#include "cache.h" #include "mru.h" #include "pack.h" #include "dir.h" #include "mergesort.h" #include "packfile.h" #include "delta.h" char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext) { strbuf_reset(buf); strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(), sha1_to_hex(sha1), ext); return buf->buf; } char *sha1_pack_name(const unsigned char *sha1) { static struct strbuf buf = STRBUF_INIT; return odb_pack_name(&buf, sha1, "pack"); } char *sha1_pack_index_name(const unsigned char *sha1) { static struct strbuf buf = STRBUF_INIT; return odb_pack_name(&buf, sha1, "idx"); } static unsigned int pack_used_ctr; static unsigned int pack_mmap_calls; static unsigned int peak_pack_open_windows; static unsigned int pack_open_windows; static unsigned int pack_open_fds; static unsigned int pack_max_fds; static size_t peak_pack_mapped; static size_t pack_mapped; struct packed_git *packed_git; static struct mru packed_git_mru_storage; struct mru *packed_git_mru = &packed_git_mru_storage; #define SZ_FMT PRIuMAX static inline uintmax_t sz_fmt(size_t s) { return s; } void pack_report(void) { fprintf(stderr, "pack_report: getpagesize() = %10" SZ_FMT "\n" "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", sz_fmt(getpagesize()), sz_fmt(packed_git_window_size), sz_fmt(packed_git_limit)); fprintf(stderr, "pack_report: pack_used_ctr = %10u\n" "pack_report: pack_mmap_calls = %10u\n" "pack_report: pack_open_windows = %10u / %10u\n" "pack_report: pack_mapped = " "%10" SZ_FMT " / %10" SZ_FMT "\n", pack_used_ctr, pack_mmap_calls, pack_open_windows, peak_pack_open_windows, sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped)); } /* * Open and mmap the index file at path, perform a couple of * consistency checks, then record its information to p. Return 0 on * success. */ static int check_packed_git_idx(const char *path, struct packed_git *p) { void *idx_map; struct pack_idx_header *hdr; size_t idx_size; uint32_t version, nr, i, *index; int fd = git_open(path); struct stat st; if (fd < 0) return -1; if (fstat(fd, &st)) { close(fd); return -1; } idx_size = xsize_t(st.st_size); if (idx_size < 4 * 256 + 20 + 20) { close(fd); return error("index file %s is too small", path); } idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0); close(fd); hdr = idx_map; if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) { version = ntohl(hdr->idx_version); if (version < 2 || version > 2) { munmap(idx_map, idx_size); return error("index file %s is version %"PRIu32 " and is not supported by this binary" " (try upgrading GIT to a newer version)", path, version); } } else version = 1; nr = 0; index = idx_map; if (version > 1) index += 2; /* skip index header */ for (i = 0; i < 256; i++) { uint32_t n = ntohl(index[i]); if (n < nr) { munmap(idx_map, idx_size); return error("non-monotonic index %s", path); } nr = n; } if (version == 1) { /* * Total size: * - 256 index entries 4 bytes each * - 24-byte entries * nr (20-byte sha1 + 4-byte offset) * - 20-byte SHA1 of the packfile * - 20-byte SHA1 file checksum */ if (idx_size != 4*256 + nr * 24 + 20 + 20) { munmap(idx_map, idx_size); return error("wrong index v1 file size in %s", path); } } else if (version == 2) { /* * Minimum size: * - 8 bytes of header * - 256 index entries 4 bytes each * - 20-byte sha1 entry * nr * - 4-byte crc entry * nr * - 4-byte offset entry * nr * - 20-byte SHA1 of the packfile * - 20-byte SHA1 file checksum * And after the 4-byte offset table might be a * variable sized table containing 8-byte entries * for offsets larger than 2^31. */ unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20; unsigned long max_size = min_size; if (nr) max_size += (nr - 1)*8; if (idx_size < min_size || idx_size > max_size) { munmap(idx_map, idx_size); return error("wrong index v2 file size in %s", path); } if (idx_size != min_size && /* * make sure we can deal with large pack offsets. * 31-bit signed offset won't be enough, neither * 32-bit unsigned one will be. */ (sizeof(off_t) <= 4)) { munmap(idx_map, idx_size); return error("pack too large for current definition of off_t in %s", path); } } p->index_version = version; p->index_data = idx_map; p->index_size = idx_size; p->num_objects = nr; return 0; } int open_pack_index(struct packed_git *p) { char *idx_name; size_t len; int ret; if (p->index_data) return 0; if (!strip_suffix(p->pack_name, ".pack", &len)) die("BUG: pack_name does not end in .pack"); idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name); ret = check_packed_git_idx(idx_name, p); free(idx_name); return ret; } static struct packed_git *alloc_packed_git(int extra) { struct packed_git *p = xmalloc(st_add(sizeof(*p), extra)); memset(p, 0, sizeof(*p)); p->pack_fd = -1; return p; } struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) { const char *path = sha1_pack_name(sha1); size_t alloc = st_add(strlen(path), 1); struct packed_git *p = alloc_packed_git(alloc); memcpy(p->pack_name, path, alloc); /* includes NUL */ hashcpy(p->sha1, sha1); if (check_packed_git_idx(idx_path, p)) { free(p); return NULL; } return p; } static void scan_windows(struct packed_git *p, struct packed_git **lru_p, struct pack_window **lru_w, struct pack_window **lru_l) { struct pack_window *w, *w_l; for (w_l = NULL, w = p->windows; w; w = w->next) { if (!w->inuse_cnt) { if (!*lru_w || w->last_used < (*lru_w)->last_used) { *lru_p = p; *lru_w = w; *lru_l = w_l; } } w_l = w; } } static int unuse_one_window(struct packed_git *current) { struct packed_git *p, *lru_p = NULL; struct pack_window *lru_w = NULL, *lru_l = NULL; if (current) scan_windows(current, &lru_p, &lru_w, &lru_l); for (p = packed_git; p; p = p->next) scan_windows(p, &lru_p, &lru_w, &lru_l); if (lru_p) { munmap(lru_w->base, lru_w->len); pack_mapped -= lru_w->len; if (lru_l) lru_l->next = lru_w->next; else lru_p->windows = lru_w->next; free(lru_w); pack_open_windows--; return 1; } return 0; } void release_pack_memory(size_t need) { size_t cur = pack_mapped; while (need >= (cur - pack_mapped) && unuse_one_window(NULL)) ; /* nothing */ } void close_pack_windows(struct packed_git *p) { while (p->windows) { struct pack_window *w = p->windows; if (w->inuse_cnt) die("pack '%s' still has open windows to it", p->pack_name); munmap(w->base, w->len); pack_mapped -= w->len; pack_open_windows--; p->windows = w->next; free(w); } } static int close_pack_fd(struct packed_git *p) { if (p->pack_fd < 0) return 0; close(p->pack_fd); pack_open_fds--; p->pack_fd = -1; return 1; } void close_pack_index(struct packed_git *p) { if (p->index_data) { munmap((void *)p->index_data, p->index_size); p->index_data = NULL; } } static void close_pack(struct packed_git *p) { close_pack_windows(p); close_pack_fd(p); close_pack_index(p); } void close_all_packs(void) { struct packed_git *p; for (p = packed_git; p; p = p->next) if (p->do_not_close) die("BUG: want to close pack marked 'do-not-close'"); else close_pack(p); } /* * The LRU pack is the one with the oldest MRU window, preferring packs * with no used windows, or the oldest mtime if it has no windows allocated. */ static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struct pack_window **mru_w, int *accept_windows_inuse) { struct pack_window *w, *this_mru_w; int has_windows_inuse = 0; /* * Reject this pack if it has windows and the previously selected * one does not. If this pack does not have windows, reject * it if the pack file is newer than the previously selected one. */ if (*lru_p && !