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 "repository.h"
#include "config.h"
#include "tempfile.h"
#include "lockfile.h"
#include "parse-options.h"
#include "run-command.h"
#include "sigchain.h"
#include "argv-array.h"
#include "commit.h"
#include "commit-graph.h"
#include "packfile.h"
#include "object-store.h"
#include "pack.h"
#include "pack-objects.h"
#include "blob.h"
#include "tree.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 prune_reflogs = 1;
static int aggressive_depth = 50;
static int aggressive_window = 250;
static int gc_auto_threshold = 6700;
static int gc_auto_pack_limit = 50;
static int gc_write_commit_graph;
static int detach_auto = 1;
static timestamp_t gc_log_expire_time;
static const char *gc_log_expire = "1.day.ago";
static const char *prune_expire = "2.weeks.ago";
static const char *prune_worktrees_expire = "3.months.ago";
static unsigned long big_pack_threshold;
static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE;

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 prune_worktrees = ARGV_ARRAY_INIT;
static struct argv_array rerere = ARGV_ARRAY_INIT;

static struct tempfile *pidfile;
static struct lock_file log_lock;

static struct string_list pack_garbage = STRING_LIST_INIT_DUP;

static void clean_pack_garbage(void)
{
	int i;
	for (i = 0; i < pack_garbage.nr; i++)
		unlink_or_warn(pack_garbage.items[i].string);
	string_list_clear(&pack_garbage, 0);
}

static void report_pack_garbage(unsigned seen_bits, const char *path)
{
	if (seen_bits == PACKDIR_FILE_IDX)
		string_list_append(&pack_garbage, path);
}

static void process_log_file(void)
{
	struct stat st;
	if (fstat(get_lock_file_fd(&log_lock), &st)) {
		/*
		 * Perhaps there was an i/o error or another
		 * unlikely situation.  Try to make a note of
		 * this in gc.log along with any existing
		 * messages.
		 */
		int saved_errno = errno;
		fprintf(stderr, _("Failed to fstat %s: %s"),
			get_tempfile_path(log_lock.tempfile),
			strerror(saved_errno));
		fflush(stderr);
		commit_lock_file(&log_lock);
		errno = saved_errno;
	} else if (st.st_size) {
		/* There was some error recorded in the lock file */
		commit_lock_file(&log_lock);
	} else {
		/* No error, clean up any old gc.log */
		unlink(git_path("gc.log"));
		rollback_lock_file(&log_lock);
	}
}

static void process_log_file_at_exit(void)
{
	fflush(stderr);
	process_log_file();
}

static void process_log_file_on_signal(int signo)
{
	process_log_file();
	sigchain_pop(signo);
	raise(signo);
}

static void gc_config(void)
{
	const char *value;

	if (!git_config_get_value("gc.packrefs", &value)) {
		if (value && !strcmp(value, "notbare"))
			pack_refs = -1;
		else
			pack_refs = git_config_bool("gc.packrefs", value);
	}

	git_config_get_int("gc.aggressivewindow", &aggressive_window);
	git_config_get_int("gc.aggressivedepth", &aggressive_depth);
	git_config_get_int("gc.auto", &gc_auto_threshold);
	git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
	git_config_get_bool("gc.writecommitgraph", &gc_write_commit_graph);
	git_config_get_bool("gc.autodetach", &detach_auto);
	git_config_get_expiry("gc.pruneexpire", &prune_expire);
	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
	git_config_get_expiry("gc.logexpiry", &gc_log_expire);

	git_config_get_ulong("gc.bigpackthreshold", &big_pack_threshold);
	git_config_get_ulong("pack.deltacachesize", &max_delta_cache_size);

	git_config(git_default_config, 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.
	 */
	DIR *dir;
	struct dirent *ent;
	int auto_threshold;
	int num_loose = 0;
	int needed = 0;

	if (gc_auto_threshold <= 0)
		return 0;

	dir = opendir(git_path("objects/17"));
	if (!dir)
		return 0;

	auto_threshold = DIV_ROUND_UP(gc_auto_threshold, 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 struct packed_git *find_base_packs(struct string_list *packs,
					  unsigned long limit)
{
	struct packed_git *p, *base = NULL;

