git-commit-vandalism/object.c

300 lines
6.4 KiB
C
Raw Normal View History

#include "cache.h"
#include "object.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "tag.h"
static struct object **obj_hash;
static int nr_objs, obj_hash_size;
unsigned int get_max_object_index(void)
{
return obj_hash_size;
}
struct object *get_indexed_object(unsigned int idx)
{
return obj_hash[idx];
}
static const char *object_type_strings[] = {
NULL, /* OBJ_NONE = 0 */
"commit", /* OBJ_COMMIT = 1 */
"tree", /* OBJ_TREE = 2 */
"blob", /* OBJ_BLOB = 3 */
"tag", /* OBJ_TAG = 4 */
};
const char *typename(unsigned int type)
{
if (type >= ARRAY_SIZE(object_type_strings))
return NULL;
return object_type_strings[type];
}
int type_from_string(const char *str)
{
int i;
for (i = 1; i < ARRAY_SIZE(object_type_strings); i++)
if (!strcmp(str, object_type_strings[i]))
return i;
die("invalid object type \"%s\"", str);
}
static unsigned int hash_obj(struct object *obj, unsigned int n)
{
unsigned int hash;
memcpy(&hash, obj->sha1, sizeof(unsigned int));
return hash % n;
}
static void insert_obj_hash(struct object *obj, struct object **hash, unsigned int size)
{
unsigned int j = hash_obj(obj, size);
while (hash[j]) {
j++;
if (j >= size)
j = 0;
}
hash[j] = obj;
}
static unsigned int hashtable_index(const unsigned char *sha1)
{
unsigned int i;
memcpy(&i, sha1, sizeof(unsigned int));
return i % obj_hash_size;
}
struct object *lookup_object(const unsigned char *sha1)
{
unsigned int i;
struct object *obj;
if (!obj_hash)
return NULL;
i = hashtable_index(sha1);
while ((obj = obj_hash[i]) != NULL) {
if (!hashcmp(sha1, obj->sha1))
break;
i++;
if (i == obj_hash_size)
i = 0;
}
return obj;
}
static void grow_object_hash(void)
{
int i;
int new_hash_size = obj_hash_size < 32 ? 32 : 2 * obj_hash_size;
struct object **new_hash;
new_hash = xcalloc(new_hash_size, sizeof(struct object *));
for (i = 0; i < obj_hash_size; i++) {
struct object *obj = obj_hash[i];
if (!obj)
continue;
insert_obj_hash(obj, new_hash, new_hash_size);
}
free(obj_hash);
obj_hash = new_hash;
obj_hash_size = new_hash_size;
}
void *create_object(const unsigned char *sha1, int type, void *o)
{
struct object *obj = o;
obj->parsed = 0;
obj->used = 0;
obj->type = type;
obj->flags = 0;
hashcpy(obj->sha1, sha1);
if (obj_hash_size - 1 <= nr_objs * 2)
grow_object_hash();
insert_obj_hash(obj, obj_hash, obj_hash_size);
nr_objs++;
return obj;
}
struct object *lookup_unknown_object(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
if (!obj)
obj = create_object(sha1, OBJ_NONE, alloc_object_node());
return obj;
}
struct object *parse_object_buffer(const unsigned char *sha1, enum object_type type, unsigned long size, void *buffer, int *eaten_p)
{
struct object *obj;
int eaten = 0;
obj = NULL;
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(sha1);
if (blob) {
if (parse_blob_buffer(blob, buffer, size))
return NULL;
obj = &blob->object;
}
} else if (type == OBJ_TREE) {
struct tree *tree = lookup_tree(sha1);
if (tree) {
obj = &tree->object;
if (!tree->buffer)
tree->object.parsed = 0;
if (!tree->object.parsed) {
if (parse_tree_buffer(tree, buffer, size))
return NULL;
eaten = 1;
}
}
} else if (type == OBJ_COMMIT) {
struct commit *commit = lookup_commit(sha1);
if (commit) {
if (parse_commit_buffer(commit, buffer, size))
return NULL;
if (!commit->buffer) {
commit->buffer = buffer;
eaten = 1;
}
obj = &commit->object;
}
} else if (type == OBJ_TAG) {
struct tag *tag = lookup_tag(sha1);
if (tag) {
if (parse_tag_buffer(tag, buffer, size))
return NULL;
obj = &tag->object;
}
} else {
warning("object %s has unknown type id %d\n", sha1_to_hex(sha1), type);
obj = NULL;
}
if (obj && obj->type == OBJ_NONE)
obj->type = type;
*eaten_p = eaten;
return obj;
}
struct object *parse_object(const unsigned char *sha1)
{
unsigned long size;
enum object_type type;
int eaten;
const unsigned char *repl = lookup_replace_object(sha1);
