diff options
Diffstat (limited to 'builtin/pack-objects.c')
-rw-r--r-- | builtin/pack-objects.c | 717 |
1 files changed, 562 insertions, 155 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 13cde5896a..1a3dd445f8 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -37,6 +37,134 @@ #include "shallow.h" #include "promisor-remote.h" +/* + * Objects we are going to pack are collected in the `to_pack` structure. + * It contains an array (dynamically expanded) of the object data, and a map + * that can resolve SHA1s to their position in the array. + */ +static struct packing_data to_pack; + +static inline struct object_entry *oe_delta( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (!e->delta_idx) + return NULL; + if (e->ext_base) + return &pack->ext_bases[e->delta_idx - 1]; + else + return &pack->objects[e->delta_idx - 1]; +} + +static inline unsigned long oe_delta_size(struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_size_valid) + return e->delta_size_; + + /* + * pack->delta_size[] can't be NULL because oe_set_delta_size() + * must have been called when a new delta is saved with + * oe_set_delta(). + * If oe_delta() returns NULL (i.e. default state, which means + * delta_size_valid is also false), then the caller must never + * call oe_delta_size(). + */ + return pack->delta_size[e - pack->objects]; +} + +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e); + +static inline unsigned long oe_size(struct packing_data *pack, + const struct object_entry *e) +{ + if (e->size_valid) + return e->size_; + + return oe_get_size_slow(pack, e); +} + +static inline void oe_set_delta(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_idx = (delta - pack->objects) + 1; + else + e->delta_idx = 0; +} + +static inline struct object_entry *oe_delta_sibling( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_sibling_idx) + return &pack->objects[e->delta_sibling_idx - 1]; + return NULL; +} + +static inline struct object_entry *oe_delta_child( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_child_idx) + return &pack->objects[e->delta_child_idx - 1]; + return NULL; +} + +static inline void oe_set_delta_child(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_child_idx = (delta - pack->objects) + 1; + else + e->delta_child_idx = 0; +} + +static inline void oe_set_delta_sibling(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_sibling_idx = (delta - pack->objects) + 1; + else + e->delta_sibling_idx = 0; +} + +static inline void oe_set_size(struct packing_data *pack, + struct object_entry *e, + unsigned long size) +{ + if (size < pack->oe_size_limit) { + e->size_ = size; + e->size_valid = 1; + } else { + e->size_valid = 0; + if (oe_get_size_slow(pack, e) != size) + BUG("'size' is supposed to be the object size!"); + } +} + +static inline void oe_set_delta_size(struct packing_data *pack, + struct object_entry *e, + unsigned long size) +{ + if (size < pack->oe_delta_size_limit) { + e->delta_size_ = size; + e->delta_size_valid = 1; + } else { + packing_data_lock(pack); + if (!pack->delta_size) + ALLOC_ARRAY(pack->delta_size, pack->nr_alloc); + packing_data_unlock(pack); + + pack->delta_size[e - pack->objects] = size; + e->delta_size_valid = 0; + } +} + #define IN_PACK(obj) oe_in_pack(&to_pack, obj) #define SIZE(obj) oe_size(&to_pack, obj) #define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size) @@ -56,13 +184,6 @@ static const char *pack_usage[] = { NULL }; -/* - * Objects we are going to pack are collected in the `to_pack` structure. - * It contains an array (dynamically expanded) of the object data, and a map - * that can resolve SHA1s to their position in the array. - */ -static struct packing_data to_pack; - static struct pack_idx_entry **written_list; static uint32_t nr_result, nr_written, nr_seen; static struct bitmap_index *bitmap_git; @@ -301,6 +422,17 @@ static void copy_pack_data(struct hashfile *f, } } +static inline int oe_size_greater_than(struct packing_data *pack, + const struct object_entry *lhs, + unsigned long rhs) +{ + if (lhs->size_valid) + return lhs->size_ > rhs; + if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */ + return 1; + return oe_get_size_slow(pack, lhs) > rhs; +} + /* Return 0 if we will bust the pack-size limit */ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_entry *entry, unsigned long limit, int usable_delta) @@ -642,6 +774,14 @@ static int mark_tagged(const char *path, const struct object_id *oid, int flag, return 0; } +static inline unsigned char oe_layer(struct packing_data *pack, + struct object_entry *e) +{ + if (!pack->layer) + return 0; + return pack->layer[e - pack->objects]; +} + static inline void add_to_write_order(struct object_entry **wo, unsigned int *endp, struct object_entry *e) @@ -815,8 +955,8 @@ static struct reused_chunk { /* The offset of the first object of this chunk in the original * packfile. */ off_t original; - /* The offset of the first object of this chunk in the generated - * packfile minus "original". */ + /* The difference for "original" minus the offset of the first object of + * this chunk in the generated packfile. */ off_t difference; } *reused_chunks; static int reused_chunks_nr; @@ -984,6 +1124,11 @@ static void write_reused_pack(struct hashfile *f) break; offset += ewah_bit_ctz64(word >> offset); + /* + * Can use bit positions directly, even for MIDX + * bitmaps. See comment in try_partial_reuse() + * for why. + */ write_reused_pack_one(pos + offset, f, &w_curs); display_progress(progress_state, ++written); } @@ -1030,7 +1175,7 @@ static void write_pack_file(void) write_order = compute_write_order(); do { - struct object_id oid; + unsigned char hash[GIT_MAX_RAWSZ]; char *pack_tmp_name = NULL; if (pack_to_stdout) @@ -1059,13 +1204,13 @@ static void write_pack_file(void) * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); + finalize_hashfile(f, hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); } else if (nr_written == nr_remaining) { - finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); + finalize_hashfile(f, hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { - int fd = finalize_hashfile(f, oid.hash, 0); - fixup_pack_header_footer(fd, oid.hash, pack_tmp_name, - nr_written, oid.hash, offset); + int fd = finalize_hashfile(f, hash, 0); + fixup_pack_header_footer(fd, hash, pack_tmp_name, + nr_written, hash, offset); close(fd); if (write_bitmap_index) { if (write_bitmap_index != WRITE_BITMAP_QUIET) @@ -1077,6 +1222,7 @@ static void write_pack_file(void) if (!pack_to_stdout) { struct stat st; struct strbuf tmpname = STRBUF_INIT; + char *idx_tmp_name = NULL; /* * Packs are runtime accessed in their mtime @@ -1097,34 +1243,41 @@ static void write_pack_file(void) warning_errno(_("failed utime() on %s"), pack_tmp_name); } - strbuf_addf(&tmpname, "%s-", base_name); + strbuf_addf(&tmpname, "%s-%s.", base_name, + hash_to_hex(hash)); if (write_bitmap_index) { - bitmap_writer_set_checksum(oid.hash); + bitmap_writer_set_checksum(hash); bitmap_writer_build_type_index( &to_pack, written_list, nr_written); } - finish_tmp_packfile(&tmpname, pack_tmp_name, + stage_tmp_packfiles(&tmpname, pack_tmp_name, written_list, nr_written, - &pack_idx_opts, oid.hash); + &pack_idx_opts, hash, &idx_tmp_name); if (write_bitmap_index) { - strbuf_addf(&tmpname, "%s.bitmap", oid_to_hex(&oid)); + size_t tmpname_len = tmpname.len; + strbuf_addstr(&tmpname, "bitmap"); stop_progress(&progress_state); bitmap_writer_show_progress(progress); bitmap_writer_select_commits(indexed_commits, indexed_commits_nr, -1); - bitmap_writer_build(&to_pack); + if (bitmap_writer_build(&to_pack) < 0) + die(_("failed to write bitmap index")); bitmap_writer_finish(written_list, nr_written, tmpname.buf, write_bitmap_options); write_bitmap_index = 0; + strbuf_setlen(&tmpname, tmpname_len); } + rename_tmp_packfile_idx(&tmpname, &idx_tmp_name); + + free(idx_tmp_name); strbuf_release(&tmpname); free(pack_tmp_name); - puts(oid_to_hex(&oid)); + puts(hash_to_hex(hash)); } /* mark written objects as written to previous pack */ @@ -1188,7 +1341,8 @@ static int have_duplicate_entry(const struct object_id *oid, return 1; } -static int want_found_object(int exclude, struct packed_git *p) +static int want_found_object(const struct object_id *oid, int exclude, + struct packed_git *p) { if (exclude) return 1; @@ -1204,27 +1358,82 @@ static int want_found_object(int exclude, struct packed_git *p) * make sure no copy of this object appears in _any_ pack that makes us * to omit the object, so we need to check all the packs. * - * We can however first check whether these options can possible matter; + * We can however first check whether these options can possibly matter; * if they do not matter we know we want the object in generated pack. * Otherwise, we signal "-1" at the end to tell the caller that we do * not know either way, and it needs to check more packs. */ - if (!ignore_packed_keep_on_disk && - !ignore_packed_keep_in_core && - (!local || !have_non_local_packs)) - return 1; + /* + * Objects in packs borrowed from elsewhere are discarded regardless of + * if they appear in other packs that weren't borrowed. + */ if (local && !p->pack_local) return 0; - if (p->pack_local && - ((ignore_packed_keep_on_disk && p->pack_keep) || - (ignore_packed_keep_in_core && p->pack_keep_in_core))) - return 0; + + /* + * Then handle .keep first, as we have a fast(er) path there. + */ + if (ignore_packed_keep_on_disk || ignore_packed_keep_in_core) { + /* + * Set the flags for the kept-pack cache to be the ones we want + * to ignore. + * + * That is, if we are ignoring objects in on-disk keep packs, + * then we want to search through the on-disk keep and ignore + * the in-core ones. + */ + unsigned flags = 0; + if (ignore_packed_keep_on_disk) + flags |= ON_DISK_KEEP_PACKS; + if (ignore_packed_keep_in_core) + flags |= IN_CORE_KEEP_PACKS; + + if (ignore_packed_keep_on_disk && p->pack_keep) + return 0; + if (ignore_packed_keep_in_core && p->pack_keep_in_core) + return 0; + if (has_object_kept_pack(oid, flags)) + return 0; + } + + /* + * At this point we know definitively that either we don't care about + * keep-packs, or the object is not in one. Keep checking other + * conditions... + */ + if (!local || !have_non_local_packs) + return 1; /* we don't know yet; keep looking for more packs */ return -1; } +static int want_object_in_pack_one(struct packed_git *p, + const struct object_id *oid, + int exclude, + struct packed_git **found_pack, + off_t *found_offset) +{ + off_t offset; + + if (p == *found_pack) + offset = *found_offset; + else + offset = find_pack_entry_one(oid->hash, p); + + if (offset) { + if (!*found_pack) { + if (!is_pack_valid(p)) + return -1; + *found_offset = offset; + *found_pack = p; + } + return want_found_object(oid, exclude, p); + } + return -1; +} + /* * Check whether we want the object in the pack (e.g., we do not want * objects found in non-local stores if the "--local" option was used). @@ -1252,7 +1461,7 @@ static int want_object_in_pack(const struct object_id *oid, * are present we will determine the answer right now. */ if (*found_pack) { - want = want_found_object(exclude, *found_pack); + want = want_found_object(oid, exclude, *found_pack); if (want != -1) return want; } @@ -1260,51 +1469,20 @@ static int want_object_in_pack(const struct object_id *oid, for (m = get_multi_pack_index(the_repository); m; m = m->next) { struct pack_entry e; if (fill_midx_entry(the_repository, oid, &e, m)) { - struct packed_git *p = e.p; - off_t offset; - - if (p == *found_pack) - offset = *found_offset; - else - offset = find_pack_entry_one(oid->hash, p); - - if (offset) { - if (!*found_pack) { - if (!is_pack_valid(p)) - continue; - *found_offset = offset; - *found_pack = p; - } - want = want_found_object(exclude, p); - if (want != -1) - return want; - } + want = want_object_in_pack_one(e.p, oid, exclude, found_pack, found_offset); + if (want != -1) + return want; } } list_for_each(pos, get_packed_git_mru(the_repository)) { struct packed_git *p = list_entry(pos, struct packed_git, mru); - off_t offset; - - if (p == *found_pack) - offset = *found_offset; - else - offset = find_pack_entry_one(oid->hash, p); - - if (offset) { - if (!*found_pack) { - if (!is_pack_valid(p)) - continue; - *found_offset = offset; - *found_pack = p; - } - want = want_found_object(exclude, p); - if (!exclude && want > 0) - list_move(&p->mru, - get_packed_git_mru(the_repository)); - if (want != -1) - return want; - } + want = want_object_in_pack_one(p, oid, exclude, found_pack, found_offset); + if (!exclude && want > 0) + list_move(&p->mru, + get_packed_git_mru(the_repository)); + if (want != -1) + return want; } if (uri_protocols.nr) { @@ -1635,7 +1813,7 @@ static void add_preferred_base(struct object_id *oid) } } - it = xcalloc(1, sizeof(*it)); + CALLOC_ARRAY(it, 1); it->next = pbase_tree; pbase_tree = it; @@ -2096,7 +2274,7 @@ static void get_object_details(void) progress_state = start_progress(_("Counting objects"), to_pack.nr_objects); - sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *)); + CALLOC_ARRAY(sorted_by_offset, to_pack.nr_objects); for (i = 0; i < to_pack.nr_objects; i++) sorted_by_offset[i] = to_pack.objects + i; QSORT(sorted_by_offset, to_pack.nr_objects, pack_offset_sort); @@ -2206,6 +2384,26 @@ static pthread_mutex_t progress_mutex; * progress_mutex for protection. */ +static inline int oe_size_less_than(struct packing_data *pack, + const struct object_entry *lhs, + unsigned long rhs) +{ + if (lhs->size_valid) + return lhs->size_ < rhs; + if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */ + return 0; + return oe_get_size_slow(pack, lhs) < rhs; +} + +static inline void oe_set_tree_depth(struct packing_data *pack, + struct object_entry *e, + unsigned int tree_depth) +{ + if (!pack->tree_depth) + CALLOC_ARRAY(pack->tree_depth, pack->nr_alloc); + pack->tree_depth[e - pack->objects] = tree_depth; +} + /* * Return the size of the object without doing any delta * reconstruction (so non-deltas are true object sizes, but deltas @@ -2428,7 +2626,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, struct unpacked *array; unsigned long mem_usage = 0; - array = xcalloc(window, sizeof(struct unpacked)); + CALLOC_ARRAY(array, window); for (;;) { struct object_entry *entry; @@ -2665,7 +2863,7 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, if (progress > pack_to_stdout) fprintf_ln(stderr, _("Delta compression using up to %d threads"), delta_search_threads); - p = xcalloc(delta_search_threads, sizeof(*p)); + CALLOC_ARRAY(p, delta_search_threads); /* Partition the work amongst work threads. */ for (i = 0; i < delta_search_threads; i++) { @@ -2953,6 +3151,13 @@ static int git_pack_config(const char *k, const char *v, void *cb) pack_idx_opts.version); return 0; } + if (!strcmp(k, "pack.writereverseindex")) { + if (git_config_bool(k, v)) + pack_idx_opts.flags |= WRITE_REV; + else + pack_idx_opts.flags &= ~WRITE_REV; + return 0; + } if (!strcmp(k, "uploadpack.blobpackfileuri")) { struct configured_exclusion *ex = xmalloc(sizeof(*ex)); const char *oid_end, *pack_end; @@ -2979,6 +3184,208 @@ static int git_pack_config(const char *k, const char *v, void *cb) return git_default_config(k, v, cb); } +/* Counters for trace2 output when in --stdin-packs mode. */ +static int stdin_packs_found_nr; +static int stdin_packs_hints_nr; + +static int add_object_entry_from_pack(const struct object_id *oid, + struct packed_git *p, + uint32_t pos, + void *_data) +{ + struct rev_info *revs = _data; + struct object_info oi = OBJECT_INFO_INIT; + off_t ofs; + enum object_type type; + + display_progress(progress_state, ++nr_seen); + + if (have_duplicate_entry(oid, 0)) + return 0; + + ofs = nth_packed_object_offset(p, pos); + if (!want_object_in_pack(oid, 0, &p, &ofs)) + return 0; + + oi.typep = &type; + if (packed_object_info(the_repository, p, ofs, &oi) < 0) + die(_("could not get type of object %s in pack %s"), + oid_to_hex(oid), p->pack_name); + else if (type == OBJ_COMMIT) { + /* + * commits in included packs are used as starting points for the + * subsequent revision walk + */ + add_pending_oid(revs, NULL, oid, 0); + } + + stdin_packs_found_nr++; + + create_object_entry(oid, type, 0, 0, 0, p, ofs); + + return 0; +} + +static void show_commit_pack_hint(struct commit *commit, void *_data) +{ + /* nothing to do; commits don't have a namehash */ +} + +static void show_object_pack_hint(struct object *object, const char *name, + void *_data) +{ + struct object_entry *oe = packlist_find(&to_pack, &object->oid); + if (!oe) + return; + + /* + * Our 'to_pack' list was constructed by iterating all objects packed in + * included packs, and so doesn't have a non-zero hash field that you + * would typically pick up during a reachability traversal. + * + * Make a best-effort