diff options
Diffstat (limited to 'builtin/pack-objects.c')
| -rw-r--r-- | builtin/pack-objects.c | 1081 |
1 files changed, 892 insertions, 189 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 5876583220..de00adbb9e 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -26,14 +26,144 @@ #include "pack-bitmap.h" #include "delta-islands.h" #include "reachable.h" -#include "sha1-array.h" -#include "argv-array.h" +#include "oid-array.h" +#include "strvec.h" #include "list.h" #include "packfile.h" #include "object-store.h" #include "dir.h" #include "midx.h" #include "trace2.h" +#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) @@ -54,13 +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; @@ -92,10 +215,11 @@ static struct progress *progress_state; static struct packed_git *reuse_packfile; static uint32_t reuse_packfile_objects; -static off_t reuse_packfile_offset; +static struct bitmap *reuse_packfile_bitmap; static int use_bitmap_index_default = 1; static int use_bitmap_index = -1; +static int allow_pack_reuse = 1; static enum { WRITE_BITMAP_FALSE = 0, WRITE_BITMAP_QUIET, @@ -115,6 +239,8 @@ static unsigned long window_memory_limit = 0; static struct list_objects_filter_options filter_options; +static struct string_list uri_protocols = STRING_LIST_INIT_NODUP; + enum missing_action { MA_ERROR = 0, /* fail if any missing objects are encountered */ MA_ALLOW_ANY, /* silently allow ALL missing objects */ @@ -123,6 +249,15 @@ enum missing_action { static enum missing_action arg_missing_action; static show_object_fn fn_show_object; +struct configured_exclusion { + struct oidmap_entry e; + char *pack_hash_hex; + char *uri; +}; +static struct oidmap configured_exclusions; + +static struct oidset excluded_by_config; + /* * stats */ @@ -163,7 +298,7 @@ static void *get_delta(struct object_entry *entry) delta_buf = diff_delta(base_buf, base_size, buf, size, &delta_size, 0); /* - * We succesfully computed this delta once but dropped it for + * We successfully computed this delta once but dropped it for * memory reasons. Something is very wrong if this time we * recompute and create a different delta. */ @@ -287,6 +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) @@ -303,7 +449,8 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent if (!usable_delta) { if (oe_type(entry) == OBJ_BLOB && oe_size_greater_than(&to_pack, entry, big_file_threshold) && - (st = open_istream(&entry->idx.oid, &type, &size, NULL)) != NULL) + (st = open_istream(the_repository, &entry->idx.oid, &type, + &size, NULL)) != NULL) buf = NULL; else { buf = read_object_file(&entry->idx.oid, &type, &size); @@ -404,7 +551,7 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, { struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; - struct revindex_entry *revidx; + uint32_t pos; off_t offset; enum object_type type = oe_type(entry); off_t datalen; @@ -421,10 +568,15 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, type, entry_size); offset = entry->in_pack_offset; - revidx = find_pack_revindex(p, offset); - datalen = revidx[1].offset - offset; + if (offset_to_pack_pos(p, offset, &pos) < 0) + die(_("write_reuse_object: could not locate %s, expected at " + "offset %"PRIuMAX" in pack %s"), + oid_to_hex(&entry->idx.oid), (uintmax_t)offset, + p->pack_name); + datalen = pack_pos_to_offset(p, pos + 1) - offset; if (!pack_to_stdout && p->index_version > 1 && - check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) { + check_pack_crc(p, &w_curs, offset, datalen, + pack_pos_to_index(p, pos))) { error(_("bad packed object CRC for %s"), oid_to_hex(&entry->idx.oid)); unuse_pack(&w_curs); @@ -614,7 +766,7 @@ static int mark_tagged(const char *path, const struct object_id *oid, int flag, if (entry) entry->tagged = 1; - if (!peel_ref(path, &peeled)) { + if (!peel_iterated_oid(oid, &peeled)) { entry = packlist_find(&to_pack, &peeled); if (entry) entry->tagged = 1; @@ -622,6 +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) @@ -784,57 +944,211 @@ static struct object_entry **compute_write_order(void) return wo; } -static off_t write_reused_pack(struct hashfile *f) + +/* + * A reused set of objects. All objects in a chunk have the same + * relative position in the original packfile and the generated + * packfile. + */ + +static struct reused_chunk { + /* The offset of the first object of this chunk in the original + * packfile. */ + off_t 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; +static int reused_chunks_alloc; + +static void record_reused_object(off_t where, off_t offset) +{ + if (reused_chunks_nr && reused_chunks[reused_chunks_nr-1].difference == offset) + return; + + ALLOC_GROW(reused_chunks, reused_chunks_nr + 1, + reused_chunks_alloc); + reused_chunks[reused_chunks_nr].original = where; + reused_chunks[reused_chunks_nr].difference = offset; + reused_chunks_nr++; +} + +/* + * Binary search to find the chunk that "where" is in. Note + * that we're not looking for an exact match, just the first + * chunk that contains it (which implicitly ends at the start + * of the next chunk. + */ +static off_t find_reused_offset(off_t where) +{ + int lo = 0, hi = reused_chunks_nr; + while (lo < hi) { + int mi = lo + ((hi - lo) / 2); + if (where == reused_chunks[mi].original) + return reused_chunks[mi].difference; + if (where < reused_chunks[mi].original) + hi = mi; + else + lo = mi + 1; + } + + /* + * The first chunk starts at zero, so we can't have gone below + * there. + */ + assert(lo); + return reused_chunks[lo-1].difference; +} + +static void write_reused_pack_one(size_t pos, struct hashfile *out, + struct pack_window **w_curs) { - unsigned char buffer[8192]; - off_t to_write, total; - int fd; + off_t offset, next, cur; + enum object_type type; + unsigned long size; + + offset = pack_pos_to_offset(reuse_packfile, pos); + next = pack_pos_to_offset(reuse_packfile, pos + 1); - if (!is_pack_valid(reuse_packfile)) - die(_("packfile is invalid: %s"), reuse_packfile->pack_name); + record_reused_object(offset, offset - hashfile_total(out)); - fd = git_open(reuse_packfile->pack_name); - if (fd < 0) - die_errno(_("unable to open packfile for reuse: %s"), - reuse_packfile->pack_name); + cur = offset; + type = unpack_object_header(reuse_packfile, w_curs, &cur, &size); + assert(type >= 0); - if (lseek(fd, sizeof(struct pack_header), SEEK_SET) == -1) - die_errno(_("unable to seek in reused packfile")); + if (type == OBJ_OFS_DELTA) { + off_t base_offset; + off_t fixup; + + unsigned char header[MAX_PACK_OBJECT_HEADER]; + unsigned len; + + base_offset = get_delta_base(reuse_packfile, w_curs, &cur, type, offset); + assert(base_offset != 0); + + /* Convert to REF_DELTA if we must... */ + if (!allow_ofs_delta) { + uint32_t base_pos; + struct object_id base_oid; + + if (offset_to_pack_pos(reuse_packfile, base_offset, &base_pos) < 0) + die(_("expected object at offset %"PRIuMAX" " + "in pack %s"), + (uintmax_t)base_offset, + reuse_packfile->pack_name); + + nth_packed_object_id(&base_oid, reuse_packfile, + pack_pos_to_index(reuse_packfile, base_pos)); + + len = encode_in_pack_object_header(header, sizeof(header), + OBJ_REF_DELTA, size); + hashwrite(out, header, len); + hashwrite(out, base_oid.hash, the_hash_algo->rawsz); + copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur); + return; + } - if (reuse_packfile_offset < 0) - reuse_packfile_offset = reuse_packfile->pack_size - the_hash_algo->rawsz; + /* Otherwise see if we need to rewrite the offset... */ + fixup = find_reused_offset(offset) - + find_reused_offset(base_offset); + if (fixup) { + unsigned char ofs_header[10]; + unsigned i, ofs_len; + off_t ofs = offset - base_offset - fixup; - total = to_write = reuse_packfile_offset - sizeof(struct pack_header); + len = encode_in_pack_object_header(header, sizeof(header), + OBJ_OFS_DELTA, size); - while (to_write) { - int read_pack = xread(fd, buffer, sizeof(buffer)); + i = sizeof(ofs_header) - 1; + ofs_header[i] = ofs & 127; + while (ofs >>= 7) + ofs_header[--i] = 128 | (--ofs & 127); - if (read_pack <= 0) - die_errno(_("unable to read from reused packfile")); + ofs_len = sizeof(ofs_header) - i; + + hashwrite(out, header, len); + hashwrite(out, ofs_header + sizeof(ofs_header) - ofs_len, ofs_len); + copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur); + return; + } - if (read_pack > to_write) - read_pack = to_write; + /* ...otherwise we have no fixup, and can write it verbatim */ + } - hashwrite(f, buffer, read_pack); - to_write -= read_pack; + copy_pack_data(out, reuse_packfile, w_curs, offset, next - offset); +} + +static size_t write_reused_pack_verbatim(struct hashfile *out, + struct pack_window **w_curs) +{ + size_t pos = 0; + + while (pos < reuse_packfile_bitmap->word_alloc && + reuse_packfile_bitmap->words[pos] == (eword_t)~0) + pos++; + + if (pos) { + off_t to_write; + + written = (pos * BITS_IN_EWORD); + to_write = pack_pos_to_offset(reuse_packfile, written) + - sizeof(struct pack_header); + + /* We're recording one chunk, not one object. */ + record_reused_object(sizeof(struct pack_header), 0); + hashflush(out); + copy_pack_data(out, reuse_packfile, w_curs, + sizeof(struct pack_header), to_write); - /* - * We don't know the actual number of objects written, - * only how many bytes written, how many bytes total, and - * how many objects total. So we can fake it by pretending all - * objects we are writing are the same size. This gives us a - * smooth progress meter, and at the end it matches the true - * answer. - */ - written = reuse_packfile_objects * - (((double)(total - to_write)) / total); display_progress(progress_state, written); } + return pos; +} + +static void write_reused_pack(struct hashfile *f) +{ + size_t i = 0; + uint32_t offset; + struct pack_window *w_curs = NULL; - close(fd); - written = reuse_packfile_objects; - display_progress(progress_state, written); - return reuse_packfile_offset - sizeof(struct pack_header); + if (allow_ofs_delta) + i = write_reused_pack_verbatim(f, &w_curs); + + for (; i < reuse_packfile_bitmap->word_alloc; ++i) { + eword_t word = reuse_packfile_bitmap->words[i]; + size_t pos = (i * BITS_IN_EWORD); + + for (offset = 0; offset < BITS_IN_EWORD; ++offset) { + if ((word >> offset) == 0) + break; + + offset += ewah_bit_ctz64(word >> offset); + write_reused_pack_one(pos + offset, f, &w_curs); + display_progress(progress_state, ++written); + } + } + + unuse_pack(&w_curs); +} + +static void write_excluded_by_configs(void) +{ + struct oidset_iter iter; + const struct object_id *oid; + + oidset_iter_init(&excluded_by_config, &iter); + while ((oid = oidset_iter_next(&iter))) { + struct configured_exclusion *ex = + oidmap_get(&configured_exclusions, oid); + + if (!ex) + BUG("configured exclusion wasn't configured"); + write_in_full(1, ex->pack_hash_hex, strlen(ex->pack_hash_hex)); + write_in_full(1, " ", 1); + write_in_full(1, ex->uri, strlen(ex->uri)); + write_in_full(1, "\n", 1); + } } static const char no_split_warning[] = N_( @@ -856,7 +1170,7 @@ 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) @@ -867,11 +1181,9 @@ static void write_pack_file(void) offset = write_pack_header(f, nr_remaining); if (reuse_packfile) { - off_t packfile_size; assert(pack_to_stdout); - - packfile_size = write_reused_pack(f); - offset += packfile_size; + write_reused_pack(f); + offset = hashfile_total(f); } nr_written = 0; @@ -887,13 +1199,13 @@ 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) @@ -928,22 +1240,21 @@ static void write_pack_file(void) strbuf_addf(&tmpname, "%s-", base_name); 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, written_list, nr_written, - &pack_idx_opts, oid.hash); + &pack_idx_opts, hash); if (write_bitmap_index) { - strbuf_addf(&tmpname, "%s.bitmap", oid_to_hex(&oid)); + strbuf_addf(&tmpname, "%s.bitmap", hash_to_hex(hash)); stop_progress(&progress_state); bitmap_writer_show_progress(progress); - bitmap_writer_reuse_bitmaps(&to_pack); bitmap_writer_select_commits(indexed_commits, indexed_commits_nr, -1); bitmap_writer_build(&to_pack); bitmap_writer_finish(written_list, nr_written, @@ -953,7 +1264,7 @@ static void write_pack_file(void) 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 */ @@ -1000,6 +1311,10 @@ static int have_duplicate_entry(const struct object_id *oid, { struct object_entry *entry; + if (reuse_packfile_bitmap && + bitmap_walk_contains(bitmap_git, reuse_packfile_bitmap, oid)) + return 1; + entry = packlist_find(&to_pack, oid); if (!entry) return 0; @@ -1013,7 +1328,8 @@ 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; @@ -1029,27 +1345,82 @@ 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). @@ -1077,7 +1448,7 @@ 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; } @@ -1085,50 +1456,38 @@ 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; + 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 (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; + if (uri_protocols.nr) { + struct configured_exclusion *ex = + oidmap_get(&configured_exclusions, oid); + int i; + const char *p; + + if (ex) { + for (i = 0; i < uri_protocols.nr; i++) { + if (skip_prefix(ex->uri, + uri_protocols.items[i].string, + &p) && + *p == ':') { + oidset_insert(&excluded_by_config, oid); + return 0; + } } - 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; } } @@ -1441,7 +1800,7 @@ 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; @@ -1486,23 +1845,17 @@ static void cleanup_preferred_base(void) * deltify other objects against, in order to avoid * circular deltas. */ -static int can_reuse_delta(const unsigned char *base_sha1, +static int can_reuse_delta(const struct object_id *base_oid, struct object_entry *delta, struct object_entry **base_out) { struct object_entry *base; - struct object_id base_oid; - - if (!base_sha1) - return 0; - - oidread(&base_oid, base_sha1); /* * First see if we're already sending the base (or it's explicitly in * our "excluded" list). */ - base = packlist_find(&to_pack, &base_oid); + base = packlist_find(&to_pack, base_oid); if (base) { if (!in_same_island(&delta->idx.oid, &base->idx.oid)) return 0; @@ -1515,9 +1868,9 @@ static int can_reuse_delta(const unsigned char *base_sha1, * even if it was buried too deep in history to make it into the * packing list. */ - if (thin && bitmap_has_oid_in_uninteresting(bitmap_git, &base_oid)) { + if (thin && bitmap_has_oid_in_uninteresting(bitmap_git, base_oid)) { if (use_delta_islands) { - if (!in_same_island(&delta->idx.oid, &base_oid)) + if (!in_same_island(&delta->idx.oid, base_oid)) return 0; } *base_out = NULL; @@ -1527,14 +1880,36 @@ static int can_reuse_delta(const unsigned char *base_sha1, return 0; } -static void check_object(struct object_entry *entry) +static void prefetch_to_pack(uint32_t object_index_start) { + struct oid_array to_fetch = OID_ARRAY_INIT; + uint32_t i; + + for (i = object_index_start; i < to_pack.nr_objects; i++) { + struct object_entry *entry = to_pack.objects + i; + + if (!oid_object_info_extended(the_repository, + &entry->idx.oid, + NULL, + OBJECT_INFO_FOR_PREFETCH)) + continue; + oid_array_append(&to_fetch, &entry->idx.oid); + } + promisor_remote_get_direct(the_repository, + to_fetch.oid, to_fetch.nr); + oid_array_clear(&to_fetch); +} + +static void check_object(struct object_entry *entry, uint32_t object_index) { unsigned long canonical_size; + enum object_type type; + struct object_info oi = {.typep = &type, .sizep = &canonical_size}; if (IN_PACK(entry)) { struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; - const unsigned char *base_ref = NULL; + int have_base = 0; + struct object_id base_ref; struct object_entry *base_entry; unsigned long used, used_0; unsigned long avail; @@ -1575,9 +1950,13 @@ static void check_object(struct object_entry *entry) unuse_pack(&w_curs); return; case OBJ_REF_DELTA: - if (reuse_delta && !entry->preferred_base) - base_ref = use_pack(p, &w_curs, - entry->in_pack_offset + used, NULL); + if (reuse_delta && !entry->preferred_base) { + oidread(&base_ref, + use_pack(p, &w_curs, + entry->in_pack_offset + used, + NULL)); + have_base = 1; + } entry->in_pack_header_size = used + the_hash_algo->rawsz; break; case OBJ_OFS_DELTA: @@ -1603,17 +1982,19 @@ static void check_object(struct object_entry *entry) goto give_up; } if (reuse_delta && !entry->preferred_base) { - struct revindex_entry *revidx; - revidx = find_pack_revindex(p, ofs); - if (!revidx) + uint32_t pos; + if (offset_to_pack_pos(p, ofs, &pos) < 0) goto give_up; - base_ref = nth_packed_object_sha1(p, revidx->nr); + if (!nth_packed_object_id(&base_ref, p, + pack_pos_to_index(p, pos))) + have_base = 1; } entry->in_pack_header_size = used + used_0; break; } - if (can_reuse_delta(base_ref, entry, &base_entry)) { + if (have_base && + can_reuse_delta(&base_ref, entry, &base_entry)) { oe_set_type(entry, entry->in_pack_type); SET_SIZE(entry, in_pack_size); /* delta size */ SET_DELTA_SIZE(entry, in_pack_size); @@ -1623,7 +2004,7 @@ static void check_object(struct object_entry *entry) entry->delta_sibling_idx = base_entry->delta_child_idx; SET_DELTA_CHILD(base_entry, entry); } else { - SET_DELTA_EXT(entry, base_ref); + SET_DELTA_EXT(entry, &base_ref); } unuse_pack(&w_curs); @@ -1656,8 +2037,18 @@ static void check_object(struct object_entry *entry) unuse_pack(&w_curs); } - oe_set_type(entry, - oid_object_info(the_repository, &entry->idx.oid, &canonical_size)); + if (oid_object_info_extended(the_repository, &entry->idx.oid, &oi, + OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0) { + if (has_promisor_remote()) { + prefetch_to_pack(object_index); + if (oid_object_info_extended(the_repository, &entry->idx.oid, &oi, + OBJECT_INFO_SKIP_FETCH_OBJECT | OBJECT_INFO_LOOKUP_REPLACE) < 0) + type = -1; + } else { + type = -1; + } + } + oe_set_type(entry, type); if (entry->type_valid) { SET_SIZE(entry, canonical_size); } else { @@ -1870,14 +2261,14 @@ 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); for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = sorted_by_offset[i]; - check_object(entry); + check_object(entry, i); if (entry->type_valid && oe_size_greater_than(&to_pack, entry, big_file_threshold)) entry->no_try_delta = 1; @@ -1980,6 +2371,26 @@ 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 @@ -2202,7 +2613,7 @@ 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; @@ -2439,7 +2850,7 @@ 