere.argv[0]);

	if (auto_gc && too_many_loose_objects())
		warning(_("There are too many unreachable loose objects; "
			"run 'git prune' to remove them."));

	return 0;
}
Commit	Line	Data
6757ada4 JB	1	/*
	2	* git gc builtin command
	3	*
	4	* Cleanup unreachable files and optimize the repository.
	5	*
	6	* Copyright (c) 2007 James Bowes
	7	*
	8	* Based on git-gc.sh, which is
	9	*
	10	* Copyright (c) 2006 Shawn O. Pearce
	11	*/
	12
baffc0e7	13	#include "builtin.h"
6757ada4	14	#include "cache.h"
44c637c8	15	#include "parse-options.h"
6757ada4	16	#include "run-command.h"
234587fc	17	#include "argv-array.h"
6757ada4 JB	18
	19	#define FAILED_RUN "failed to run %s"
	20
44c637c8	21	static const char * const builtin_gc_usage[] = {
6705c162	22	N_("git gc [options]"),
44c637c8 JB	23	NULL
44c637c8 JB	24	};
6757ada4	25
56752391	26	static int pack_refs = 1;
1c192f34	27	static int aggressive_window = 250;
2c3c4399	28	static int gc_auto_threshold = 6700;
97063974	29	static int gc_auto_pack_limit = 50;
d3154b44	30	static const char *prune_expire = "2.weeks.ago";
6757ada4	31
234587fc JK	32	static struct argv_array pack_refs_cmd = ARGV_ARRAY_INIT;
	33	static struct argv_array reflog = ARGV_ARRAY_INIT;
	34	static struct argv_array repack = ARGV_ARRAY_INIT;
	35	static struct argv_array prune = ARGV_ARRAY_INIT;
	36	static struct argv_array rerere = ARGV_ARRAY_INIT;
6757ada4	37
ef90d6d4	38	static int gc_config(const char var, const char value, void *cb)
6757ada4 JB	39	{
6757ada4 JB	40	if (!strcmp(var, "gc.packrefs")) {
c5e5a2c0	41	if (value && !strcmp(value, "notbare"))
6757ada4 JB	42	pack_refs = -1;
	43	else
	44	pack_refs = git_config_bool(var, value);
	45	return 0;
	46	}
0d7566a5 TT	47	if (!strcmp(var, "gc.aggressivewindow")) {
	48	aggressive_window = git_config_int(var, value);
	49	return 0;
	50	}
2c3c4399 JH	51	if (!strcmp(var, "gc.auto")) {
	52	gc_auto_threshold = git_config_int(var, value);
	53	return 0;
	54	}
17815501 JH	55	if (!strcmp(var, "gc.autopacklimit")) {
	56	gc_auto_pack_limit = git_config_int(var, value);
	57	return 0;
	58	}
25ee9731	59	if (!strcmp(var, "gc.pruneexpire")) {
d3154b44	60	if (value && strcmp(value, "now")) {
25ee9731 JS	61	unsigned long now = approxidate("now");
25ee9731 JS	62	if (approxidate(value) >= now)
fea6128b	63	return error(_("Invalid %s: '%s'"), var, value);
25ee9731	64	}
d3154b44	65	return git_config_string(&prune_expire, var, value);
25ee9731	66	}
ef90d6d4	67	return git_default_config(var, value, cb);
6757ada4 JB	68	}
6757ada4 JB	69
a087cc98	70	static int too_many_loose_objects(void)
2c3c4399 JH	71	{
	72	/*
	73	* Quickly check if a "gc" is needed, by estimating how
	74	* many loose objects there are. Because SHA-1 is evenly
	75	* distributed, we can check only one and get a reasonable
	76	* estimate.
	77	*/
	78	char path[PATH_MAX];
	79	const char *objdir = get_object_directory();
	80	DIR *dir;
	81	struct dirent *ent;
	82	int auto_threshold;
	83	int num_loose = 0;
	84	int needed = 0;
	85
17815501 JH	86	if (gc_auto_threshold <= 0)
	87	return 0;
	88
2c3c4399	89	if (sizeof(path) <= snprintf(path, sizeof(path), "%s/17", objdir)) {
fea6128b	90	warning(_("insanely long object directory %.*s"), 50, objdir);
2c3c4399 JH	91	return 0;
	92	}
	93	dir = opendir(path);
	94	if (!dir)
	95	return 0;
	96
	97	auto_threshold = (gc_auto_threshold + 255) / 256;
	98	while ((ent = readdir(dir)) != NULL) {
	99	if (strspn(ent->d_name, "0123456789abcdef") != 38 \|\|
	100	ent->d_name[38] != '\0')
	101	continue;
	102	if (++num_loose > auto_threshold) {
	103	needed = 1;
	104	break;
	105	}
	106	}
	107	closedir(dir);
	108	return needed;
	109	}
	110
17815501 JH	111	static int too_many_packs(void)
	112	{
	113	struct packed_git *p;
	114	int cnt;
	115
	116	if (gc_auto_pack_limit <= 0)
	117	return 0;
	118
	119	prepare_packed_git();
	120	for (cnt = 0, p = packed_git; p; p = p->next) {
17815501 JH	121	if (!p->pack_local)
17815501 JH	122	continue;
01af249f	123	if (p->pack_keep)
17815501 JH	124	continue;
	125	/*
	126	* Perhaps check the size of the pack and count only
	127	* very small ones here?