*mru_w && (p->windows || p->mtime > (*lru_p)->mtime)) return; for (w = this_mru_w = p->windows; w; w = w->next) { /* * Reject this pack if any of its windows are in use, * but the previously selected pack did not have any * inuse windows. Otherwise, record that this pack * has windows in use. */ if (w->inuse_cnt) { if (*accept_windows_inuse) has_windows_inuse = 1; else return; } if (w->last_used > this_mru_w->last_used) this_mru_w = w; /* * Reject this pack if it has windows that have been * used more recently than the previously selected pack. * If the previously selected pack had windows inuse and * we have not encountered a window in this pack that is * inuse, skip this check since we prefer a pack with no * inuse windows to one that has inuse windows. */ if (*mru_w && *accept_windows_inuse == has_windows_inuse && this_mru_w->last_used > (*mru_w)->last_used) return; } /* * Select this pack. */ *mru_w = this_mru_w; *lru_p = p; *accept_windows_inuse = has_windows_inuse; } static int close_one_pack(void) { struct packed_git *p, *lru_p = NULL; struct pack_window *mru_w = NULL; int accept_windows_inuse = 1; for (p = packed_git; p; p = p->next) { if (p->pack_fd == -1) continue; find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); } if (lru_p) return close_pack_fd(lru_p); return 0; } static unsigned int get_max_fd_limit(void) { #ifdef RLIMIT_NOFILE { struct rlimit lim; if (!getrlimit(RLIMIT_NOFILE, &lim)) return lim.rlim_cur; } #endif #ifdef _SC_OPEN_MAX { long open_max = sysconf(_SC_OPEN_MAX); if (0 < open_max) return open_max; /* * Otherwise, we got -1 for one of the two * reasons: * * (1) sysconf() did not understand _SC_OPEN_MAX * and signaled an error with -1; or * (2) sysconf() said there is no limit. * * We _could_ clear errno before calling sysconf() to * tell these two cases apart and return a huge number * in the latter case to let the caller cap it to a * value that is not so selfish, but letting the * fallback OPEN_MAX codepath take care of these cases * is a lot simpler. */ } #endif #ifdef OPEN_MAX return OPEN_MAX; #else return 1; /* see the caller ;-) */ #endif } /* * Do not call this directly as this leaks p->pack_fd on error return; * call open_packed_git() instead. */ static int open_packed_git_1(struct packed_git *p) { struct stat st; struct pack_header hdr; unsigned char sha1[20]; unsigned char *idx_sha1; long fd_flag; if (!p->index_data && open_pack_index(p)) return error("packfile %s index unavailable", p->pack_name); if (!pack_max_fds) { unsigned int max_fds = get_max_fd_limit(); /* Save 3 for stdin/stdout/stderr, 22 for work */ if (25 < max_fds) pack_max_fds = max_fds - 25; else pack_max_fds = 1; } while (pack_max_fds <= pack_open_fds && close_one_pack()) ; /* nothing */ p->pack_fd = git_open(p->pack_name); if (p->pack_fd < 0 || fstat(p->pack_fd, &st)) return -1; pack_open_fds++; /* If we created the struct before we had the pack we lack size. */ if (!p->pack_size) { if (!S_ISREG(st.st_mode)) return error("packfile %s not a regular file", p->pack_name); p->pack_size = st.st_size; } else if (p->pack_size != st.st_size) return error("packfile %s size changed", p->pack_name); /* We leave these file descriptors open with sliding mmap; * there is no point keeping them open across exec(), though. */ fd_flag = fcntl(p->pack_fd, F_GETFD, 0); if (fd_flag < 0) return error("cannot determine file descriptor flags"); fd_flag |= FD_CLOEXEC; if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1) return error("cannot set FD_CLOEXEC"); /* Verify we recognize this pack file format. */ if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr)) return error("file %s is far too short to be a packfile", p->pack_name); if (hdr.hdr_signature != htonl(PACK_SIGNATURE)) return error("file %s is not a GIT packfile", p->pack_name); if (!pack_version_ok(hdr.hdr_version)) return error("packfile %s is version %"PRIu32" and not" " supported (try upgrading GIT to a newer version)", p->pack_name, ntohl(hdr.hdr_version)); /* Verify the pack matches its index. */ if (p->num_objects != ntohl(hdr.hdr_entries)) return