git/packfile.h

199 lines
7.0 KiB
C
Raw Normal View History

#ifndef PACKFILE_H
#define PACKFILE_H
#include "cache.h"
#include "oidset.h"
/* in object-store.h */
struct packed_git;
struct object_info;
/*
* Generate the filename to be used for a pack file with checksum "sha1" and
* extension "ext". The result is written into the strbuf "buf", overwriting
* any existing contents. A pointer to buf->buf is returned as a convenience.
*
* 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);
/*
* Return the basename of the packfile, omitting any containing directory
* (e.g., "pack-1234abcd[...].pack").
*/
const char *pack_basename(struct packed_git *p);
struct packed_git *parse_pack_index(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_pach, void *data);
void for_each_file_in_pack_dir(const char *objdir,
each_file_in_pack_dir_fn fn,
void *data);
/* 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);
midx: traverse the local MIDX first When a repository has an alternate object directory configured, callers can traverse through each alternate's MIDX by walking the '->next' pointer. But, when 'prepare_multi_pack_index_one()' loads multiple MIDXs, it places the new ones at the front of this pointer chain, not at the end. This can be confusing for callers such as 'git repack -ad', causing test failures like in t7700.6 with 'GIT_TEST_MULTI_PACK_INDEX=1'. The occurs when dropping a pack known to the local MIDX with alternates configured that have their own MIDX. Since the alternate's MIDX is returned via 'get_multi_pack_index()', 'midx_contains_pack()' returns true (which is correct, since it traverses through the '->next' pointer to find the MIDX in the chain that does contain the requested object). But, we call 'clear_midx_file()' on 'the_repository', which drops the MIDX at the path of the first MIDX in the chain, which (in the case of t7700.6 is the one in the alternate). This patch addresses that by: - placing the local MIDX first in the chain when calling 'prepare_multi_pack_index_one()', and - introducing a new 'get_local_multi_pack_index()', which explicitly returns the repository-local MIDX, if any. Don't impose an additional order on the MIDX's '->next' pointer beyond that the first item in the chain must be local if one exists so that we avoid a quadratic insertion. Likewise, use 'get_local_multi_pack_index()' in 'remove_redundant_pack()' to fix the formerly broken t7700.6 when run with 'GIT_TEST_MULTI_PACK_INDEX=1'. Finally, note that the MIDX ordering invariant is only preserved by the insertion order in 'prepare_packed_git()', which traverses through the ODB's '->next' pointer, meaning we visit the local object store first. This fragility makes this an undesirable long-term solution if more callers are added, but it is acceptable for now since this is the only caller. Helped-by: Jeff King <peff@peff.net> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-08-29 04:22:13 +08:00
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);
#define approximate_object_count() repo_approximate_object_count(the_repository)
struct packed_git *find_sha1_pack(const unsigned char *sha1,
struct packed_git *packs);
void pack_report(void);
/*
* mmap the index file for the specified packfile (if it is not
* already mmapped). Return 0 on success.
*/
int open_pack_index(struct packed_git *);
/*
* munmap the index file for the specified packfile (if it is
* currently mmapped).
*/
void close_pack_index(struct packed_git *);
int close_pack_fd(struct packed_git *p);
uint32_t get_pack_fanout(struct packed_git *p, uint32_t value);
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 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);
/*
* Unlink the .pack and associated extension files.
* Does not unlink if 'force_delete' is false and the pack-file is
* marked as ".keep".
*/
void unlink_pack_path(const char *pack_name, int force_delete);
/*
* Make sure that a pointer access into an mmap'd index file is within bounds,
* and can provide at least 8 bytes of data.
*
* Note that this is only necessary for variable-length segments of the file
* (like the 64-bit extended offset table), as we compare the size to the
* fixed-length parts when we open the file.
*/
void check_pack_index_ptr(const struct packed_git *p, const void *ptr);
/*
* Perform binary search on a pack-index for a given oid. Packfile is expected to
* have a valid pack-index.
*
* See 'bsearch_hash' for more information.
*/
int bsearch_pack(const struct object_id *oid, const struct packed_git *p, uint32_t *result);
/*
* Write the oid of the nth object within the specified packfile into the first
* parameter. Open the index if it is not already open. Returns 0 on success,
* negative otherwise.
*/
int nth_packed_object_id(struct object_id *, struct packed_git *, uint32_t n);
/*
* Return the offset of the nth object within the specified packfile.
* The index must already be opened.
