Commit 2834bc27 authored by Vicent Marti's avatar Vicent Marti Committed by Junio C Hamano

pack-objects: refactor the packing list

The hash table that stores the packing list for a given `pack-objects`
run was tightly coupled to the pack-objects code.

In this commit, we refactor the hash table and the underlying storage
array into a `packing_data` struct. The functionality for accessing and
adding entries to the packing list is hence accessible from other parts
of Git besides the `pack-objects` builtin.

This refactoring is a requirement for further patches in this series
that will require accessing the commit packing list from outside of
`pack-objects`.

The hash table implementation has been minimally altered: we now
use table sizes which are always a power of two, to ensure a uniform
index distribution in the array.
Signed-off-by: 's avatarVicent Marti <tanoku@gmail.com>
Signed-off-by: 's avatarJeff King <peff@peff.net>
Signed-off-by: 's avatarJunio C Hamano <gitster@pobox.com>
parent 92e5c77c
......@@ -694,6 +694,7 @@ LIB_H += notes-merge.h
LIB_H += notes-utils.h
LIB_H += notes.h
LIB_H += object.h
LIB_H += pack-objects.h
LIB_H += pack-revindex.h
LIB_H += pack.h
LIB_H += parse-options.h
......@@ -831,6 +832,7 @@ LIB_OBJS += notes-merge.o
LIB_OBJS += notes-utils.o
LIB_OBJS += object.o
LIB_OBJS += pack-check.o
LIB_OBJS += pack-objects.o
LIB_OBJS += pack-revindex.o
LIB_OBJS += pack-write.o
LIB_OBJS += pager.o
......
This diff is collapsed.
#include "cache.h"
#include "object.h"
#include "pack.h"
#include "pack-objects.h"
static uint32_t locate_object_entry_hash(struct packing_data *pdata,
const unsigned char *sha1,
int *found)
{
uint32_t i, hash, mask = (pdata->index_size - 1);
memcpy(&hash, sha1, sizeof(uint32_t));
i = hash & mask;
while (pdata->index[i] > 0) {
uint32_t pos = pdata->index[i] - 1;
if (!hashcmp(sha1, pdata->objects[pos].idx.sha1)) {
*found = 1;
return i;
}
i = (i + 1) & mask;
}
*found = 0;
return i;
}
static inline uint32_t closest_pow2(uint32_t v)
{
v = v - 1;
v |= v >> 1;
v |= v >> 2;
v |= v >> 4;
v |= v >> 8;
v |= v >> 16;
return v + 1;
}
static void rehash_objects(struct packing_data *pdata)
{
uint32_t i;
struct object_entry *entry;
pdata->index_size = closest_pow2(pdata->nr_objects * 3);
if (pdata->index_size < 1024)
pdata->index_size = 1024;
pdata->index = xrealloc(pdata->index, sizeof(uint32_t) * pdata->index_size);
memset(pdata->index, 0, sizeof(int) * pdata->index_size);
entry = pdata->objects;
for (i = 0; i < pdata->nr_objects; i++) {
int found;
uint32_t ix = locate_object_entry_hash(pdata, entry->idx.sha1, &found);
if (found)
die("BUG: Duplicate object in hash");
pdata->index[ix] = i + 1;
entry++;
}
}
struct object_entry *packlist_find(struct packing_data *pdata,
const unsigned char *sha1,
uint32_t *index_pos)
{
uint32_t i;
int found;
if (!pdata->index_size)
return NULL;
i = locate_object_entry_hash(pdata, sha1, &found);
if (index_pos)
*index_pos = i;
if (!found)
return NULL;
return &pdata->objects[pdata->index[i] - 1];
}
struct object_entry *packlist_alloc(struct packing_data *pdata,
const unsigned char *sha1,
uint32_t index_pos)
{
struct object_entry *new_entry;
if (pdata->nr_objects >= pdata->nr_alloc) {
pdata->nr_alloc = (pdata->nr_alloc + 1024) * 3 / 2;
pdata->objects = xrealloc(pdata->objects,
pdata->nr_alloc * sizeof(*new_entry));
}
new_entry = pdata->objects + pdata->nr_objects++;
memset(new_entry, 0, sizeof(*new_entry));
hashcpy(new_entry->idx.sha1, sha1);
if (pdata->index_size * 3 <= pdata->nr_objects * 4)
rehash_objects(pdata);
else
pdata->index[index_pos] = pdata->nr_objects;
return new_entry;
}
#ifndef PACK_OBJECTS_H
#define PACK_OBJECTS_H
struct object_entry {
struct pack_idx_entry idx;
unsigned long size; /* uncompressed size */
struct packed_git *in_pack; /* already in pack */
off_t in_pack_offset;
struct object_entry *delta; /* delta base object */
struct object_entry *delta_child; /* deltified objects who bases me */
struct object_entry *delta_sibling; /* other deltified objects who
* uses the same base as me
*/
void *delta_data; /* cached delta (uncompressed) */
unsigned long delta_size; /* delta data size (uncompressed) */
unsigned long z_delta_size; /* delta data size (compressed) */
enum object_type type;
enum object_type in_pack_type; /* could be delta */
uint32_t hash; /* name hint hash */
unsigned char in_pack_header_size;
unsigned preferred_base:1; /*
* we do not pack this, but is available
* to be used as the base object to delta
* objects against.
*/
unsigned no_try_delta:1;
unsigned tagged:1; /* near the very tip of refs */
unsigned filled:1; /* assigned write-order */
};
struct packing_data {
struct object_entry *objects;
uint32_t nr_objects, nr_alloc;
int32_t *index;
uint32_t index_size;
};
struct object_entry *packlist_alloc(struct packing_data *pdata,
const unsigned char *sha1,
uint32_t index_pos);
struct object_entry *packlist_find(struct packing_data *pdata,
const unsigned char *sha1,
uint32_t *index_pos);
#endif
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment