mirror/ git
1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-06-02 17:36:09 +02:00
Code
git/pack-objects.h
Jeff King e159b81071 pack-objects: zero-initialize tree_depth/layer arrays 
Commit 108f530385 (pack-objects: move tree_depth into 'struct
packing_data', 2018-08-16) started maintaining a tree_depth array that
matches the "objects" array. We extend the array when:

  1. The objects array is extended, in which case we use realloc to
     extend the tree_depth array.

  2. A caller asks to store a tree_depth for object N, and this is the
     first such request; we create the array from scratch and store the
     value for N.

In the latter case, though, we use regular xmalloc(), and the depth
values for any objects besides N is undefined. This happens to not
trigger a bug with the current code, but the reasons are quite subtle:

 - we never ask about the depth for any object with index i < N. This is
   because we store the depth immediately for all trees and blobs. So
   any such "i" must be a non-tree, and therefore we will never need to
   care about its depth (in fact, we really only care about the depth of
   trees).

 - there are no objects at this point with index i > N, because we
   always fill in the depth for a tree immediately after its object
   entry is created (we may still allocate uninitialized depth entries,
   but they'll be initialized by packlist_alloc() when it initializes
   the entry in the "objects" array).

So it works, but only by chance. To be defensive, let's zero the array,
which matches the "unset" values which would be handed out by
oe_tree_depth() already.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-11-21 13:50:27 +09:00

389 lines
11 KiB
C
Raw Blame History

#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;
/* delta islands */
unsigned int *tree_depth;
unsigned char *layer;
};
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");
}
static inline unsigned int oe_tree_depth(struct packing_data *pack,
struct object_entry *e)
{
if (!pack->tree_depth)
return 0;
return pack->tree_depth[e - pack->objects];
}
static inline void oe_set_tree_depth(struct packing_data *pack,
struct object_entry *e,
unsigned int tree_depth)
{
if (!pack->tree_depth)
CALLOC_ARRAY(pack->tree_depth, pack->nr_alloc);
pack->tree_depth[e - pack->objects] = tree_depth;
}
static inline unsigned char oe_layer(struct packing_data *pack,
struct object_entry *e)
{
if (!pack->layer)
return 0;
return pack->layer[e - pack->objects];
}
static inline void oe_set_layer(struct packing_data *pack,
struct object_entry *e,
unsigned char layer)
{
if (!pack->layer)
CALLOC_ARRAY(pack->layer, pack->nr_alloc);
pack->layer[e - pack->objects] = layer;
}
#endif
View Git Blame Copy Permalink