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

#ifndef PACK_OBJECTS_H
#define PACK_OBJECTS_H

#include "object-store.h"

#define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024)

#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
9806f5a7 NTND	6	#define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024)
9806f5a7 NTND	7
0c6804ab	8	#define OE_DFS_STATE_BITS 2
b5c0cbd8	9	#define OE_DEPTH_BITS 12
43fa44fa	10	#define OE_IN_PACK_BITS 10
0cb3c142	11	#define OE_Z_DELTA_BITS 20
ac77d0c3 NTND	12	/*
	13	* Note that oe_set_size() becomes expensive when the given size is
	14	* above this limit. Don't lower it too much.
	15	*/
	16	#define OE_SIZE_BITS 31
0aca34e8	17	#define OE_DELTA_SIZE_BITS 20
0c6804ab NTND	18
	19	/*
	20	* State flags for depth-first search used for analyzing delta cycles.
	21	*
	22	* The depth is measured in delta-links to the base (so if A is a delta
	23	* against B, then A has a depth of 1, and B a depth of 0).
	24	*/
	25	enum dfs_state {
	26	DFS_NONE = 0,
	27	DFS_ACTIVE,
	28	DFS_DONE,
	29	DFS_NUM_STATES
	30	};
	31
8d6ccce1	32	/*
3b13a5f2 NTND	33	* The size of struct nearly determines pack-objects's memory
	34	* consumption. This struct is packed tight for that reason. When you
	35	* add or reorder something in this struct, think a bit about this.
	36	*
8d6ccce1 NTND	37	* basic object info
	38	* -----------------
	39	* idx.oid is filled up before delta searching starts. idx.crc32 is
	40	* only valid after the object is written out and will be used for
	41	* generating the index. idx.offset will be both gradually set and
	42	* used in writing phase (base objects get offset first, then deltas
	43	* refer to them)
	44	*
	45	* "size" is the uncompressed object size. Compressed size of the raw
	46	* data for an object in a pack is not stored anywhere but is computed
27a7d067 NTND	47	* and made available when reverse .idx is made. Note that when a
	48	* delta is reused, "size" is the uncompressed _delta_ size, not the
	49	* canonical one after the delta has been applied.
8d6ccce1 NTND	50	*
	51	* "hash" contains a path name hash which is used for sorting the
	52	* delta list and also during delta searching. Once prepare_pack()
	53	* returns it's no longer needed.
	54	*
	55	* source pack info
	56	* ----------------
	57	* The (in_pack, in_pack_offset) tuple contains the location of the
	58	* object in the source pack. in_pack_header_size allows quickly
	59	* skipping the header and going straight to the zlib stream.
	60	*
	61	* "type" and "in_pack_type" both describe object type. in_pack_type
	62	* may contain a delta type, while type is always the canonical type.
	63	*
	64	* deltas
	65	* ------
	66	* Delta links (delta, delta_child and delta_sibling) are created to
	67	* reflect that delta graph from the source pack then updated or added
	68	* during delta searching phase when we find better deltas.
	69	*
	70	* delta_child and delta_sibling are last needed in
	71	* compute_write_order(). "delta" and "delta_size" must remain valid
	72	* at object writing phase in case the delta is not cached.
	73	*
	74	* If a delta is cached in memory and is compressed, delta_data points
	75	* to the data and z_delta_size contains the compressed size. If it's
	76	* uncompressed [1], z_delta_size must be zero. delta_size is always
	77	* the uncompressed size and must be valid even if the delta is not
	78	* cached.
	79	*
	80	* [1] during try_delta phase we don't bother with compressing because
	81	* the delta could be quickly replaced with a better one.
	82	*/
2834bc27 VM	83	struct object_entry {
2834bc27 VM	84	struct pack_idx_entry idx;
2834bc27	85	void delta_data; / cached delta (uncompressed) */
3b13a5f2	86	off_t in_pack_offset;
2834bc27	87	uint32_t hash; /* name hint hash */
ac77d0c3 NTND	88	unsigned size_:OE_SIZE_BITS;
ac77d0c3 NTND	89	unsigned size_valid:1;
898eba5e NTND	90	uint32_t delta_idx; /* delta base object */
	91	uint32_t delta_child_idx; /* deltified objects who bases me */
	92	uint32_t delta_sibling_idx; /* other deltified objects who
	93	* uses the same base as me
	94	*/
0aca34e8 NTND	95	unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
0aca34e8 NTND	96	unsigned delta_size_valid:1;
3b13a5f2	97	unsigned in_pack_idx:OE_IN_PACK_BITS; /* already in pack */
0cb3c142	98	unsigned z_delta_size:OE_Z_DELTA_BITS;
3b13a5f2	99	unsigned type_valid:1;
fd9b1bae	100	unsigned type_:TYPE_BITS;
3b13a5f2	101	unsigned no_try_delta:1;
fd9b1bae	102	unsigned in_pack_type:TYPE_BITS; /* could be delta */
2834bc27 VM	103	unsigned preferred_base:1; /*
	104	* we do not pack this, but is available
	105	* to be used as the base object to delta
	106	* objects against.
	107	*/
2834bc27 VM	108	unsigned tagged:1; /* near the very tip of refs */
2834bc27 VM	109	unsigned filled:1; /* assigned write-order */
0c6804ab	110	unsigned dfs_state:OE_DFS_STATE_BITS;
3b13a5f2	111	unsigned char in_pack_header_size;
b5c0cbd8	112	unsigned depth:OE_DEPTH_BITS;
4cf2143e JK	113
4cf2143e JK	114	/*
3b13a5f2	115	* pahole results on 64-bit linux (gcc and clang)
7dbabbbe	116	*
3b13a5f2 NTND	117	* size: 80, bit_padding: 20 bits, holes: 8 bits
	118	*
	119	* and on 32-bit (gcc)
	120	*
	121	* size: 76, bit_padding: 20 bits, holes: 8 bits
4cf2143e	122	*/
2834bc27 VM	123	};
	124
	125	struct packing_data {
	126	struct object_entry *objects;
	127	uint32_t nr_objects, nr_alloc;
	128
	129	int32_t *index;
	130	uint32_t index_size;
06af3bba NTND	131
06af3bba NTND	132	unsigned int *in_pack_pos;
43fa44fa NTND	133
	134	/*
	135	* Only one of these can be non-NULL and they have different
	136	* sizes. if in_pack_by_idx is allocated, oe_in_pack() returns
	137	* the pack of an object using in_pack_idx field. If not,
	138	* in_pack[] array is used the same way as in_pack_pos[]
	139	*/
	140	struct packed_git **in_pack_by_idx;
	141	struct packed_git **in_pack;
ac77d0c3 NTND	142
ac77d0c3 NTND	143	uintmax_t oe_size_limit;
2834bc27 VM	144	};
2834bc27 VM	145
43fa44fa	146	void prepare_packing_data(struct packing_data *pdata);
2834bc27 VM	147	struct object_entry packlist_alloc(struct packing_data pdata,
	148	const unsigned char *sha1,
	149	uint32_t index_pos);
	150
	151	struct object_entry packlist_find(struct packing_data pdata,
	152	const unsigned char *sha1,
	153	uint32_t *index_pos);
	154
68fb36eb VM	155	static inline uint32_t pack_name_hash(const char *name)
	156	{
	157	uint32_t c, hash = 0;
	158
	159	if (!name)
	160	return 0;
	161
	162	/*
	163	* This effectively just creates a sortable number from the
	164	* last sixteen non-whitespace characters. Last characters
	165	* count "most", so things that end in ".c" sort together.
	166	*/
	167	while ((c = *name++) != 0) {
	168	if (isspace(c))
	169	continue;
	170	hash = (hash >> 2) + (c << 24);
	171	}
	172	return hash;
	173	}
	174
fd9b1bae NTND	175	static inline enum object_type oe_type(const struct object_entry *e)
	176	{
	177	return e->type_valid ? e->type_ : OBJ_BAD;
	178	}
	179
	180	static inline void oe_set_type(struct object_entry *e,
	181	enum object_type type)
	182	{
	183	if (type >= OBJ_ANY)
	184	BUG("OBJ_ANY cannot be set in pack-objects code");
	185
	186	e->type_valid = type >= OBJ_NONE;
	187	e->type_ = (unsigned)type;
	188	}
	189
06af3bba NTND	190	static inline unsigned int oe_in_pack_pos(const struct packing_data *pack,
	191	const struct object_entry *e)
	192	{
	193	return pack->in_pack_pos[e - pack->objects];
	194	}
	195
	196	static inline void oe_set_in_pack_pos(const struct packing_data *pack,
	197	const struct object_entry *e,
	198	unsigned int pos)
	199	{
	200	pack->in_pack_pos[e - pack->objects] = pos;
	201	}
	202
43fa44fa NTND	203	static inline struct packed_git oe_in_pack(const struct packing_data pack,
	204	const struct object_entry *e)
	205	{
	206	if (pack->in_pack_by_idx)
	207	return pack->in_pack_by_idx[e->in_pack_idx];
	208	else
	209	return pack->in_pack[e - pack->objects];
	210	}
	211
	212	void oe_map_new_pack(struct packing_data *pack,
	213	struct packed_git *p);
	214	static inline void oe_set_in_pack(struct packing_data *pack,
	215	struct object_entry *e,
	216	struct packed_git *p)
	217	{
	218	if (!p->index)
	219	oe_map_new_pack(pack, p);
	220	if (pack->in_pack_by_idx)
	221	e->in_pack_idx = p->index;
	222	else
	223	pack->in_pack[e - pack->objects] = p;
	224	}
	225
898eba5e NTND	226	static inline struct object_entry *oe_delta(
	227	const struct packing_data *pack,
	228	const struct object_entry *e)
	229	{
	230	if (e->delta_idx)
	231	return &pack->objects[e->delta_idx - 1];
	232	return NULL;
	233	}
	234
	235	static inline void oe_set_delta(struct packing_data *pack,
	236	struct object_entry *e,
	237	struct object_entry *delta)
	238	{
	239	if (delta)
	240	e->delta_idx = (delta - pack->objects) + 1;
	241	else
	242	e->delta_idx = 0;
	243	}
	244
	245	static inline struct object_entry *oe_delta_child(
	246	const struct packing_data *pack,
	247	const struct object_entry *e)
	248	{
	249	if (e->delta_child_idx)
	250	return &pack->objects[e->delta_child_idx - 1];
	251	return NULL;
	252	}
	253
	254	static inline void oe_set_delta_child(struct packing_data *pack,
	255	struct object_entry *e,
	256	struct object_entry *delta)
	257	{
	258	if (delta)
	259	e->delta_child_idx = (delta - pack->objects) + 1;
	260	else
	261	e->delta_child_idx = 0;
	262	}
	263
	264	static inline struct object_entry *oe_delta_sibling(
	265	const struct packing_data *pack,
	266	const struct object_entry *e)
	267	{
	268	if (e->delta_sibling_idx)
	269	return &pack->objects[e->delta_sibling_idx - 1];
	270	return NULL;
	271	}
	272
	273	static inline void oe_set_delta_sibling(struct packing_data *pack,
	274	struct object_entry *e,
	275	struct object_entry *delta)
	276	{
	277	if (delta)
	278	e->delta_sibling_idx = (delta - pack->objects) + 1;
	279	else
	280	e->delta_sibling_idx = 0;
	281	}
	282
ac77d0c3 NTND	283	unsigned long oe_get_size_slow(struct packing_data *pack,
	284	const struct object_entry *e);
	285	static inline unsigned long oe_size(struct packing_data *pack,
	286	const struct object_entry *e)
	287	{
	288	if (e->size_valid)
	289	return e->size_;
	290
	291	return oe_get_size_slow(pack, e);
	292	}
	293
	294	static inline int oe_size_less_than(struct packing_data *pack,
	295	const struct object_entry *lhs,
	296	unsigned long rhs)
	297	{
	298	if (lhs->size_valid)
	299	return lhs->size_ < rhs;
	300	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
	301	return 0;
	302	return oe_get_size_slow(pack, lhs) < rhs;
	303	}
	304
	305	static inline int oe_size_greater_than(struct packing_data *pack,
	306	const struct object_entry *lhs,
	307	unsigned long rhs)
	308	{
	309	if (lhs->size_valid)
	310	return lhs->size_ > rhs;
	311	if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */
	312	return 1;
	313	return oe_get_size_slow(pack, lhs) > rhs;
	314	}
	315
	316	static inline void oe_set_size(struct packing_data *pack,
	317	struct object_entry *e,
	318	unsigned long size)
	319	{
	320	if (size < pack->oe_size_limit) {
	321	e->size_ = size;
	322	e->size_valid = 1;
	323	} else {
	324	e->size_valid = 0;
	325	if (oe_get_size_slow(pack, e) != size)
	326	BUG("'size' is supposed to be the object size!");
	327	}
	328	}
	329
0aca34e8 NTND	330	static inline unsigned long oe_delta_size(struct packing_data *pack,
	331	const struct object_entry *e)
	332	{
	333	if (e->delta_size_valid)
	334	return e->delta_size_;
	335	return oe_size(pack, e);
	336	}
	337
	338	static inline void oe_set_delta_size(struct packing_data *pack,
	339	struct object_entry *e,
	340	unsigned long size)
	341	{
	342	e->delta_size_ = size;
	343	e->delta_size_valid = e->delta_size_ == size;
	344	if (!e->delta_size_valid && size != oe_size(pack, e))
	345	BUG("this can only happen in check_object() "
	346	"where delta size is the same as entry size");
	347	}
	348
2834bc27	349	#endif