git/builtin-prune-packed.c

87 lines
1.9 KiB
C
Raw Normal View History

#include "builtin.h"
#include "cache.h"
#include "progress.h"
#include "parse-options.h"
static const char * const prune_packed_usage[] = {
"git prune-packed [-n|--dry-run] [-q|--quiet]",
NULL
};
#define DRY_RUN 01
#define VERBOSE 02
static struct progress *progress;
static void prune_dir(int i, DIR *dir, char *pathname, int len, int opts)
{
struct dirent *de;
char hex[40];
sprintf(hex, "%02x", i);
while ((de = readdir(dir)) != NULL) {
unsigned char sha1[20];
if (strlen(de->d_name) != 38)
continue;
memcpy(hex+2, de->d_name, 38);
if (get_sha1_hex(hex, sha1))
continue;
if (!has_sha1_pack(sha1))
continue;
memcpy(pathname + len, de->d_name, 38);
if (opts & DRY_RUN)
printf("rm -f %s\n", pathname);
else
unlink_or_warn(pathname);
display_progress(progress, i + 1);
}
Create object subdirectories on demand This makes it possible to have a "sparse" git object subdirectory structure, something that has become much more attractive now that people use pack-files all the time. As a result of pack-files, a git object directory doesn't necessarily have any individual objects lying around, and in that case it's just wasting space to keep the empty first-level object directories around: on many filesystems the 256 empty directories will be aboue 1MB of diskspace. Even more importantly, after you re-pack a project that _used_ to be unpacked, you could be left with huge directories that no longer contain anything, but that waste space and take time to look through. With this change, "git prune-packed" can just do an rmdir() on the directories, and they'll get removed if empty, and re-created on demand. This patch also tries to fix up "write_sha1_from_fd()" to use the new common infrastructure for creating the object files, closing a hole where we might otherwise leave half-written objects in the object database. [jc: I unoptimized the part that really removes the fan-out directories to ease transition. init-db still wastes 1MB of diskspace to hold 256 empty fan-outs, and prune-packed rmdir()'s the grown but empty directories, but runs mkdir() immediately after that -- reducing the saving from 150KB to 146KB. These parts will be re-introduced when everybody has the on-demand capability.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-10-09 06:54:01 +08:00
pathname[len] = 0;
rmdir(pathname);
}
void prune_packed_objects(int opts)
{
int i;
static char pathname[PATH_MAX];
const char *dir = get_object_directory();
int len = strlen(dir);
if (opts == VERBOSE)
progress = start_progress_delay("Removing duplicate objects",
256, 95, 2);
if (len > PATH_MAX - 42)
die("impossible object directory");
memcpy(pathname, dir, len);
if (len && pathname[len-1] != '/')
pathname[len++] = '/';
for (i = 0; i < 256; i++) {
DIR *d;
display_progress(progress, i + 1);
sprintf(pathname + len, "%02x/", i);
d = opendir(pathname);
if (!d)
Create object subdirectories on demand This makes it possible to have a "sparse" git object subdirectory structure, something that has become much more attractive now that people use pack-files all the time. As a result of pack-files, a git object directory doesn't necessarily have any individual objects lying around, and in that case it's just wasting space to keep the empty first-level object directories around: on many filesystems the 256 empty directories will be aboue 1MB of diskspace. Even more importantly, after you re-pack a project that _used_ to be unpacked, you could be left with huge directories that no longer contain anything, but that waste space and take time to look through. With this change, "git prune-packed" can just do an rmdir() on the directories, and they'll get removed if empty, and re-created on demand. This patch also tries to fix up "write_sha1_from_fd()" to use the new common infrastructure for creating the object files, closing a hole where we might otherwise leave half-written objects in the object database. [jc: I unoptimized the part that really removes the fan-out directories to ease transition. init-db still wastes 1MB of diskspace to hold 256 empty fan-outs, and prune-packed rmdir()'s the grown but empty directories, but runs mkdir() immediately after that -- reducing the saving from 150KB to 146KB. These parts will be re-introduced when everybody has the on-demand capability.] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-10-09 06:54:01 +08:00
continue;
prune_dir(i, d, pathname, len + 3, opts);
closedir(d);
}
stop_progress(&progress);
}
int cmd_prune_packed(int argc, const char **argv, const char *prefix)
{
int opts = VERBOSE;
const struct option prune_packed_options[] = {
OPT_BIT('n', "dry-run", &opts, "dry run", DRY_RUN),
OPT_NEGBIT('q', "quiet", &opts, "be quiet", VERBOSE),
OPT_END()
};
argc = parse_options(argc, argv, prefix, prune_packed_options,
prune_packed_usage, 0);
prune_packed_objects(opts);
return 0;
}