	128	*/
	129	cnt++;
	130	}
	131	return gc_auto_pack_limit <= cnt;
	132	}
	133
7e52f566 JK	134	static void add_repack_all_option(void)
	135	{
	136	if (prune_expire && !strcmp(prune_expire, "now"))
234587fc	137	argv_array_push(&repack, "-a");
7e52f566	138	else {
234587fc JK	139	argv_array_push(&repack, "-A");
	140	if (prune_expire)
	141	argv_array_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
7e52f566 JK	142	}
	143	}
	144
a087cc98 JH	145	static int need_to_gc(void)
	146	{
	147	/*
b14d255b BC	148	* Setting gc.auto to 0 or negative can disable the
b14d255b BC	149	* automatic gc.
a087cc98	150	*/
b14d255b	151	if (gc_auto_threshold <= 0)
95143f9e JH	152	return 0;
95143f9e JH	153
17815501 JH	154	/*
	155	* If there are too many loose objects, but not too many
	156	* packs, we run "repack -d -l". If there are too many packs,
	157	* we run "repack -A -d -l". Otherwise we tell the caller
	158	* there is no need.
	159	*/
17815501	160	if (too_many_packs())
7e52f566	161	add_repack_all_option();
17815501 JH	162	else if (!too_many_loose_objects())
17815501 JH	163	return 0;
bde30540	164
ae98a008	165	if (run_hook(NULL, "pre-auto-gc", NULL))
bde30540	166	return 0;
95143f9e	167	return 1;
a087cc98 JH	168	}
a087cc98 JH	169
6757ada4 JB	170	int cmd_gc(int argc, const char *argv, const char prefix)
6757ada4 JB	171	{
44c637c8	172	int aggressive = 0;
2c3c4399	173	int auto_gc = 0;
a0c14cbb	174	int quiet = 0;
6757ada4	175
44c637c8	176	struct option builtin_gc_options[] = {
6705c162 NTND	177	OPT__QUIET(&quiet, N_("suppress progress reporting")),
	178	{ OPTION_STRING, 0, "prune", &prune_expire, N_("date"),
	179	N_("prune unreferenced objects"),
58e9d9d4	180	PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
d5d09d47 SB	181	OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
d5d09d47 SB	182	OPT_BOOL(0, "auto", &auto_gc, N_("enable auto-gc mode")),
44c637c8 JB	183	OPT_END()
	184	};
	185
0c8151b6 NTND	186	if (argc == 2 && !strcmp(argv[1], "-h"))
	187	usage_with_options(builtin_gc_usage, builtin_gc_options);
	188
234587fc JK	189	argv_array_pushl(&pack_refs_cmd, "pack-refs", "--all", "--prune", NULL);
	190	argv_array_pushl(&reflog, "reflog", "expire", "--all", NULL);
	191	argv_array_pushl(&repack, "repack", "-d", "-l", NULL);
	192	argv_array_pushl(&prune, "prune", "--expire", NULL );
	193	argv_array_pushl(&rerere, "rerere", "gc", NULL);
	194
ef90d6d4	195	git_config(gc_config, NULL);
6757ada4 JB	196
	197	if (pack_refs < 0)
	198	pack_refs = !is_bare_repository();
	199
37782920 SB	200	argc = parse_options(argc, argv, prefix, builtin_gc_options,
37782920 SB	201	builtin_gc_usage, 0);
44c637c8 JB	202	if (argc > 0)
	203	usage_with_options(builtin_gc_usage, builtin_gc_options);
	204
	205	if (aggressive) {
234587fc JK	206	argv_array_push(&repack, "-f");
	207	argv_array_push(&repack, "--depth=250");
	208	if (aggressive_window > 0)
	209	argv_array_pushf(&repack, "--window=%d", aggressive_window);
6757ada4	210	}
a0c14cbb	211	if (quiet)
234587fc	212	argv_array_push(&repack, "-q");
6757ada4	213
2c3c4399 JH	214	if (auto_gc) {
	215	/*
	216	* Auto-gc should be least intrusive as possible.
	217	*/
2c3c4399 JH	218	if (!need_to_gc())
2c3c4399 JH	219	return 0;
df995c7d	220	if (!quiet)
f6908ae8 ÆAB	221	fprintf(stderr,
	222	_("Auto packing the repository for optimum performance. You may also\n"
	223	"run \"git gc\" manually. See "
daab4eea	224	"\"git help gc\" for more information.\n"));
a37cce3b	225	} else
7e52f566	226	add_repack_all_option();
2c3c4399	227
234587fc JK	228	if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD))
234587fc JK	229	return error(FAILED_RUN, pack_refs_cmd.argv[0]);
6757ada4	230
234587fc JK	231	if (run_command_v_opt(reflog.argv, RUN_GIT_CMD))
234587fc JK	232	return error(FAILED_RUN, reflog.argv[0]);
6757ada4	233
234587fc JK	234	if (run_command_v_opt(repack.argv, RUN_GIT_CMD))
234587fc JK	235	return error(FAILED_RUN, repack.argv[0]);
6757ada4	236
58e9d9d4	237	if (prune_expire) {
234587fc	238	argv_array_push(&prune, prune_expire);
bf0a59b3	239	if (quiet)
234587fc JK	240	argv_array_push(&prune, "--no-progress");
	241	if (run_command_v_opt(prune.argv, RUN_GIT_CMD))
	242	return error(FAILED_RUN, prune.argv[0]);
58e9d9d4	243	}
6757ada4	244
234587fc JK	245	if (run_command_v_opt(rerere.argv, RUN_GIT_CMD))
234587fc JK	246	return error(FAILED_RUN, rerere.argv[0]);
6757ada4	247
a087cc98	248	if (auto_gc && too_many_loose_objects())
fea6128b ÆAB	249	warning(_("There are too many unreachable loose objects; "
fea6128b ÆAB	250	"run 'git prune' to remove them."));
a087cc98	251
6757ada4 JB	252	return 0;
6757ada4 JB	253	}