git/midx.h
Taylor Blau 7f514b7a5e midx: read RIDX chunk when present
When a MIDX contains the new `RIDX` chunk, ensure that the reverse index
is read from it instead of the on-disk .rev file. Since we need to
encode the object order in the MIDX itself for correctness reasons,
there is no point in storing the same data again outside of the MIDX.

So, this patch stops writing separate .rev files, and reads it out of
the MIDX itself. This is possible to do with relatively little new code,
since the format of the RIDX chunk is identical to the data in the .rev
file. In other words, we can implement this by pointing the
`revindex_data` field at the reverse index chunk of the MIDX instead of
the .rev file without any other changes.

Note that we have two knobs that are adjusted for the new tests:
GIT_TEST_MIDX_WRITE_REV and GIT_TEST_MIDX_READ_RIDX. The former controls
whether the MIDX .rev is written at all, and the latter controls whether
we read the MIDX's RIDX chunk.

Both are necessary to ensure that the test added at the beginning of
this series continues to work. This is because we always need to write
the RIDX chunk in the MIDX in order to change its checksum, but we want
to make sure reading the existing .rev file still works (since the RIDX
chunk takes precedence by default).

Arguably this isn't a very interesting mode to test, because the
precedence rules mean that we'll always read the RIDX chunk over the
.rev file. But it makes it impossible for a user to induce corruption in
their repository by adjusting the test knobs (since if we had an
either/or knob they could stop writing the RIDX chunk, allowing them to
tweak the MIDX's object order without changing its checksum).

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Reviewed-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-01-27 12:07:53 -08:00

88 lines
2.9 KiB
C

#ifndef MIDX_H
#define MIDX_H
#include "repository.h"
#include "string-list.h"
struct object_id;
struct pack_entry;
struct repository;
#define GIT_TEST_MULTI_PACK_INDEX "GIT_TEST_MULTI_PACK_INDEX"
#define GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP \
"GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP"
struct multi_pack_index {
struct multi_pack_index *next;
const unsigned char *data;
size_t data_len;
const uint32_t *revindex_data;
const uint32_t *revindex_map;
size_t revindex_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 unsigned char *chunk_revindex;
const char **pack_names;
struct packed_git **packs;
char object_dir[FLEX_ARRAY];
};
#define MIDX_PROGRESS (1 << 0)
#define MIDX_WRITE_REV_INDEX (1 << 1)
#define MIDX_WRITE_BITMAP (1 << 2)
#define MIDX_WRITE_BITMAP_HASH_CACHE (1 << 3)
const unsigned char *get_midx_checksum(struct multi_pack_index *m);
void get_midx_filename(struct strbuf *out, const char *object_dir);
void get_midx_rev_filename(struct strbuf *out, struct multi_pack_index *m);
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);
off_t nth_midxed_offset(struct multi_pack_index *m, uint32_t pos);
uint32_t nth_midxed_pack_int_id(struct multi_pack_index *m, uint32_t pos);
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);
/*
* Variant of write_midx_file which writes a MIDX containing only the packs
* specified in packs_to_include.
*/
int write_midx_file(const char *object_dir,
const char *preferred_pack_name,
const char *refs_snapshot,
unsigned flags);
int write_midx_file_only(const char *object_dir,
struct string_list *packs_to_include,
const char *preferred_pack_name,
const char *refs_snapshot,
unsigned flags);
void clear_midx_file(struct repository *r);
int verify_midx_file(struct repository *r, const char *object_dir, unsigned flags);
int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags);
int midx_repack(struct repository *r, const char *object_dir, size_t batch_size, unsigned flags);
void close_midx(struct multi_pack_index *m);
#endif