[thirdparty/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
#define OE_DELTA_SIZE_BITS	20

/*
 * 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
};

/*
 * The size of struct nearly determines pack-objects's memory
 * consumption. This struct is packed tight for that reason. When you
 * add or reorder something in this struct, think a bit about this.
 *
 * 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;
	void *delta_data;	/* cached delta (uncompressed) */
	off_t in_pack_offset;
	uint32_t hash;			/* name hint hash */
	unsigned size_:OE_SIZE_BITS;
	unsigned size_valid:1;
	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
				     */
	unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
	unsigned delta_size_valid:1;
	unsigned in_pack_idx:OE_IN_PACK_BITS;	/* already in pack */
	unsigned z_delta_size:OE_Z_DELTA_BITS;
	unsigned type_valid:1;
	unsigned type_:TYPE_BITS;
	unsigned no_try_delta:1;
	unsigned in_pack_type:TYPE_BITS; /* could be delta */
	unsigned preferred_base:1; /*
				    * we do not pack this, but is available
				    * to be used as the base object to delta
				    * objects against.
				    */
	unsigned tagged:1; /* near the very tip of refs */
	unsigned filled:1; /* assigned write-order */
	unsigned dfs_state:OE_DFS_STATE_BITS;
	unsigned char in_pack_header_size;
	unsigned depth:OE_DEPTH_BITS;

	/*
	 * pahole results on 64-bit linux (gcc and clang)
	 *
	 *   size: 80, bit_padding: 20 bits, holes: 8 bits
	 *
	 * and on 32-bit (gcc)
	 *
	 *   size: 76, bit_padding: 20 bits, holes: 8 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!");
	}
}

static inline unsigned long oe_delta_size(struct packing_data *pack,
					  const struct object_entry *e)
{
	if (e->delta_size_valid)
		return e->delta_size_;
	return oe_size(pack, e);
}

static inline void oe_set_delta_size(struct packing_data *pack,
				     struct object_entry *e,
				     unsigned long size)
{
	e->delta_size_ = size;
	e->delta_size_valid = e->delta_size_ == size;
	if (!e->delta_size_valid && size != oe_size(pack, e))
		BUG("this can only happen in check_object() "
		    "where delta size is the same as entry 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
0aca34e8	15	#define OE_DELTA_SIZE_BITS 20
0c6804ab NTND	16
	17	/*
	18	* State flags for depth-first search used for analyzing delta cycles.
	19	*
	20	* The depth is measured in delta-links to the base (so if A is a delta
	21	* against B, then A has a depth of 1, and B a depth of 0).
	22	*/
	23	enum dfs_state {
	24	DFS_NONE = 0,
	25	DFS_ACTIVE,
	26	DFS_DONE,
	27	DFS_NUM_STATES
	28	};
	29
8d6ccce1	30	/*
3b13a5f2 NTND	31	* The size of struct nearly determines pack-objects's memory
	32	* consumption. This struct is packed tight for that reason. When you
	33	* add or reorder something in this struct, think a bit about this.
	34	*
8d6ccce1 NTND	35	* basic object info
	36	* -----------------
	37	* idx.oid is filled up before delta searching starts. idx.crc32 is
	38	* only valid after the object is written out and will be used for
	39	* generating the index. idx.offset will be both gradually set and
	40	* used in writing phase (base objects get offset first, then deltas
	41	* refer to them)
	42	*
	43	* "size" is the uncompressed object size. Compressed size of the raw
	44	* data for an object in a pack is not stored anywhere but is computed
27a7d067 NTND	45	* and made available when reverse .idx is made. Note that when a
	46	* delta is reused, "size" is the uncompressed _delta_ size, not the
	47	* canonical one after the delta has been applied.
8d6ccce1 NTND	48	*
	49	* "hash" contains a path name hash which is used for sorting the
	50	* delta list and also during delta searching. Once prepare_pack()
	51	* returns it's no longer needed.
	52	*
	53	* source pack info
	54	* ----------------
	55	* The (in_pack, in_pack_offset) tuple contains the location of the
	56	* object in the source pack. in_pack_header_size allows quickly
	57	* skipping the header and going straight to the zlib stream.
	58	*
	59	* "type" and "in_pack_type" both describe object type. in_pack_type
	60	* may contain a delta type, while type is always the canonical type.
	61	*
	62	* deltas
	63	* ------
	64	* Delta links (delta, delta_child and delta_sibling) are created to
	65	* reflect that delta graph from the source pack then updated or added
	66	* during delta searching phase when we find better deltas.
	67	*
	68	* delta_child and delta_sibling are last needed in
	69	* compute_write_order(). "delta" and "delta_size" must remain valid
	70	* at object writing phase in case the delta is not cached.
	71	*
	72	* If a delta is cached in memory and is compressed, delta_data points
	73	* to the data and z_delta_size contains the compressed size. If it's
	74	* uncompressed [1], z_delta_size must be zero. delta_size is always
	75	* the uncompressed size and must be valid even if the delta is not
	76	* cached.
	77	*
	78	* [1] during try_delta phase we don't bother with compressing because
	79	* the delta could be quickly replaced with a better one.
	80	*/
2834bc27 VM	81	struct object_entry {
2834bc27 VM	82	struct pack_idx_entry idx;
3b13a5f2 NTND	83	void delta_data; / cached delta (uncompressed) */
	84	off_t in_pack_offset;
	85	uint32_t hash; /* name hint hash */
ac77d0c3 NTND	86	unsigned size_:OE_SIZE_BITS;
ac77d0c3 NTND	87	unsigned size_valid:1;
898eba5e NTND	88	uint32_t delta_idx; /* delta base object */
	89	uint32_t delta_child_idx; /* deltified objects who bases me */
	90	uint32_t delta_sibling_idx; /* other deltified objects who
	91	* uses the same base as me
	92	*/
0aca34e8 NTND	93	unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
0aca34e8 NTND	94	unsigned delta_size_valid:1;
3b13a5f2	95	unsigned in_pack_idx:OE_IN_PACK_BITS; /* already in pack */
0cb3c142	96	unsigned z_delta_size:OE_Z_DELTA_BITS;
3b13a5f2	97	unsigned type_valid:1;
fd9b1bae	98	unsigned type_:TYPE_BITS;
3b13a5f2	99	unsigned no_try_delta:1;
fd9b1bae	100	unsigned in_pack_type:TYPE_BITS; /* could be delta */
2834bc27 VM	101	unsigned preferred_base:1; /*
	102	* we do not pack this, but is available
	103	* to be used as the base object to delta
	104	* objects against.
	105	*/
2834bc27 VM	106	unsigned tagged:1; /* near the very tip of refs */
2834bc27 VM	107	unsigned filled:1; /* assigned write-order */
0c6804ab	108	unsigned dfs_state:OE_DFS_STATE_BITS;
3b13a5f2	109	unsigned char in_pack_header_size;
b5c0cbd8	110	unsigned depth:OE_DEPTH_BITS;
3b13a5f2 NTND	111
	112	/*
	113	* pahole results on 64-bit linux (gcc and clang)
	114	*
	115	* size: 80, bit_padding: 20 bits, holes: 8 bits
	116	*
	117	* and on 32-bit (gcc)
	118	*
	119	* size: 76, bit_padding: 20 bits, holes: 8 bits
	120	*/
2834bc27 VM	121	};
	122
	123	struct packing_data {
	124	struct object_entry *objects;
	125	uint32_t nr_objects, nr_alloc;
	126
	127	int32_t *index;
	128	uint32_t index_size;
06af3bba NTND	129
06af3bba NTND	130	unsigned int *in_pack_pos;
43fa44fa NTND	131
	132	/*
	133	* Only one of these can be non-NULL and they have different
	134	* sizes. if in_pack_by_idx is allocated, oe_in_pack() returns
	135	* the pack of an object using in_pack_idx field. If not,
	136	* in_pack[] array is used the same way as in_pack_pos[]
	137	*/
	138	struct packed_git **in_pack_by_idx;
	139	struct packed_git **in_pack;
ac77d0c3 NTND	140
ac77d0c3 NTND	141	uintmax_t oe_size_limit;
2834bc27 VM	142	};
2834bc27 VM	143
43fa44fa	144	void prepare_packing_data(struct packing_data *pdata);
2834bc27 VM	145	struct object_entry packlist_alloc(struct packing_data pdata,
