1 files changed, 328 insertions, 98 deletions

diff --git a/builtin/gc.c b/builtin/gc.c
index 1a80702b3d..3c5eae0edf 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -11,73 +11,122 @@
  */
 
 #include "builtin.h"
-#include "cache.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 "packfile.h"
 
 #define FAILED_RUN "failed to run %s"
 
 static const char * const builtin_gc_usage[] = {
-	"git gc [options]",
+	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 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";
 
-#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 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 int gc_config(const char *var, const char *value, void *cb)
+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)
 {
-	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);
+	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);
 	}
-	return git_default_config(var, value, cb);
 }
 
-static void append_option(const char **cmd, const char *opt, int max_length)
+static void process_log_file_at_exit(void)
 {
-	int i;
+	fflush(stderr);
+	process_log_file();
+}
+
+static void process_log_file_on_signal(int signo)
+{
+	process_log_file();
+	sigchain_pop(signo);
+	raise(signo);
+}
 
-	for (i = 0; cmd[i]; i++)
-		;
+static void gc_config(void)
+{
+	const char *value;
 
-	if (i + 2 >= max_length)
-		die("Too many options specified");
-	cmd[i++] = opt;
-	cmd[i] = NULL;
+	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.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(git_default_config, NULL);
 }
 
 static int too_many_loose_objects(void)
@@ -88,8 +137,6 @@ static int too_many_loose_objects(void)
 	 * 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;
@@ -99,15 +146,11 @@ static int too_many_loose_objects(void)
 	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);
+	dir = opendir(git_path("objects/17"));
 	if (!dir)
 		return 0;
 
-	auto_threshold = (gc_auto_threshold + 255) / 256;
+	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')
@@ -141,7 +184,23 @@ static int too_many_packs(void)
 		 */
 		cnt++;
 	}
-	return gc_auto_pack_limit <= 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 void add_repack_incremental_option(void)
+{
+       argv_array_push(&repack, "--no-write-bitmap-index");
 }
 
 static int need_to_gc(void)
@@ -160,39 +219,166 @@ static int need_to_gc(void)
 	 * 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())
+		add_repack_all_option();
+	else if (too_many_loose_objects())
+		add_repack_incremental_option();
+	else
 		return 0;
 
-	if (run_hook(NULL, "pre-auto-gc", NULL))
+	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)
+{
+	static struct lock_file lock;
+	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;
-	char buf[80];
+	int force = 0;
+	const char *name;
+	pid_t pid;
+	int daemonized = 0;
 
 	struct option builtin_gc_options[] = {
-		OPT__QUIET(&quiet, "suppress progress reporting"),
-		{ OPTION_STRING, 0, "prune", &prune_expire, "date",
-			"prune unreferenced objects",
+		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_BOOLEAN(0, "aggressive", &aggressive, "be more thorough (increased runtime)"),
-		OPT_BOOLEAN(0, "auto", &auto_gc, "enable auto-gc mode"),
+		OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
+		OPT_BOOL(0, "auto", &auto_gc, N_("enable auto-gc mode")),
+		OPT_BOOL(0, "force", &force, N_("force running gc even if there may be another gc running")),
 		OPT_END()
 	};
 
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage_with_options(builtin_gc_usage, builtin_gc_options);
 
-	git_config(gc_config, NULL);
+	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();
@@ -203,15 +389,14 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		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);
-		}
+		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)
-		append_option(argv_repack, "-q", MAX_ADD);
+		argv_array_push(&repack, "-q");
 
 	if (auto_gc) {
 		/*
@@ -219,40 +404,85 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		 */
 		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."));
+		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
-		append_option(argv_repack,
-			      prune_expire && !strcmp(prune_expire, "now")
-			      ? "-a" : "-A",
-			      MAX_ADD);
+		add_repack_all_option();
+
+	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 (pack_refs && run_command_v_opt(argv_pack_refs, RUN_GIT_CMD))
-		return error(FAILED_RUN, argv_pack_refs[0]);
+	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 (run_command_v_opt(argv_reflog, RUN_GIT_CMD))
-		return error(FAILED_RUN, argv_reflog[0]);
+	if (gc_before_repack())
+		return -1;
 
-	if (run_command_v_opt(argv_repack, RUN_GIT_CMD))
-		return error(FAILED_RUN, argv_repack[0]);
+	if (!repository_format_precious_objects) {
+		if (run_command_v_opt(repack.argv, RUN_GIT_CMD))
+			return error(FAILED_RUN, repack.argv[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 (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(argv_rerere, RUN_GIT_CMD))
-		return error(FAILED_RUN, argv_rerere[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();
+	if (pack_garbage.nr > 0)
+		clean_pack_garbage();
 
 	if (auto_gc && too_many_loose_objects())
-		warning("There are too many unreachable loose objects; "
-			"run 'git prune' to remove them.");
+		warning(_("There are too many unreachable loose objects; "
+			"run 'git prune' to remove them."));
+
+	if (!daemonized)
+		unlink(git_path("gc.log"));
 
 	return 0;
 }