[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 = 50;
static 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)
			return config_error_nonbool(var);
		if (strcmp(value, "now")) {
			unsigned long now = approxidate("now");
			if (approxidate(value) >= now)
				return error("Invalid %s: '%s'", var, value);
		}
		prune_expire = xstrdup(value);
		return 0;
	}
	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) {
		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 run_hook(void)
{
	const char *argv[2];
	struct child_process hook;
	int ret;

	argv[0] = git_path("hooks/pre-auto-gc");
	argv[1] = NULL;

	if (access(argv[0], X_OK) < 0)
		return 0;

	memset(&hook, 0, sizeof(hook));
	hook.argv = argv;
	hook.no_stdin = 1;
	hook.stdout_to_stderr = 1;

	ret = start_command(&hook);
	if (ret) {
		warning("Could not spawn %s", argv[0]);
		return ret;
	}
	ret = finish_command(&hook);
	if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL)
		warning("%s exited due to uncaught signal", argv[0]);
	return ret;
}

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, "-A", MAX_ADD);
	else if (!too_many_loose_objects())
		return 0;

	if (run_hook())
		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;
	int quiet = 0;
	char buf[80];

	struct option builtin_gc_options[] = {
		OPT_BOOLEAN(0, "prune", &prune, "prune unreferenced objects (deprecated)"),
		OPT_BOOLEAN(0, "aggressive", &aggressive, "be more thorough (increased runtime)"),
		OPT_BOOLEAN(0, "auto", &auto_gc, "enable auto-gc mode"),
		OPT_BOOLEAN('q', "quiet", &quiet, "suppress progress reports"),
		OPT_END()
	};

	git_config(gc_config, NULL);

	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 (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 your repository for optimum "
			"performance. You may also\n"
			"run \"git gc\" manually. See "
			"\"git help gc\" for more information.\n");
	} 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]);