*/
off_t nth_packed_object_offset(const struct packed_git *, uint32_t n);
/*
* If the object named sha1 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 *);
int is_pack_valid(struct packed_git *);
void *unpack_entry(struct repository *r, struct packed_git *, off_t, enum object_type *, unsigned long *);
unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep);
unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t);
int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *);
off_t get_delta_base(struct packed_git *p, struct pack_window **w_curs,
off_t *curpos, enum object_type type,
off_t delta_obj_offset);
void release_pack_memory(size_t);
/* global flag to enable extra checks when accessing packed objects */
extern int do_check_packed_object_crc;
int packed_object_info(struct repository *r,
struct packed_git *pack,
off_t offset, struct object_info *);
void mark_bad_packed_object(struct packed_git *, const struct object_id *);
const struct packed_git *has_packed_and_bad(struct repository *, const struct object_id *);
packfile: introduce 'find_kept_pack_entry()' Future callers will want a function to fill a 'struct pack_entry' for a given object id but _only_ from its position in any kept pack(s). In particular, an new 'git repack' mode which ensures the resulting packs form a geometric progress by object count will mark packs that it does not want to repack as "kept in-core", and it will want to halt a reachability traversal as soon as it visits an object in any of the kept packs. But, it does not want to halt the traversal at non-kept, or .keep packs. The obvious alternative is 'find_pack_entry()', but this doesn't quite suffice since it only returns the first pack it finds, which may or may not be kept (and the mru cache makes it unpredictable which one you'll get if there are options). Short of that, you could walk over all packs looking for the object in each one, but it scales with the number of packs, which may be prohibitive. Introduce 'find_kept_pack_entry()', a function which is like 'find_pack_entry()', but only fills in objects in the kept packs. Handle packs which have .keep files, as well as in-core kept packs separately, since certain callers will want to distinguish one from the other. (Though on-disk and in-core kept packs share the adjective "kept", it is best to think of the two sets as independent.) There is a gotcha when looking up objects that are duplicated in kept and non-kept packs, particularly when the MIDX stores the non-kept version and the caller asked for kept objects only. This could be resolved by teaching the MIDX to resolve duplicates by always favoring the kept pack (if one exists), but this breaks an assumption in existing MIDXs, and so it would require a format change. The benefit to changing the MIDX in this way is marginal, so we instead have a more thorough check here which is explained with a comment. Callers will be added in subsequent patches. Co-authored-by: Jeff King <peff@peff.net> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-23 10:25:03 +08:00
#define ON_DISK_KEEP_PACKS 1
#define IN_CORE_KEEP_PACKS 2
/*
* Iff a pack file in the given repository contains the object named by sha1,
* return true and store its location to e.
*/
int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e);
packfile: introduce 'find_kept_pack_entry()' Future callers will want a function to fill a 'struct pack_entry' for a given object id but _only_ from its position in any kept pack(s). In particular, an new 'git repack' mode which ensures the resulting packs form a geometric progress by object count will mark packs that it does not want to repack as "kept in-core", and it will want to halt a reachability traversal as soon as it visits an object in any of the kept packs. But, it does not want to halt the traversal at non-kept, or .keep packs. The obvious alternative is 'find_pack_entry()', but this doesn't quite suffice since it only returns the first pack it finds, which may or may not be kept (and the mru cache makes it unpredictable which one you'll get if there are options). Short of that, you could walk over all packs looking for the object in each one, but it scales with the number of packs, which may be prohibitive. Introduce 'find_kept_pack_entry()', a function which is like 'find_pack_entry()', but only fills in objects in the kept packs. Handle packs which have .keep files, as well as in-core kept packs separately, since certain callers will want to distinguish one from the other. (Though on-disk and in-core kept packs share the adjective "kept", it is best to think of the two sets as independent.) There is a gotcha when looking up objects that are duplicated in kept and non-kept packs, particularly when the MIDX stores the non-kept version and the caller asked for kept objects only. This could be resolved by teaching the MIDX to resolve duplicates by always favoring the kept pack (if one exists), but this breaks an assumption in existing MIDXs, and so it would require a format change. The benefit to changing the MIDX in this way is marginal, so we instead have a more thorough check here which is explained with a comment. Callers will be added in subsequent patches. Co-authored-by: Jeff King <peff@peff.net> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-23 10:25:03 +08:00
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);
packfile: introduce 'find_kept_pack_entry()' Future callers will want a function to fill a 'struct pack_entry' for a given object id but _only_ from its position in any kept pack(s). In particular, an new 'git repack' mode which ensures the resulting packs form a geometric progress by object count will mark packs that it does not want to repack as "kept in-core", and it will want to halt a reachability traversal as soon as it visits an object in any of the kept packs. But, it does not want to halt the traversal at non-kept, or .keep packs. The obvious alternative is 'find_pack_entry()', but this doesn't quite suffice since it only returns the first pack it finds, which may or may not be kept (and the mru cache makes it unpredictable which one you'll get if there are options). Short of that, you could walk over all packs looking for the object in each one, but it scales with the number of packs, which may be prohibitive. Introduce 'find_kept_pack_entry()', a function which is like 'find_pack_entry()', but only fills in objects in the kept packs. Handle packs which have .keep files, as well as in-core kept packs separately, since certain callers will want to distinguish one from the other. (Though on-disk and in-core kept packs share the adjective "kept", it is best to think of the two sets as independent.) There is a gotcha when looking up objects that are duplicated in kept and non-kept packs, particularly when the MIDX stores the non-kept version and the caller asked for kept objects only. This could be resolved by teaching the MIDX to resolve duplicates by always favoring the kept pack (if one exists), but this breaks an assumption in existing MIDXs, and so it would require a format change. The benefit to changing the MIDX in this way is marginal, so we instead have a more thorough check here which is explained with a comment. Callers will be added in subsequent patches. Co-authored-by: Jeff King <peff@peff.net> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Reviewed-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-23 10:25:03 +08:00
int has_object_kept_pack(const struct object_id *oid, unsigned flags);
int has_pack_index(const unsigned char *sha1);
/*
* 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);
/*
* Expose a function for fuzz testing.
*
* load_idx() parses a block of memory as a packfile index and puts the results
* into a struct packed_git.
*
* 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.
*/
int load_idx(const char *path, const unsigned int hashsz, void *idx_map,
size_t idx_size, struct packed_git *p);
#endif