git/pack-bitmap.h
Taylor Blau b1e3333068 midx: implement midx_preferred_pack()
When performing a binary search over the objects in a MIDX's bitmap
(i.e. in pseudo-pack order), the reader reconstructs the pseudo-pack
ordering using a combination of (a) the preferred pack, (b) the pack's
lexical position in the MIDX based on pack names, and (c) the object
offset within the pack.

In order to perform this binary search, the reader must know the
identity of the preferred pack. This could be stored in the MIDX, but
isn't for historical reasons, mostly because it can easily be inferred
at read-time by looking at the object in the first bit position and
finding out which pack it was selected from in the MIDX, like so:

    nth_midxed_pack_int_id(m, pack_pos_to_midx(m, 0));

In midx_to_pack_pos() which performs this binary search, we look up the
identity of the preferred pack before each search. This is relatively
quick, since it involves two table-driven lookups (one in the MIDX's
revindex for `pack_pos_to_midx()`, and another in the MIDX's object
table for `nth_midxed_pack_int_id()`).

But since the preferred pack does not change after the MIDX is written,
it is safe to cache this value on the MIDX itself.

Write a helper to do just that, and rewrite all of the existing
call-sites that care about the identity of the preferred pack in terms
of this new helper.

This will prepare us for a subsequent patch where we will need to binary
search through the MIDX's pseudo-pack order multiple times.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2023-12-14 14:38:08 -08:00

128 lines
3.9 KiB
C

#ifndef PACK_BITMAP_H
#define PACK_BITMAP_H
#include "ewah/ewok.h"
#include "khash.h"
#include "pack.h"
#include "pack-objects.h"
#include "string-list.h"
struct commit;
struct repository;
struct rev_info;
static const char BITMAP_IDX_SIGNATURE[] = {'B', 'I', 'T', 'M'};
struct bitmap_disk_header {
char magic[ARRAY_SIZE(BITMAP_IDX_SIGNATURE)];
uint16_t version;
uint16_t options;
uint32_t entry_count;
unsigned char checksum[GIT_MAX_RAWSZ];
};
#define NEEDS_BITMAP (1u<<22)
/*
* The width in bytes of a single triplet in the lookup table
* extension:
* (commit_pos, offset, xor_row)
*
* whose fields ar 32-, 64-, 32- bits wide, respectively.
*/
#define BITMAP_LOOKUP_TABLE_TRIPLET_WIDTH (16)
enum pack_bitmap_opts {
BITMAP_OPT_FULL_DAG = 0x1,
BITMAP_OPT_HASH_CACHE = 0x4,
BITMAP_OPT_LOOKUP_TABLE = 0x10,
};
enum pack_bitmap_flags {
BITMAP_FLAG_REUSE = 0x1
};
typedef int (*show_reachable_fn)(
const struct object_id *oid,
enum object_type type,
int flags,
uint32_t hash,
struct packed_git *found_pack,
off_t found_offset);
struct bitmap_index;
struct bitmapped_pack {
struct packed_git *p;
uint32_t bitmap_pos;
uint32_t bitmap_nr;
uint32_t pack_int_id; /* MIDX only */
};
struct bitmap_index *prepare_bitmap_git(struct repository *r);
struct bitmap_index *prepare_midx_bitmap_git(struct multi_pack_index *midx);
void count_bitmap_commit_list(struct bitmap_index *, uint32_t *commits,
uint32_t *trees, uint32_t *blobs, uint32_t *tags);
void traverse_bitmap_commit_list(struct bitmap_index *,
struct rev_info *revs,
show_reachable_fn show_reachable);
void test_bitmap_walk(struct rev_info *revs);
int test_bitmap_commits(struct repository *r);
int test_bitmap_hashes(struct repository *r);
#define GIT_TEST_PACK_USE_BITMAP_BOUNDARY_TRAVERSAL \
"GIT_TEST_PACK_USE_BITMAP_BOUNDARY_TRAVERSAL"
struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs,
int filter_provided_objects);
void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git,
struct bitmapped_pack **packs_out,
size_t *packs_nr_out,
struct bitmap **reuse_out);
int rebuild_existing_bitmaps(struct bitmap_index *, struct packing_data *mapping,
kh_oid_map_t *reused_bitmaps, int show_progress);
void free_bitmap_index(struct bitmap_index *);
int bitmap_walk_contains(struct bitmap_index *,
struct bitmap *bitmap, const struct object_id *oid);
/*
* After a traversal has been performed by prepare_bitmap_walk(), this can be
* queried to see if a particular object was reachable from any of the
* objects flagged as UNINTERESTING.
*/
int bitmap_has_oid_in_uninteresting(struct bitmap_index *, const struct object_id *oid);
off_t get_disk_usage_from_bitmap(struct bitmap_index *, struct rev_info *);
void bitmap_writer_show_progress(int show);
void bitmap_writer_set_checksum(const unsigned char *sha1);
void bitmap_writer_build_type_index(struct packing_data *to_pack,
struct pack_idx_entry **index,
uint32_t index_nr);
uint32_t *create_bitmap_mapping(struct bitmap_index *bitmap_git,
struct packing_data *mapping);
int rebuild_bitmap(const uint32_t *reposition,
struct ewah_bitmap *source,
struct bitmap *dest);
struct ewah_bitmap *bitmap_for_commit(struct bitmap_index *bitmap_git,
struct commit *commit);
void bitmap_writer_select_commits(struct commit **indexed_commits,
unsigned int indexed_commits_nr, int max_bitmaps);
int bitmap_writer_build(struct packing_data *to_pack);
void bitmap_writer_finish(struct pack_idx_entry **index,
uint32_t index_nr,
const char *filename,
uint16_t options);
char *midx_bitmap_filename(struct multi_pack_index *midx);
char *pack_bitmap_filename(struct packed_git *p);
int bitmap_is_midx(struct bitmap_index *bitmap_git);
const struct string_list *bitmap_preferred_tips(struct repository *r);
int bitmap_is_preferred_refname(struct repository *r, const char *refname);
int verify_bitmap_files(struct repository *r);
#endif