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++) { @@ -2552,6 +2963,13 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, free(p); } +static int obj_is_packed(const struct object_id *oid) +{ + return packlist_find(&to_pack, oid) || + (reuse_packfile_bitmap && + bitmap_walk_contains(bitmap_git, reuse_packfile_bitmap, oid)); +} + static void add_tag_chain(const struct object_id *oid) { struct tag *tag; @@ -2563,7 +2981,7 @@ static void add_tag_chain(const struct object_id *oid) * it was included via bitmaps, we would not have parsed it * previously). */ - if (packlist_find(&to_pack, oid)) + if (obj_is_packed(oid)) return; tag = lookup_tag(the_repository, oid); @@ -2581,13 +2999,11 @@ static void add_tag_chain(const struct object_id *oid) } } -static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data) +static int add_ref_tag(const char *tag, const struct object_id *oid, int flag, void *cb_data) { struct object_id peeled; - if (starts_with(path, "refs/tags/") && /* is a tag? */ - !peel_ref(path, &peeled) && /* peelable? */ - packlist_find(&to_pack, &peeled)) /* object packed? */ + if (!peel_iterated_oid(oid, &peeled) && obj_is_packed(&peeled)) add_tag_chain(oid); return 0; } @@ -2655,6 +3071,7 @@ static void prepare_pack(int window, int depth) if (nr_deltas && n > 1) { unsigned nr_done = 0; + if (progress) progress_state = start_progress(_("Compressing objects"), nr_deltas); @@ -2699,6 +3116,10 @@ static int git_pack_config(const char *k, const char *v, void *cb) use_bitmap_index_default = git_config_bool(k, v); return 0; } + if (!strcmp(k, "pack.allowpackreuse")) { + allow_pack_reuse = git_config_bool(k, v); + return 0; + } if (!strcmp(k, "pack.threads")) { delta_search_threads = git_config_int(k, v); if (delta_search_threads < 0) @@ -2717,9 +3138,224 @@ 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; + /* + * Stores the pack hash. This is not a true object ID, but is + * of the same form. + */ + struct object_id pack_hash; + + if (parse_oid_hex(v, &ex->e.oid, &oid_end) || + *oid_end != ' ' || + parse_oid_hex(oid_end + 1, &pack_hash, &pack_end) || + *pack_end != ' ') + die(_("value of uploadpack.blobpackfileuri must be " + "of the form '<object-hash> <pack-hash> <uri>' (got '%s')"), v); + if (oidmap_get(&configured_exclusions, &ex->e.oid)) + die(_("object already configured in another " + "uploadpack.blobpackfileuri (got '%s')"), v); + ex->pack_hash_hex = xcalloc(1, pack_end - oid_end); + memcpy(ex->pack_hash_hex, oid_end + 1, pack_end - oid_end - 1); + ex->uri = xstrdup(pack_end + 1); + oidmap_put(&configured_exclusions, ex); + } 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; + } + + /* + * First 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]; @@ -2797,7 +3433,7 @@ static void show_object__ma_allow_any(struct object *obj, const char *name, void * Quietly ignore ALL missing objects. This avoids problems with * staging them now and getting an odd error later. */ - if (!has_object_file(&obj->oid)) + if (!has_object(the_repository, &obj->oid, 0)) return; show_object(obj, name, data); @@ -2811,7 +3447,7 @@ static void show_object__ma_allow_promisor(struct object *obj, const char *name, * Quietly ignore EXPECTED missing objects. This avoids problems with * staging them now and getting an odd error later. */ - if (!has_object_file(&obj->oid) && is_promisor_object(&obj->oid)) + if (!has_object(the_repository, &obj->oid, 0) && is_promisor_object(&obj->oid)) return; show_object(obj, name, data); @@ -2909,8 +3545,8 @@ static void add_objects_in_unpacked_packs(void) in_pack.alloc); for (i = 0; i < p->num_objects; i++) { - nth_packed_object_oid(&oid, p, i); - o = lookup_unknown_object(&oid); + nth_packed_object_id(&oid, p, i); + o = lookup_unknown_object(the_repository, &oid); if (!