attempt to fill in the ->hash and ->no_try_delta + * here using a now in order to perhaps improve the delta selection + * process. + */ + oe->hash = pack_name_hash(name); + oe->no_try_delta = name && no_try_delta(name); + + stdin_packs_hints_nr++; +} + +static int pack_mtime_cmp(const void *_a, const void *_b) +{ + struct packed_git *a = ((const struct string_list_item*)_a)->util; + struct packed_git *b = ((const struct string_list_item*)_b)->util; + + /* + * order packs by descending mtime so that objects are laid out + * roughly as newest-to-oldest + */ + if (a->mtime < b->mtime) + return 1; + else if (b->mtime < a->mtime) + return -1; + else + return 0; +} + +static void read_packs_list_from_stdin(void) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list include_packs = STRING_LIST_INIT_DUP; + struct string_list exclude_packs = STRING_LIST_INIT_DUP; + struct string_list_item *item = NULL; + + struct packed_git *p; + struct rev_info revs; + + repo_init_revisions(the_repository, &revs, NULL); + /* + * Use a revision walk to fill in the namehash of objects in the include + * packs. To save time, we'll avoid traversing through objects that are + * in excluded packs. + * + * That may cause us to avoid populating all of the namehash fields of + * all included objects, but our goal is best-effort, since this is only + * an optimization during delta selection. + */ + revs.no_kept_objects = 1; + revs.keep_pack_cache_flags |= IN_CORE_KEEP_PACKS; + revs.blob_objects = 1; + revs.tree_objects = 1; + revs.tag_objects = 1; + revs.ignore_missing_links = 1; + + while (strbuf_getline(&buf, stdin) != EOF) { + if (!buf.len) + continue; + + if (*buf.buf == '^') + string_list_append(&exclude_packs, buf.buf + 1); + else + string_list_append(&include_packs, buf.buf); + + strbuf_reset(&buf); + } + + string_list_sort(&include_packs); + string_list_sort(&exclude_packs); + + for (p = get_all_packs(the_repository); p; p = p->next) { + const char *pack_name = pack_basename(p); + + item = string_list_lookup(&include_packs, pack_name); + if (!item) + item = string_list_lookup(&exclude_packs, pack_name); + + if (item) + item->util = p; + } + + /* + * Arguments we got on stdin may not even be packs. First + * check that to avoid segfaulting later on in + * e.g. pack_mtime_cmp(), excluded packs are handled below. + * + * Since we first parsed our STDIN and then sorted the input + * lines the pack we error on will be whatever line happens to + * sort first. This is lazy, it's enough that we report one + * bad case here, we don't need to report the first/last one, + * or all of them. + */ + for_each_string_list_item(item, &include_packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + } + + /* + * Then, handle all of the excluded packs, marking them as + * kept in-core so that later calls to add_object_entry() + * discards any objects that are also found in excluded packs. + */ + for_each_string_list_item(item, &exclude_packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + p->pack_keep_in_core = 1; + } + + /* + * Order packs by ascending mtime; use QSORT directly to access the + * string_list_item's ->util pointer, which string_list_sort() does not + * provide. + */ + QSORT(include_packs.items, include_packs.nr, pack_mtime_cmp); + + for_each_string_list_item(item, &include_packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + for_each_object_in_pack(p, + add_object_entry_from_pack, + &revs, + FOR_EACH_OBJECT_PACK_ORDER); + } + + if (prepare_revision_walk(&revs)) + die(_("revision walk setup failed")); + traverse_commit_list(&revs, + show_commit_pack_hint, + show_object_pack_hint, + NULL); + + trace2_data_intmax("pack-objects", the_repository, "stdin_packs_found", + stdin_packs_found_nr); + trace2_data_intmax("pack-objects", the_repository, "stdin_packs_hints", + stdin_packs_hints_nr); + + strbuf_release(&buf); + string_list_clear(&include_packs, 0); + string_list_clear(&exclude_packs, 0); +} + static void read_object_list_from_stdin(void) { char line[GIT_MAX_HEXSZ + 1 + PATH_MAX + 2]; @@ -3011,13 +3418,9 @@ static void read_object_list_from_stdin(void) } } -/* Remember to update object flag allocation in object.h */ -#define OBJECT_ADDED (1u<<20) - static void show_commit(struct commit *commit, void *data) { add_object_entry(&commit->object.oid, OBJ_COMMIT, NULL, 0); - commit->object.flags |= OBJECT_ADDED; if (write_bitmap_index) index_commit_for_bitmap(commit); @@ -3030,7 +3433,6 @@ static void show_object(struct object *obj, const char *name, void *data) { add_preferred_base_object(name); add_object_entry(&obj->oid, obj->type, name, 0); - obj->flags |= OBJECT_ADDED; if (use_delta_islands) { const char *p; @@ -3111,79 +3513,23 @@ static void show_edge(struct commit *commit) add_preferred_base(&commit->object.oid); } -struct in_pack_object { - off_t offset; - struct object *object; -}; - -struct in_pack { - unsigned int alloc; - unsigned int nr; - struct in_pack_object *array; -}; - -static void mark_in_pack_object(struct object *object, struct packed_git *p, struct in_pack *in_pack) +static int add_object_in_unpacked_pack(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *_data) { - in_pack->array[in_pack->nr].offset = find_pack_entry_one(object->oid.hash, p); - in_pack->array[in_pack->nr].object = object; - in_pack->nr++; -} - -/* - * Compare the objects in the offset order, in order to emulate the - * "git rev-list --objects" output that produced the pack originally. - */ -static int ofscmp(const void *a_, const void *b_) -{ - struct in_pack_object *a = (struct in_pack_object *)a_; - struct in_pack_object *b = (struct in_pack_object *)b_; - - if (a->offset < b->offset) - return -1; - else if (a->offset > b->offset) - return 1; - else - return oidcmp(&a->object->oid, &b->object->oid); + add_object_entry(oid, OBJ_NONE, "", 0); + return 0; } static void add_objects_in_unpacked_packs(void) { - struct packed_git *p; - struct in_pack in_pack; - uint32_t i; - - memset(&in_pack, 0, sizeof(in_pack)); - - for (p = get_all_packs(the_repository); p; p = p->next) { - struct object_id oid; - struct object *o; - - if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) - continue; - if (open_pack_index(p)) - die(_("cannot open pack index")); - - ALLOC_GROW(in_pack.array, - in_pack.nr + p->num_objects, - in_pack.alloc); - - for (i = 0; i < p->num_objects; i++) { - nth_packed_object_id(&oid, p, i); - o = lookup_unknown_object(&oid); - if (!(o->flags & OBJECT_ADDED)) - mark_in_pack_object(o, p, &in_pack); - o->flags |= OBJECT_ADDED; - } - } - - if (in_pack.nr) { - QSORT(in_pack.array, in_pack.nr, ofscmp); - for (i = 0; i < in_pack.nr; i++) { - struct object *o = in_pack.array[i].object; - add_object_entry(&o->oid, o->type, "", 0); - } - } - free(in_pack.array); + if (for_each_packed_object(add_object_in_unpacked_pack, NULL, + FOR_EACH_OBJECT_PACK_ORDER | + FOR_EACH_OBJECT_LOCAL_ONLY | + FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS | + FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS)) + die(_("cannot open pack index")); } static int add_loose_object(const struct object_id *oid, const char *path, @@ -3262,6 +3608,7 @@ static void loosen_unused_packed_objects(void) { struct packed_git *p; uint32_t i; + uint32_t loosened_objects_nr = 0; struct object_id oid; for (p = get_all_packs(the_repository); p; p = p->next) { @@ -3275,11 +3622,16 @@ static void loosen_unused_packed_objects(void) nth_packed_object_id(&oid, p, i); if (!packlist_find(&to_pack, &oid) && !has_sha1_pack_kept_or_nonlocal(&oid) && - !loosened_object_can_be_discarded(&oid, p->mtime)) + !loosened_object_can_be_discarded(&oid, p->mtime)) { if (force_object_loose(&oid, p->mtime)) die(_("unable to force loose object")); + loosened_objects_nr++; + } } } + + trace2_data_intmax("pack-objects", the_repository, + "loosen_unused_packed_objects/loosened", loosened_objects_nr); } /* @@ -3299,7 +3651,7 @@ static int pack_options_allow_reuse(void) static int get_object_list_from_bitmap(struct rev_info *revs) { - if (!(bitmap_git = prepare_bitmap_walk(revs, &filter_options))) + if (!