mirror of
https://github.com/git/git
synced 2024-10-06 00:29:28 +00:00
Merge branch 'jk/pack-revindex'
In-core storage of the reverse index for .pack files (which lets you go from a pack offset to an object name) has been streamlined. * jk/pack-revindex: pack-revindex: store entries directly in packed_git pack-revindex: drop hash table
This commit is contained in:
Junio C Hamano
commit
4fd1359158
2
cache.h
2
cache.h
|
|
@ -9,6 +9,7 @@
|
|||
#include "convert.h"
|
||||
#include "trace.h"
|
||||
#include "string-list.h"
|
||||
#include "pack-revindex.h"
|
||||
|
||||
#include SHA1_HEADER
|
||||
#ifndef platform_SHA_CTX
|
||||
|
|
@ -1299,6 +1300,7 @@ extern struct packed_git {
|
|||
freshened:1,
|
||||
do_not_close:1;
|
||||
unsigned char sha1[20];
|
||||
struct revindex_entry *revindex;
|
||||
/* something like ".git/objects/pack/xxxxx.pack" */
|
||||
char pack_name[FLEX_ARRAY]; /* more */
|
||||
} *packed_git;
|
||||
|
|
|
|||
|
|
@ -33,9 +33,6 @@ static struct bitmap_index {
|
|||
/* Packfile to which this bitmap index belongs to */
|
||||
struct packed_git *pack;
|
||||
|
||||
/* reverse index for the packfile */
|
||||
struct pack_revindex *reverse_index;
|
||||
|
||||
/*
|
||||
* Mark the first `reuse_objects` in the packfile as reused:
|
||||
* they will be sent as-is without using them for repacking
|
||||
|
|
@ -308,7 +305,7 @@ static int load_pack_bitmap(void)
|
|||
|
||||
bitmap_git.bitmaps = kh_init_sha1();
|
||||
bitmap_git.ext_index.positions = kh_init_sha1_pos();
|
||||
bitmap_git.reverse_index = revindex_for_pack(bitmap_git.pack);
|
||||
load_pack_revindex(bitmap_git.pack);
|
||||
|
||||
if (!(bitmap_git.commits = read_bitmap_1(&bitmap_git)) ||
|
||||
!(bitmap_git.trees = read_bitmap_1(&bitmap_git)) ||
|
||||
|
|
@ -380,7 +377,7 @@ static inline int bitmap_position_packfile(const unsigned char *sha1)
|
|||
if (!offset)
|
||||
return -1;
|
||||
|
||||
return find_revindex_position(bitmap_git.reverse_index, offset);
|
||||
return find_revindex_position(bitmap_git.pack, offset);
|
||||
}
|
||||
|
||||
static int bitmap_position(const unsigned char *sha1)
|
||||
|
|
@ -630,7 +627,7 @@ static void show_objects_for_type(
|
|||
if (pos + offset < bitmap_git.reuse_objects)
|
||||
continue;
|
||||
|
||||
entry = &bitmap_git.reverse_index->revindex[pos + offset];
|
||||
entry = &bitmap_git.pack->revindex[pos + offset];
|
||||
sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr);
|
||||
|
||||
if (bitmap_git.hashes)
|
||||
|
|
@ -804,7 +801,7 @@ int reuse_partial_packfile_from_bitmap(struct packed_git **packfile,
|
|||
return -1;
|
||||
|
||||
bitmap_git.reuse_objects = *entries = reuse_objects;
|
||||
*up_to = bitmap_git.reverse_index->revindex[reuse_objects].offset;
|
||||
*up_to = bitmap_git.pack->revindex[reuse_objects].offset;
|
||||
*packfile = bitmap_git.pack;
|
||||
|
||||
return 0;
|
||||
|
|
@ -1038,7 +1035,7 @@ int rebuild_existing_bitmaps(struct packing_data *mapping,
|
|||
struct revindex_entry *entry;
|
||||
struct object_entry *oe;
|
||||
|
||||
entry = &bitmap_git.reverse_index->revindex[i];
|
||||
entry = &bitmap_git.pack->revindex[i];
|
||||
sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr);
|
||||
oe = packlist_find(mapping, sha1, NULL);
|
||||
|
||||
|
|
|
|||
|
|
@ -8,52 +8,13 @@
|
|||
* size is easily available by examining the pack entry header). It is
|
||||
* also rather expensive to find the sha1 for an object given its offset.
