git-commit-vandalism/builtin/multi-pack-index.c

185 lines
5.0 KiB
C
Raw Normal View History

#include "builtin.h"
#include "cache.h"
#include "config.h"
#include "parse-options.h"
#include "midx.h"
#include "trace2.h"
#include "object-store.h"
#define BUILTIN_MIDX_WRITE_USAGE \
N_("git multi-pack-index [<options>] write [--preferred-pack=<pack>]")
#define BUILTIN_MIDX_VERIFY_USAGE \
N_("git multi-pack-index [<options>] verify")
#define BUILTIN_MIDX_EXPIRE_USAGE \
N_("git multi-pack-index [<options>] expire")
#define BUILTIN_MIDX_REPACK_USAGE \
N_("git multi-pack-index [<options>] repack [--batch-size=<size>]")
static char const * const builtin_multi_pack_index_write_usage[] = {
BUILTIN_MIDX_WRITE_USAGE,
NULL
};
static char const * const builtin_multi_pack_index_verify_usage[] = {
BUILTIN_MIDX_VERIFY_USAGE,
NULL
};
static char const * const builtin_multi_pack_index_expire_usage[] = {
BUILTIN_MIDX_EXPIRE_USAGE,
NULL
};
static char const * const builtin_multi_pack_index_repack_usage[] = {
BUILTIN_MIDX_REPACK_USAGE,
NULL
};
static char const * const builtin_multi_pack_index_usage[] = {
BUILTIN_MIDX_WRITE_USAGE,
BUILTIN_MIDX_VERIFY_USAGE,
BUILTIN_MIDX_EXPIRE_USAGE,
BUILTIN_MIDX_REPACK_USAGE,
NULL
};
static struct opts_multi_pack_index {
const char *object_dir;
const char *preferred_pack;
multi-pack-index: prepare 'repack' subcommand In an environment where the multi-pack-index is useful, it is due to many pack-files and an inability to repack the object store into a single pack-file. However, it is likely that many of these pack-files are rather small, and could be repacked into a slightly larger pack-file without too much effort. It may also be important to ensure the object store is highly available and the repack operation does not interrupt concurrent git commands. Introduce a 'repack' subcommand to 'git multi-pack-index' that takes a '--batch-size' option. The subcommand will inspect the multi-pack-index for referenced pack-files whose size is smaller than the batch size, until collecting a list of pack-files whose sizes sum to larger than the batch size. Then, a new pack-file will be created containing the objects from those pack-files that are referenced by the multi-pack-index. The resulting pack is likely to actually be smaller than the batch size due to compression and the fact that there may be objects in the pack- files that have duplicate copies in other pack-files. The current change introduces the command-line arguments, and we add a test that ensures we parse these options properly. Since we specify a small batch size, we will guarantee that future implementations do not change the list of pack-files. In addition, we hard-code the modified times of the packs in the pack directory to ensure the list of packs sorted by modified time matches the order if sorted by size (ascending). This will be important in a future test. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-11 01:35:26 +02:00
unsigned long batch_size;
unsigned flags;
} opts;
static struct option common_opts[] = {
OPT_FILENAME(0, "object-dir", &opts.object_dir,
N_("object directory containing set of packfile and pack-index pairs")),
OPT_BIT(0, "progress", &opts.flags, N_("force progress reporting"), MIDX_PROGRESS),
OPT_END(),
};
static struct option *add_common_options(struct option *prev)
{
return parse_options_concat(common_opts, prev);
}
static int cmd_multi_pack_index_write(int argc, const char **argv)
{
struct option *options;
static struct option builtin_multi_pack_index_write_options[] = {
OPT_STRING(0, "preferred-pack", &opts.preferred_pack,
N_("preferred-pack"),
N_("pack for reuse when computing a multi-pack bitmap")),
OPT_END(),
};
options = add_common_options(builtin_multi_pack_index_write_options);
trace2_cmd_mode(argv[0]);
argc = parse_options(argc, argv, NULL,
options, builtin_multi_pack_index_write_usage,
PARSE_OPT_KEEP_UNKNOWN);
if (argc)
usage_with_options(builtin_multi_pack_index_write_usage,
options);
FREE_AND_NULL(options);
return write_midx_file(opts.object_dir, opts.preferred_pack,
opts.flags);
}
static int cmd_multi_pack_index_verify(int argc, const char **argv)
{
struct option *options = common_opts;
trace2_cmd_mode(argv[0]);
argc = parse_options(argc, argv, NULL,
options, builtin_multi_pack_index_verify_usage,
PARSE_OPT_KEEP_UNKNOWN);
if (argc)
usage_with_options(builtin_multi_pack_index_verify_usage,
options);
return verify_midx_file(the_repository, opts.object_dir, opts.flags);
}
static int cmd_multi_pack_index_expire(int argc, const char **argv)
{
struct option *options = common_opts;
trace2_cmd_mode(argv[0]);
argc = parse_options(argc, argv, NULL,
options, builtin_multi_pack_index_expire_usage,
PARSE_OPT_KEEP_UNKNOWN);
if (argc)
usage_with_options(builtin_multi_pack_index_expire_usage,
options);
return expire_midx_packs(the_repository, opts.object_dir, opts.flags);
}
static int cmd_multi_pack_index_repack(int argc, const char **argv)
