diff options
Diffstat (limited to 'builtin/pack-objects.c')
-rw-r--r-- | builtin/pack-objects.c | 1547 |
1 files changed, 1220 insertions, 327 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 7016b28..baf0090 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1,13 +1,13 @@ #include "builtin.h" -#include "cache.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" #include "repository.h" #include "config.h" #include "attr.h" #include "object.h" -#include "blob.h" #include "commit.h" #include "tag.h" -#include "tree.h" #include "delta.h" #include "pack.h" #include "pack-revindex.h" @@ -16,7 +16,6 @@ #include "diff.h" #include "revision.h" #include "list-objects.h" -#include "list-objects-filter.h" #include "list-objects-filter-options.h" #include "pack-objects.h" #include "progress.h" @@ -27,14 +26,147 @@ #include "delta-islands.h" #include "reachable.h" #include "oid-array.h" -#include "argv-array.h" +#include "strvec.h" #include "list.h" #include "packfile.h" -#include "object-store.h" +#include "object-file.h" +#include "object-store-ll.h" +#include "replace-object.h" #include "dir.h" #include "midx.h" #include "trace2.h" #include "shallow.h" +#include "promisor-remote.h" +#include "pack-mtimes.h" +#include "parse-options.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) @@ -50,18 +182,11 @@ #define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val) static const char *pack_usage[] = { - N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"), - N_("git pack-objects [<options>...] <base-name> [< <ref-list> | < <object-list>]"), + N_("git pack-objects --stdout [<options>] [< <ref-list> | < <object-list>]"), + N_("git pack-objects [<options>] <base-name> [< <ref-list> | < <object-list>]"), 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; @@ -72,6 +197,8 @@ static int reuse_delta = 1, reuse_object = 1; static int keep_unreachable, unpack_unreachable, include_tag; static timestamp_t unpack_unreachable_expiration; static int pack_loose_unreachable; +static int cruft; +static timestamp_t cruft_expiration; static int local; static int have_non_local_packs; static int incremental; @@ -91,13 +218,19 @@ static int thin; static int num_preferred_base; static struct progress *progress_state; -static struct packed_git *reuse_packfile; +static struct bitmapped_pack *reuse_packfiles; +static size_t reuse_packfiles_nr; +static size_t reuse_packfiles_used_nr; static uint32_t reuse_packfile_objects; 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 { + NO_PACK_REUSE = 0, + SINGLE_PACK_REUSE, + MULTI_PACK_REUSE, +} allow_pack_reuse = SINGLE_PACK_REUSE; static enum { WRITE_BITMAP_FALSE = 0, WRITE_BITMAP_QUIET, @@ -115,8 +248,6 @@ static unsigned long cache_max_small_delta_size = 1000; 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 { @@ -165,11 +296,13 @@ static void *get_delta(struct object_entry *entry) void *buf, *base_buf, *delta_buf; enum object_type type; - buf = read_object_file(&entry->idx.oid, &type, &size); + buf = repo_read_object_file(the_repository, &entry->idx.oid, &type, + &size); if (!buf) die(_("unable to read %s"), oid_to_hex(&entry->idx.oid)); - base_buf = read_object_file(&DELTA(entry)->idx.oid, &type, - &base_size); + base_buf = repo_read_object_file(the_repository, + &DELTA(entry)->idx.oid, &type, + &base_size); if (!base_buf) die("unable to read %s", oid_to_hex(&DELTA(entry)->idx.oid)); @@ -300,6 +433,17 @@ 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) @@ -320,7 +464,9 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent &size, NULL)) != NULL) buf = NULL; else { - buf = read_object_file(&entry->idx.oid, &type, &size); + buf = repo_read_object_file(the_repository, + &entry->idx.oid, &type, + &size); if (!buf) die(_("unable to read %s"), oid_to_hex(&entry->idx.oid)); @@ -418,7 +564,7 @@ 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; @@ -435,10 +581,15 @@ 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); @@ -620,15 +771,15 @@ static enum write_one_status write_one(struct hashfile *f, return WRITE_ONE_WRITTEN; } -static int mark_tagged(const char *path, const struct object_id *oid, int flag, - void *cb_data) +static int mark_tagged(const char *path UNUSED, const struct object_id *oid, + int flag UNUSED, void *cb_data UNUSED) { struct object_id peeled; struct object_entry *entry = packlist_find(&to_pack, oid); 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; @@ -636,6 +787,14 @@ 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) @@ -782,8 +941,10 @@ static struct object_entry **compute_write_order(void) */ for_each_tag_ref(mark_tagged, NULL); - if (use_delta_islands) + if (use_delta_islands) { max_layers = compute_pack_layers(&to_pack); + free_island_marks(); + } ALLOC_ARRAY(wo, to_pack.nr_objects); wo_end = 0; @@ -809,8 +970,8 @@ 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; @@ -855,17 +1016,20 @@ static off_t find_reused_offset(off_t where) return reused_chunks[lo-1].difference; } -static void write_reused_pack_one(size_t pos, struct hashfile *out, +static void write_reused_pack_one(struct packed_git *reuse_packfile, + size_t pos, struct hashfile *out, + off_t pack_start, struct pack_window **w_curs) { off_t offset, next, cur; enum object_type type; unsigned long size; - offset = reuse_packfile->revindex[pos].offset; - next = reuse_packfile->revindex[pos + 1].offset; + offset = pack_pos_to_offset(reuse_packfile, pos); + next = pack_pos_to_offset(reuse_packfile, pos + 1); - record_reused_object(offset, offset - hashfile_total(out)); + record_reused_object(offset, + offset - (hashfile_total(out) - pack_start)); cur = offset; type = unpack_object_header(reuse_packfile, w_curs, &cur, &size); @@ -883,11 +1047,17 @@ static void write_reused_pack_one(size_t pos, struct hashfile *out, /* Convert to REF_DELTA if we must... */ if (!allow_ofs_delta) { - int base_pos = find_revindex_position(reuse_packfile, base_offset); + 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, - reuse_packfile->revindex[base_pos].nr); + pack_pos_to_index(reuse_packfile, base_pos)); len = encode_in_pack_object_header(header, sizeof(header), OBJ_REF_DELTA, size); @@ -927,41 +1097,93 @@ static void write_reused_pack_one(size_t pos, struct hashfile *out, copy_pack_data(out, reuse_packfile, w_curs, offset, next - offset); } -static size_t write_reused_pack_verbatim(struct hashfile *out, +static size_t write_reused_pack_verbatim(struct bitmapped_pack *reuse_packfile, + struct hashfile *out, + off_t pack_start, struct pack_window **w_curs) { - size_t pos = 0; + size_t pos = reuse_packfile->bitmap_pos; + size_t end; + + if (pos % BITS_IN_EWORD) { + size_t word_pos = (pos / BITS_IN_EWORD); + size_t offset = pos % BITS_IN_EWORD; + size_t last; + eword_t word = reuse_packfile_bitmap->words[word_pos]; + + if (offset + reuse_packfile->bitmap_nr < BITS_IN_EWORD) + last = offset + reuse_packfile->bitmap_nr; + else + last = BITS_IN_EWORD; + + for (; offset < last; offset++) { + if (word >> offset == 0) + return word_pos; + if (!bitmap_get(reuse_packfile_bitmap, + word_pos * BITS_IN_EWORD + offset)) + return word_pos; + } + + pos += BITS_IN_EWORD - (pos % BITS_IN_EWORD); + } + + /* + * Now we're going to copy as many whole eword_t's as possible. + * "end" is the index of the last whole eword_t we copy, but + * there may be additional bits to process. Those are handled + * individually by write_reused_pack(). + * + * Begin by advancing to the first word boundary in range of the + * bit positions occupied by objects in "reuse_packfile". Then + * pick the last word boundary in the same range. If we have at + * least one word's worth of bits to process, continue on. + */ + end = reuse_packfile->bitmap_pos + reuse_packfile->bitmap_nr; + if (end % BITS_IN_EWORD) + end -= end % BITS_IN_EWORD; + if (pos >= end) + return reuse_packfile->bitmap_pos / BITS_IN_EWORD; + + while (pos < end && + reuse_packfile_bitmap->words[pos / BITS_IN_EWORD] == (eword_t)~0) + pos += BITS_IN_EWORD; - while (pos < reuse_packfile_bitmap->word_alloc && - reuse_packfile_bitmap->words[pos] == (eword_t)~0) - pos++; + if (pos > end) + pos = end; - if (pos) { - off_t to_write; + if (reuse_packfile->bitmap_pos < pos) { + off_t pack_start_off = pack_pos_to_offset(reuse_packfile->p, 0); + off_t pack_end_off = pack_pos_to_offset(reuse_packfile->p, + pos - reuse_packfile->bitmap_pos); - written = (pos * BITS_IN_EWORD); - to_write = reuse_packfile->revindex[written].offset - - sizeof(struct pack_header); + written += pos - reuse_packfile->bitmap_pos; /* We're recording one chunk, not one object. */ - record_reused_object(sizeof(struct pack_header), 0); + record_reused_object(pack_start_off, + pack_start_off - (hashfile_total(out) - pack_start)); hashflush(out); - copy_pack_data(out, reuse_packfile, w_curs, - sizeof(struct pack_header), to_write); + copy_pack_data(out, reuse_packfile->p, w_curs, + pack_start_off, pack_end_off - pack_start_off); display_progress(progress_state, written); } - return pos; + if (pos % BITS_IN_EWORD) + BUG("attempted to jump past a word boundary to %"PRIuMAX, + (uintmax_t)pos); + return pos / BITS_IN_EWORD; } -static void write_reused_pack(struct hashfile *f) +static void write_reused_pack(struct bitmapped_pack *reuse_packfile, + struct hashfile *f) { - size_t i = 0; + size_t i = reuse_packfile->bitmap_pos / BITS_IN_EWORD; uint32_t offset; + off_t pack_start = hashfile_total(f) - sizeof(struct pack_header); struct pack_window *w_curs = NULL; if (allow_ofs_delta) - i = write_reused_pack_verbatim(f, &w_curs); + i = write_reused_pack_verbatim(reuse_packfile, f, pack_start, + &w_curs); for (; i < reuse_packfile_bitmap->word_alloc; ++i) { eword_t word = reuse_packfile_bitmap->words[i]; @@ -972,11 +1194,23 @@ static void write_reused_pack(struct hashfile *f) break; offset += ewah_bit_ctz64(word >> offset); - write_reused_pack_one(pos + offset, f, &w_curs); + if (pos + offset < reuse_packfile->bitmap_pos) + continue; + if (pos + offset >= reuse_packfile->bitmap_pos + reuse_packfile->bitmap_nr) + goto done; + /* + * Can use bit positions directly, even for MIDX + * bitmaps. See comment in try_partial_reuse() + * for why. + */ + write_reused_pack_one(reuse_packfile->p, + pos + offset - reuse_packfile->bitmap_pos, + f, pack_start, &w_curs); display_progress(progress_state, ++written); } } +done: unuse_pack(&w_curs); } @@ -1018,7 +1252,7 @@ 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) @@ -1028,9 +1262,14 @@ static void write_pack_file(void) offset = write_pack_header(f, nr_remaining); - if (reuse_packfile) { + if (reuse_packfiles_nr) { assert(pack_to_stdout); - write_reused_pack(f); + for (j = 0; j < reuse_packfiles_nr; j++) { + reused_chunks_nr = 0; + write_reused_pack(&reuse_packfiles[j], f); + if (reused_chunks_nr) + reuse_packfiles_used_nr++; + } offset = hashfile_total(f); } @@ -1042,18 +1281,28 @@ static void write_pack_file(void) display_progress(progress_state, written); } - /* - * Did we write the wrong # entries in the header? - * If so, rewrite it like in fast-import - */ if (pack_to_stdout) { - finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); + /* + * We never fsync when writing to stdout since we may + * not be writing to an actual pack file. For instance, + * the upload-pack code passes a pipe here. Calling + * fsync on a pipe results in unnecessary + * synchronization with the reader on some platforms. + */ + finalize_hashfile(f, hash, FSYNC_COMPONENT_NONE, + 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, FSYNC_COMPONENT_PACK, + 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); + /* + * If we wrote the wrong number of entries in the + * header, rewrite it like in fast-import. + */ + + int fd = finalize_hashfile(f, hash, FSYNC_COMPONENT_PACK, 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) @@ -1065,6 +1314,7 @@ 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 @@ -1085,35 +1335,45 @@ 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, + if (cruft) + pack_idx_opts.flags |= WRITE_MTIMES; + + stage_tmp_packfiles(&tmpname, pack_tmp_name, written_list, nr_written, - &pack_idx_opts, oid.hash); + &to_pack, &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_reuse_bitmaps(&to_pack); 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 */ @@ -1177,13 +1437,17 @@ 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; if (incremental) return 0; + if (!is_pack_valid(p)) + return -1; + /* * When asked to do --local (do not include an object that appears in a * pack we borrow from elsewhere) or --honor-pack-keep (do not include @@ -1193,27 +1457,82 @@ 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). @@ -1241,59 +1560,31 @@ 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; + + *found_pack = NULL; + *found_offset = 0; } 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) { @@ -1318,13 +1609,13 @@ static int want_object_in_pack(const struct object_id *oid, return 1; } -static void create_object_entry(const struct object_id *oid, - enum object_type type, - uint32_t hash, - int exclude, - int no_try_delta, - struct packed_git *found_pack, - off_t found_offset) +static struct object_entry *create_object_entry(const struct object_id *oid, + enum object_type type, + uint32_t hash, + int exclude, + int no_try_delta, + struct packed_git *found_pack, + off_t found_offset) { struct object_entry *entry; @@ -1341,6 +1632,8 @@ static void create_object_entry(const struct object_id *oid, } entry->no_try_delta = no_try_delta; + + return entry; } static const char no_closure_warning[] = N_( @@ -1376,7 +1669,7 @@ static int add_object_entry(const struct object_id *oid, enum object_type type, static int add_object_entry_from_bitmap(const struct object_id *oid, enum object_type type, - int flags, uint32_t name_hash, + int flags UNUSED, uint32_t name_hash, struct packed_git *pack, off_t offset) { display_progress(progress_state, ++nr_seen); @@ -1451,7 +1744,7 @@ static struct pbase_tree_cache *pbase_tree_get(const struct object_id *oid) /* Did not find one. Either we got a bogus request or * we need to read and perhaps cache. */ - data = read_object_file(oid, &type, &size); + data = repo_read_object_file(the_repository, oid, &type, &size); if (!data) return NULL; if (type != OBJ_TREE) { @@ -1496,17 +1789,14 @@ static void pbase_tree_put(struct pbase_tree_cache *cache) free(cache); } -static int name_cmp_len(const char *name) +static size_t name_cmp_len(const char *name) { - int i; - for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++) - ; - return i; + return strcspn(name, "\n/"); } static void add_pbase_object(struct tree_desc *tree, const char *name, - int cmplen, + size_t cmplen, const char *fullname) { struct name_entry entry; @@ -1531,12 +1821,13 @@ static void add_pbase_object(struct tree_desc *tree, struct tree_desc sub; struct pbase_tree_cache *tree; const char *down = name+cmplen+1; - int downlen = name_cmp_len(down); + size_t downlen = name_cmp_len(down); tree = pbase_tree_get(&entry.oid); if (!tree) return; - init_tree_desc(&sub, tree->tree_data, tree->tree_size); + init_tree_desc(&sub, &tree->oid, + tree->tree_data, tree->tree_size); add_pbase_object(&sub, down, downlen, fullname); pbase_tree_put(tree); @@ -1583,7 +1874,7 @@ static int check_pbase_path(unsigned hash) static void add_preferred_base_object(const char *name) { struct pbase_tree *it; - int cmplen; + size_t cmplen; unsigned hash = pack_name_hash(name); if (!num_preferred_base || check_pbase_path(hash)) @@ -1596,7 +1887,8 @@ static void add_preferred_base_object(const char *name) } else { struct tree_desc tree; - init_tree_desc(&tree, it->pcache.tree_data, it->pcache.tree_size); + init_tree_desc(&tree, &it->pcache.oid, + it->pcache.tree_data, it->pcache.tree_size); add_pbase_object(&tree, name, cmplen, name); } } @@ -1613,7 +1905,7 @@ static void add_preferred_base(struct object_id *oid) return; data = read_object_with_reference(the_repository, oid, - tree_type, &size, &tree_oid); + OBJ_TREE, &size, &tree_oid); if (!data) return; @@ -1624,7 +1916,7 @@ 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; @@ -1704,9 +1996,30 @@ static int can_reuse_delta(const struct object_id *base_oid, 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); @@ -1785,11 +2098,11 @@ 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; - if (!nth_packed_object_id(&base_ref, 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; @@ -1840,8 +2153,18 @@ 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 (repo_has_promisor_remote(the_repository)) { + 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 { @@ -2054,14 +2377,14 @@ 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; @@ -2164,6 +2487,26 @@ 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 @@ -2263,7 +2606,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, /* Load data if not already done */ if (!trg->data) { packing_data_lock(&to_pack); - trg->data = read_object_file(&trg_entry->idx.oid, &type, &sz); + trg->data = repo_read_object_file(the_repository, + &trg_entry->idx.oid, &type, + &sz); packing_data_unlock(&to_pack); if (!trg->data) die(_("object %s cannot be read"), @@ -2276,7 +2621,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, } if (!src->data) { packing_data_lock(&to_pack); - src->data = read_object_file(&src_entry->idx.oid, &type, &sz); + src->data = repo_read_object_file(the_repository, + &src_entry->idx.oid, &type, + &sz); packing_data_unlock(&to_pack); if (!src->data) { if (src_entry->preferred_base) { @@ -2386,7 +2733,7 @@ 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; @@ -2623,7 +2970,7 @@ 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++) { @@ -2772,13 +3119,12 @@ 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 UNUSED, const struct object_id *oid, + int flag UNUSED, void *cb_data UNUSED) { struct object_id peeled; - if (starts_with(path, "refs/tags/") && /* is a tag? */ - !peel_ref(path, &peeled) && /* peelable? */ - obj_is_packed(&peeled)) /* object packed? */ + if (!peel_iterated_oid(oid, &peeled) && obj_is_packed(&peeled)) add_tag_chain(oid); return 0; } @@ -2859,26 +3205,27 @@ static void prepare_pack(int window, int depth) free(delta_list); } -static int git_pack_config(const char *k, const char *v, void *cb) +static int git_pack_config(const char *k, const char *v, + const struct config_context *ctx, void *cb) { if (!strcmp(k, "pack.window")) { - window = git_config_int(k, v); + window = git_config_int(k, v, ctx->kvi); return 0; } if (!strcmp(k, "pack.windowmemory")) { - window_memory_limit = git_config_ulong(k, v); + window_memory_limit = git_config_ulong(k, v, ctx->kvi); return 0; } if (!strcmp(k, "pack.depth")) { - depth = git_config_int(k, v); + depth = git_config_int(k, v, ctx->kvi); return 0; } if (!strcmp(k, "pack.deltacachesize")) { - max_delta_cache_size = git_config_int(k, v); + max_delta_cache_size = git_config_int(k, v, ctx->kvi); return 0; } if (!strcmp(k, "pack.deltacachelimit")) { - cache_max_small_delta_size = git_config_int(k, v); + cache_max_small_delta_size = git_config_int(k, v, ctx->kvi); return 0; } if (!strcmp(k, "pack.writebitmaphashcache")) { @@ -2887,16 +3234,36 @@ static int git_pack_config(const char *k, const char *v, void *cb) else write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE; } + + if (!strcmp(k, "pack.writebitmaplookuptable")) { + if (git_config_bool(k, v)) + write_bitmap_options |= BITMAP_OPT_LOOKUP_TABLE; + else + write_bitmap_options &= ~BITMAP_OPT_LOOKUP_TABLE; + } + if (!strcmp(k, "pack.usebitmaps")) { use_bitmap_index_default = git_config_bool(k, v); return 0; } if (!strcmp(k, "pack.allowpackreuse")) { - allow_pack_reuse = git_config_bool(k, v); + int res = git_parse_maybe_bool_text(v); + if (res < 0) { + if (!strcasecmp(v, "single")) + allow_pack_reuse = SINGLE_PACK_REUSE; + else if (!strcasecmp(v, "multi")) + allow_pack_reuse = MULTI_PACK_REUSE; + else + die(_("invalid pack.allowPackReuse value: '%s'"), v); + } else if (res) { + allow_pack_reuse = SINGLE_PACK_REUSE; + } else { + allow_pack_reuse = NO_PACK_REUSE; + } return 0; } if (!strcmp(k, "pack.threads")) { - delta_search_threads = git_config_int(k, v); + delta_search_threads = git_config_int(k, v, ctx->kvi); if (delta_search_threads < 0) die(_("invalid number of threads specified (%d)"), delta_search_threads); @@ -2907,14 +3274,21 @@ static int git_pack_config(const char *k, const char *v, void *cb) return 0; } if (!strcmp(k, "pack.indexversion")) { - pack_idx_opts.version = git_config_int(k, v); + pack_idx_opts.version = git_config_int(k, v, ctx->kvi); if (pack_idx_opts.version > 2) - die(_("bad pack.indexversion=%"PRIu32), + die(_("bad pack.indexVersion=%"PRIu32), 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)); + struct configured_exclusion *ex; const char *oid_end, *pack_end; /* * Stores the pack hash. This is not a true object ID, but is @@ -2922,6 +3296,10 @@ static int git_pack_config(const char *k, const char *v, void *cb) */ struct object_id pack_hash; + if (!v) + return config_error_nonbool(k); + + ex = xmalloc(sizeof(*ex)); if (parse_oid_hex(v, &ex->e.oid, &oid_end) || *oid_end != ' ' || parse_oid_hex(oid_end + 1, &pack_hash, &pack_end) || @@ -2936,7 +3314,423 @@ static int git_pack_config(const char *k, const char *v, void *cb) ex->uri = xstrdup(pack_end + 1); oidmap_put(&configured_exclusions, ex); } - return git_default_config(k, v, cb); + return git_default_config(k, v, ctx, 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) +{ + off_t ofs; + enum object_type type = OBJ_NONE; + + 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; + + if (p) { + struct rev_info *revs = _data; + struct object_info oi = OBJECT_INFO_INIT; + + 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 UNUSED, + void *data UNUSED) +{ + /* nothing to do; commits don't have a namehash */ +} + +static void show_object_pack_hint(struct object *object, const char *name, + void *data UNUSED) +{ + 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_remove_duplicates(&include_packs, 0); + string_list_sort(&exclude_packs); + string_list_remove_duplicates(&exclude_packs, 0); + + for (p = get_all_packs(the_repository); p; p = p->next) { + const char *pack_name = pack_basename(p); + + if ((item = string_list_lookup(&include_packs, pack_name))) + item->util = p; + if ((item = string_list_lookup(&exclude_packs, pack_name))) + 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); + if (!is_pack_valid(p)) + die(_("packfile %s cannot be accessed"), p->pack_name); + } + + /* + * 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; + 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 add_cruft_object_entry(const struct object_id *oid, enum object_type type, + struct packed_git *pack, off_t offset, + const char *name, uint32_t mtime) +{ + struct object_entry *entry; + + display_progress(progress_state, ++nr_seen); + + entry = packlist_find(&to_pack, oid); + if (entry) { + if (name) { + entry->hash = pack_name_hash(name); + entry->no_try_delta = no_try_delta(name); + } + } else { + if (!want_object_in_pack(oid, 0, &pack, &offset)) + return; + if (!pack && type == OBJ_BLOB && !has_loose_object(oid)) { + /* + * If a traversed tree has a missing blob then we want + * to avoid adding that missing object to our pack. + * + * This only applies to missing blobs, not trees, + * because the traversal needs to parse sub-trees but + * not blobs. + * + * Note we only perform this check when we couldn't + * already find the object in a pack, so we're really + * limited to "ensure non-tip blobs which don't exist in + * packs do exist via loose objects". Confused? + */ + return; + } + + entry = create_object_entry(oid, type, pack_name_hash(name), + 0, name && no_try_delta(name), + pack, offset); + } + + if (mtime > oe_cruft_mtime(&to_pack, entry)) + oe_set_cruft_mtime(&to_pack, entry, mtime); + return; +} + +static void show_cruft_object(struct object *obj, const char *name, void *data UNUSED) +{ + /* + * if we did not record it earlier, it's at least as old as our + * expiration value. Rather than find it exactly, just use that + * value. This may bump it forward from its real mtime, but it + * will still be "too old" next time we run with the same + * expiration. + * + * if obj does appear in the packing list, this call is a noop (or may + * set the namehash). + */ + add_cruft_object_entry(&obj->oid, obj->type, NULL, 0, name, cruft_expiration); +} + +static void show_cruft_commit(struct commit *commit, void *data) +{ + show_cruft_object((struct object*)commit, NULL, data); +} + +static int cruft_include_check_obj(struct object *obj, void *data UNUSED) +{ + return !has_object_kept_pack(&obj->oid, IN_CORE_KEEP_PACKS); +} + +static int cruft_include_check(struct commit *commit, void *data) +{ + return cruft_include_check_obj((struct object*)commit, data); +} + +static void set_cruft_mtime(const struct object *object, + struct packed_git *pack, + off_t offset, time_t mtime) +{ + add_cruft_object_entry(&object->oid, object->type, pack, offset, NULL, + mtime); +} + +static void mark_pack_kept_in_core(struct string_list *packs, unsigned keep) +{ + struct string_list_item *item = NULL; + for_each_string_list_item(item, packs) { + struct packed_git *p = item->util; + if (!p) + die(_("could not find pack '%s'"), item->string); + p->pack_keep_in_core = keep; + } +} + +static void add_unreachable_loose_objects(void); +static void add_objects_in_unpacked_packs(void); + +static void enumerate_cruft_objects(void) +{ + if (progress) + progress_state = start_progress(_("Enumerating cruft objects"), 0); + + add_objects_in_unpacked_packs(); + add_unreachable_loose_objects(); + + stop_progress(&progress_state); +} + +static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs) +{ + struct packed_git *p; + struct rev_info revs; + int ret; + + repo_init_revisions(the_repository, &revs, NULL); + + revs.tag_objects = 1; + revs.tree_objects = 1; + revs.blob_objects = 1; + + revs.include_check = cruft_include_check; + revs.include_check_obj = cruft_include_check_obj; + + revs.ignore_missing_links = 1; + + if (progress) + progress_state = start_progress(_("Enumerating cruft objects"), 0); + ret = add_unseen_recent_objects_to_traversal(&revs, cruft_expiration, + set_cruft_mtime, 1); + stop_progress(&progress_state); + + if (ret) + die(_("unable to add cruft objects")); + + /* + * Re-mark only the fresh packs as kept so that objects in + * unknown packs do not halt the reachability traversal early. + */ + for (p = get_all_packs(the_repository); p; p = p->next) + p->pack_keep_in_core = 0; + mark_pack_kept_in_core(fresh_packs, 1); + + if (prepare_revision_walk(&revs)) + die(_("revision walk setup failed")); + if (progress) + progress_state = start_progress(_("Traversing cruft objects"), 0); + nr_seen = 0; + traverse_commit_list(&revs, show_cruft_commit, show_cruft_object, NULL); + + stop_progress(&progress_state); +} + +static void read_cruft_objects(void) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list discard_packs = STRING_LIST_INIT_DUP; + struct string_list fresh_packs = STRING_LIST_INIT_DUP; + struct packed_git *p; + + ignore_packed_keep_in_core = 1; + + while (strbuf_getline(&buf, stdin) != EOF) { + if (!buf.len) + continue; + + if (*buf.buf == '-') + string_list_append(&discard_packs, buf.buf + 1); + else + string_list_append(&fresh_packs, buf.buf); + } + + string_list_sort(&discard_packs); + string_list_sort(&fresh_packs); + + for (p = get_all_packs(the_repository); p; p = p->next) { + const char *pack_name = pack_basename(p); + struct string_list_item *item; + + item = string_list_lookup(&fresh_packs, pack_name); + if (!item) + item = string_list_lookup(&discard_packs, pack_name); + + if (item) { + item->util = p; + } else { + /* + * This pack wasn't mentioned in either the "fresh" or + * "discard" list, so the caller didn't know about it. + * + * Mark it as kept so that its objects are ignored by + * add_unseen_recent_objects_to_traversal(). We'll + * unmark it before starting the traversal so it doesn't + * halt the traversal early. + */ + p->pack_keep_in_core = 1; + } + } + + mark_pack_kept_in_core(&fresh_packs, 1); + mark_pack_kept_in_core(&discard_packs, 0); + + if (cruft_expiration) + enumerate_and_traverse_cruft_objects(&fresh_packs); + else + enumerate_cruft_objects(); + + strbuf_release(&buf); + string_list_clear(&discard_packs, 0); + string_list_clear(&fresh_packs, 0); } static void read_object_list_from_stdin(void) @@ -2950,7 +3744,7 @@ static void read_object_list_from_stdin(void) if (feof(stdin)) break; if (!ferror(stdin)) - die("BUG: fgets returned NULL, not EOF, not error!"); + BUG("fgets returned NULL, not EOF, not error!"); if (errno != EINTR) die_errno("fgets"); clearerr(stdin); @@ -2971,13 +3765,9 @@ 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) +static void show_commit(struct commit *commit, void *data UNUSED) { add_object_entry(&commit->object.oid, OBJ_COMMIT, NULL, 0); - commit->object.flags |= OBJECT_ADDED; if (write_bitmap_index) index_commit_for_bitmap(commit); @@ -2986,11 +3776,11 @@ static void show_commit(struct commit *commit, void *data) propagate_island_marks(commit); } -static void show_object(struct object *obj, const char *name, void *data) +static void show_object(struct object *obj, const char *name, + void *data UNUSED) { 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; @@ -3016,7 +3806,7 @@ 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); @@ -3030,13 +3820,13 @@ 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); } -static int option_parse_missing_action(const struct option *opt, +static int option_parse_missing_action(const struct option *opt UNUSED, const char *arg, int unset) { assert(arg); @@ -3062,7 +3852,7 @@ static int option_parse_missing_action(const struct option *opt, return 0; } - die(_("invalid value for --missing")); + die(_("invalid value for '%s': '%s'"), "--missing", arg); return 0; } @@ -3071,83 +3861,44 @@ 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 UNUSED) { - 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++; -} + if (cruft) { + off_t offset; + time_t mtime; -/* - * 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 (pack->is_cruft) { + if (load_pack_mtimes(pack) < 0) + die(_("could not load cruft pack .mtimes")); + mtime = nth_packed_mtime(pack, pos); + } else { + mtime = pack->mtime; + } + offset = nth_packed_object_offset(pack, pos); - 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_cruft_object_entry(oid, OBJ_NONE, pack, offset, + NULL, mtime); + } else { + 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, - void *data) + void *data UNUSED) { enum object_type type = oid_object_info(the_repository, oid, NULL); @@ -3156,7 +3907,19 @@ static int add_loose_object(const struct object_id *oid, const char *path, return 0; } - add_object_entry(oid, type, "", 0); + if (cruft) { + struct stat st; + if (stat(path, &st) < 0) { + if (errno == ENOENT) + return 0; + return error_errno("unable to stat %s", oid_to_hex(oid)); + } + + add_cruft_object_entry(oid, type, NULL, 0, NULL, + st.st_mtime); + } else { + add_object_entry(oid, type, "", 0); + } return 0; } @@ -3222,6 +3985,7 @@ 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) { @@ -3235,11 +3999,16 @@ 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); } /* @@ -3249,7 +4018,7 @@ static void loosen_unused_packed_objects(void) */ static int pack_options_allow_reuse(void) { - return allow_pack_reuse && + return allow_pack_reuse != NO_PACK_REUSE && pack_to_stdout && !ignore_packed_keep_on_disk && !ignore_packed_keep_in_core && @@ -3259,18 +4028,24 @@ 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, 0))) return -1; - if (pack_options_allow_reuse() && - !reuse_partial_packfile_from_bitmap( - bitmap_git, - &reuse_packfile, - &reuse_packfile_objects, - &reuse_packfile_bitmap)) { - assert(reuse_packfile_objects); + if (pack_options_allow_reuse()) + reuse_partial_packfile_from_bitmap(bitmap_git, + &reuse_packfiles, + &reuse_packfiles_nr, + &reuse_packfile_bitmap, + allow_pack_reuse == MULTI_PACK_REUSE); + + if (reuse_packfiles) { + reuse_packfile_objects = bitmap_popcount(reuse_packfile_bitmap); + if (!reuse_packfile_objects) + BUG("expected non-empty reuse bitmap"); + 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, @@ -3279,20 +4054,51 @@ static int get_object_list_from_bitmap(struct rev_info *revs) } static void record_recent_object(struct object *obj, - const char *name, - void *data) + const char *name UNUSED, + void *data UNUSED) { oid_array_append(&recent_objects, &obj->oid); } -static void record_recent_commit(struct commit *commit, void *data) +static void record_recent_commit(struct commit *commit, void *data UNUSED) { oid_array_append(&recent_objects, &commit->object.oid); } -static void get_object_list(int ac, const char **av) +static int mark_bitmap_preferred_tip(const char *refname, + const struct object_id *oid, + int flags UNUSED, + void *data UNUSED) +{ + 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(struct rev_info *revs, int ac, const char **av) { - struct rev_info revs; struct setup_revision_opt s_r_opt = { .allow_exclude_promisor_objects = 1, }; @@ -3300,9 +4106,8 @@ static void get_object_list(int ac, const char **av) int flags = 0; int save_warning; - repo_init_revisions(the_repository, &revs, NULL); save_commit_buffer = 0; - setup_revisions(ac, av, &revs, &s_r_opt); + setup_revisions(ac, av, revs, &s_r_opt); /* make sure shallows are read */ is_repository_shallow(the_repository); @@ -3325,43 +4130,46 @@ 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; } die(_("not a rev '%s'"), line); } - if (handle_revision_arg(line, &revs, flags, REVARG_CANNOT_BE_FILENAME)) + if (handle_revision_arg(line, revs, flags, REVARG_CANNOT_BE_FILENAME)) die(_("bad revision '%s'"), line); } warn_on_object_refname_ambiguity = save_warning; - if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) + if (use_bitmap_index && !get_object_list_from_bitmap(revs)) return; if (use_delta_islands) load_delta_islands(the_repository, progress); - if (prepare_revision_walk(&revs)) + 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); + mark_edges_uninteresting(revs, show_edge, sparse); if (!fn_show_object) fn_show_object = show_object; - traverse_commit_list_filtered(&filter_options, &revs, - show_commit, fn_show_object, NULL, - NULL); + traverse_commit_list(revs, + show_commit, fn_show_object, + NULL); if (unpack_unreachable_expiration) { - revs.ignore_missing_links = 1; - if (add_unseen_recent_objects_to_traversal(&revs, - unpack_unreachable_expiration)) + revs->ignore_missing_links = 1; + if (add_unseen_recent_objects_to_traversal(revs, + unpack_unreachable_expiration, NULL, 0)) die(_("unable to add recent objects")); - if (prepare_revision_walk(&revs)) + if (prepare_revision_walk(revs)) die(_("revision walk setup failed")); - traverse_commit_list(&revs, record_recent_commit, + traverse_commit_list(revs, record_recent_commit, record_recent_object, NULL); } @@ -3401,25 +4209,40 @@ static void add_extra_kept_packs(const struct string_list *names) } } +static int option_parse_quiet(const struct option *opt, const char *arg, + int unset) +{ + int *val = opt->value; + + BUG_ON_OPT_ARG(arg); + + if (!unset) + *val = 0; + else if (!*val) + *val = 1; + return 0; +} + static int option_parse_index_version(const struct option *opt, const char *arg, int unset) { + struct pack_idx_option *popts = opt->value; char *c; const char *val = arg; BUG_ON_OPT_NEG(unset); - pack_idx_opts.version = strtoul(val, &c, 10); - if (pack_idx_opts.version > 2) + popts->version = strtoul(val, &c, 10); + if (popts->version > 2) die(_("unsupported index version %s"), val); if (*c == ',' && c[1]) - pack_idx_opts.off32_limit = strtoul(c+1, &c, 0); - if (*c || pack_idx_opts.off32_limit & 0x80000000) + popts->off32_limit = strtoul(c+1, &c, 0); + if (*c || popts->off32_limit & 0x80000000) die(_("bad index version '%s'"), val); return 0; } -static int option_parse_unpack_unreachable(const struct option *opt, +static int option_parse_unpack_unreachable(const struct option *opt UNUSED, const char *arg, int unset) { if (unset) { @@ -3434,18 +4257,37 @@ static int option_parse_unpack_unreachable(const struct option *opt, return 0; } +static int option_parse_cruft_expiration(const struct option *opt UNUSED, + const char *arg, int unset) +{ + if (unset) { + cruft = 0; + cruft_expiration = 0; + } else { + cruft = 1; + if (arg) + cruft_expiration = approxidate(arg); + } + return 0; +} + 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 list_objects_filter_options filter_options = + LIST_OBJECTS_FILTER_INIT; + struct option pack_objects_options[] = { - OPT_SET_INT('q', "quiet", &progress, - N_("do not show progress meter"), 0), + OPT_CALLBACK_F('q', "quiet", &progress, NULL, + N_("do not show progress meter"), + PARSE_OPT_NOARG, option_parse_quiet), OPT_SET_INT(0, "progress", &progress, N_("show progress meter"), 1), OPT_SET_INT(0, "all-progress", &progress, @@ -3453,7 +4295,7 @@ 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")), - OPT_CALLBACK_F(0, "index-version", NULL, N_("<version>[,<offset>]"), + OPT_CALLBACK_F(0, "index-version", &pack_idx_opts, N_("<version>[,<offset>]"), N_("write