|
||||
*
|
||||
* We build a hashtable of existing packs (pack_revindex), and keep reverse
|
||||
* index here -- pack index file is sorted by object name mapping to offset;
|
||||
* this pack_revindex[].revindex array is a list of offset/index_nr pairs
|
||||
* The pack index file is sorted by object name mapping to offset;
|
||||
* this revindex array is a list of offset/index_nr pairs
|
||||
* ordered by offset, so if you know the offset of an object, next offset
|
||||
* is where its packed representation ends and the index_nr can be used to
|
||||
* get the object sha1 from the main index.
|
||||
*/
|
||||
|
||||
static struct pack_revindex *pack_revindex;
|
||||
static int pack_revindex_hashsz;
|
||||
|
||||
static int pack_revindex_ix(struct packed_git *p)
|
||||
{
|
||||
unsigned long ui = (unsigned long)(intptr_t)p;
|
||||
int i;
|
||||
|
||||
ui = ui ^ (ui >> 16); /* defeat structure alignment */
|
||||
i = (int)(ui % pack_revindex_hashsz);
|
||||
while (pack_revindex[i].p) {
|
||||
if (pack_revindex[i].p == p)
|
||||
return i;
|
||||
if (++i == pack_revindex_hashsz)
|
||||
i = 0;
|
||||
}
|
||||
return -1 - i;
|
||||
}
|
||||
|
||||
static void init_pack_revindex(void)
|
||||
{
|
||||
int num;
|
||||
struct packed_git *p;
|
||||
|
||||
for (num = 0, p = packed_git; p; p = p->next)
|
||||
num++;
|
||||
if (!num)
|
||||
return;
|
||||
pack_revindex_hashsz = num * 11;
|
||||
pack_revindex = xcalloc(pack_revindex_hashsz, sizeof(*pack_revindex));
|
||||
for (p = packed_git; p; p = p->next) {
|
||||
num = pack_revindex_ix(p);
|
||||
num = - 1 - num;
|
||||
pack_revindex[num].p = p;
|
||||
}
|
||||
/* revindex elements are lazily initialized */
|
||||
}
|
||||
|
||||
/*
|
||||
* This is a least-significant-digit radix sort.
|
||||
*
|
||||
|
|
@ -154,14 +115,13 @@ static void sort_revindex(struct revindex_entry *entries, unsigned n, off_t max)
|
|||
/*
|
||||
* Ordered list of offsets of objects in the pack.
|
||||
*/
|
||||
static void create_pack_revindex(struct pack_revindex *rix)
|
||||
static void create_pack_revindex(struct packed_git *p)
|
||||
{
|
||||
struct packed_git *p = rix->p;
|
||||
unsigned num_ent = p->num_objects;
|
||||
unsigned i;
|
||||
const char *index = p->index_data;
|
||||
|
||||
rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
|
||||
p->revindex = xmalloc(sizeof(*p->revindex) * (num_ent + 1));
|
||||
index += 4 * 256;
|
||||
|
||||
if (p->index_version > 1) {
|
||||
|
|
@ -171,55 +131,42 @@ static void create_pack_revindex(struct pack_revindex *rix)
|
|||
for (i = 0; i < num_ent; i++) {
|
||||
uint32_t off = ntohl(*off_32++);
|
||||
if (!(off & 0x80000000)) {
|
||||
rix->revindex[i].offset = off;
|
||||
p->revindex[i].offset = off;
|
||||
} else {
|
||||
rix->revindex[i].offset =
|
||||
p->revindex[i].offset =
|
||||
((uint64_t)ntohl(*off_64++)) << 32;
|
||||
rix->revindex[i].offset |=
|
||||
p->revindex[i].offset |=
|
||||
ntohl(*off_64++);
|
||||
}
|
||||
rix->revindex[i].nr = i;
|
||||
p->revindex[i].nr = i;
|
||||
}
|
||||
} else {
|
||||
for (i = 0; i < num_ent; i++) {
|
||||
uint32_t hl = *((uint32_t *)(index + 24 * i));
|
||||
rix->revindex[i].offset = ntohl(hl);
|
||||
rix->revindex[i].nr = i;
|
||||
p->revindex[i].offset = ntohl(hl);
|
||||
p->revindex[i].nr = i;
|
||||
}
|
||||
}
|
||||
|
||||
/* This knows the pack format -- the 20-byte trailer
|
||||
* follows immediately after the last object data.
