diff options
Diffstat (limited to 'packfile.h')
| -rw-r--r-- | packfile.h | 258 |
1 files changed, 219 insertions, 39 deletions
diff --git a/packfile.h b/packfile.h index 28c8fd3e39..c9d0b93446 100644 --- a/packfile.h +++ b/packfile.h @@ -1,13 +1,168 @@ #ifndef PACKFILE_H #define PACKFILE_H +#include "list.h" #include "object.h" +#include "odb.h" #include "oidset.h" -/* in object-store.h */ -struct packed_git; +/* in odb.h */ struct object_info; +struct packed_git { + struct hashmap_entry packmap_ent; + struct packed_git *next; + struct list_head mru; + struct pack_window *windows; + off_t pack_size; + const void *index_data; + size_t index_size; + uint32_t num_objects; + size_t crc_offset; + struct oidset bad_objects; + int index_version; + time_t mtime; + int pack_fd; + int index; /* for builtin/pack-objects.c */ + unsigned pack_local:1, + pack_keep:1, + pack_keep_in_core:1, + freshened:1, + do_not_close:1, + pack_promisor:1, + multi_pack_index:1, + is_cruft:1; + unsigned char hash[GIT_MAX_RAWSZ]; + struct revindex_entry *revindex; + const uint32_t *revindex_data; + const uint32_t *revindex_map; + size_t revindex_size; + /* + * mtimes_map points at the beginning of the memory mapped region of + * this pack's corresponding .mtimes file, and mtimes_size is the size + * of that .mtimes file + */ + const uint32_t *mtimes_map; + size_t mtimes_size; + + /* repo denotes the repository this packfile belongs to */ + struct repository *repo; + + /* something like ".git/objects/pack/xxxxx.pack" */ + char pack_name[FLEX_ARRAY]; /* more */ +}; + +/* + * A store that manages packfiles for a given object database. + */ +struct packfile_store { + struct object_database *odb; + + /* + * The list of packfiles in the order in which they are being added to + * the store. + */ + struct packed_git *packs; + + /* + * Cache of packfiles which are marked as "kept", either because there + * is an on-disk ".keep" file or because they are marked as "kept" in + * memory. + * + * Should not be accessed directly, but via `kept_pack_cache()`. The + * list of packs gets invalidated when the stored flags and the flags + * passed to `kept_pack_cache()` mismatch. + */ + struct { + struct packed_git **packs; + unsigned flags; + } kept_cache; + + /* A most-recently-used ordered version of the packs list. */ + struct list_head mru; + + /* + * A map of packfile names to packed_git structs for tracking which + * packs have been loaded already. + */ + struct hashmap map; + + /* + * Whether packfiles have already been populated with this store's + * packs. + */ + bool initialized; +}; + +/* + * Allocate and initialize a new empty packfile store for the given object + * database. + */ +struct packfile_store *packfile_store_new(struct object_database *odb); + +/* + * Free the packfile store and all its associated state. All packfiles + * tracked by the store will be closed. + */ +void packfile_store_free(struct packfile_store *store); + +/* + * Close all packfiles associated with this store. The packfiles won't be + * free'd, so they can be re-opened at a later point in time. + */ +void packfile_store_close(struct packfile_store *store); + +/* + * Prepare the packfile store by loading packfiles and multi-pack indices for + * all alternates. This becomes a no-op if the store is already prepared. + * + * It shouldn't typically be necessary to call this function directly, as + * functions that access the store know to prepare it. + */ +void packfile_store_prepare(struct packfile_store *store); + +/* + * Clear the packfile caches and try to look up any new packfiles that have + * appeared since last preparing the packfiles store. + * + * This function must be called under the `odb_read_lock()`. + */ +void packfile_store_reprepare(struct packfile_store *store); + +/* + * Add the pack to the store so that contained objects become accessible via + * the store. This moves ownership into the store. + */ +void packfile_store_add_pack(struct packfile_store *store, + struct packed_git *pack); + +/* + * Load and iterate through all packs of the given repository. This helper + * function will yield packfiles from all object sources connected to the + * repository. + */ +#define repo_for_each_pack(repo, p) \ + for (p = packfile_store_get_packs(repo->objects->packfiles); p; p = p->next) + +/* + * Get all packs managed by the given store, including packfiles that are + * referenced by multi-pack indices. + */ +struct packed_git *packfile_store_get_packs(struct packfile_store *store); + +/* + * Get all packs in most-recently-used order. + */ +struct list_head *packfile_store_get_packs_mru(struct packfile_store *store); + +/* + * Open the packfile and add it to the store if it isn't yet known. Returns + * either the newly opened packfile or the preexisting packfile. Returns a + * `NULL` pointer in case the packfile could not be opened. + */ +struct packed_git *packfile_store_load_pack(struct packfile_store *store, + const char *idx_path, int local); + struct pack_window { struct pack_window *next; unsigned char *base; @@ -29,21 +184,8 @@ struct pack_entry { * * Example: odb_pack_name(out, sha1, "idx") => ".git/objects/pack/pack-1234..idx" */ -char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext); - -/* - * Return the name of the (local) packfile with the specified sha1 in - * its name. The return value is a pointer to memory that is - * overwritten each time this function is called. - */ -char *sha1_pack_name(const unsigned char *sha1); - -/* - * Return the name of the (local) pack index file with the specified - * sha1 in its name. The return value is a pointer to memory that is - * overwritten each time this function is called. - */ -char *sha1_pack_index_name(const unsigned char *sha1); +char *odb_pack_name(struct repository *r, struct strbuf *buf, + const unsigned char *hash, const char *ext); /* * Return the basename of the packfile, omitting any containing directory @@ -51,39 +193,67 @@ char *sha1_pack_index_name(const unsigned char *sha1); */ const char *pack_basename(struct