	146	const unsigned char *sha1,
	147	uint32_t index_pos);
	148
	149	struct object_entry packlist_find(struct packing_data pdata,
	150	const unsigned char *sha1,
	151	uint32_t *index_pos);
	152
68fb36eb VM	153	static inline uint32_t pack_name_hash(const char *name)
	154	{
	155	uint32_t c, hash = 0;
	156
	157	if (!name)
	158	return 0;
	159
	160	/*
	161	* This effectively just creates a sortable number from the
	162	* last sixteen non-whitespace characters. Last characters
	163	* count "most", so things that end in ".c" sort together.
	164	*/
	165	while ((c = *name++) != 0) {
	166	if (isspace(c))
	167	continue;
	168	hash = (hash >> 2) + (c << 24);
	169	}
	170	return hash;
	171	}
	172
fd9b1bae NTND	173	static inline enum object_type oe_type(const struct object_entry *e)
	174	{
	175	return e->type_valid ? e->type_ : OBJ_BAD;
	176	}
	177
	178	static inline void oe_set_type(struct object_entry *e,
	179	enum object_type type)
	180	{
	181	if (type >= OBJ_ANY)
	182	BUG("OBJ_ANY cannot be set in pack-objects code");
	183
	184	e->type_valid = type >= OBJ_NONE;
	185	e->type_ = (unsigned)type;
	186	}
	187
06af3bba NTND	188	static inline unsigned int oe_in_pack_pos(const struct packing_data *pack,
	189	const struct object_entry *e)
	190	{
	191	return pack->in_pack_pos[e - pack->objects];
	192	}
	193
	194	static inline void oe_set_in_pack_pos(const struct packing_data *pack,
	195	const struct object_entry *e,
	196	unsigned int pos)
	197	{
	198	pack->in_pack_pos[e - pack->objects] = pos;
	199	}
	200
43fa44fa NTND	201	static inline struct packed_git oe_in_pack(const struct packing_data pack,
	202	const struct object_entry *e)
	203	{
	204	if (pack->in_pack_by_idx)
	205	return pack->in_pack_by_idx[e->in_pack_idx];
	206	else
	207	return pack->in_pack[e - pack->objects];
	208	}
	209
	210	void oe_map_new_pack(struct packing_data *pack,
	211	struct packed_git *p);
	212	static inline void oe_set_in_pack(struct packing_data *pack,
	213	struct object_entry *e,
	214	struct packed_git *p)
	215	{
	216	if (!p->index)
	217	oe_map_new_pack(pack, p);
	218	if (pack->in_pack_by_idx)
	219	e->in_pack_idx = p->index;
	220	else
	221	pack->in_pack[e - pack->objects] = p;
	222	}
	223
898eba5e NTND	224	static inline struct object_entry *oe_delta(
	225	const struct packing_data *pack,
	226	const struct object_entry *e)
	227	{
	228	if (e->delta_idx)
	229	return &pack->objects[e->delta_idx - 1];
	230	return NULL;
	231	}
	232
	233	static inline void oe_set_delta(struct packing_data *pack,
	234	struct object_entry *e,
	235	struct object_entry *delta)
	236	{
	237	if (delta)
	238	e->delta_idx = (delta - pack->objects) + 1;
	239	else
	240	e->delta_idx = 0;
	241	}
	242
	243	static inline struct object_entry *oe_delta_child(
	244	const struct packing_data *pack,
	245	const struct object_entry *e)
	246	{
	247	if (e->delta_child_idx)
	248	return &pack->objects[e->delta_child_idx - 1];
	249	return NULL;
	250	}
	251
	252	static inline void oe_set_delta_child(struct packing_data *pack,
	253	struct object_entry *e,
	254	struct object_entry *delta)
	255	{
	256	if (delta)
	257	e->delta_child_idx = (delta - pack->objects) + 1;
	258	else
	259	e->delta_child_idx = 0;
	260	}
	261
	262	static inline struct object_entry *oe_delta_sibling(
	263	const struct packing_data *pack,
	264	const struct object_entry *e)
	265	{
	266	if (e->delta_sibling_idx)
	267	return &pack->objects[e->delta_sibling_idx - 1];
	268	return NULL;
	269	}
	270
	271	static inline void oe_set_delta_sibling(struct packing_data *pack,
	272	struct object_entry *e,
	273	struct object_entry *delta)
	274	{
	275	if (delta)
	276	e->delta_sibling_idx = (delta - pack->objects) + 1;
	277	else
	278	e->delta_sibling_idx = 0;
	279	}
	280
ac77d0c3 NTND	281	unsigned long oe_get_size_slow(struct packing_data *pack,
	282	const struct object_entry *e);
	283	static inline unsigned long oe_size(struct packing_data *pack,
	284	const struct object_entry *e)
	285	{
	286	if (e->size_valid)
	287	return e->size_;
	288
	289	return oe_get_size_slow(pack, e);
	290	}
	291
	292	static inline int oe_size_less_than(struct packing_data *pack,
	293	const struct object_entry *lhs,
	294	unsigned long rhs)
	295	{
	296	if (lhs->size_valid)
	297	return lhs->size_ < rhs;
	298	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
	299	return 0;
	300	return oe_get_size_slow(pack, lhs) < rhs;
	301	}
	302
	303	static inline int oe_size_greater_than(struct packing_data *pack,
	304	const struct object_entry *lhs,
	305	unsigned long rhs)
	306	{
	307	if (lhs->size_valid)
	308	return lhs->size_ > rhs;
	309	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
	310	return 1;
	311	return oe_get_size_slow(pack, lhs) > rhs;
	312	}
	313
	314	static inline void oe_set_size(struct packing_data *pack,
	315	struct object_entry *e,
	316	unsigned long size)
	317	{
	318	if (size < pack->oe_size_limit) {
	319	e->size_ = size;
	320	e->size_valid = 1;
	321	} else {
	322	e->size_valid = 0;
	323	if (oe_get_size_slow(pack, e) != size)
	324	BUG("'size' is supposed to be the object size!");
	325	}
	326	}
	327
0aca34e8 NTND	328	static inline unsigned long oe_delta_size(struct packing_data *pack,
	329	const struct object_entry *e)
	330	{
	331	if (e->delta_size_valid)
	332	return e->delta_size_;
	333	return oe_size(pack, e);
	334	}
	335
	336	static inline void oe_set_delta_size(struct packing_data *pack,
	337	struct object_entry *e,
	338	unsigned long size)
	339	{
	340	e->delta_size_ = size;
	341	e->delta_size_valid = e->delta_size_ == size;
	342	if (!e->delta_size_valid && size != oe_size(pack, e))
	343	BUG("this can only happen in check_object() "
	344	"where delta size is the same as entry size");
	345	}
	346
2834bc27	347	#endif