	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 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;
97063974	28	static int gc_auto_pack_limit = 50;
25ee9731	29	static 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 JS	59	if (!strcmp(var, "gc.pruneexpire")) {
	60	if (!value)
	61	return config_error_nonbool(var);
	62	if (strcmp(value, "now")) {
	63	unsigned long now = approxidate("now");
	64	if (approxidate(value) >= now)
	65	return error("Invalid %s: '%s'", var, value);
	66	}
	67	prune_expire = xstrdup(value);
	68	return 0;
	69	}
ef90d6d4	70	return git_default_config(var, value, cb);
6757ada4 JB	71	}
6757ada4 JB	72
0d7566a5 TT	73	static void append_option(const char *cmd, const char opt, int max_length)
	74	{
	75	int i;
	76
	77	for (i = 0; cmd[i]; i++)
	78	;
	79
	80	if (i + 2 >= max_length)
	81	die("Too many options specified");
	82	cmd[i++] = opt;
	83	cmd[i] = NULL;
	84	}
	85
a087cc98	86	static int too_many_loose_objects(void)
2c3c4399 JH	87	{
	88	/*
	89	* Quickly check if a "gc" is needed, by estimating how
	90	* many loose objects there are. Because SHA-1 is evenly
	91	* distributed, we can check only one and get a reasonable
	92	* estimate.
	93	*/
	94	char path[PATH_MAX];
	95	const char *objdir = get_object_directory();
	96	DIR *dir;
	97	struct dirent *ent;
	98	int auto_threshold;
	99	int num_loose = 0;
	100	int needed = 0;
	101
17815501 JH	102	if (gc_auto_threshold <= 0)
	103	return 0;
	104
2c3c4399 JH	105	if (sizeof(path) <= snprintf(path, sizeof(path), "%s/17", objdir)) {
	106	warning("insanely long object directory %.*s", 50, objdir);
	107	return 0;
	108	}
	109	dir = opendir(path);
	110	if (!dir)
	111	return 0;
	112
	113	auto_threshold = (gc_auto_threshold + 255) / 256;
	114	while ((ent = readdir(dir)) != NULL) {
	115	if (strspn(ent->d_name, "0123456789abcdef") != 38 \|\|
	116	ent->d_name[38] != '\0')
	117	continue;
	118	if (++num_loose > auto_threshold) {
	119	needed = 1;
	120	break;
	121	}
	122	}
	123	closedir(dir);
	124	return needed;
	125	}
	126
17815501 JH	127	static int too_many_packs(void)
	128	{
	129	struct packed_git *p;
	130	int cnt;
	131
	132	if (gc_auto_pack_limit <= 0)
	133	return 0;
	134
	135	prepare_packed_git();
	136	for (cnt = 0, p = packed_git; p; p = p->next) {
	137	char path[PATH_MAX];
	138	size_t len;
	139	int keep;
	140
	141	if (!p->pack_local)
	142	continue;
	143	len = strlen(p->pack_name);
	144	if (PATH_MAX <= len + 1)
	145	continue; /* oops, give up */
	146	memcpy(path, p->pack_name, len-5);
	147	memcpy(path + len - 5, ".keep", 6);
	148	keep = access(p->pack_name, F_OK) && (errno == ENOENT);
	149	if (keep)
	150	continue;
	151	/*
	152	* Perhaps check the size of the pack and count only
	153	* very small ones here?
	154	*/
	155	cnt++;
	156	}
	157	return gc_auto_pack_limit <= cnt;
	158	}
	159
bde30540 MV	160	static int run_hook(void)
	161	{
	162	const char *argv[2];
	163	struct child_process hook;
	164	int ret;
	165
	166	argv[0] = git_path("hooks/pre-auto-gc");
	167	argv[1] = NULL;
	168
	169	if (access(argv[0], X_OK) < 0)
	170	return 0;
	171
	172	memset(&hook, 0, sizeof(hook));
	173	hook.argv = argv;
	174	hook.no_stdin = 1;
	175	hook.stdout_to_stderr = 1;
	176
	177	ret = start_command(&hook);
	178	if (ret) {
	179	warning("Could not spawn %s", argv[0]);
	180	return ret;
	181	}
	182	ret = finish_command(&hook);
	183	if (ret == -ERR_RUN_COMMAND_WAITPID_SIGNAL)
	184	warning("%s exited due to uncaught signal", argv[0]);
	185	return ret;
	186	}
	187
a087cc98 JH	188	static int need_to_gc(void)
	189	{
	190	/*
b14d255b BC	191	* Setting gc.auto to 0 or negative can disable the
b14d255b BC	192	* automatic gc.
a087cc98	193	*/
b14d255b	194	if (gc_auto_threshold <= 0)
95143f9e JH	195	return 0;
95143f9e JH	196
17815501 JH	197	/*
	198	* If there are too many loose objects, but not too many
	199	* packs, we run "repack -d -l". If there are too many packs,
	200	* we run "repack -A -d -l". Otherwise we tell the caller
	201	* there is no need.
	202	*/
17815501	203	if (too_many_packs())
729f5045	204	append_option(argv_repack, "-A", MAX_ADD);
17815501 JH	205	else if (!too_many_loose_objects())
17815501 JH	206	return 0;
bde30540 MV	207
	208	if (run_hook())
	209	return 0;
95143f9e	210	return 1;
a087cc98 JH	211	}
a087cc98 JH	212
6757ada4 JB	213	int cmd_gc(int argc, const char *argv, const char prefix)
6757ada4 JB	214	{
6757ada4	215	int prune = 0;
44c637c8	216	int aggressive = 0;
2c3c4399	217	int auto_gc = 0;
a0c14cbb	218	int quiet = 0;
0d7566a5	219	char buf[80];
6757ada4	220
44c637c8	221	struct option builtin_gc_options[] = {
9e7d5019	222	OPT_BOOLEAN(0, "prune", &prune, "prune unreferenced objects (deprecated)"),
44c637c8 JB	223	OPT_BOOLEAN(0, "aggressive", &aggressive, "be more thorough (increased runtime)"),
44c637c8 JB	224	OPT_BOOLEAN(0, "auto", &auto_gc, "enable auto-gc mode"),
a0c14cbb	225	OPT_BOOLEAN('q', "quiet", &quiet, "suppress progress reports"),
44c637c8 JB	226	OPT_END()
	227	};
	228
ef90d6d4	229	git_config(gc_config, NULL);
6757ada4 JB	230
	231	if (pack_refs < 0)
	232	pack_refs = !is_bare_repository();
	233
44c637c8 JB	234	argc = parse_options(argc, argv, builtin_gc_options, builtin_gc_usage, 0);
	235	if (argc > 0)
	236	usage_with_options(builtin_gc_usage, builtin_gc_options);
	237
	238	if (aggressive) {
	239	append_option(argv_repack, "-f", MAX_ADD);
	240	if (aggressive_window > 0) {
	241	sprintf(buf, "--window=%d", aggressive_window);
	242	append_option(argv_repack, buf, MAX_ADD);
2c3c4399	243	}
6757ada4	244	}
a0c14cbb FL	245	if (quiet)
a0c14cbb FL	246	append_option(argv_repack, "-q", MAX_ADD);
6757ada4	247
2c3c4399 JH	248	if (auto_gc) {
	249	/*
	250	* Auto-gc should be least intrusive as possible.
	251	*/
2c3c4399 JH	252	if (!need_to_gc())
2c3c4399 JH	253	return 0;
7ec43959	254	fprintf(stderr, "Auto packing your repository for optimum "
dd8b883a JK	255	"performance. You may also\n"
	256	"run \"git gc\" manually. See "
	257	"\"git help gc\" for more information.\n");
a37cce3b BC	258	} else
a37cce3b BC	259	append_option(argv_repack, "-A", MAX_ADD);
2c3c4399	260
6757ada4 JB	261	if (pack_refs && run_command_v_opt(argv_pack_refs, RUN_GIT_CMD))
	262	return error(FAILED_RUN, argv_pack_refs[0]);
	263
	264	if (run_command_v_opt(argv_reflog, RUN_GIT_CMD))
	265	return error(FAILED_RUN, argv_reflog[0]);
	266
	267	if (run_command_v_opt(argv_repack, RUN_GIT_CMD))
	268	return error(FAILED_RUN, argv_repack[0]);
	269
25ee9731 JS	270	argv_prune[2] = prune_expire;
25ee9731 JS	271	if (run_command_v_opt(argv_prune, RUN_GIT_CMD))
6757ada4 JB	272	return error(FAILED_RUN, argv_prune[0]);
	273
	274	if (run_command_v_opt(argv_rerere, RUN_GIT_CMD))
	275	return error(FAILED_RUN, argv_rerere[0]);
	276
a087cc98 JH	277	if (auto_gc && too_many_loose_objects())
	278	warning("There are too many unreachable loose objects; "
	279	"run 'git prune' to remove them.");
	280
6757ada4 JB	281	return 0;
6757ada4 JB	282	}