packed_git *p); -struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path); +/* + * Parse the pack idx file found at idx_path and create a packed_git struct + * which can be used with find_pack_entry_one(). + * + * You probably don't want to use this function! It skips most of the normal + * sanity checks (including whether we even have the matching .pack file), + * and does not add the resulting packed_git struct to the internal list of + * packs. You probably want add_packed_git() instead. + */ +struct packed_git *parse_pack_index(struct repository *r, unsigned char *sha1, + const char *idx_path); typedef void each_file_in_pack_dir_fn(const char *full_path, size_t full_path_len, const char *file_name, void *data); +void for_each_file_in_pack_subdir(const char *objdir, + const char *subdir, + each_file_in_pack_dir_fn fn, + void *data); void for_each_file_in_pack_dir(const char *objdir, each_file_in_pack_dir_fn fn, void *data); +/* + * Iterate over all accessible packed objects without respect to reachability. + * By default, this includes both local and alternate packs. + * + * Note that some objects may appear twice if they are found in multiple packs. + * Each pack is visited in an unspecified order. By default, objects within a + * pack are visited in pack-idx order (i.e., sorted by oid). + */ +typedef int each_packed_object_fn(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *data); +int for_each_object_in_pack(struct packed_git *p, + each_packed_object_fn, void *data, + enum for_each_object_flags flags); +int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, + void *data, enum for_each_object_flags flags); + /* A hook to report invalid files in pack directory */ #define PACKDIR_FILE_PACK 1 #define PACKDIR_FILE_IDX 2 #define PACKDIR_FILE_GARBAGE 4 extern void (*report_garbage)(unsigned seen_bits, const char *path); -void reprepare_packed_git(struct repository *r); -void install_packed_git(struct repository *r, struct packed_git *pack); - -struct packed_git *get_packed_git(struct repository *r); -struct list_head *get_packed_git_mru(struct repository *r); -struct multi_pack_index *get_multi_pack_index(struct repository *r); -struct multi_pack_index *get_local_multi_pack_index(struct repository *r); -struct packed_git *get_all_packs(struct repository *r); - /* * Give a rough count of objects in the repository. This sacrifices accuracy * for speed. */ unsigned long repo_approximate_object_count(struct repository *r); -struct packed_git *find_sha1_pack(const unsigned char *sha1, - struct packed_git *packs); +/* + * Find the pack within the "packs" list whose index contains the object "oid". + * For general object lookups, you probably don't want this; use + * find_pack_entry() instead. + */ +struct packed_git *find_oid_pack(const struct object_id *oid, + struct packed_git *packs); -void pack_report(void); +void pack_report(struct repository *repo); /* * mmap the index file for the specified packfile (if it is not @@ -101,13 +271,16 @@ int close_pack_fd(struct packed_git *p); uint32_t get_pack_fanout(struct packed_git *p, uint32_t value); +struct object_database; + unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); void close_pack_windows(struct packed_git *); void close_pack(struct packed_git *); -void close_object_store(struct raw_object_store *o); +void close_object_store(struct object_database *o); void unuse_pack(struct pack_window **); void clear_delta_base_cache(void); -struct packed_git *add_packed_git(const char *path, size_t path_len, int local); +struct packed_git *add_packed_git(struct repository *r, const char *path, + size_t path_len, int local); /* * Unlink the .pack and associated extension files. @@ -148,10 +321,10 @@ int nth_packed_object_id(struct object_id *, struct packed_git *, uint32_t n); off_t nth_packed_object_offset(const struct packed_git *, uint32_t n); /* - * If the object named sha1 is present in the specified packfile, + * If the object named by oid is present in the specified packfile, * return its offset within the packfile; otherwise, return 0. */ -off_t find_pack_entry_one(const unsigned char *sha1, struct packed_git *); +off_t find_pack_entry_one(const struct object_id *oid, struct packed_git *); int is_pack_valid(struct packed_git *); void *unpack_entry(struct repository *r, struct packed_git *, off_t, enum object_type *, unsigned long *); @@ -184,16 +357,17 @@ const struct packed_git *has_packed_and_bad(struct repository *, const struct ob int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e); int find_kept_pack_entry(struct repository *r, const struct object_id *oid, unsigned flags, struct pack_entry *e); -int has_object_pack(const struct object_id *oid); -int has_object_kept_pack(const struct object_id *oid, unsigned flags); +int has_object_pack(struct repository *r, const struct object_id *oid); +int has_object_kept_pack(struct repository *r, const struct object_id *oid, + unsigned flags); -int has_pack_index(const unsigned char *sha1); +struct packed_git **kept_pack_cache(struct repository *r, unsigned flags); /* * Return 1 if an object in a promisor packfile is or refers to the given * object, 0 otherwise. */ -int is_promisor_object(const struct object_id *oid); +int is_promisor_object(struct repository *r, const struct object_id *oid); /* * Expose a function for fuzz testing. @@ -203,9 +377,15 @@ int is_promisor_object(const struct object_id *oid); * * This function should not be used directly. It is exposed here only so that we * have a convenient entry-point for fuzz testing. For real uses, you should - * probably use open_pack_index() or parse_pack_index() instead. + * probably use open_pack_index() instead. */ int load_idx(const char *path, const unsigned int hashsz, void *idx_map, size_t idx_size, struct packed_git *p); +/* + * Parse a --pack_header option as accepted by index-pack and unpack-objects, + * turning it into the matching bytes we'd find in a pack. + */ +int parse_pack_header_option(const char *in, unsigned char *out, unsigned int *len); + #endif |