	for (p = get_packed_git(the_repository); p; p = p->next) {
		if (!p->pack_local)
			continue;
		if (limit) {
			if (p->pack_size >= limit)
				string_list_append(packs, p->pack_name);
		} else if (!base || base->pack_size < p->pack_size) {
			base = p;
		}
	}

	if (base)
		string_list_append(packs, base->pack_name);

	return base;
}

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

	if (gc_auto_pack_limit <= 0)
		return 0;

	for (cnt = 0, p = get_packed_git(the_repository); 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 uint64_t total_ram(void)
{
#if defined(HAVE_SYSINFO)
	struct sysinfo si;

	if (!sysinfo(&si))
		return si.totalram;
#elif defined(HAVE_BSD_SYSCTL) && (defined(HW_MEMSIZE) || defined(HW_PHYSMEM))
	int64_t physical_memory;
	int mib[2];
	size_t length;

	mib[0] = CTL_HW;
# if defined(HW_MEMSIZE)
	mib[1] = HW_MEMSIZE;
# else
	mib[1] = HW_PHYSMEM;
# endif
	length = sizeof(int64_t);
	if (!sysctl(mib, 2, &physical_memory, &length, NULL, 0))
		return physical_memory;
#elif defined(GIT_WINDOWS_NATIVE)
	MEMORYSTATUSEX memInfo;

	memInfo.dwLength = sizeof(MEMORYSTATUSEX);
	if (GlobalMemoryStatusEx(&memInfo))
		return memInfo.ullTotalPhys;
#endif
	return 0;
}

static uint64_t estimate_repack_memory(struct packed_git *pack)
{
	unsigned long nr_objects = approximate_object_count();
	size_t os_cache, heap;

	if (!pack || !nr_objects)
		return 0;

	/*
	 * First we have to scan through at least one pack.
	 * Assume enough room in OS file cache to keep the entire pack
	 * or we may accidentally evict data of other processes from
	 * the cache.
	 */
	os_cache = pack->pack_size + pack->index_size;
	/* then pack-objects needs lots more for book keeping */
	heap = sizeof(struct object_entry) * nr_objects;
	/*
	 * internal rev-list --all --objects takes up some memory too,
	 * let's say half of it is for blobs
	 */
	heap += sizeof(struct blob) * nr_objects / 2;
	/*
	 * and the other half is for trees (commits and tags are
	 * usually insignificant)
	 */
	heap += sizeof(struct tree) * nr_objects / 2;
	/* and then obj_hash[], underestimated in fact */
	heap += sizeof(struct object *) * nr_objects;
	/* revindex is used also */
	heap += sizeof(struct revindex_entry) * nr_objects;
	/*
	 * read_sha1_file() (either at delta calculation phase, or
	 * writing phase) also fills up the delta base cache
	 */
	heap += delta_base_cache_limit;
	/* and of course pack-objects has its own delta cache */
	heap += max_delta_cache_size;

	return os_cache + heap;
}

static int keep_one_pack(struct string_list_item *item, void *data)
{
	argv_array_pushf(&repack, "--keep-pack=%s", basename(item->string));
	return 0;
}

static void add_repack_all_option(struct string_list *keep_pack)
{
	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);
	}

	if (keep_pack)
		for_each_string_list(keep_pack, keep_one_pack, NULL);
}

static void add_repack_incremental_option(void)
{
       argv_array_push(&repack, "--no-write-bitmap-index");
}

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()) {
		struct string_list keep_pack = STRING_LIST_INIT_NODUP;

		if (big_pack_threshold) {
			find_base_packs(&keep_pack, big_pack_threshold);
			if (keep_pack.nr >= gc_auto_pack_limit) {
				big_pack_threshold = 0;
				string_list_clear(&keep_pack, 0);
				find_base_packs(&keep_pack, 0);
			}
		} else {
			struct packed_git *p = find_base_packs(&keep_pack, 0);
			uint64_t mem_have, mem_want;

			mem_have = total_ram();
			mem_want = estimate_repack_memory(p);