error("packfile %s claims to have %"PRIu32" objects" " while index indicates %"PRIu32" objects", p->pack_name, ntohl(hdr.hdr_entries), p->num_objects); if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1) return error("end of packfile %s is unavailable", p->pack_name); if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1)) return error("packfile %s signature is unavailable", p->pack_name); idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40; if (hashcmp(sha1, idx_sha1)) return error("packfile %s does not match index", p->pack_name); return 0; } int open_packed_git(struct packed_git *p) { if (!open_packed_git_1(p)) return 0; close_pack_fd(p); return -1; } static int in_window(struct pack_window *win, off_t offset) { /* We must promise at least 20 bytes (one hash) after the * offset is available from this window, otherwise the offset * is not actually in this window and a different window (which * has that one hash excess) must be used. This is to support * the object header and delta base parsing routines below. */ off_t win_off = win->offset; return win_off <= offset && (offset + 20) <= (win_off + win->len); } unsigned char *use_pack(struct packed_git *p, struct pack_window **w_cursor, off_t offset, unsigned long *left) { struct pack_window *win = *w_cursor; /* Since packfiles end in a hash of their content and it's * pointless to ask for an offset into the middle of that * hash, and the in_window function above wouldn't match * don't allow an offset too close to the end of the file. */ if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p)) die("packfile %s cannot be accessed", p->pack_name); if (offset > (p->pack_size - 20)) die("offset beyond end of packfile (truncated pack?)"); if (offset < 0) die(_("offset before end of packfile (broken .idx?)")); if (!win || !in_window(win, offset)) { if (win) win->inuse_cnt--; for (win = p->windows; win; win = win->next) { if (in_window(win, offset)) break; } if (!win) { size_t window_align = packed_git_window_size / 2; off_t len; if (p->pack_fd == -1 && open_packed_git(p)) die("packfile %s cannot be accessed", p->pack_name); win = xcalloc(1, sizeof(*win)); win->offset = (offset / window_align) * window_align; len = p->pack_size - win->offset; if (len > packed_git_window_size) len = packed_git_window_size; win->len = (size_t)len; pack_mapped += win->len; while (packed_git_limit < pack_mapped && unuse_one_window(p)) ; /* nothing */ win->base = xmmap(NULL, win->len, PROT_READ, MAP_PRIVATE, p->pack_fd, win->offset); if (win->base == MAP_FAILED) die_errno("packfile %s cannot be mapped", p->pack_name); if (!win->offset && win->len == p->pack_size && !p->do_not_close) close_pack_fd(p); pack_mmap_calls++; pack_open_windows++; if (pack_mapped > peak_pack_mapped) peak_pack_mapped = pack_mapped; if (pack_open_windows > peak_pack_open_windows) peak_pack_open_windows = pack_open_windows; win->next = p->windows; p->windows = win; } } if (win != *w_cursor) { win->last_used = pack_used_ctr++; win->inuse_cnt++; *w_cursor = win; } offset -= win->offset; if (left) *left = win->len - xsize_t(offset); return win->base + offset; } void unuse_pack(struct pack_window **w_cursor) { struct pack_window *w = *w_cursor; if (w) { w->inuse_cnt--; *w_cursor = NULL; } } static void try_to_free_pack_memory(size_t size) { release_pack_memory(size); } struct packed_git *add_packed_git(const char *path, size_t path_len, int local) { static int have_set_try_to_free_routine; struct stat st; size_t alloc; struct packed_git *p; if (!have_set_try_to_free_routine) { have_set_try_to_free_routine = 1; set_try_to_free_routine(try_to_free_pack_memory); } /* * Make sure a corresponding .pack file exists and that * the index looks sane. */ if (!strip_suffix_mem(path, &path_len, ".idx")) return NULL; /* * ".pack" is long enough to hold any suffix