(bitmap_git = prepare_bitmap_walk(revs, &filter_options, 0))) return -1; if (pack_options_allow_reuse() && @@ -3310,7 +3662,8 @@ static int get_object_list_from_bitmap(struct rev_info *revs) &reuse_packfile_bitmap)) { assert(reuse_packfile_objects); nr_result += reuse_packfile_objects; - display_progress(progress_state, nr_result); + nr_seen += reuse_packfile_objects; + display_progress(progress_state, nr_seen); } traverse_bitmap_commit_list(bitmap_git, revs, @@ -3330,6 +3683,37 @@ static void record_recent_commit(struct commit *commit, void *data) oid_array_append(&recent_objects, &commit->object.oid); } +static int mark_bitmap_preferred_tip(const char *refname, + const struct object_id *oid, int flags, + void *_data) +{ + struct object_id peeled; + struct object *object; + + if (!peel_iterated_oid(oid, &peeled)) + oid = &peeled; + + object = parse_object_or_die(oid, refname); + if (object->type == OBJ_COMMIT) + object->flags |= NEEDS_BITMAP; + + return 0; +} + +static void mark_bitmap_preferred_tips(void) +{ + struct string_list_item *item; + const struct string_list *preferred_tips; + + preferred_tips = bitmap_preferred_tips(the_repository); + if (!preferred_tips) + return; + + for_each_string_list_item(item, preferred_tips) { + for_each_ref_in(item->string, mark_bitmap_preferred_tip, NULL); + } +} + static void get_object_list(int ac, const char **av) { struct rev_info revs; @@ -3384,6 +3768,9 @@ static void get_object_list(int ac, const char **av) if (use_delta_islands) load_delta_islands(the_repository, progress); + if (write_bitmap_index) + mark_bitmap_preferred_tips(); + if (prepare_revision_walk(&revs)) die(_("revision walk setup failed")); mark_edges_uninteresting(&revs, show_edge, sparse); @@ -3482,6 +3869,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) struct strvec rp = STRVEC_INIT; int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0; int rev_list_index = 0; + int stdin_packs = 0; struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; struct option pack_objects_options[] = { OPT_SET_INT('q', "quiet", &progress, @@ -3532,6 +3920,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) OPT_SET_INT_F(0, "indexed-objects", &rev_list_index, N_("include objects referred to by the index"), 1, PARSE_OPT_NONEG), + OPT_BOOL(0, "stdin-packs", &stdin_packs, + N_("read packs from stdin")), OPT_BOOL(0, "stdout", &pack_to_stdout, N_("output pack to stdout")), OPT_BOOL(0, "include-tag", &include_tag, @@ -3592,6 +3982,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) reset_pack_idx_option(&pack_idx_opts); git_config(git_pack_config, NULL); + if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0)) + pack_idx_opts.flags |= WRITE_REV; progress = isatty(2); argc = parse_options(argc, argv, prefix, pack_objects_options, @@ -3604,6 +3996,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (pack_to_stdout != !base_name || argc) usage_with_options(pack_usage, pack_objects_options); + if (depth < 0) + depth = 0; if (depth >= (1 << OE_DEPTH_BITS)) { warning(_("delta chain depth %d is too deep, forcing %d"), depth, (1 << OE_DEPTH_BITS) - 1); @@ -3614,6 +4008,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) (1U << OE_Z_DELTA_BITS) - 1); cache_max_small_delta_size = (1U << OE_Z_DELTA_BITS) - 1; } + if (window < 0) + window = 0; strvec_push(&rp, "pack-objects"); if (thin) { @@ -3636,7 +4032,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) use_internal_rev_list = 1; strvec_push(&rp, "--indexed-objects"); } - if (rev_list_unpacked) { + if (rev_list_unpacked && !stdin_packs) { use_internal_rev_list = 1; strvec_push(&rp, "--unpacked"); } @@ -3681,8 +4077,13 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (filter_options.choice) { if (!pack_to_stdout) die(_("cannot use --filter without --stdout")); + if (stdin_packs) + die(_("cannot use --filter with --stdin-packs")); } + if (stdin_packs && use_internal_rev_list) + die(_("cannot use internal rev list with --stdin-packs")); + /* * "soft" reasons not to use bitmaps - for on-disk repack by default we want * @@ -3741,7 +4142,13 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (progress) progress_state = start_progress(_("Enumerating objects"), 0); - if (!use_internal_rev_list) + if (stdin_packs) { + /* avoids adding objects in excluded packs */ + ignore_packed_keep_in_core = 1; + read_packs_list_from_stdin(); + if (rev_list_unpacked) + add_unreachable_loose_objects(); + } else if (!use_internal_rev_list) read_object_list_from_stdin(); else { get_object_list(rp.nr, rp.v); |