			/*
			 * Only allow 1/2 of memory for pack-objects, leave
			 * the rest for the OS and other processes in the
			 * system.
			 */
			if (!mem_have || mem_want < mem_have / 2)
				string_list_clear(&keep_pack, 0);
		}

		add_repack_all_option(&keep_pack);
		string_list_clear(&keep_pack, 0);
	} else if (too_many_loose_objects())
		add_repack_incremental_option();
	else
		return 0;

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

/* return NULL on success, else hostname running the gc */
static const char *lock_repo_for_gc(int force, pid_t* ret_pid)
{
	struct lock_file lock = LOCK_INIT;
	char my_host[HOST_NAME_MAX + 1];
	struct strbuf sb = STRBUF_INIT;
	struct stat st;
	uintmax_t pid;
	FILE *fp;
	int fd;
	char *pidfile_path;

	if (is_tempfile_active(pidfile))
		/* already locked */
		return NULL;

	if (xgethostname(my_host, sizeof(my_host)))
		xsnprintf(my_host, sizeof(my_host), "unknown");

	pidfile_path = git_pathdup("gc.pid");
	fd = hold_lock_file_for_update(&lock, pidfile_path,
				       LOCK_DIE_ON_ERROR);
	if (!force) {
		static char locking_host[HOST_NAME_MAX + 1];
		static char *scan_fmt;
		int should_exit;

		if (!scan_fmt)
			scan_fmt = xstrfmt("%s %%%ds", "%"SCNuMAX, HOST_NAME_MAX);
		fp = fopen(pidfile_path, "r");
		memset(locking_host, 0, sizeof(locking_host));
		should_exit =
			fp != NULL &&
			!fstat(fileno(fp), &st) &&
			/*
			 * 12 hour limit is very generous as gc should
			 * never take that long. On the other hand we
			 * don't really need a strict limit here,
			 * running gc --auto one day late is not a big
			 * problem. --force can be used in manual gc
			 * after the user verifies that no gc is
			 * running.
			 */
			time(NULL) - st.st_mtime <= 12 * 3600 &&
			fscanf(fp, scan_fmt, &pid, locking_host) == 2 &&
			/* be gentle to concurrent "gc" on remote hosts */
			(strcmp(locking_host, my_host) || !kill(pid, 0) || errno == EPERM);
		if (fp != NULL)
			fclose(fp);
		if (should_exit) {
			if (fd >= 0)
				rollback_lock_file(&lock);
			*ret_pid = pid;
			free(pidfile_path);
			return locking_host;
		}
	}

	strbuf_addf(&sb, "%"PRIuMAX" %s",
		    (uintmax_t) getpid(), my_host);
	write_in_full(fd, sb.buf, sb.len);
	strbuf_release(&sb);
	commit_lock_file(&lock);
	pidfile = register_tempfile(pidfile_path);
	free(pidfile_path);
	return NULL;
}

static int report_last_gc_error(void)
{
	struct strbuf sb = STRBUF_INIT;
	int ret = 0;
	struct stat st;
	char *gc_log_path = git_pathdup("gc.log");

	if (stat(gc_log_path, &st)) {
		if (errno == ENOENT)
			goto done;

		ret = error_errno(_("Can't stat %s"), gc_log_path);
		goto done;
	}

	if (st.st_mtime < gc_log_expire_time)
		goto done;

	ret = strbuf_read_file(&sb, gc_log_path, 0);
	if (ret > 0)
		ret = error(_("The last gc run reported the following. "
			       "Please correct the root cause\n"
			       "and remove %s.\n"
			       "Automatic cleanup will not be performed "
			       "until the file is removed.\n\n"
			       "%s"),
			    gc_log_path, sb.buf);
	strbuf_release(&sb);
done:
	free(gc_log_path);
	return ret;
}

static int gc_before_repack(void)
{
	if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD))
		return error(FAILED_RUN, pack_refs_cmd.argv[0]);

