[git/git.git] / pack-objects.h

#ifndef PACK_OBJECTS_H
#define PACK_OBJECTS_H

#include "object-store.h"

#define OE_DFS_STATE_BITS	2
#define OE_DEPTH_BITS		12
#define OE_IN_PACK_BITS		10
#define OE_Z_DELTA_BITS		20
/*
 * Note that oe_set_size() becomes expensive when the given size is
 * above this limit. Don't lower it too much.
 */
#define OE_SIZE_BITS		31

/*
 * State flags for depth-first search used for analyzing delta cycles.
 *
 * The depth is measured in delta-links to the base (so if A is a delta
 * against B, then A has a depth of 1, and B a depth of 0).
 */
enum dfs_state {
	DFS_NONE = 0,
	DFS_ACTIVE,
	DFS_DONE,
	DFS_NUM_STATES
};

/*
 * basic object info
 * -----------------
 * idx.oid is filled up before delta searching starts. idx.crc32 is
 * only valid after the object is written out and will be used for
 * generating the index. idx.offset will be both gradually set and
 * used in writing phase (base objects get offset first, then deltas
 * refer to them)
 *
 * "size" is the uncompressed object size. Compressed size of the raw
 * data for an object in a pack is not stored anywhere but is computed
 * and made available when reverse .idx is made. Note that when a
 * delta is reused, "size" is the uncompressed _delta_ size, not the
 * canonical one after the delta has been applied.
 *
 * "hash" contains a path name hash which is used for sorting the
 * delta list and also during delta searching. Once prepare_pack()
 * returns it's no longer needed.
 *
 * source pack info
 * ----------------
 * The (in_pack, in_pack_offset) tuple contains the location of the
 * object in the source pack. in_pack_header_size allows quickly
 * skipping the header and going straight to the zlib stream.
 *
 * "type" and "in_pack_type" both describe object type. in_pack_type
 * may contain a delta type, while type is always the canonical type.
 *
 * deltas
 * ------
 * Delta links (delta, delta_child and delta_sibling) are created to
 * reflect that delta graph from the source pack then updated or added
 * during delta searching phase when we find better deltas.
 *
 * delta_child and delta_sibling are last needed in
 * compute_write_order(). "delta" and "delta_size" must remain valid
 * at object writing phase in case the delta is not cached.
 *
 * If a delta is cached in memory and is compressed, delta_data points
 * to the data and z_delta_size contains the compressed size. If it's
 * uncompressed [1], z_delta_size must be zero. delta_size is always
 * the uncompressed size and must be valid even if the delta is not
 * cached.
 *
 * [1] during try_delta phase we don't bother with compressing because
 * the delta could be quickly replaced with a better one.
 */
struct object_entry {
	struct pack_idx_entry idx;
	unsigned size_:OE_SIZE_BITS;
	unsigned size_valid:1;
	unsigned in_pack_idx:OE_IN_PACK_BITS;	/* already in pack */
	off_t in_pack_offset;
	uint32_t delta_idx;	/* delta base object */
	uint32_t delta_child_idx; /* deltified objects who bases me */
	uint32_t delta_sibling_idx; /* 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 z_delta_size:OE_Z_DELTA_BITS;
	unsigned type_:TYPE_BITS;
	unsigned in_pack_type:TYPE_BITS; /* could be delta */
	unsigned type_valid:1;
	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 */
	unsigned dfs_state:OE_DFS_STATE_BITS;
	unsigned depth:OE_DEPTH_BITS;
};

struct packing_data {
	struct object_entry *objects;
	uint32_t nr_objects, nr_alloc;

	int32_t *index;
	uint32_t index_size;

	unsigned int *in_pack_pos;

	/*
	 * Only one of these can be non-NULL and they have different
	 * sizes. if in_pack_by_idx is allocated, oe_in_pack() returns
	 * the pack of an object using in_pack_idx field. If not,
	 * in_pack[] array is used the same way as in_pack_pos[]
	 */
	struct packed_git **in_pack_by_idx;
	struct packed_git **in_pack;

	uintmax_t oe_size_limit;
};

void prepare_packing_data(struct packing_data *pdata);
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);

static inline uint32_t pack_name_hash(const char *name)
{
	uint32_t c, hash = 0;

	if (!name)
		return 0;

