[PATCH 02/17] pack-mtimes: support reading .mtimes files
- From
Taylor Blau <me@ttaylorr.com>
- Date
- Nov 29, 2021, 22:25 UTC
- Message-ID
- <7d4ae7bd3e28e2ec904abb37b6f26505e37531c5.1638224692.git.me@ttaylorr.com>
- In-Reply-To
- <cover.1638224692.git.me@ttaylorr.com>
To store the individual mtimes of objects in a cruft pack, introduce a new `.mtimes` format that can optionally accompany a single pack in the repository.
The format is defined in Documentation/technical/pack-format.txt, and stores a 4-byte network order timestamp for each object in name (index) order.
This patch prepares for cruft packs by defining the `.mtimes` format, and introducing a basic API that callers can use to read out individual mtimes.
Signed-off-by: Taylor Blau <me@ttaylorr.com> --- Documentation/technical/pack-format.txt | 22 ++++ Makefile | 1 + builtin/repack.c | 1 + object-store.h | 5 +- pack-mtimes.c | 139 ++++++++++++++++++++++++ pack-mtimes.h | 16 +++ packfile.c | 18 ++- packfile.h | 1 + 8 files changed, 200 insertions(+), 3 deletions(-) create mode 100644 pack-mtimes.c create mode 100644 pack-mtimes.h
diff --git a/Documentation/technical/pack-format.txt b/Documentation/technical/pack-format.txt index 8d2f42f29e..61d8d960e7 100644 --- a/Documentation/technical/pack-format.txt +++ b/Documentation/technical/pack-format.txt @@ -294,6 +294,28 @@ Pack file entry: <+ All 4-byte numbers are in network order. +== pack-*.mtimes files have the format: + + - A 4-byte magic number '0x4d544d45' ('MTME'). + + - A 4-byte version identifier (= 1). + + - A 4-byte hash function identifier (= 1 for SHA-1, 2 for SHA-256). + + - A table of mtimes (one per packed object, num_objects in total, each + a 4-byte unsigned integer in network order), in the same order as + objects appear in the index file (e.g., the first entry in the mtime + table corresponds to the object with the lowest lexically-sorted + oid). The mtimes count standard epoch seconds. + + - A trailer, containing a: + + checksum of the corresponding packfile, and + + a checksum of all of the above. + +All 4-byte numbers are in network order. + == multi-pack-index (MIDX) files have the following format: The multi-pack-index files refer to multiple pack-files and loose objects. diff --git a/Makefile b/Makefile index 12be39ac49..efd5e00717 100644 --- a/Makefile +++ b/Makefile @@ -949,6 +949,7 @@ LIB_OBJS += oidtree.o LIB_OBJS += pack-bitmap-write.o LIB_OBJS += pack-bitmap.o LIB_OBJS += pack-check.o +LIB_OBJS += pack-mtimes.o LIB_OBJS += pack-objects.o LIB_OBJS += pack-revindex.o LIB_OBJS += pack-write.o diff --git a/builtin/repack.c b/builtin/repack.c index 0b2d1e5d82..acbb7b8c3b 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -212,6 +212,7 @@ static struct { } exts[] = { {".pack"}, {".rev", 1}, + {".mtimes", 1}, {".bitmap", 1}, {".promisor", 1}, {".idx"}, diff --git a/object-store.h b/object-store.h index 952efb6a4b..d87481f101 100644 --- a/object-store.h +++ b/object-store.h @@ -89,12 +89,15 @@ struct packed_git { freshened:1, do_not_close:1, pack_promisor:1, - multi_pack_index: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; + const uint32_t *mtimes_map; + size_t mtimes_size; /* something like ".git/objects/pack/xxxxx.pack" */ char pack_name[FLEX_ARRAY]; /* more */ }; diff --git a/pack-mtimes.c b/pack-mtimes.c new file mode 100644 index 0000000000..4c7c00fa67 --- /dev/null +++ b/pack-mtimes.c @@ -0,0 +1,139 @@ +#include "pack-mtimes.h" +#include "object-store.h" +#include "packfile.h" + +static char *pack_mtimes_filename(struct packed_git *p) +{ + size_t len; + if (!strip_suffix(p->pack_name, ".pack", &len)) + BUG("pack_name does not end in .pack"); + /* NEEDSWORK: this could reuse code from pack-revindex.c. */ + return xstrfmt("%.*s.mtimes", (int)len, p->pack_name); +} + +int pack_has_mtimes(struct packed_git *p) +{ + struct stat st; + char *fname = pack_mtimes_filename(p); + + if (stat(fname, &st) < 0) { + if (errno == ENOENT) + return 0; + die_errno(_("could not stat %s"), fname); + } + + free(fname); + return 1; +} + +#define MTIMES_HEADER_SIZE (12) +#define MTIMES_MIN_SIZE (MTIMES_HEADER_SIZE + (2 * the_hash_algo->rawsz)) + +struct mtimes_header { + uint32_t signature; + uint32_t version; + uint32_t hash_id; +}; + +static int load_pack_mtimes_file(char *mtimes_file, + uint32_t num_objects, + const uint32_t **data_p, size_t *len_p) +{ + int fd, ret = 0; + struct stat st; + void *data = NULL; + size_t mtimes_size; + uint32_t *hdr; + + fd = git_open(mtimes_file); + + if (fd < 0) { + ret = -1; + goto cleanup; + } + if (fstat(fd, &st)) { + ret = error_errno(_("failed to read %s"), mtimes_file); + goto cleanup; + } + + mtimes_size = xsize_t(st.st_size); + + if (mtimes_size < MTIMES_MIN_SIZE) { + ret = error(_("mtimes file %s is too small"), mtimes_file); + goto cleanup; + } + + if (mtimes_size - MTIMES_MIN_SIZE != st_mult(sizeof(uint32_t), num_objects)) { + ret = error(_("mtimes file %s is corrupt"), mtimes_file); + goto cleanup; + } + + data = hdr = xmmap(NULL, mtimes_size, PROT_READ, MAP_PRIVATE, fd, 0); + + if (ntohl(*hdr) != MTIMES_SIGNATURE) { + ret = error(_("mtimes file %s has unknown signature"), mtimes_file); + goto cleanup; + } + + if (ntohl(*++hdr) != 1) { + ret = error(_("mtimes file %s has unsupported version %"PRIu32), + mtimes_file, ntohl(*hdr)); + goto cleanup; + } + hdr++; + if (!(ntohl(*hdr) == 1 || ntohl(*hdr) == 2)) { + ret = error(_("mtimes file %s has unsupported hash id %"PRIu32), + mtimes_file, ntohl(*hdr)); + goto cleanup; + } + +cleanup: + if (ret) { + if (data) + munmap(data, mtimes_size); + } else { + *len_p = mtimes_size; + *data_p = (const uint32_t *)data; + } + + close(fd); + return ret; +} + +int load_pack_mtimes(struct packed_git *p) +{ + char *mtimes_name = NULL; + int ret = 0; + + if (!p->is_cruft) + return ret; /* not a cruft pack */ + if (p->mtimes_map) + return ret; /* already loaded */ + + ret = open_pack_index(p); + if (ret < 0) + goto cleanup; + + mtimes_name = pack_mtimes_filename(p); + ret = load_pack_mtimes_file(mtimes_name, + p->num_objects, + &p->mtimes_map, + &p->mtimes_size); + if (ret) + goto cleanup; + +cleanup: + free(mtimes_name); + return ret; +} + +uint32_t nth_packed_mtime(struct packed_git *p, uint32_t pos) +{ + if (!p->mtimes_map) + BUG("pack .mtimes file not loaded for %s", p->pack_name); + if (p->num_objects <= pos) + BUG("pack .mtimes out-of-bounds (%"PRIu32" vs %"PRIu32")", + pos, p->num_objects); + + return get_be32(p->mtimes_map + pos + 3); +} diff --git a/pack-mtimes.h b/pack-mtimes.h new file mode 100644 index 0000000000..ac4247bb5e --- /dev/null +++ b/pack-mtimes.h @@ -0,0 +1,16 @@ +#ifndef PACK_MTIMES_H +#define PACK_MTIMES_H + +#include "git-compat-util.h" + +#define MTIMES_SIGNATURE 0x4d544d45 /* "MTME" */ +#define MTIMES_VERSION 1 + +struct packed_git; + +int pack_has_mtimes(struct packed_git *p); +int load_pack_mtimes(struct packed_git *p); + +uint32_t nth_packed_mtime(struct packed_git *p, uint32_t pos); + +#endif diff --git a/packfile.c b/packfile.c index 89402cfc69..ae79ac644e 100644 --- a/packfile.c +++ b/packfile.c @@ -333,12 +333,21 @@ void close_pack_revindex(struct packed_git *p) { p->revindex_data = NULL; } +void close_pack_mtimes(struct packed_git *p) { + if (!p->mtimes_map) + return; + + munmap((void *)p->mtimes_map, p->mtimes_size); + p->mtimes_map = NULL; +} + void close_pack(struct packed_git *p) { close_pack_windows(p); close_pack_fd(p); close_pack_index(p); close_pack_revindex(p); + close_pack_mtimes(p); oidset_clear(&p->bad_objects); } @@ -362,7 +371,7 @@ void close_object_store(struct raw_object_store *o) void unlink_pack_path(const char *pack_name, int force_delete) { - static const char *exts[] = {".pack", ".idx", ".rev", ".keep", ".bitmap", ".promisor"}; + static const char *exts[] = {".pack", ".idx", ".rev", ".keep", ".bitmap", ".promisor", ".mtimes"}; int i; struct strbuf buf = STRBUF_INIT; size_t plen; @@ -717,6 +726,10 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local) if (!access(p->pack_name, F_OK)) p->pack_promisor = 1; + xsnprintf(p->pack_name + path_len, alloc - path_len, ".mtimes"); + if (!access(p->pack_name, F_OK)) + p->is_cruft = 1; + xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack"); if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { free(p); @@ -868,7 +881,8 @@ static void prepare_pack(const char *full_name, size_t full_name_len, ends_with(file_name, ".pack") || ends_with(file_name, ".bitmap") || ends_with(file_name, ".keep") || - ends_with(file_name, ".promisor")) + ends_with(file_name, ".promisor") || + ends_with(file_name, ".mtimes")) string_list_append(data->garbage, full_name); else report_garbage(PACKDIR_FILE_GARBAGE, full_name); diff --git a/packfile.h b/packfile.h index 186146779d..32201d8af7 100644 --- a/packfile.h +++ b/packfile.h @@ -91,6 +91,7 @@ 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_revindex(struct packed_git *); +void close_pack_mtimes(struct packed_git *p); void close_pack(struct packed_git *); void close_object_store(struct raw_object_store *o); void unuse_pack(struct pack_window **);
-- 2.34.1.25.gb3157a20e6