git-commit-vandalism/midx.h

59 lines
1.7 KiB
C
Raw Normal View History

#ifndef MIDX_H
#define MIDX_H
#include "repository.h"
struct object_id;
struct pack_entry;
struct repository;
#define GIT_TEST_MULTI_PACK_INDEX "GIT_TEST_MULTI_PACK_INDEX"
struct multi_pack_index {
struct multi_pack_index *next;
int fd;
const unsigned char *data;
size_t data_len;
uint32_t signature;
unsigned char version;
unsigned char hash_len;
unsigned char num_chunks;
uint32_t num_packs;
uint32_t num_objects;
int local;
const unsigned char *chunk_pack_names;
const uint32_t *chunk_oid_fanout;
const unsigned char *chunk_oid_lookup;
const unsigned char *chunk_object_offsets;
const unsigned char *chunk_large_offsets;
const char **pack_names;
struct packed_git **packs;
char object_dir[FLEX_ARRAY];
};
struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local);
int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id);
int bsearch_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result);
struct object_id *nth_midxed_object_oid(struct object_id *oid,
struct multi_pack_index *m,
uint32_t n);
int fill_midx_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e, struct multi_pack_index *m);
int midx_contains_pack(struct multi_pack_index *m, const char *idx_or_pack_name);
int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, int local);
int write_midx_file(const char *object_dir);
void clear_midx_file(struct repository *r);
int verify_midx_file(struct repository *r, const char *object_dir);
int expire_midx_packs(struct repository *r, const char *object_dir);
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
int midx_repack(struct repository *r, const char *object_dir, size_t batch_size);
void close_midx(struct multi_pack_index *m);
#endif