we're adding (and * the use xsnprintf double-checks that) */ alloc = st_add3(path_len, strlen(".pack"), 1); p = alloc_packed_git(alloc); memcpy(p->pack_name, path, path_len); xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); if (!access(p->pack_name, F_OK)) p->pack_keep = 1; xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack"); if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { free(p); return NULL; } /* ok, it looks sane as far as we can check without * actually mapping the pack file. */ p->pack_size = st.st_size; p->pack_local = local; p->mtime = st.st_mtime; if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1)) hashclr(p->sha1); return p; } void install_packed_git(struct packed_git *pack) { if (pack->pack_fd != -1) pack_open_fds++; pack->next = packed_git; packed_git = pack; } void (*report_garbage)(unsigned seen_bits, const char *path); static void report_helper(const struct string_list *list, int seen_bits, int first, int last) { if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX)) return; for (; first < last; first++) report_garbage(seen_bits, list->items[first].string); } static void report_pack_garbage(struct string_list *list) { int i, baselen = -1, first = 0, seen_bits = 0; if (!report_garbage) return; string_list_sort(list); for (i = 0; i < list->nr; i++) { const char *path = list->items[i].string; if (baselen != -1 && strncmp(path, list->items[first].string, baselen)) { report_helper(list, seen_bits, first, i); baselen = -1; seen_bits = 0; } if (baselen == -1) { const char *dot = strrchr(path, '.'); if (!dot) { report_garbage(PACKDIR_FILE_GARBAGE, path); continue; } baselen = dot - path + 1; first = i; } if (!strcmp(path + baselen, "pack")) seen_bits |= 1; else if (!strcmp(path + baselen, "idx")) seen_bits |= 2; } report_helper(list, seen_bits, first, list->nr); } static void prepare_packed_git_one(char *objdir, int local) { struct strbuf path = STRBUF_INIT; size_t dirnamelen; DIR *dir; struct dirent *de; struct string_list garbage = STRING_LIST_INIT_DUP; strbuf_addstr(&path, objdir); strbuf_addstr(&path, "/pack"); dir = opendir(path.buf); if (!dir) { if (errno != ENOENT) error_errno("unable to open object pack directory: %s", path.buf); strbuf_release(&path); return; } strbuf_addch(&path, '/'); dirnamelen = path.len; while ((de = readdir(dir)) != NULL) { struct packed_git *p; size_t base_len; if (is_dot_or_dotdot(de->d_name)) continue; strbuf_setlen(&path, dirnamelen); strbuf_addstr(&path, de->d_name); base_len = path.len; if (strip_suffix_mem(path.buf, &base_len, ".idx")) { /* Don't reopen a pack we already have. */ for (p = packed_git; p; p = p->next) { size_t len; if (strip_suffix(p->pack_name, ".pack", &len) && len == base_len && !memcmp(p->pack_name, path.buf, len)) break; } if (p == NULL && /* * See if it really is a valid .idx file with * corresponding .pack file that we can map. */ (p = add_packed_git(path.buf, path.len, local)) != NULL) install_packed_git(p); } if (!report_garbage) continue; if (ends_with(de->d_name, ".idx") || ends_with(de->d_name, ".pack") || ends_with(de->d_name, ".bitmap") || ends_with(de->d_name, ".keep")) string_list_append(&garbage, path.buf); else report_garbage(PACKDIR_FILE_GARBAGE, path.buf); } closedir(dir); report_pack_garbage(&garbage); string_list_clear(&garbage, 0); strbuf_release(&path); } static int approximate_object_count_valid; /* * Give a fast, rough count of the number of objects in the repository. This * ignores loose objects completely. If you have a lot of them, then either * you should repack because your performance will be awful, or they are * all unreachable objects about to be pruned, in which case they're not really * interesting as a measure of repo size in the first place. */ unsigned long approximate_object_count(void) { static unsigned long count; if (!approximate_object_count_valid) { struct packed_git *p; prepare_packed_git(); count = 0; for (p = packed_git; p; p = p->next) { if (open_pack_index(p)) continue; count += p->num_objects; } } return count; } static void *get_next_packed_git(const void *p) { return ((const struct packed_git *)p)->next; } static void set_next_packed_git(void *p, void *next) { ((struct packed_git *)p)->next = next; } static int sort_pack(const void *a_, const void *b_) { const struct packed_git *a = a_; const struct packed_git *b = b_; int st; /* * Local packs tend to contain objects specific to our * variant of the project than remote ones. In addition, * remote ones could be on a network mounted filesystem. * Favor local ones for these reasons. */ st = a->pack_local - b->pack_local; if (st) return -st; /* * Younger packs tend to contain more recent objects, * and more recent objects tend to get accessed more * often. */ if (a->mtime < b->mtime) return 1; else if (a->mtime == b->mtime) return 0; return -1; } static void rearrange_packed_git(void) { packed_git = llist_mergesort(packed_git, get_next_packed_git, set_next_packed_git, sort_pack); } static void prepare_packed_git_mru(void) { struct packed_git *p; mru_clear(packed_git_mru); for (p = packed_git; p; p = p->next) mru_append(packed_git_mru, p); } static int prepare_packed_git_run_once = 0; void prepare_packed_git(void) { struct alternate_object_database *alt; if (prepare_packed_git_run_once) return; prepare_packed_git_one(get_object_directory(), 1); prepare_alt_odb(); for (alt = alt_odb_list; alt; alt = alt->next) prepare_packed_git_one(alt->path, 0); rearrange_packed_git(); prepare_packed_git_mru(); prepare_packed_git_run_once = 1; } void reprepare_packed_git(void) { approximate_object_count_valid = 0; prepare_packed_git_run_once = 0; prepare_packed_git(); } unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep) { unsigned shift; unsigned long size, c; unsigned long used = 0; c = buf[used++]; *type = (c >> 4) & 7; size = c & 15; shift = 4; while (c & 0x80) { if (len <= used || bitsizeof(long) <= shift) { error("bad object header"); size = used = 0; break; } c = buf[used++]; size += (c & 0x7f) << shift; shift += 7; } *sizep = size; return used; } unsigned long get_size_from_delta(struct packed_git *p, struct pack_window **w_curs, off_t curpos) { const unsigned char *data; unsigned char delta_head[20], *in; git_zstream stream; int st; memset(&stream, 0, sizeof(stream)); stream.next_out = delta_head; stream.avail_out = sizeof(delta_head); git_inflate_init(&stream); do { in = use_pack(p, w_curs, curpos, &stream.avail_in); stream.next_in = in; st = git_inflate(&stream, Z_FINISH); curpos += stream.next_in - in; } while ((st == Z_OK || st == Z_BUF_ERROR) && stream.total_out < sizeof(delta_head)); git_inflate_end(&stream); if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) { error("delta data unpack-initial failed"); return 0; } /* Examine the initial part of the delta to figure out * the result size. */ data = delta_head; /* ignore base size */ get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); /* Read the result size */ return get_delta_hdr_size(&data, delta_head+sizeof(delta_head)); } int unpack_object_header(struct packed_git *p, struct pack_window **w_curs, off_t *curpos, unsigned long *sizep) { unsigned char *base; unsigned long left; unsigned long used; enum object_type type; /* use_pack() assures us we have [base, base + 20) available * as a range that we can look at. (Its actually the hash * size that is assured.) With our object header encoding * the maximum deflated object size is 2^137, which is just * insane, so we know won't exceed what we have been given. */ base = use_pack(p, w_curs, *curpos, &left); used = unpack_object_header_buffer(base, left, &type, sizep); if (!used) { type = OBJ_BAD; } else *curpos += used; return type; }