{
struct option *options;
static struct option builtin_multi_pack_index_repack_options[] = {
multi-pack-index: prepare 'repack' subcommand In an environment where the multi-pack-index is useful, it is due to many pack-files and an inability to repack the object store into a single pack-file. However, it is likely that many of these pack-files are rather small, and could be repacked into a slightly larger pack-file without too much effort. It may also be important to ensure the object store is highly available and the repack operation does not interrupt concurrent git commands. Introduce a 'repack' subcommand to 'git multi-pack-index' that takes a '--batch-size' option. The subcommand will inspect the multi-pack-index for referenced pack-files whose size is smaller than the batch size, until collecting a list of pack-files whose sizes sum to larger than the batch size. Then, a new pack-file will be created containing the objects from those pack-files that are referenced by the multi-pack-index. The resulting pack is likely to actually be smaller than the batch size due to compression and the fact that there may be objects in the pack- files that have duplicate copies in other pack-files. The current change introduces the command-line arguments, and we add a test that ensures we parse these options properly. Since we specify a small batch size, we will guarantee that future implementations do not change the list of pack-files. In addition, we hard-code the modified times of the packs in the pack directory to ensure the list of packs sorted by modified time matches the order if sorted by size (ascending). This will be important in a future test. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-11 01:35:26 +02:00
OPT_MAGNITUDE(0, "batch-size", &opts.batch_size,
N_("during repack, collect pack-files of smaller size into a batch that is larger than this size")),
OPT_END(),
};
options = add_common_options(builtin_multi_pack_index_repack_options);
trace2_cmd_mode(argv[0]);
argc = parse_options(argc, argv, NULL,
options,
builtin_multi_pack_index_repack_usage,
PARSE_OPT_KEEP_UNKNOWN);
if (argc)
usage_with_options(builtin_multi_pack_index_repack_usage,
options);
FREE_AND_NULL(options);
return midx_repack(the_repository, opts.object_dir,
(size_t)opts.batch_size, opts.flags);
}
int cmd_multi_pack_index(int argc, const char **argv,
const char *prefix)
{
struct option *builtin_multi_pack_index_options = common_opts;
git_config(git_default_config, NULL);
if (isatty(2))
opts.flags |= MIDX_PROGRESS;
argc = parse_options(argc, argv, prefix,
builtin_multi_pack_index_options,
builtin_multi_pack_index_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!opts.object_dir)
opts.object_dir = get_object_directory();
if (argc == 0)
goto usage;
multi-pack-index: prepare 'repack' subcommand In an environment where the multi-pack-index is useful, it is due to many pack-files and an inability to repack the object store into a single pack-file. However, it is likely that many of these pack-files are rather small, and could be repacked into a slightly larger pack-file without too much effort. It may also be important to ensure the object store is highly available and the repack operation does not interrupt concurrent git commands. Introduce a 'repack' subcommand to 'git multi-pack-index' that takes a '--batch-size' option. The subcommand will inspect the multi-pack-index for referenced pack-files whose size is smaller than the batch size, until collecting a list of pack-files whose sizes sum to larger than the batch size. Then, a new pack-file will be created containing the objects from those pack-files that are referenced by the multi-pack-index. The resulting pack is likely to actually be smaller than the batch size due to compression and the fact that there may be objects in the pack- files that have duplicate copies in other pack-files. The current change introduces the command-line arguments, and we add a test that ensures we parse these options properly. Since we specify a small batch size, we will guarantee that future implementations do not change the list of pack-files. In addition, we hard-code the modified times of the packs in the pack directory to ensure the list of packs sorted by modified time matches the order if sorted by size (ascending). This will be important in a future test. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-06-11 01:35:26 +02:00
if (!strcmp(argv[0], "repack"))
return cmd_multi_pack_index_repack(argc, argv);
else if (!strcmp(argv[0], "write"))
return cmd_multi_pack_index_write(argc, argv);
else if (!strcmp(argv[0], "verify"))
return cmd_multi_pack_index_verify(argc, argv);
else if (!strcmp(argv[0], "expire"))
return cmd_multi_pack_index_expire(argc, argv);
else {
error(_("unrecognized subcommand: %s"), argv[0]);
usage:
usage_with_options(builtin_multi_pack_index_usage,
builtin_multi_pack_index_options);
}
}