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

	pack_refs = 0;
	prune_reflogs = 0;
	return 0;
}

int cmd_gc(int argc, const char **argv, const char *prefix)
{
	int aggressive = 0;
	int auto_gc = 0;
	int quiet = 0;
	int force = 0;
	const char *name;
	pid_t pid;
	int daemonized = 0;
	int keep_base_pack = -1;
	timestamp_t dummy;

	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_F(0, "auto", &auto_gc, N_("enable auto-gc mode"),
			   PARSE_OPT_NOCOMPLETE),
		OPT_BOOL_F(0, "force", &force,
			   N_("force running gc even if there may be another gc running"),
			   PARSE_OPT_NOCOMPLETE),
		OPT_BOOL(0, "keep-largest-pack", &keep_base_pack,
			 N_("repack all other packs except the largest pack")),
		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(&prune_worktrees, "worktree", "prune", "--expire", NULL);
	argv_array_pushl(&rerere, "rerere", "gc", NULL);

	/* default expiry time, overwritten in gc_config */
	gc_config();
	if (parse_expiry_date(gc_log_expire, &gc_log_expire_time))
		die(_("failed to parse gc.logexpiry value %s"), gc_log_expire);

	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 (prune_expire && parse_expiry_date(prune_expire, &dummy))
		die(_("failed to parse prune expiry value %s"), prune_expire);

	if (aggressive) {
		argv_array_push(&repack, "-f");
		if (aggressive_depth > 0)
			argv_array_pushf(&repack, "--depth=%d", aggressive_depth);
		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) {
			if (detach_auto)
				fprintf(stderr, _("Auto packing the repository in background for optimum performance.\n"));
			else
				fprintf(stderr, _("Auto packing the repository for optimum performance.\n"));
			fprintf(stderr, _("See \"git help gc\" for manual housekeeping.\n"));
		}
		if (detach_auto) {
			if (report_last_gc_error())
				return -1;

			if (lock_repo_for_gc(force, &pid))
				return 0;
			if (gc_before_repack())
				return -1;
			delete_tempfile(&pidfile);

			/*
			 * failure to daemonize is ok, we'll continue
			 * in foreground
			 */
			daemonized = !daemonize();
		}
	} else {
		struct string_list keep_pack = STRING_LIST_INIT_NODUP;

		if (keep_base_pack != -1) {
			if (keep_base_pack)
				find_base_packs(&keep_pack, 0);
		} else if (big_pack_threshold) {
			find_base_packs(&keep_pack, big_pack_threshold);
		}

		add_repack_all_option(&keep_pack);
		string_list_clear(&keep_pack, 0);
	}

	name = lock_repo_for_gc(force, &pid);
	if (name) {
		if (auto_gc)
			return 0; /* be quiet on --auto */
		die(_("gc is already running on machine '%s' pid %"PRIuMAX" (use --force if not)"),
		    name, (uintmax_t)pid);
	}

	if (daemonized) {
		hold_lock_file_for_update(&log_lock,
					  git_path("gc.log"),
					  LOCK_DIE_ON_ERROR);
		dup2(get_lock_file_fd(&log_lock), 2);
		sigchain_push_common(process_log_file_on_signal);
		atexit(process_log_file_at_exit);
	}

	if (gc_before_repack())
		return -1;

	if (!repository_format_precious_objects) {
		close_all_packs(the_repository->objects);
		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 (repository_format_partial_clone)
				argv_array_push(&prune,
						"--exclude-promisor-objects");
			if (run_command_v_opt(prune.argv, RUN_GIT_CMD))
				return error(FAILED_RUN, prune.argv[0]);
		}
	}

	if (prune_worktrees_expire) {
		argv_array_push(&prune_worktrees, prune_worktrees_expire);
		if (run_command_v_opt(prune_worktrees.argv, RUN_GIT_CMD))
			return error(FAILED_RUN, prune_worktrees.argv[0]);
	}

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

	report_garbage = report_pack_garbage;
	reprepare_packed_git(the_repository);
	if (pack_garbage.nr > 0)
		clean_pack_garbage();

	if (gc_write_commit_graph)
		write_commit_graph_reachable(get_object_directory(), 0,
					     !daemonized);

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

	if (!daemonized)
		unlink(git_path("gc.log"));

	return 0;
}