git/t/helper/test-read-midx.c
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

141 lines
3.1 KiB
C

#include "test-tool.h"
#include "hex.h"
#include "midx.h"
#include "repository.h"
#include "object-store-ll.h"
#include "pack-bitmap.h"
#include "packfile.h"
#include "setup.h"
#include "gettext.h"
static int read_midx_file(const char *object_dir, int show_objects)
{
uint32_t i;
struct multi_pack_index *m;
setup_git_directory();
m = load_multi_pack_index(object_dir, 1);
if (!m)
return 1;
printf("header: %08x %d %d %d %d\n",
m->signature,
m->version,
m->hash_len,
m->num_chunks,
m->num_packs);
printf("chunks:");
if (m->chunk_pack_names)
printf(" pack-names");
if (m->chunk_oid_fanout)
printf(" oid-fanout");
if (m->chunk_oid_lookup)
printf(" oid-lookup");
if (m->chunk_object_offsets)
printf(" object-offsets");
if (m->chunk_large_offsets)
printf(" large-offsets");
printf("\nnum_objects: %d\n", m->num_objects);
printf("packs:\n");
for (i = 0; i < m->num_packs; i++)
printf("%s\n", m->pack_names[i]);
printf("object-dir: %s\n", m->object_dir);
if (show_objects) {
struct object_id oid;
struct pack_entry e;
for (i = 0; i < m->num_objects; i++) {
nth_midxed_object_oid(&oid, m, i);
fill_midx_entry(the_repository, &oid, &e, m);
printf("%s %"PRIu64"\t%s\n",
oid_to_hex(&oid), e.offset, e.p->pack_name);
}
}
close_midx(m);
return 0;
}
static int read_midx_checksum(const char *object_dir)
{
struct multi_pack_index *m;
setup_git_directory();
m = load_multi_pack_index(object_dir, 1);
if (!m)
return 1;
printf("%s\n", hash_to_hex(get_midx_checksum(m)));
return 0;
}
static int read_midx_preferred_pack(const char *object_dir)
{
struct multi_pack_index *midx = NULL;
uint32_t preferred_pack;
setup_git_directory();
midx = load_multi_pack_index(object_dir, 1);
if (!midx)
return 1;
if (midx_preferred_pack(midx, &preferred_pack) < 0) {
warning(_("could not determine MIDX preferred pack"));
return 1;
}
printf("%s\n", midx->pack_names[preferred_pack]);
return 0;
}
static int read_midx_bitmapped_packs(const char *object_dir)
{
struct multi_pack_index *midx = NULL;
struct bitmapped_pack pack;
uint32_t i;
setup_git_directory();
midx = load_multi_pack_index(object_dir, 1);
if (!midx)
return 1;
for (i = 0; i < midx->num_packs; i++) {
if (nth_bitmapped_pack(the_repository, midx, &pack, i) < 0)
return 1;
printf("%s\n", pack_basename(pack.p));
printf(" bitmap_pos: %"PRIuMAX"\n", (uintmax_t)pack.bitmap_pos);
printf(" bitmap_nr: %"PRIuMAX"\n", (uintmax_t)pack.bitmap_nr);
}
close_midx(midx);
return 0;
}
int cmd__read_midx(int argc, const char **argv)
{
if (!(argc == 2 || argc == 3))
usage("read-midx [--show-objects|--checksum|--preferred-pack|--bitmap] <object-dir>");
if (!strcmp(argv[1], "--show-objects"))
return read_midx_file(argv[2], 1);
else if (!strcmp(argv[1], "--checksum"))
return read_midx_checksum(argv[2]);
else if (!strcmp(argv[1], "--preferred-pack"))
return read_midx_preferred_pack(argv[2]);
else if (!strcmp(argv[1], "--bitmap"))
return read_midx_bitmapped_packs(argv[2]);
return read_midx_file(argv[1], 0);
}