parse_object: try internal cache before reading object db When parse_object is called, we do the following: 1. read the object data into a buffer via read_sha1_file 2. call parse_object_buffer, which then: a. calls the appropriate lookup_{commit,tree,blob,tag} to either create a new "struct object", or to find an existing one. We know the appropriate type from the lookup in step 1. b. calls the appropriate parse_{commit,tree,blob,tag} to parse the buffer for the new (or existing) object In step 2b, all of the called functions are no-ops for object "X" if "X->object.parsed" is set. I.e., when we have already parsed an object, we end up going to a lot of work just to find out at a low level that there is nothing left for us to do (and we throw away the data from read_sha1_file unread). We can optimize this by moving the check for "do we have an in-memory object" from 2a before the expensive call to read_sha1_file in step 1. This might seem circular, since step 2a uses the type information determined in step 1 to call the appropriate lookup function. However, we can notice that all of the lookup_* functions are backed by lookup_object. In other words, all of the objects are kept in a master hash table, and we don't actually need the type to do the "do we have it" part of the lookup, only to do the "and create it if it doesn't exist" part. This can save time whenever we call parse_object on the same sha1 twice in a single program. Some code paths already perform this optimization manually, with either: if (!obj->parsed) obj = parse_object(obj->sha1); if you already have a "struct object", or: struct object *obj = lookup_unknown_object(sha1); if (!obj || !obj->parsed) obj = parse_object(sha1); if you don't. This patch moves the optimization into parse_object itself. Most git operations won't notice any impact. Either they don't parse a lot of duplicate sha1s, or the calling code takes special care not to re-parse objects. I timed two code paths that do benefit (there may be more, but these two were immediately obvious and easy to time). The first is fast-export, which calls parse_object on each object it outputs, like this: object = parse_object(sha1); if (!object) die(...); if (object->flags & SHOWN) return; which means that just to realize we have already shown an object, we will read the whole object from disk! With this patch, my best-of-five time for "fast-export --all" on git.git dropped from 26.3s to 21.3s. The second case is upload-pack, which will call parse_object for each advertised ref (because it needs to peel tags to show "^{}" entries). This doesn't matter for most repositories, because they don't have a lot of refs pointing to the same objects. However, if you have a big alternates repository with a shared object db for a number of child repositories, then the alternates repository will have duplicated refs representing each of its children. For example, GitHub's alternates repository for git.git has ~120,000 refs, of which only ~3200 are unique. The time for upload-pack to print its list of advertised refs dropped from 3.4s to 0.76s. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-05 22:00:01 +01:00
void *buffer;
struct object *obj;
obj = lookup_object(sha1);
if (obj && obj->parsed)
return obj;
if ((obj && obj->type == OBJ_BLOB) ||
(!obj && has_sha1_file(sha1) &&
sha1_object_info(sha1, NULL) == OBJ_BLOB)) {
if (check_sha1_signature(repl, NULL, 0, NULL) < 0) {
error("sha1 mismatch %s\n", sha1_to_hex(repl));
return NULL;
}
parse_blob_buffer(lookup_blob(sha1), NULL, 0);
return lookup_object(sha1);
}
parse_object: try internal cache before reading object db When parse_object is called, we do the following: 1. read the object data into a buffer via read_sha1_file 2. call parse_object_buffer, which then: a. calls the appropriate lookup_{commit,tree,blob,tag} to either create a new "struct object", or to find an existing one. We know the appropriate type from the lookup in step 1. b. calls the appropriate parse_{commit,tree,blob,tag} to parse the buffer for the new (or existing) object In step 2b, all of the called functions are no-ops for object "X" if "X->object.parsed" is set. I.e., when we have already parsed an object, we end up going to a lot of work just to find out at a low level that there is nothing left for us to do (and we throw away the data from read_sha1_file unread). We can optimize this by moving the check for "do we have an in-memory object" from 2a before the expensive call to read_sha1_file in step 1. This might seem circular, since step 2a uses the type information determined in step 1 to call the appropriate lookup function. However, we can notice that all of the lookup_* functions are backed by lookup_object. In other words, all of the objects are kept in a master hash table, and we don't actually need the type to do the "do we have it" part of the lookup, only to do the "and create it if it doesn't exist" part. This can save time whenever we call parse_object on the same sha1 twice in a single program. Some code paths already perform this optimization manually, with either: if (!obj->parsed) obj = parse_object(obj->sha1); if you already have a "struct object", or: struct object *obj = lookup_unknown_object(sha1); if (!obj || !obj->parsed) obj = parse_object(sha1); if you don't. This patch moves the optimization into parse_object itself. Most git operations won't notice any impact. Either they don't parse a lot of duplicate sha1s, or the calling code takes special care not to re-parse objects. I timed two code paths that do benefit (there may be more, but these two were immediately obvious and easy to time). The first is fast-export, which calls parse_object on each object it outputs, like this: object = parse_object(sha1); if (!object) die(...); if (object->flags & SHOWN) return; which means that just to realize we have already shown an object, we will read the whole object from disk! With this patch, my best-of-five time for "fast-export --all" on git.git dropped from 26.3s to 21.3s. The second case is upload-pack, which will call parse_object for each advertised ref (because it needs to peel tags to show "^{}" entries). This doesn't matter for most repositories, because they don't have a lot of refs pointing to the same objects. However, if you have a big alternates repository with a shared object db for a number of child repositories, then the alternates repository will have duplicated refs representing each of its children. For example, GitHub's alternates repository for git.git has ~120,000 refs, of which only ~3200 are unique. The time for upload-pack to print its list of advertised refs dropped from 3.4s to 0.76s. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-05 22:00:01 +01:00
buffer = read_sha1_file(sha1, &type, &size);
if (buffer) {
if (check_sha1_signature(repl, buffer, size, typename(type)) < 0) {
free(buffer);
error("sha1 mismatch %s\n", sha1_to_hex(repl));
return NULL;
}
obj = parse_object_buffer(sha1, type, size, buffer, &eaten);
if (!eaten)
free(buffer);
return obj;
}
return NULL;
}
struct object_list *object_list_insert(struct object *item,
struct object_list **list_p)
{
struct object_list *new_list = xmalloc(sizeof(struct object_list));
new_list->item = item;
new_list->next = *list_p;
*list_p = new_list;
return new_list;
}
int object_list_contains(struct object_list *list, struct object *obj)
{
while (list) {
if (list->item == obj)
return 1;
list = list->next;
}
return 0;
}
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
void add_object_array(struct object *obj, const char *name, struct object_array *array)
{
add_object_array_with_mode(obj, name, array, S_IFINVALID);
}
void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode)
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
{
unsigned nr = array->nr;
unsigned alloc = array->alloc;
struct object_array_entry *objects = array->objects;
if (nr >= alloc) {
alloc = (alloc + 32) * 2;
objects = xrealloc(objects, alloc * sizeof(*objects));
array->alloc = alloc;
array->objects = objects;
}
objects[nr].item = obj;
objects[nr].name = name;
objects[nr].mode = mode;
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
array->nr = ++nr;
}
void object_array_remove_duplicates(struct object_array *array)
{
unsigned int ref, src, dst;
struct object_array_entry *objects = array->objects;
for (ref = 0; ref + 1 < array->nr; ref++) {
for (src = ref + 1, dst = src;
src < array->nr;
src++) {
if (!strcmp(objects[ref].name, objects[src].name))
continue;
if (src != dst)
objects[dst] = objects[src];
dst++;
}
array->nr = dst;
}
}
void clear_object_flags(unsigned flags)
{
int i;
for (i=0; i < obj_hash_size; i++) {
struct object *obj = obj_hash[i];
if (obj)
obj->flags &= ~flags;
}
}