#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 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
*
* "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.
+ * 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()
*/
struct object_entry {
struct pack_idx_entry idx;
- unsigned long size; /* uncompressed size */
- struct packed_git *in_pack; /* already in pack */
- off_t in_pack_offset;
- struct object_entry *delta; /* delta base object */
- struct object_entry *delta_child; /* deltified objects who bases me */
- struct object_entry *delta_sibling; /* 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 long z_delta_size; /* delta data size (compressed) */
+ 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 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 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 {
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);
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