(o->flags & OBJECT_ADDED)) mark_in_pack_object(o, p, &in_pack); o->flags |= OBJECT_ADDED; @@ -3003,6 +3639,7 @@ 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) { @@ -3013,14 +3650,19 @@ static void loosen_unused_packed_objects(void) die(_("cannot open pack index")); for (i = 0; i < p->num_objects; i++) { - nth_packed_object_oid(&oid, p, i); + 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); } /* @@ -3030,8 +3672,8 @@ static void loosen_unused_packed_objects(void) */ static int pack_options_allow_reuse(void) { - return pack_to_stdout && - allow_ofs_delta && + return allow_pack_reuse && + pack_to_stdout && !ignore_packed_keep_on_disk && !ignore_packed_keep_in_core && (!local || !have_non_local_packs) && @@ -3040,7 +3682,7 @@ 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))) + if (!(bitmap_git = prepare_bitmap_walk(revs, &filter_options, 0))) return -1; if (pack_options_allow_reuse() && @@ -3048,13 +3690,15 @@ static int get_object_list_from_bitmap(struct rev_info *revs) bitmap_git, &reuse_packfile, &reuse_packfile_objects, - &reuse_packfile_offset)) { + &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, &add_object_entry_from_bitmap); + traverse_bitmap_commit_list(bitmap_git, revs, + &add_object_entry_from_bitmap); return 0; } @@ -3070,6 +3714,37 @@ 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; @@ -3105,7 +3780,7 @@ static void get_object_list(int ac, const char **av) if (starts_with(line, "--shallow ")) { struct object_id oid; if (get_oid_hex(line + 10, &oid)) - die("not an SHA-1 '%s'", line + 10); + die("not an object name '%s'", line + 10); register_shallow(the_repository, &oid); use_bitmap_index = 0; continue; @@ -3124,6 +3799,9 @@ 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); @@ -3219,9 +3897,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) int use_internal_rev_list = 0; int shallow = 0; int all_progress_implied = 0; - struct argv_array rp = ARGV_ARRAY_INIT; + 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, @@ -3233,9 +3912,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) OPT_BOOL(0, "all-progress-implied", &all_progress_implied, N_("similar to --all-progress when progress meter is shown")), - { OPTION_CALLBACK, 0, "index-version", NULL, N_("<version>[,<offset>]"), + OPT_CALLBACK_F(0, "index-version", NULL, N_("<version>[,<offset>]"), N_("write the pack index file in the specified idx format version"), - PARSE_OPT_NONEG, option_parse_index_version }, + PARSE_OPT_NONEG, option_parse_index_version), OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit, N_("maximum size of each output pack file")), OPT_BOOL(0, "local", &local, @@ -3272,6 +3951,8 @@ 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, @@ -3280,9 +3961,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("keep unreachable objects")), OPT_BOOL(0, "pack-loose-unreachable", &pack_loose_unreachable, N_("pack loose unreachable objects")), - { OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"), + OPT_CALLBACK_F(0, "unpack-unreachable", NULL, N_("time"), N_("unpack unreachable objects newer than <time>"), - PARSE_OPT_OPTARG, option_parse_unpack_unreachable }, + PARSE_OPT_OPTARG, option_parse_unpack_unreachable), OPT_BOOL(0, "sparse", &sparse, N_("use the sparse reachability algorithm")), OPT_BOOL(0, "thin", &thin, @@ -3307,13 +3988,16 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("write a bitmap index if possible"), WRITE_BITMAP_QUIET, PARSE_OPT_HIDDEN), OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options), - { OPTION_CALLBACK, 0, "missing", NULL, N_("action"), + OPT_CALLBACK_F(0, "missing", NULL, N_("action"), N_("handling for missing objects"), PARSE_OPT_NONEG, - option_parse_missing_action }, + option_parse_missing_action), OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects, N_("do not pack objects in promisor packfiles")), OPT_BOOL(0, "delta-islands", &use_delta_islands, N_("respect islands during delta compression")), + OPT_STRING_LIST(0, "uri-protocol", &uri_protocols, + N_("protocol"), + N_("exclude any configured uploadpack.blobpackfileuri with this protocol")), OPT_END(), }; @@ -3322,13 +4006,15 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) read_replace_refs = 0; - sparse = git_env_bool("GIT_TEST_PACK_SPARSE", 0); + sparse = git_env_bool("GIT_TEST_PACK_SPARSE", -1); prepare_repo_settings(the_repository); - if (!sparse && the_repository->settings.pack_use_sparse != -1) + if (sparse < 0) sparse = the_repository->settings.pack_use_sparse; 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, @@ -3341,6 +4027,8 @@ 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); @@ -3351,37 +4039,39 @@ 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; - argv_array_push(&rp, "pack-objects"); + strvec_push(&rp, "pack-objects"); if (thin) { use_internal_rev_list = 1; - argv_array_push(&rp, shallow + strvec_push(&rp, shallow ? "--objects-edge-aggressive" : "--objects-edge"); } else - argv_array_push(&rp, "--objects"); + strvec_push(&rp, "--objects"); if (rev_list_all) { use_internal_rev_list = 1; - argv_array_push(&rp, "--all"); + strvec_push(&rp, "--all"); } if (rev_list_reflog) { use_internal_rev_list = 1; - argv_array_push(&rp, "--reflog"); + strvec_push(&rp, "--reflog"); } if (rev_list_index) { use_internal_rev_list = 1; - argv_array_push(&rp, "--indexed-objects"); + strvec_push(&rp, "--indexed-objects"); } - if (rev_list_unpacked) { + if (rev_list_unpacked && !stdin_packs) { use_internal_rev_list = 1; - argv_array_push(&rp, "--unpacked"); + strvec_push(&rp, "--unpacked"); } if (exclude_promisor_objects) { use_internal_rev_list = 1; fetch_if_missing = 0; - argv_array_push(&rp, "--exclude-promisor-objects"); + strvec_push(&rp, "--exclude-promisor-objects"); } if (unpack_unreachable || keep_unreachable || pack_loose_unreachable) use_internal_rev_list = 1; @@ -3418,9 +4108,13 @@ 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")); - use_bitmap_index = 0; + 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 * @@ -3444,7 +4138,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) write_bitmap_index = 0; if (use_delta_islands) - argv_array_push(&rp, "--topo-order"); + strvec_push(&rp, "--topo-order"); if (progress && all_progress_implied) progress = 2; @@ -3479,15 +4173,21 @@ 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.argc, rp.argv); - argv_array_clear(&rp); + get_object_list(rp.nr, rp.v); + strvec_clear(&rp); } cleanup_preferred_base(); if (include_tag && nr_result) - for_each_ref(add_ref_tag, NULL); + for_each_tag_ref(add_ref_tag, NULL); stop_progress(&progress_state); trace2_region_leave("pack-objects", "enumerate-objects", the_repository); @@ -3503,13 +4203,16 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) } trace2_region_enter("pack-objects", "write-pack-file", the_repository); + write_excluded_by_configs(); write_pack_file(); trace2_region_leave("pack-objects", "write-pack-file", the_repository); if (progress) fprintf_ln(stderr, _("Total %"PRIu32" (delta %"PRIu32")," - " reused %"PRIu32" (delta %"PRIu32")"), - written, written_delta, reused, reused_delta); + " reused %"PRIu32" (delta %"PRIu32")," + " pack-reused %"PRIu32), + written, written_delta, reused, reused_delta, + reuse_packfile_objects); return 0; } |