git/object.c
Nicolas Pitre bd2c39f58f [PATCH] don't load and decompress objects twice with parse_object()
It turns out that parse_object() is loading and decompressing given
object to free it just before calling the specific object parsing
function which does mmap and decompress the same object again. This
patch introduces the ability to parse specific objects directly from a
memory buffer.

Without this patch, running git-fsck-cache on the kernel repositorytake:

	real    0m13.006s
	user    0m11.421s
	sys     0m1.218s

With this patch applied:

	real    0m8.060s
	user    0m7.071s
	sys     0m0.710s

The performance increase is significant, and this is kind of a
prerequisite for sane delta object support with fsck.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-06 11:02:01 -07:00

140 lines
3.0 KiB
C

#include "object.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "cache.h"
#include "tag.h"
#include <stdlib.h>
#include <string.h>
struct object **objs;
int nr_objs;
static int obj_allocs;
static int find_object(unsigned char *sha1)
{
int first = 0, last = nr_objs;
while (first < last) {
int next = (first + last) / 2;
struct object *obj = objs[next];
int cmp;
cmp = memcmp(sha1, obj->sha1, 20);
if (!cmp)
return next;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
return -first-1;
}
struct object *lookup_object(unsigned char *sha1)
{
int pos = find_object(sha1);
if (pos >= 0)
return objs[pos];
return NULL;
}
void created_object(unsigned char *sha1, struct object *obj)
{
int pos = find_object(sha1);
obj->parsed = 0;
memcpy(obj->sha1, sha1, 20);
obj->type = NULL;
obj->refs = NULL;
obj->used = 0;
if (pos >= 0)
die("Inserting %s twice\n", sha1_to_hex(sha1));
pos = -pos-1;
if (obj_allocs == nr_objs) {
obj_allocs = alloc_nr(obj_allocs);
objs = xrealloc(objs, obj_allocs * sizeof(struct object *));
}
/* Insert it into the right place */
memmove(objs + pos + 1, objs + pos, (nr_objs - pos) *
sizeof(struct object *));
objs[pos] = obj;
nr_objs++;
}
void add_ref(struct object *refer, struct object *target)
{
struct object_list **pp = &refer->refs;
struct object_list *p;
while ((p = *pp) != NULL) {
if (p->item == target)
return;
pp = &p->next;
}
target->used = 1;
p = xmalloc(sizeof(*p));
p->item = target;
p->next = NULL;
*pp = p;
}
void mark_reachable(struct object *obj, unsigned int mask)
{
struct object_list *p = obj->refs;
/* If we've been here already, don't bother */
if (obj->flags & mask)
return;
obj->flags |= mask;
while (p) {
mark_reachable(p->item, mask);
p = p->next;
}
}
struct object *parse_object(unsigned char *sha1)
{
unsigned long mapsize;
void *map = map_sha1_file(sha1, &mapsize);
if (map) {
struct object *obj;
char type[100];
unsigned long size;
void *buffer = unpack_sha1_file(map, mapsize, type, &size);
munmap(map, mapsize);
if (!buffer)
return NULL;
if (check_sha1_signature(sha1, buffer, size, type) < 0)
printf("sha1 mismatch %s\n", sha1_to_hex(sha1));
if (!strcmp(type, "blob")) {
struct blob *blob = lookup_blob(sha1);
parse_blob_buffer(blob, buffer, size);
obj = &blob->object;
} else if (!strcmp(type, "tree")) {
struct tree *tree = lookup_tree(sha1);
parse_tree_buffer(tree, buffer, size);
obj = &tree->object;
} else if (!strcmp(type, "commit")) {
struct commit *commit = lookup_commit(sha1);
parse_commit_buffer(commit, buffer, size);
obj = &commit->object;
} else if (!strcmp(type, "tag")) {
struct tag *tag = lookup_tag(sha1);
parse_tag_buffer(tag, buffer, size);
obj = &tag->object;
} else {
obj = NULL;
}
free(buffer);
return obj;
}
return NULL;
}