[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 = -1;
static int gc_auto_threshold = 6700;
static int gc_auto_pack_limit = 20;

#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", NULL};
static const char *argv_rerere[] = {"rerere", "gc", NULL};

static int gc_config(const char *var, const char *value)
{
	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;
	}
	return git_default_config(var, value);
}

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) {
		char path[PATH_MAX];
		size_t len;
		int keep;

		if (!p->pack_local)
			continue;
		len = strlen(p->pack_name);
		if (PATH_MAX <= len + 1)
			continue; /* oops, give up */
		memcpy(path, p->pack_name, len-5);
		memcpy(path + len - 5, ".keep", 6);
		keep = access(p->pack_name, F_OK) && (errno == ENOENT);
		if (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 and gc.autopacklimit to 0 or negative can
	 * disable the automatic gc.
	 */
	if (gc_auto_threshold <= 0 && gc_auto_pack_limit <= 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, "-A", MAX_ADD);
	else if (!too_many_loose_objects())
		return 0;
	return 1;
}

int cmd_gc(int argc, const char **argv, const char *prefix)
{
	int prune = 0;
	int aggressive = 0;
	int auto_gc = 0;
	char buf[80];

	struct option builtin_gc_options[] = {
		OPT_BOOLEAN(0, "prune", &prune, "prune unreferenced objects"),
		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);

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

	argc = parse_options(argc, argv, 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);
		if (aggressive_window > 0) {
			sprintf(buf, "--window=%d", aggressive_window);
			append_option(argv_repack, buf, MAX_ADD);
		}
	}

	if (auto_gc) {
		/*
		 * Auto-gc should be least intrusive as possible.
		 */
		prune = 0;
		if (!need_to_gc())
			return 0;
		fprintf(stderr, "Auto packing your repository for optimum "
			"performance. You may also\n"
			"run \"git gc\" manually. See "
			"\"git help gc\" for more information.\n");
	} else {
		/*
		 * Use safer (for shared repos) "-A" option to
		 * repack when not pruning. Auto-gc makes its
		 * own decision.
		 */
		if (prune)
			append_option(argv_repack, "-a", MAX_ADD);
		else
			append_option(argv_repack, "-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 && 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 JB	20	static const char * const builtin_gc_usage[] = {
	21	"git-gc [options]",
	22	NULL
	23	};
6757ada4	24
56752391	25	static int pack_refs = 1;
0d7566a5	26	static int aggressive_window = -1;
2c3c4399	27	static int gc_auto_threshold = 6700;
17815501	28	static int gc_auto_pack_limit = 20;
6757ada4	29
0d7566a5	30	#define MAX_ADD 10
56752391	31	static const char *argv_pack_refs[] = {"pack-refs", "--all", "--prune", NULL};
6757ada4	32	static const char *argv_reflog[] = {"reflog", "expire", "--all", NULL};
edb0e04e	33	static const char *argv_repack[MAX_ADD] = {"repack", "-d", "-l", NULL};
6757ada4 JB	34	static const char *argv_prune[] = {"prune", NULL};
	35	static const char *argv_rerere[] = {"rerere", "gc", NULL};
	36
	37	static int gc_config(const char var, const char value)
	38	{
	39	if (!strcmp(var, "gc.packrefs")) {
c5e5a2c0	40	if (value && !strcmp(value, "notbare"))
6757ada4 JB	41	pack_refs = -1;
	42	else
	43	pack_refs = git_config_bool(var, value);
	44	return 0;
	45	}
0d7566a5 TT	46	if (!strcmp(var, "gc.aggressivewindow")) {
	47	aggressive_window = git_config_int(var, value);
	48	return 0;
	49	}
2c3c4399 JH	50	if (!strcmp(var, "gc.auto")) {
	51	gc_auto_threshold = git_config_int(var, value);
	52	return 0;
	53	}
17815501 JH	54	if (!strcmp(var, "gc.autopacklimit")) {
	55	gc_auto_pack_limit = git_config_int(var, value);
	56	return 0;
	57	}
6757ada4 JB	58	return git_default_config(var, value);
	59	}
	60
0d7566a5 TT	61	static void append_option(const char *cmd, const char opt, int max_length)
	62	{
	63	int i;
	64
	65	for (i = 0; cmd[i]; i++)
	66	;
	67
	68	if (i + 2 >= max_length)
	69	die("Too many options specified");
	70	cmd[i++] = opt;
	71	cmd[i] = NULL;
	72	}
	73
a087cc98	74	static int too_many_loose_objects(void)
2c3c4399 JH	75	{
	76	/*
	77	* Quickly check if a "gc" is needed, by estimating how
	78	* many loose objects there are. Because SHA-1 is evenly
	79	* distributed, we can check only one and get a reasonable
	80	* estimate.
	81	*/
	82	char path[PATH_MAX];
	83	const char *objdir = get_object_directory();
	84	DIR *dir;
	85	struct dirent *ent;
	86	int auto_threshold;
	87	int num_loose = 0;
	88	int needed = 0;
	89
17815501 JH	90	if (gc_auto_threshold <= 0)
	91	return 0;
	92
2c3c4399 JH	93	if (sizeof(path) <= snprintf(path, sizeof(path), "%s/17", objdir)) {
	94	warning("insanely long object directory %.*s", 50, objdir);
	95	return 0;
	96	}
	97	dir = opendir(path);
	98	if (!dir)
	99	return 0;
	100
	101	auto_threshold = (gc_auto_threshold + 255) / 256;
	102	while ((ent = readdir(dir)) != NULL) {
	103	if (strspn(ent->d_name, "0123456789abcdef") != 38 \|\|
	104	ent->d_name[38] != '\0')
	105	continue;
	106	if (++num_loose > auto_threshold) {
	107	needed = 1;
	108	break;
	109	}
	110	}
	111	closedir(dir);
	112	return needed;
	113	}
	114
17815501 JH	115	static int too_many_packs(void)
	116	{
	117	struct packed_git *p;
	118	int cnt;
	119
	120	if (gc_auto_pack_limit <= 0)
	121	return 0;
	122
	123	prepare_packed_git();
	124	for (cnt = 0, p = packed_git; p; p = p->next) {
	125	char path[PATH_MAX];
	126	size_t len;
	127	int keep;
	128
	129	if (!p->pack_local)
	130	continue;
	131	len = strlen(p->pack_name);
	132	if (PATH_MAX <= len + 1)
	133	continue; /* oops, give up */
	134	memcpy(path, p->pack_name, len-5);
	135	memcpy(path + len - 5, ".keep", 6);
	136	keep = access(p->pack_name, F_OK) && (errno == ENOENT);
	137	if (keep)
	138	continue;
	139	/*
	140	* Perhaps check the size of the pack and count only
	141	* very small ones here?
	142	*/
	143	cnt++;
	144	}
	145	return gc_auto_pack_limit <= cnt;
	146	}
	147
a087cc98 JH	148	static int need_to_gc(void)
	149	{
	150	/*
17815501 JH	151	* Setting gc.auto and gc.autopacklimit to 0 or negative can
17815501 JH	152	* disable the automatic gc.
a087cc98	153	*/
17815501	154	if (gc_auto_threshold <= 0 && gc_auto_pack_limit <= 0)
95143f9e JH	155	return 0;
95143f9e JH	156
17815501 JH	157	/*
	158	* If there are too many loose objects, but not too many
	159	* packs, we run "repack -d -l". If there are too many packs,
	160	* we run "repack -A -d -l". Otherwise we tell the caller
	161	* there is no need.
	162	*/
17815501	163	if (too_many_packs())
729f5045	164	append_option(argv_repack, "-A", MAX_ADD);
17815501 JH	165	else if (!too_many_loose_objects())
17815501 JH	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	{
6757ada4	172	int prune = 0;
44c637c8	173	int aggressive = 0;
2c3c4399	174	int auto_gc = 0;
0d7566a5	175	char buf[80];
6757ada4	176
44c637c8	177	struct option builtin_gc_options[] = {
0aab4abd	178	OPT_BOOLEAN(0, "prune", &prune, "prune unreferenced objects"),
44c637c8 JB	179	OPT_BOOLEAN(0, "aggressive", &aggressive, "be more thorough (increased runtime)"),
	180	OPT_BOOLEAN(0, "auto", &auto_gc, "enable auto-gc mode"),
	181	OPT_END()
	182	};
	183
6757ada4 JB	184	git_config(gc_config);
	185
	186	if (pack_refs < 0)
	187	pack_refs = !is_bare_repository();
	188
44c637c8 JB	189	argc = parse_options(argc, argv, builtin_gc_options, builtin_gc_usage, 0);
	190	if (argc > 0)
	191	usage_with_options(builtin_gc_usage, builtin_gc_options);
	192
	193	if (aggressive) {
	194	append_option(argv_repack, "-f", MAX_ADD);
	195	if (aggressive_window > 0) {
	196	sprintf(buf, "--window=%d", aggressive_window);
	197	append_option(argv_repack, buf, MAX_ADD);
2c3c4399	198	}
6757ada4	199	}
6757ada4	200
2c3c4399 JH	201	if (auto_gc) {
	202	/*
	203	* Auto-gc should be least intrusive as possible.
	204	*/
	205	prune = 0;
2c3c4399 JH	206	if (!need_to_gc())
2c3c4399 JH	207	return 0;
7ec43959	208	fprintf(stderr, "Auto packing your repository for optimum "
dd8b883a JK	209	"performance. You may also\n"
	210	"run \"git gc\" manually. See "
	211	"\"git help gc\" for more information.\n");
edb0e04e BC	212	} else {
	213	/*
	214	* Use safer (for shared repos) "-A" option to
	215	* repack when not pruning. Auto-gc makes its
	216	* own decision.
	217	*/
	218	if (prune)
	219	append_option(argv_repack, "-a", MAX_ADD);
	220	else
	221	append_option(argv_repack, "-A", MAX_ADD);
2c3c4399 JH	222	}
2c3c4399 JH	223
6757ada4 JB	224	if (pack_refs && run_command_v_opt(argv_pack_refs, RUN_GIT_CMD))
	225	return error(FAILED_RUN, argv_pack_refs[0]);
	226
	227	if (run_command_v_opt(argv_reflog, RUN_GIT_CMD))
	228	return error(FAILED_RUN, argv_reflog[0]);
	229
	230	if (run_command_v_opt(argv_repack, RUN_GIT_CMD))
	231	return error(FAILED_RUN, argv_repack[0]);
	232
	233	if (prune && run_command_v_opt(argv_prune, RUN_GIT_CMD))
	234	return error(FAILED_RUN, argv_prune[0]);
	235
	236	if (run_command_v_opt(argv_rerere, RUN_GIT_CMD))
	237	return error(FAILED_RUN, argv_rerere[0]);
	238
a087cc98 JH	239	if (auto_gc && too_many_loose_objects())
	240	warning("There are too many unreachable loose objects; "
	241	"run 'git prune' to remove them.");
	242
6757ada4 JB	243	return 0;
6757ada4 JB	244	}