the pack index file in the specified idx format version"), PARSE_OPT_NONEG, option_parse_index_version), OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit, @@ -3492,6 +4334,8 @@ 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, @@ -3503,6 +4347,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) OPT_CALLBACK_F(0, "unpack-unreachable", NULL, N_("time"), N_("unpack unreachable objects newer than <time>"), PARSE_OPT_OPTARG, option_parse_unpack_unreachable), + OPT_BOOL(0, "cruft", &cruft, N_("create a cruft pack")), + OPT_CALLBACK_F(0, "cruft-expiration", NULL, N_("time"), + N_("expire cruft objects older than <time>"), + PARSE_OPT_OPTARG, option_parse_cruft_expiration), OPT_BOOL(0, "sparse", &sparse, N_("use the sparse reachability algorithm")), OPT_BOOL(0, "thin", &thin, @@ -3515,8 +4363,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("ignore this pack")), OPT_INTEGER(0, "compression", &pack_compression_level, N_("pack compression level")), - OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents, - N_("do not hide commits by grafts"), 0), + OPT_BOOL(0, "keep-true-parents", &grafts_keep_true_parents, + N_("do not hide commits by grafts")), OPT_BOOL(0, "use-bitmap-index", &use_bitmap_index, N_("use a bitmap index if available to speed up counting objects")), OPT_SET_INT(0, "write-bitmap-index", &write_bitmap_index, @@ -3543,15 +4391,22 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS)) BUG("too many dfs states, increase OE_DFS_STATE_BITS"); - read_replace_refs = 0; + disable_replace_refs(); sparse = git_env_bool("GIT_TEST_PACK_SPARSE", -1); - prepare_repo_settings(the_repository); - if (sparse < 0) - sparse = the_repository->settings.pack_use_sparse; + if (the_repository->gitdir) { + prepare_repo_settings(the_repository); + if (sparse < 0) + sparse = the_repository->settings.pack_use_sparse; + if (the_repository->settings.pack_use_multi_pack_reuse) + allow_pack_reuse = MULTI_PACK_REUSE; + } reset_pack_idx_option(&pack_idx_opts); + pack_idx_opts.flags |= WRITE_REV; git_config(git_pack_config, NULL); + if (git_env_bool(GIT_TEST_NO_WRITE_REV_INDEX, 0)) + pack_idx_opts.flags &= ~WRITE_REV; progress = isatty(2); argc = parse_options(argc, argv, prefix, pack_objects_options, @@ -3564,6 +4419,8 @@ 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); @@ -3574,37 +4431,39 @@ 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; @@ -3634,13 +4493,21 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) die(_("--thin cannot be used to build an indexable pack")); if (keep_unreachable && unpack_unreachable) - die(_("--keep-unreachable and --unpack-unreachable are incompatible")); + die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "--unpack-unreachable"); if (!rev_list_all || !rev_list_reflog || !rev_list_index) unpack_unreachable_expiration = 0; - if (filter_options.choice) { - if (!pack_to_stdout) - die(_("cannot use --filter without --stdout")); + if (stdin_packs && filter_options.choice) + die(_("cannot use --filter with --stdin-packs")); + + if (stdin_packs && use_internal_rev_list) + die(_("cannot use internal rev list with --stdin-packs")); + + if (cruft) { + if (use_internal_rev_list) + die(_("cannot use internal rev list with --cruft")); + if (stdin_packs) + die(_("cannot use --stdin-packs with --cruft")); } /* @@ -3666,7 +4533,7 @@ 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; @@ -3699,23 +4566,35 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) the_repository); prepare_packing_data(the_repository, &to_pack); - if (progress) + if (progress && !cruft) 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 (cruft) { + read_cruft_objects(); + } else if (!use_internal_rev_list) { read_object_list_from_stdin(); - else { - get_object_list(rp.argc, rp.argv); - argv_array_clear(&rp); + } else { + struct rev_info revs; + + repo_init_revisions(the_repository, &revs, NULL); + list_objects_filter_copy(&revs.filter, &filter_options); + get_object_list(&revs, rp.nr, rp.v); + release_revisions(&revs); } 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); if (non_empty && !nr_result) - return 0; + goto cleanup; if (nr_result) { trace2_region_enter("pack-objects", "prepare-pack", the_repository); @@ -3733,8 +4612,22 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) fprintf_ln(stderr, _("Total %"PRIu32" (delta %"PRIu32")," " reused %"PRIu32" (delta %"PRIu32")," - " pack-reused %"PRIu32), + " pack-reused %"PRIu32" (from %"PRIuMAX")"), written, written_delta, reused, reused_delta, - reuse_packfile_objects); + reuse_packfile_objects, + (uintmax_t)reuse_packfiles_used_nr); + + trace2_data_intmax("pack-objects", the_repository, "written", written); + trace2_data_intmax("pack-objects", the_repository, "written/delta", written_delta); + trace2_data_intmax("pack-objects", the_repository, "reused", reused); + trace2_data_intmax("pack-objects", the_repository, "reused/delta", reused_delta); + trace2_data_intmax("pack-objects", the_repository, "pack-reused", reuse_packfile_objects); + trace2_data_intmax("pack-objects", the_repository, "packs-reused", reuse_packfiles_used_nr); + +cleanup: + clear_packing_data(&to_pack); + list_objects_filter_release(&filter_options); + strvec_clear(&rp); + return 0; } |