git/builtin/gc.c
Jeff King 234587fc87 gc: use argv-array for sub-commands
git-gc executes many sub-commands. The argument list for
some of these is constant, but for others we add more
arguments at runtime. The latter is implemented by allocating
a constant extra number of NULLs, and either using a custom
append function, or just referencing unused slots by number.

As of commit 7e52f56, which added two new arguments, it is
possible to exceed the constant number of slots for "repack"
by running "git gc --aggressive", causing "git gc" to die.

This patch converts all of the static argv lists to use
argv-array. In addition to fixing the overflow caused by
7e52f56, it has a few advantages:

  1. We can drop the custom append function (which,
     incidentally, had an off-by-one error exacerbating the
     static limit).

  2. We can drop the ugly magic numbers used when adding
     arguments to "prune".

  3. Adding further arguments will be easier; you can just
     add new "push" calls without worrying about increasing
     any static limits.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-04-18 16:17:42 -07:00

256 lines
6.4 KiB
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"
#include "argv-array.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";
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 rerere = ARGV_ARRAY_INIT;
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 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 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 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())
add_repack_all_option();
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;
struct option builtin_gc_options[] = {
OPT__QUIET(&quiet, "suppress progress reporting"),
{ 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()
};
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(&rerere, "rerere", "gc", NULL);
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) {
argv_array_push(&repack, "-f");
argv_array_push(&repack, "--depth=250");
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)
fprintf(stderr, _("Auto packing the repository for optimum performance.\n"));
else
fprintf(stderr,
_("Auto packing the repository for optimum performance. You may also\n"
"run \"git gc\" manually. See "
"\"git help gc\" for more information.\n"));
} else
add_repack_all_option();
if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD))
return error(FAILED_RUN, pack_refs_cmd.argv[0]);
if (run_command_v_opt(reflog.argv, RUN_GIT_CMD))
return error(FAILED_RUN, reflog.argv[0]);
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 (run_command_v_opt(prune.argv, RUN_GIT_CMD))
return error(FAILED_RUN, prune.argv[0]);
}
if (run_command_v_opt(rerere.argv, RUN_GIT_CMD))
return error(FAILED_RUN, rerere.argv[0]);
if (auto_gc && too_many_loose_objects())
warning(_("There are too many unreachable loose objects; "
"run 'git prune' to remove them."));
return 0;
}