|
||||
*/
|
||||
rix->revindex[num_ent].offset = p->pack_size - 20;
|
||||
rix->revindex[num_ent].nr = -1;
|
||||
sort_revindex(rix->revindex, num_ent, p->pack_size);
|
||||
p->revindex[num_ent].offset = p->pack_size - 20;
|
||||
p->revindex[num_ent].nr = -1;
|
||||
sort_revindex(p->revindex, num_ent, p->pack_size);
|
||||
}
|
||||
|
||||
struct pack_revindex *revindex_for_pack(struct packed_git *p)
|
||||
void load_pack_revindex(struct packed_git *p)
|
||||
{
|
||||
int num;
|
||||
struct pack_revindex *rix;
|
||||
|
||||
if (!pack_revindex_hashsz)
|
||||
init_pack_revindex();
|
||||
|
||||
num = pack_revindex_ix(p);
|
||||
if (num < 0)
|
||||
die("internal error: pack revindex fubar");
|
||||
|
||||
rix = &pack_revindex[num];
|
||||
if (!rix->revindex)
|
||||
create_pack_revindex(rix);
|
||||
|
||||
return rix;
|
||||
if (!p->revindex)
|
||||
create_pack_revindex(p);
|
||||
}
|
||||
|
||||
int find_revindex_position(struct pack_revindex *pridx, off_t ofs)
|
||||
int find_revindex_position(struct packed_git *p, off_t ofs)
|
||||
{
|
||||
int lo = 0;
|
||||
int hi = pridx->p->num_objects + 1;
|
||||
struct revindex_entry *revindex = pridx->revindex;
|
||||
int hi = p->num_objects + 1;
|
||||
struct revindex_entry *revindex = p->revindex;
|
||||
|
||||
do {
|
||||
unsigned mi = lo + (hi - lo) / 2;
|
||||
|
|
@ -237,11 +184,13 @@ int find_revindex_position(struct pack_revindex *pridx, off_t ofs)
|
|||
|
||||
struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs)
|
||||
{
|
||||
struct pack_revindex *pridx = revindex_for_pack(p);
|
||||
int pos = find_revindex_position(pridx, ofs);
|
||||
int pos;
|
||||
|
||||
load_pack_revindex(p);
|
||||
pos = find_revindex_position(p, ofs);
|
||||
|
||||
if (pos < 0)
|
||||
return NULL;
|
||||
|
||||
return pridx->revindex + pos;
|
||||
return p->revindex + pos;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,18 +1,15 @@
|
|||
#ifndef PACK_REVINDEX_H
|
||||
#define PACK_REVINDEX_H
|
||||
|
||||
struct packed_git;
|
||||
|
||||
struct revindex_entry {
|
||||
off_t offset;
|
||||
unsigned int nr;
|
||||
};
|
||||
|
||||
struct pack_revindex {
|
||||
struct packed_git *p;
|
||||
struct revindex_entry *revindex;
|
||||
};
|
||||
|
||||
struct pack_revindex *revindex_for_pack(struct packed_git *p);
|
||||
int find_revindex_position(struct pack_revindex *pridx, off_t ofs);
|
||||
void load_pack_revindex(struct packed_git *p);
|
||||
int find_revindex_position(struct packed_git *p, off_t ofs);
|
||||
|
||||
struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs);
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue