mirror of
https://github.com/git/git
synced 2024-08-28 12:09:19 +00:00
![Jeff King](/assets/img/avatar_default.png)
We may run for_each_alternate_ref() twice, once in find_common() and once in everything_local(). This operation can be expensive, because it involves running a sub-process which must freshly load all of the alternate's refs from disk. Let's cache and reuse the results between the two calls. We can make some optimizations based on the particular use pattern in fetch-pack to keep our memory usage down. The first is that we only care about the sha1s, not the refs themselves. So it's OK to store only the sha1s, and to suppress duplicates. The natural fit would therefore be a sha1_array. However, sha1_array's de-duplication happens only after it has read and sorted all entries. It still stores each duplicate. For an alternate with a large number of refs pointing to the same commits, this is a needless expense. Instead, we'd prefer to eliminate duplicates before putting them in the cache, which implies using a hash. We can further note that fetch-pack will call parse_object() on each alternate sha1. We can therefore keep our cache as a set of pointers to "struct object". That gives us a place to put our "already seen" bit with an optimized hash lookup. And as a bonus, the object stores the sha1 for us, so pointer-to-object is all we need. There are two extra optimizations I didn't do here: - we actually store an array of pointer-to-object. Technically we could just walk the obj_hash table looking for entries with the ALTERNATE flag set (because our use case doesn't care about the order here). But that hash table may be mostly composed of non-ALTERNATE entries, so we'd waste time walking over them. So it would be a slight win in memory use, but a loss in CPU. - the items we pull out of the cache are actual "struct object"s, but then we feed "obj->sha1" to our sub-functions, which promptly call parse_object(). This second parse is cheap, because it starts with lookup_object() and will bail immediately when it sees we've already parsed the object. We could save the extra hash lookup, but it would involve refactoring the functions we call. It may or may not be worth the trouble. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
144 lines
4.5 KiB
C
144 lines
4.5 KiB
C
#ifndef OBJECT_H
|
|
#define OBJECT_H
|
|
|
|
struct object_list {
|
|
struct object *item;
|
|
struct object_list *next;
|
|
};
|
|
|
|
struct object_array {
|
|
unsigned int nr;
|
|
unsigned int alloc;
|
|
struct object_array_entry {
|
|
struct object *item;
|
|
/*
|
|
* name or NULL. If non-NULL, the memory pointed to
|
|
* is owned by this object *except* if it points at
|
|
* object_array_slopbuf, which is a static copy of the
|
|
* empty string.
|
|
*/
|
|
char *name;
|
|
char *path;
|
|
unsigned mode;
|
|
} *objects;
|
|
};
|
|
|
|
#define OBJECT_ARRAY_INIT { 0, 0, NULL }
|
|
|
|
#define TYPE_BITS 3
|
|
/*
|
|
* object flag allocation:
|
|
* revision.h: 0---------10 26
|
|
* fetch-pack.c: 0---5
|
|
* walker.c: 0-2
|
|
* upload-pack.c: 4 11----------------19
|
|
* builtin/blame.c: 12-13
|
|
* bisect.c: 16
|
|
* bundle.c: 16
|
|
* http-push.c: 16-----19
|
|
* commit.c: 16-----19
|
|
* sha1_name.c: 20
|
|
*/
|
|
#define FLAG_BITS 27
|
|
|
|
/*
|
|
* The object type is stored in 3 bits.
|
|
*/
|
|
struct object {
|
|
unsigned parsed : 1;
|
|
unsigned used : 1;
|
|
unsigned type : TYPE_BITS;
|
|
unsigned flags : FLAG_BITS;
|
|
struct object_id oid;
|
|
};
|
|
|
|
extern const char *typename(unsigned int type);
|
|
extern int type_from_string_gently(const char *str, ssize_t, int gentle);
|
|
#define type_from_string(str) type_from_string_gently(str, -1, 0)
|
|
|
|
/*
|
|
* Return the current number of buckets in the object hashmap.
|
|
*/
|
|
extern unsigned int get_max_object_index(void);
|
|
|
|
/*
|
|
* Return the object from the specified bucket in the object hashmap.
|
|
*/
|
|
extern struct object *get_indexed_object(unsigned int);
|
|
|
|
/*
|
|
* This can be used to see if we have heard of the object before, but
|
|
* it can return "yes we have, and here is a half-initialised object"
|
|
* for an object that we haven't loaded/parsed yet.
|
|
*
|
|
* When parsing a commit to create an in-core commit object, its
|
|
* parents list holds commit objects that represent its parents, but
|
|
* they are expected to be lazily initialized and do not know what
|
|
* their trees or parents are yet. When this function returns such a
|
|
* half-initialised objects, the caller is expected to initialize them
|
|
* by calling parse_object() on them.
|
|
*/
|
|
struct object *lookup_object(const unsigned char *sha1);
|
|
|
|
extern void *create_object(const unsigned char *sha1, void *obj);
|
|
|
|
void *object_as_type(struct object *obj, enum object_type type, int quiet);
|
|
|
|
/*
|
|
* Returns the object, having parsed it to find out what it is.
|
|
*
|
|
* Returns NULL if the object is missing or corrupt.
|
|
*/
|
|
struct object *parse_object(const unsigned char *sha1);
|
|
|
|
/*
|
|
* Like parse_object, but will die() instead of returning NULL. If the
|
|
* "name" parameter is not NULL, it is included in the error message
|
|
* (otherwise, the sha1 hex is given).
|
|
*/
|
|
struct object *parse_object_or_die(const unsigned char *sha1, const char *name);
|
|
|
|
/* Given the result of read_sha1_file(), returns the object after
|
|
* parsing it. eaten_p indicates if the object has a borrowed copy
|
|
* of buffer and the caller should not free() it.
|
|
*/
|
|
struct object *parse_object_buffer(const unsigned char *sha1, enum object_type type, unsigned long size, void *buffer, int *eaten_p);
|
|
|
|
/** Returns the object, with potentially excess memory allocated. **/
|
|
struct object *lookup_unknown_object(const unsigned char *sha1);
|
|
|
|
struct object_list *object_list_insert(struct object *item,
|
|
struct object_list **list_p);
|
|
|
|
int object_list_contains(struct object_list *list, struct object *obj);
|
|
|
|
/* Object array handling .. */
|
|
void add_object_array(struct object *obj, const char *name, struct object_array *array);
|
|
void add_object_array_with_path(struct object *obj, const char *name, struct object_array *array, unsigned mode, const char *path);
|
|
|
|
typedef int (*object_array_each_func_t)(struct object_array_entry *, void *);
|
|
|
|
/*
|
|
* Apply want to each entry in array, retaining only the entries for
|
|
* which the function returns true. Preserve the order of the entries
|
|
* that are retained.
|
|
*/
|
|
void object_array_filter(struct object_array *array,
|
|
object_array_each_func_t want, void *cb_data);
|
|
|
|
/*
|
|
* Remove from array all but the first entry with a given name.
|
|
* Warning: this function uses an O(N^2) algorithm.
|
|
*/
|
|
void object_array_remove_duplicates(struct object_array *array);
|
|
|
|
/*
|
|
* Remove any objects from the array, freeing all used memory; afterwards
|
|
* the array is ready to store more objects with add_object_array().
|
|
*/
|
|
void object_array_clear(struct object_array *array);
|
|
|
|
void clear_object_flags(unsigned flags);
|
|
|
|
#endif /* OBJECT_H */
|