1190a1acf8
Our current scheme for naming packfiles is to calculate the sha1 hash of the sorted list of objects contained in the packfile. This gives us a unique name, so we are reasonably sure that two packs with the same name will contain the same objects. It does not, however, tell us that two such packs have the exact same bytes. This makes things awkward if we repack the same set of objects. Due to run-to-run variations, the bytes may not be identical (e.g., changed zlib or git versions, different source object reuse due to new packs in the repository, or even different deltas due to races during a multi-threaded delta search). In theory, this could be helpful to a program that cares that the packfile contains a certain set of objects, but does not care about the particular representation. In practice, no part of git makes use of that, and in many cases it is potentially harmful. For example, if a dumb http client fetches the .idx file, it must be sure to get the exact .pack that matches it. Similarly, a partial transfer of a .pack file cannot be safely resumed, as the actual bytes may have changed. This could also affect a local client which opened the .idx and .pack files, closes the .pack file (due to memory or file descriptor limits), and then re-opens a changed packfile. In all of these cases, git can detect the problem, as we have the sha1 of the bytes themselves in the pack trailer (which we verify on transfer), and the .idx file references the trailer from the matching packfile. But it would be simpler and more efficient to actually get the correct bytes, rather than noticing the problem and having to restart the operation. This patch simply uses the pack trailer sha1 as the pack name. It should be similarly unique, but covers the exact representation of the objects. Other parts of git should not care, as the pack name is returned by pack-objects and is essentially opaque. One test needs to be updated, because it actually corrupts a pack and expects that re-packing the corrupted bytes will use the same name. It won't anymore, but we can easily just use the name that pack-objects hands back. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
97 lines
3.2 KiB
C
97 lines
3.2 KiB
C
#ifndef PACK_H
|
|
#define PACK_H
|
|
|
|
#include "object.h"
|
|
#include "csum-file.h"
|
|
|
|
/*
|
|
* Packed object header
|
|
*/
|
|
#define PACK_SIGNATURE 0x5041434b /* "PACK" */
|
|
#define PACK_VERSION 2
|
|
#define pack_version_ok(v) ((v) == htonl(2) || (v) == htonl(3))
|
|
struct pack_header {
|
|
uint32_t hdr_signature;
|
|
uint32_t hdr_version;
|
|
uint32_t hdr_entries;
|
|
};
|
|
|
|
/*
|
|
* The first four bytes of index formats later than version 1 should
|
|
* start with this signature, as all older git binaries would find this
|
|
* value illegal and abort reading the file.
|
|
*
|
|
* This is the case because the number of objects in a packfile
|
|
* cannot exceed 1,431,660,000 as every object would need at least
|
|
* 3 bytes of data and the overall packfile cannot exceed 4 GiB with
|
|
* version 1 of the index file due to the offsets limited to 32 bits.
|
|
* Clearly the signature exceeds this maximum.
|
|
*
|
|
* Very old git binaries will also compare the first 4 bytes to the
|
|
* next 4 bytes in the index and abort with a "non-monotonic index"
|
|
* error if the second 4 byte word is smaller than the first 4
|
|
* byte word. This would be true in the proposed future index
|
|
* format as idx_signature would be greater than idx_version.
|
|
*/
|
|
#define PACK_IDX_SIGNATURE 0xff744f63 /* "\377tOc" */
|
|
|
|
struct pack_idx_option {
|
|
unsigned flags;
|
|
/* flag bits */
|
|
#define WRITE_IDX_VERIFY 01 /* verify only, do not write the idx file */
|
|
#define WRITE_IDX_STRICT 02
|
|
|
|
uint32_t version;
|
|
uint32_t off32_limit;
|
|
|
|
/*
|
|
* List of offsets that would fit within off32_limit but
|
|
* need to be written out as 64-bit entity for byte-for-byte
|
|
* verification.
|
|
*/
|
|
int anomaly_alloc, anomaly_nr;
|
|
uint32_t *anomaly;
|
|
};
|
|
|
|
extern void reset_pack_idx_option(struct pack_idx_option *);
|
|
|
|
/*
|
|
* Packed object index header
|
|
*/
|
|
struct pack_idx_header {
|
|
uint32_t idx_signature;
|
|
uint32_t idx_version;
|
|
};
|
|
|
|
/*
|
|
* Common part of object structure used for write_idx_file
|
|
*/
|
|
struct pack_idx_entry {
|
|
unsigned char sha1[20];
|
|
uint32_t crc32;
|
|
off_t offset;
|
|
};
|
|
|
|
|
|
struct progress;
|
|
typedef int (*verify_fn)(const unsigned char*, enum object_type, unsigned long, void*, int*);
|
|
|
|
extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, const struct pack_idx_option *, const unsigned char *sha1);
|
|
extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr);
|
|
extern int verify_pack_index(struct packed_git *);
|
|
extern int verify_pack(struct packed_git *, verify_fn fn, struct progress *, uint32_t);
|
|
extern off_t write_pack_header(struct sha1file *f, uint32_t);
|
|
extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t, unsigned char *, off_t);
|
|
extern char *index_pack_lockfile(int fd);
|
|
extern int encode_in_pack_object_header(enum object_type, uintmax_t, unsigned char *);
|
|
|
|
#define PH_ERROR_EOF (-1)
|
|
#define PH_ERROR_PACK_SIGNATURE (-2)
|
|
#define PH_ERROR_PROTOCOL (-3)
|
|
extern int read_pack_header(int fd, struct pack_header *);
|
|
|
|
extern struct sha1file *create_tmp_packfile(char **pack_tmp_name);
|
|
extern void finish_tmp_packfile(char *name_buffer, const char *pack_tmp_name, struct pack_idx_entry **written_list, uint32_t nr_written, struct pack_idx_option *pack_idx_opts, unsigned char sha1[]);
|
|
|
|
#endif
|