	/*
	 * This effectively just creates a sortable number from the
	 * last sixteen non-whitespace characters. Last characters
	 * count "most", so things that end in ".c" sort together.
	 */
	while ((c = *name++) != 0) {
		if (isspace(c))
			continue;
		hash = (hash >> 2) + (c << 24);
	}
	return hash;
}

static inline enum object_type oe_type(const struct object_entry *e)
{
	return e->type_valid ? e->type_ : OBJ_BAD;
}

static inline void oe_set_type(struct object_entry *e,
			       enum object_type type)
{
	if (type >= OBJ_ANY)
		BUG("OBJ_ANY cannot be set in pack-objects code");

	e->type_valid = type >= OBJ_NONE;
	e->type_ = (unsigned)type;
}

static inline unsigned int oe_in_pack_pos(const struct packing_data *pack,
					  const struct object_entry *e)
{
	return pack->in_pack_pos[e - pack->objects];
}

static inline void oe_set_in_pack_pos(const struct packing_data *pack,
				      const struct object_entry *e,
				      unsigned int pos)
{
	pack->in_pack_pos[e - pack->objects] = pos;
}

static inline struct packed_git *oe_in_pack(const struct packing_data *pack,
					    const struct object_entry *e)
{
	if (pack->in_pack_by_idx)
		return pack->in_pack_by_idx[e->in_pack_idx];
	else
		return pack->in_pack[e - pack->objects];
}

void oe_map_new_pack(struct packing_data *pack,
		     struct packed_git *p);
static inline void oe_set_in_pack(struct packing_data *pack,
				  struct object_entry *e,
				  struct packed_git *p)
{
	if (!p->index)
		oe_map_new_pack(pack, p);
	if (pack->in_pack_by_idx)
		e->in_pack_idx = p->index;
	else
		pack->in_pack[e - pack->objects] = p;
}

static inline struct object_entry *oe_delta(
		const struct packing_data *pack,
		const struct object_entry *e)
{
	if (e->delta_idx)
		return &pack->objects[e->delta_idx - 1];
	return NULL;
}

static inline void oe_set_delta(struct packing_data *pack,
				struct object_entry *e,
				struct object_entry *delta)
{
	if (delta)
		e->delta_idx = (delta - pack->objects) + 1;
	else
		e->delta_idx = 0;
}

static inline struct object_entry *oe_delta_child(
		const struct packing_data *pack,
		const struct object_entry *e)
{
	if (e->delta_child_idx)
		return &pack->objects[e->delta_child_idx - 1];
	return NULL;
}

static inline void oe_set_delta_child(struct packing_data *pack,
				      struct object_entry *e,
				      struct object_entry *delta)
{
	if (delta)
		e->delta_child_idx = (delta - pack->objects) + 1;
	else
		e->delta_child_idx = 0;
}

static inline struct object_entry *oe_delta_sibling(
		const struct packing_data *pack,
		const struct object_entry *e)
{
	if (e->delta_sibling_idx)
		return &pack->objects[e->delta_sibling_idx - 1];
	return NULL;
}

static inline void oe_set_delta_sibling(struct packing_data *pack,
					struct object_entry *e,
					struct object_entry *delta)
{
	if (delta)
		e->delta_sibling_idx = (delta - pack->objects) + 1;
	else
		e->delta_sibling_idx = 0;
}

unsigned long oe_get_size_slow(struct packing_data *pack,
			       const struct object_entry *e);
static inline unsigned long oe_size(struct packing_data *pack,
				    const struct object_entry *e)
{
	if (e->size_valid)
		return e->size_;

	return oe_get_size_slow(pack, e);
}

static inline int oe_size_less_than(struct packing_data *pack,
				    const struct object_entry *lhs,
				    unsigned long rhs)
{
	if (lhs->size_valid)
		return lhs->size_ < rhs;
	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
		return 0;
	return oe_get_size_slow(pack, lhs) < rhs;
}

static inline int oe_size_greater_than(struct packing_data *pack,
				       const struct object_entry *lhs,
				       unsigned long rhs)
{
	if (lhs->size_valid)
		return lhs->size_ > rhs;
	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
		return 1;
	return oe_get_size_slow(pack, lhs) > rhs;
}

static inline void oe_set_size(struct packing_data *pack,
			       struct object_entry *e,
			       unsigned long size)
{
	if (size < pack->oe_size_limit) {
		e->size_ = size;
		e->size_valid = 1;
	} else {
		e->size_valid = 0;
		if (oe_get_size_slow(pack, e) != size)
			BUG("'size' is supposed to be the object size!");
	}
}

#endif
Commit	Line	Data
2834bc27 VM	1	#ifndef PACK_OBJECTS_H
	2	#define PACK_OBJECTS_H
	3
43fa44fa NTND	4	#include "object-store.h"
43fa44fa NTND	5
0c6804ab	6	#define OE_DFS_STATE_BITS 2
b5c0cbd8	7	#define OE_DEPTH_BITS 12
43fa44fa	8	#define OE_IN_PACK_BITS 10
0cb3c142	9	#define OE_Z_DELTA_BITS 20
ac77d0c3 NTND	10	/*
	11	* Note that oe_set_size() becomes expensive when the given size is
	12	* above this limit. Don't lower it too much.
	13	*/
	14	#define OE_SIZE_BITS 31
0c6804ab NTND	15
	16	/*
	17	* State flags for depth-first search used for analyzing delta cycles.
	18	*
	19	* The depth is measured in delta-links to the base (so if A is a delta
	20	* against B, then A has a depth of 1, and B a depth of 0).
	21	*/
	22	enum dfs_state {
	23	DFS_NONE = 0,
	24	DFS_ACTIVE,
	25	DFS_DONE,
	26	DFS_NUM_STATES
	27	};
	28
8d6ccce1 NTND	29	/*
	30	* basic object info
	31	* -----------------
	32	* idx.oid is filled up before delta searching starts. idx.crc32 is
	33	* only valid after the object is written out and will be used for
	34	* generating the index. idx.offset will be both gradually set and
	35	* used in writing phase (base objects get offset first, then deltas
	36	* refer to them)
	37	*
	38	* "size" is the uncompressed object size. Compressed size of the raw
	39	* data for an object in a pack is not stored anywhere but is computed
27a7d067 NTND	40	* and made available when reverse .idx is made. Note that when a
	41	* delta is reused, "size" is the uncompressed _delta_ size, not the
	42	* canonical one after the delta has been applied.
8d6ccce1 NTND	43	*
	44	* "hash" contains a path name hash which is used for sorting the
	45	* delta list and also during delta searching. Once prepare_pack()
	46	* returns it's no longer needed.
	47	*
	48	* source pack info
	49	* ----------------
	50	* The (in_pack, in_pack_offset) tuple contains the location of the
	51	* object in the source pack. in_pack_header_size allows quickly
	52	* skipping the header and going straight to the zlib stream.
	53	*
	54	* "type" and "in_pack_type" both describe object type. in_pack_type
	55	* may contain a delta type, while type is always the canonical type.
	56	*
	57	* deltas
	58	* ------
	59	* Delta links (delta, delta_child and delta_sibling) are created to
	60	* reflect that delta graph from the source pack then updated or added
	61	* during delta searching phase when we find better deltas.
	62	*
	63	* delta_child and delta_sibling are last needed in
	64	* compute_write_order(). "delta" and "delta_size" must remain valid
	65	* at object writing phase in case the delta is not cached.
	66	*
	67	* If a delta is cached in memory and is compressed, delta_data points
	68	* to the data and z_delta_size contains the compressed size. If it's
	69	* uncompressed [1], z_delta_size must be zero. delta_size is always
	70	* the uncompressed size and must be valid even if the delta is not
	71	* cached.
	72	*
	73	* [1] during try_delta phase we don't bother with compressing because
	74	* the delta could be quickly replaced with a better one.
	75	*/
2834bc27 VM	76	struct object_entry {
2834bc27 VM	77	struct pack_idx_entry idx;
ac77d0c3 NTND	78	unsigned size_:OE_SIZE_BITS;
ac77d0c3 NTND	79	unsigned size_valid:1;
43fa44fa	80	unsigned in_pack_idx:OE_IN_PACK_BITS; /* already in pack */
2834bc27	81	off_t in_pack_offset;
898eba5e NTND	82	uint32_t delta_idx; /* delta base object */
	83	uint32_t delta_child_idx; /* deltified objects who bases me */
	84	uint32_t delta_sibling_idx; /* other deltified objects who
	85	* uses the same base as me
	86	*/
2834bc27 VM	87	void delta_data; / cached delta (uncompressed) */
2834bc27 VM	88	unsigned long delta_size; /* delta data size (uncompressed) */
0cb3c142	89	unsigned z_delta_size:OE_Z_DELTA_BITS;
fd9b1bae NTND	90	unsigned type_:TYPE_BITS;
	91	unsigned in_pack_type:TYPE_BITS; /* could be delta */
	92	unsigned type_valid:1;
2834bc27 VM	93	uint32_t hash; /* name hint hash */
	94	unsigned char in_pack_header_size;
	95	unsigned preferred_base:1; /*
	96	* we do not pack this, but is available
	97	* to be used as the base object to delta
	98	* objects against.
	99	*/
	100	unsigned no_try_delta:1;
	101	unsigned tagged:1; /* near the very tip of refs */
	102	unsigned filled:1; /* assigned write-order */
0c6804ab	103	unsigned dfs_state:OE_DFS_STATE_BITS;
b5c0cbd8	104	unsigned depth:OE_DEPTH_BITS;
2834bc27 VM	105	};
	106
	107	struct packing_data {
	108	struct object_entry *objects;
	109	uint32_t nr_objects, nr_alloc;
	110
	111	int32_t *index;
	112	uint32_t index_size;
06af3bba NTND	113
06af3bba NTND	114	unsigned int *in_pack_pos;
43fa44fa NTND	115
	116	/*
	117	* Only one of these can be non-NULL and they have different
	118	* sizes. if in_pack_by_idx is allocated, oe_in_pack() returns
	119	* the pack of an object using in_pack_idx field. If not,
	120	* in_pack[] array is used the same way as in_pack_pos[]
	121	*/
	122	struct packed_git **in_pack_by_idx;
	123	struct packed_git **in_pack;
ac77d0c3 NTND	124
ac77d0c3 NTND	125	uintmax_t oe_size_limit;
2834bc27 VM	126	};
2834bc27 VM	127
43fa44fa	128	void prepare_packing_data(struct packing_data *pdata);
2834bc27 VM	129	struct object_entry packlist_alloc(struct packing_data pdata,
	130	const unsigned char *sha1,
	131	uint32_t index_pos);
	132
	133	struct object_entry packlist_find(struct packing_data pdata,
	134	const unsigned char *sha1,
	135	uint32_t *index_pos);
	136
68fb36eb VM	137	static inline uint32_t pack_name_hash(const char *name)
	138	{
	139	uint32_t c, hash = 0;
	140
	141	if (!name)
	142	return 0;
	143
	144	/*
	145	* This effectively just creates a sortable number from the
	146	* last sixteen non-whitespace characters. Last characters
	147	* count "most", so things that end in ".c" sort together.
	148	*/
	149	while ((c = *name++) != 0) {
	150	if (isspace(c))
	151	continue;
	152	hash = (hash >> 2) + (c << 24);
	153	}
	154	return hash;
	155	}
	156
fd9b1bae NTND	157	static inline enum object_type oe_type(const struct object_entry *e)
	158	{
	159	return e->type_valid ? e->type_ : OBJ_BAD;
	160	}
	161
	162	static inline void oe_set_type(struct object_entry *e,
	163	enum object_type type)
	164	{
	165	if (type >= OBJ_ANY)
	166	BUG("OBJ_ANY cannot be set in pack-objects code");
	167
	168	e->type_valid = type >= OBJ_NONE;
	169	e->type_ = (unsigned)type;
	170	}
	171
06af3bba NTND	172	static inline unsigned int oe_in_pack_pos(const struct packing_data *pack,
	173	const struct object_entry *e)
	174	{
	175	return pack->in_pack_pos[e - pack->objects];
	176	}
	177
	178	static inline void oe_set_in_pack_pos(const struct packing_data *pack,
	179	const struct object_entry *e,
	180	unsigned int pos)
	181	{
	182	pack->in_pack_pos[e - pack->objects] = pos;
	183	}
	184
43fa44fa NTND	185	static inline struct packed_git oe_in_pack(const struct packing_data pack,
	186	const struct object_entry *e)
	187	{
	188	if (pack->in_pack_by_idx)
	189	return pack->in_pack_by_idx[e->in_pack_idx];
	190	else
	191	return pack->in_pack[e - pack->objects];
	192	}
	193
	194	void oe_map_new_pack(struct packing_data *pack,
	195	struct packed_git *p);
	196	static inline void oe_set_in_pack(struct packing_data *pack,
	197	struct object_entry *e,
	198	struct packed_git *p)
	199	{
	200	if (!p->index)
	201	oe_map_new_pack(pack, p);
	202	if (pack->in_pack_by_idx)
	203	e->in_pack_idx = p->index;
	204	else
	205	pack->in_pack[e - pack->objects] = p;
	206	}
	207
898eba5e NTND	208	static inline struct object_entry *oe_delta(
	209	const struct packing_data *pack,
	210	const struct object_entry *e)
	211	{
	212	if (e->delta_idx)
	213	return &pack->objects[e->delta_idx - 1];
	214	return NULL;
	215	}
	216
	217	static inline void oe_set_delta(struct packing_data *pack,
	218	struct object_entry *e,
	219	struct object_entry *delta)
	220	{
	221	if (delta)
	222	e->delta_idx = (delta - pack->objects) + 1;
	223	else
	224	e->delta_idx = 0;
	225	}
	226
	227	static inline struct object_entry *oe_delta_child(
	228	const struct packing_data *pack,
	229	const struct object_entry *e)
	230	{
	231	if (e->delta_child_idx)
	232	return &pack->objects[e->delta_child_idx - 1];
	233	return NULL;
	234	}
	235
	236	static inline void oe_set_delta_child(struct packing_data *pack,
	237	struct object_entry *e,
	238	struct object_entry *delta)
	239	{
	240	if (delta)
	241	e->delta_child_idx = (delta - pack->objects) + 1;
	242	else
	243	e->delta_child_idx = 0;
	244	}
	245
	246	static inline struct object_entry *oe_delta_sibling(
	247	const struct packing_data *pack,
	248	const struct object_entry *e)
	249	{
	250	if (e->delta_sibling_idx)
	251	return &pack->objects[e->delta_sibling_idx - 1];
	252	return NULL;
	253	}
	254
	255	static inline void oe_set_delta_sibling(struct packing_data *pack,
	256	struct object_entry *e,
	257	struct object_entry *delta)
	258	{
	259	if (delta)
	260	e->delta_sibling_idx = (delta - pack->objects) + 1;
	261	else
	262	e->delta_sibling_idx = 0;
	263	}
	264
ac77d0c3 NTND	265	unsigned long oe_get_size_slow(struct packing_data *pack,
	266	const struct object_entry *e);
	267	static inline unsigned long oe_size(struct packing_data *pack,
	268	const struct object_entry *e)
	269	{
	270	if (e->size_valid)
	271	return e->size_;
	272
	273	return oe_get_size_slow(pack, e);
	274	}
	275
	276	static inline int oe_size_less_than(struct packing_data *pack,
	277	const struct object_entry *lhs,
	278	unsigned long rhs)
	279	{
	280	if (lhs->size_valid)
	281	return lhs->size_ < rhs;
	282	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
	283	return 0;
	284	return oe_get_size_slow(pack, lhs) < rhs;
	285	}
	286
	287	static inline int oe_size_greater_than(struct packing_data *pack,
	288	const struct object_entry *lhs,
	289	unsigned long rhs)
	290	{
	291	if (lhs->size_valid)
	292	return lhs->size_ > rhs;
	293	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
	294	return 1;
	295	return oe_get_size_slow(pack, lhs) > rhs;
	296	}
	297
	298	static inline void oe_set_size(struct packing_data *pack,
	299	struct object_entry *e,
	300	unsigned long size)
	301	{
	302	if (size < pack->oe_size_limit) {
	303	e->size_ = size;
	304	e->size_valid = 1;
	305	} else {
	306	e->size_valid = 0;
	307	if (oe_get_size_slow(pack, e) != size)
	308	BUG("'size' is supposed to be the object size!");
	309	}
	310	}
	311
2834bc27	312	#endif