mirror of
https://github.com/git/git
synced 2024-10-01 06:05:20 +00:00
bb514de356
The old code to reuse deltas from an existing packfile just tried to dump a whole segment of the pack verbatim. That's faster than the traditional way of actually adding objects to the packing list, but it didn't kick in very often. This new code is really going for a middle ground: do _some_ per-object work, but way less than we'd traditionally do. The general strategy of the new code is to make a bitmap of objects from the packfile we'll include, and then iterate over it, writing out each object exactly as it is in our on-disk pack, but _not_ adding it to our packlist (which costs memory, and increases the search space for deltas). One complication is that if we're omitting some objects, we can't set a delta against a base that we're not sending. So we have to check each object in try_partial_reuse() to make sure we have its delta. About performance, in the worst case we might have interleaved objects that we are sending or not sending, and we'd have as many chunks as objects. But in practice we send big chunks. For instance, packing torvalds/linux on GitHub servers now reused 6.5M objects, but only needed ~50k chunks. Helped-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Christian Couder <chriscool@tuxfamily.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
83 lines
2.5 KiB
C
83 lines
2.5 KiB
C
#ifndef PACK_BITMAP_H
|
|
#define PACK_BITMAP_H
|
|
|
|
#include "ewah/ewok.h"
|
|
#include "khash.h"
|
|
#include "pack.h"
|
|
#include "pack-objects.h"
|
|
|
|
struct commit;
|
|
struct repository;
|
|
struct rev_info;
|
|
|
|
struct bitmap_disk_header {
|
|
char magic[4];
|
|
uint16_t version;
|
|
uint16_t options;
|
|
uint32_t entry_count;
|
|
unsigned char checksum[GIT_MAX_RAWSZ];
|
|
};
|
|
|
|
static const char BITMAP_IDX_SIGNATURE[] = {'B', 'I', 'T', 'M'};
|
|
|
|
#define NEEDS_BITMAP (1u<<22)
|
|
|
|
enum pack_bitmap_opts {
|
|
BITMAP_OPT_FULL_DAG = 1,
|
|
BITMAP_OPT_HASH_CACHE = 4,
|
|
};
|
|
|
|
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 bitmap_index *prepare_bitmap_git(struct repository *r);
|
|
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 *,
|
|
show_reachable_fn show_reachable);
|
|
void test_bitmap_walk(struct rev_info *revs);
|
|
struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs);
|
|
int reuse_partial_packfile_from_bitmap(struct bitmap_index *,
|
|
struct packed_git **packfile,
|
|
uint32_t *entries,
|
|
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);
|
|
|
|
void bitmap_writer_show_progress(int show);
|
|
void bitmap_writer_set_checksum(unsigned char *sha1);
|
|
void bitmap_writer_build_type_index(struct packing_data *to_pack,
|
|
struct pack_idx_entry **index,
|
|
uint32_t index_nr);
|
|
void bitmap_writer_reuse_bitmaps(struct packing_data *to_pack);
|
|
void bitmap_writer_select_commits(struct commit **indexed_commits,
|
|
unsigned int indexed_commits_nr, int max_bitmaps);
|
|
void 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);
|
|
|
|
#endif
|