[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"

#define FAILED_RUN "failed to run %s"

static const char * const builtin_gc_usage[] = {
	"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";

#define MAX_ADD 10
static const char *argv_pack_refs[] = {"pack-refs", "--all", "--prune", NULL};
static const char *argv_reflog[] = {"reflog", "expire", "--all", NULL};
static const char *argv_repack[MAX_ADD] = {"repack", "-d", "-l", NULL};
static const char *argv_prune[] = {"prune", "--expire", NULL, NULL};
static const char *argv_rerere[] = {"rerere", "gc", NULL};

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 void append_option(const char **cmd, const char *opt, int max_length)
{
	int i;

	for (i = 0; cmd[i]; i++)
		;

	if (i + 2 >= max_length)
		die("Too many options specified");
	cmd[i++] = opt;
	cmd[i] = NULL;
}

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 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())
		append_option(argv_repack,
			      prune_expire && !strcmp(prune_expire, "now") ?
			      "-a" : "-A",
			      MAX_ADD);
	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;
	char buf[80];

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

	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) {
		append_option(argv_repack, "-f", MAX_ADD);
		append_option(argv_repack, "--depth=250", MAX_ADD);
		if (aggressive_window > 0) {
			sprintf(buf, "--window=%d", aggressive_window);
			append_option(argv_repack, buf, MAX_ADD);
		}
	}
	if (quiet)
		append_option(argv_repack, "-q", MAX_ADD);

	if (auto_gc) {
		/*
		 * Auto-gc should be least intrusive as possible.
		 */
		if (!need_to_gc())
			return 0;
		fprintf(stderr,
			"Auto packing the repository for optimum performance.%s\n",
			quiet
			? ""
			: (" You may also\n"
			   "run \"git gc\" manually. See "
			   "\"git help gc\" for more information."));
	} else
		append_option(argv_repack,
			      prune_expire && !strcmp(prune_expire, "now")
			      ? "-a" : "-A",
			      MAX_ADD);

	if (pack_refs && run_command_v_opt(argv_pack_refs, RUN_GIT_CMD))
		return error(FAILED_RUN, argv_pack_refs[0]);

	if (run_command_v_opt(argv_reflog, RUN_GIT_CMD))
		return error(FAILED_RUN, argv_reflog[0]);

	if (run_command_v_opt(argv_repack, RUN_GIT_CMD))
		return error(FAILED_RUN, argv_repack[0]);

	if (prune_expire) {
		argv_prune[2] = prune_expire;
		if (run_command_v_opt(argv_prune, RUN_GIT_CMD))
			return error(FAILED_RUN, argv_prune[0]);
	}

	if (run_command_v_opt(argv_rerere, RUN_GIT_CMD))
		return error(FAILED_RUN, argv_rerere[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 JB	16	#include "run-command.h"
	17
	18	#define FAILED_RUN "failed to run %s"
	19
44c637c8	20	static const char * const builtin_gc_usage[] = {
1b1dd23f	21	"git gc [options]",
44c637c8 JB	22	NULL
44c637c8 JB	23	};
6757ada4	24
56752391	25	static int pack_refs = 1;
1c192f34	26	static int aggressive_window = 250;
2c3c4399	27	static int gc_auto_threshold = 6700;
97063974	28	static int gc_auto_pack_limit = 50;
d3154b44	29	static const char *prune_expire = "2.weeks.ago";
6757ada4	30
0d7566a5	31	#define MAX_ADD 10
56752391	32	static const char *argv_pack_refs[] = {"pack-refs", "--all", "--prune", NULL};
6757ada4	33	static const char *argv_reflog[] = {"reflog", "expire", "--all", NULL};
edb0e04e	34	static const char *argv_repack[MAX_ADD] = {"repack", "-d", "-l", NULL};
25ee9731	35	static const char *argv_prune[] = {"prune", "--expire", NULL, NULL};
6757ada4 JB	36	static const char *argv_rerere[] = {"rerere", "gc", NULL};
6757ada4 JB	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");
	62	if (approxidate(value) >= now)
	63	return error("Invalid %s: '%s'", var, value);
	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
0d7566a5 TT	70	static void append_option(const char *cmd, const char opt, int max_length)
	71	{
	72	int i;
	73
	74	for (i = 0; cmd[i]; i++)
	75	;
	76
	77	if (i + 2 >= max_length)
	78	die("Too many options specified");
	79	cmd[i++] = opt;
	80	cmd[i] = NULL;
	81	}
	82
a087cc98	83	static int too_many_loose_objects(void)
2c3c4399 JH	84	{
	85	/*
	86	* Quickly check if a "gc" is needed, by estimating how
	87	* many loose objects there are. Because SHA-1 is evenly
	88	* distributed, we can check only one and get a reasonable
	89	* estimate.
	90	*/
	91	char path[PATH_MAX];
	92	const char *objdir = get_object_directory();
	93	DIR *dir;
	94	struct dirent *ent;
	95	int auto_threshold;
	96	int num_loose = 0;
	97	int needed = 0;
	98
17815501 JH	99	if (gc_auto_threshold <= 0)
	100	return 0;
	101
2c3c4399 JH	102	if (sizeof(path) <= snprintf(path, sizeof(path), "%s/17", objdir)) {
	103	warning("insanely long object directory %.*s", 50, objdir);
	104	return 0;
	105	}
	106	dir = opendir(path);
	107	if (!dir)
	108	return 0;
	109
	110	auto_threshold = (gc_auto_threshold + 255) / 256;
	111	while ((ent = readdir(dir)) != NULL) {
	112	if (strspn(ent->d_name, "0123456789abcdef") != 38 \|\|
	113	ent->d_name[38] != '\0')
	114	continue;
	115	if (++num_loose > auto_threshold) {
	116	needed = 1;
	117	break;
	118	}
	119	}
	120	closedir(dir);
	121	return needed;
	122	}
	123
17815501 JH	124	static int too_many_packs(void)
	125	{
	126	struct packed_git *p;
	127	int cnt;
	128
	129	if (gc_auto_pack_limit <= 0)
	130	return 0;
	131
	132	prepare_packed_git();
	133	for (cnt = 0, p = packed_git; p; p = p->next) {
17815501 JH	134	if (!p->pack_local)
17815501 JH	135	continue;
01af249f	136	if (p->pack_keep)
17815501 JH	137	continue;
	138	/*
	139	* Perhaps check the size of the pack and count only
	140	* very small ones here?
	141	*/
	142	cnt++;
	143	}
	144	return gc_auto_pack_limit <= cnt;
	145	}
	146
a087cc98 JH	147	static int need_to_gc(void)
	148	{
	149	/*
b14d255b BC	150	* Setting gc.auto to 0 or negative can disable the
b14d255b BC	151	* automatic gc.
a087cc98	152	*/
b14d255b	153	if (gc_auto_threshold <= 0)
95143f9e JH	154	return 0;
95143f9e JH	155
17815501 JH	156	/*
	157	* If there are too many loose objects, but not too many
	158	* packs, we run "repack -d -l". If there are too many packs,
	159	* we run "repack -A -d -l". Otherwise we tell the caller
	160	* there is no need.
	161	*/
17815501	162	if (too_many_packs())
8e8daf33	163	append_option(argv_repack,
58e9d9d4 JS	164	prune_expire && !strcmp(prune_expire, "now") ?
58e9d9d4 JS	165	"-a" : "-A",
8e8daf33	166	MAX_ADD);
17815501 JH	167	else if (!too_many_loose_objects())
17815501 JH	168	return 0;
bde30540	169
ae98a008	170	if (run_hook(NULL, "pre-auto-gc", NULL))
bde30540	171	return 0;
95143f9e	172	return 1;
a087cc98 JH	173	}
a087cc98 JH	174
6757ada4 JB	175	int cmd_gc(int argc, const char *argv, const char prefix)
6757ada4 JB	176	{
44c637c8	177	int aggressive = 0;
2c3c4399	178	int auto_gc = 0;
a0c14cbb	179	int quiet = 0;
0d7566a5	180	char buf[80];
6757ada4	181
44c637c8	182	struct option builtin_gc_options[] = {
5d2dcc42	183	OPT__QUIET(&quiet),
58e9d9d4 JS	184	{ OPTION_STRING, 0, "prune", &prune_expire, "date",
	185	"prune unreferenced objects",
	186	PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
44c637c8 JB	187	OPT_BOOLEAN(0, "aggressive", &aggressive, "be more thorough (increased runtime)"),
	188	OPT_BOOLEAN(0, "auto", &auto_gc, "enable auto-gc mode"),
	189	OPT_END()
	190	};
	191
ef90d6d4	192	git_config(gc_config, NULL);
6757ada4 JB	193
	194	if (pack_refs < 0)
	195	pack_refs = !is_bare_repository();
	196
37782920 SB	197	argc = parse_options(argc, argv, prefix, builtin_gc_options,
37782920 SB	198	builtin_gc_usage, 0);
44c637c8 JB	199	if (argc > 0)
	200	usage_with_options(builtin_gc_usage, builtin_gc_options);
	201
	202	if (aggressive) {
	203	append_option(argv_repack, "-f", MAX_ADD);
1c192f34	204	append_option(argv_repack, "--depth=250", MAX_ADD);
44c637c8 JB	205	if (aggressive_window > 0) {
	206	sprintf(buf, "--window=%d", aggressive_window);
	207	append_option(argv_repack, buf, MAX_ADD);
2c3c4399	208	}
6757ada4	209	}
a0c14cbb FL	210	if (quiet)
a0c14cbb FL	211	append_option(argv_repack, "-q", MAX_ADD);
6757ada4	212
2c3c4399 JH	213	if (auto_gc) {
	214	/*
	215	* Auto-gc should be least intrusive as possible.
	216	*/
2c3c4399 JH	217	if (!need_to_gc())
2c3c4399 JH	218	return 0;
dad5f89f JH	219	fprintf(stderr,
	220	"Auto packing the repository for optimum performance.%s\n",
	221	quiet
	222	? ""
	223	: (" You may also\n"
	224	"run \"git gc\" manually. See "
	225	"\"git help gc\" for more information."));
a37cce3b	226	} else
8e8daf33	227	append_option(argv_repack,
58e9d9d4 JS	228	prune_expire && !strcmp(prune_expire, "now")
58e9d9d4 JS	229	? "-a" : "-A",
8e8daf33	230	MAX_ADD);
2c3c4399	231
6757ada4 JB	232	if (pack_refs && run_command_v_opt(argv_pack_refs, RUN_GIT_CMD))
	233	return error(FAILED_RUN, argv_pack_refs[0]);
	234
	235	if (run_command_v_opt(argv_reflog, RUN_GIT_CMD))
	236	return error(FAILED_RUN, argv_reflog[0]);
	237
	238	if (run_command_v_opt(argv_repack, RUN_GIT_CMD))
	239	return error(FAILED_RUN, argv_repack[0]);
	240
58e9d9d4 JS	241	if (prune_expire) {
	242	argv_prune[2] = prune_expire;
	243	if (run_command_v_opt(argv_prune, RUN_GIT_CMD))
	244	return error(FAILED_RUN, argv_prune[0]);
	245	}
6757ada4 JB	246
	247	if (run_command_v_opt(argv_rerere, RUN_GIT_CMD))
	248	return error(FAILED_RUN, argv_rerere[0]);
	249
a087cc98 JH	250	if (auto_gc && too_many_loose_objects())
	251	warning("There are too many unreachable loose objects; "
	252	"run 'git prune' to remove them.");
	253
6757ada4 JB	254	return 0;
6757ada4 JB	255	}