diff options
Diffstat (limited to 'builtin/pack-objects.c')
| -rw-r--r-- | builtin/pack-objects.c | 556 |
1 files changed, 358 insertions, 198 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index e9d3cfb9e3..71056d8294 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "cache.h" +#include "repository.h" #include "config.h" #include "attr.h" #include "object.h" @@ -28,6 +29,20 @@ #include "argv-array.h" #include "list.h" #include "packfile.h" +#include "object-store.h" +#include "dir.h" + +#define IN_PACK(obj) oe_in_pack(&to_pack, obj) +#define SIZE(obj) oe_size(&to_pack, obj) +#define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size) +#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj) +#define DELTA(obj) oe_delta(&to_pack, obj) +#define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj) +#define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj) +#define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val) +#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val) +#define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val) +#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>]"), @@ -43,7 +58,7 @@ static const char *pack_usage[] = { static struct packing_data to_pack; static struct pack_idx_entry **written_list; -static uint32_t nr_result, nr_written; +static uint32_t nr_result, nr_written, nr_seen; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@ -53,7 +68,8 @@ static int pack_loose_unreachable; static int local; static int have_non_local_packs; static int incremental; -static int ignore_packed_keep; +static int ignore_packed_keep_on_disk; +static int ignore_packed_keep_in_core; static int allow_ofs_delta; static struct pack_idx_option pack_idx_opts; static const char *base_name; @@ -78,7 +94,7 @@ static uint16_t write_bitmap_options; static int exclude_promisor_objects; static unsigned long delta_cache_size = 0; -static unsigned long max_delta_cache_size = 256 * 1024 * 1024; +static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE; static unsigned long cache_max_small_delta_size = 1000; static unsigned long window_memory_limit = 0; @@ -122,17 +138,17 @@ static void *get_delta(struct object_entry *entry) void *buf, *base_buf, *delta_buf; enum object_type type; - buf = read_sha1_file(entry->idx.oid.hash, &type, &size); + buf = read_object_file(&entry->idx.oid, &type, &size); if (!buf) die("unable to read %s", oid_to_hex(&entry->idx.oid)); - base_buf = read_sha1_file(entry->delta->idx.oid.hash, &type, - &base_size); + base_buf = read_object_file(&DELTA(entry)->idx.oid, &type, + &base_size); if (!base_buf) die("unable to read %s", - oid_to_hex(&entry->delta->idx.oid)); + oid_to_hex(&DELTA(entry)->idx.oid)); delta_buf = diff_delta(base_buf, base_size, buf, size, &delta_size, 0); - if (!delta_buf || delta_size != entry->delta_size) + if (!delta_buf || delta_size != DELTA_SIZE(entry)) die("delta size changed"); free(buf); free(base_buf); @@ -263,15 +279,15 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent enum object_type type; void *buf; struct git_istream *st = NULL; + const unsigned hashsz = the_hash_algo->rawsz; if (!usable_delta) { - if (entry->type == OBJ_BLOB && - entry->size > big_file_threshold && - (st = open_istream(entry->idx.oid.hash, &type, &size, NULL)) != NULL) + 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) buf = NULL; else { - buf = read_sha1_file(entry->idx.oid.hash, &type, - &size); + buf = read_object_file(&entry->idx.oid, &type, &size); if (!buf) die(_("unable to read %s"), oid_to_hex(&entry->idx.oid)); @@ -283,15 +299,15 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent FREE_AND_NULL(entry->delta_data); entry->z_delta_size = 0; } else if (entry->delta_data) { - size = entry->delta_size; + size = DELTA_SIZE(entry); buf = entry->delta_data; entry->delta_data = NULL; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } else { buf = get_delta(entry); - size = entry->delta_size; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + size = DELTA_SIZE(entry); + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } @@ -315,12 +331,12 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent * encoding of the relative offset for the delta * base from this object's position in the pack. */ - off_t ofs = entry->idx.offset - entry->delta->idx.offset; + off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) dheader[--pos] = 128 | (--ofs & 127); - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); @@ -332,19 +348,19 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent } else if (type == OBJ_REF_DELTA) { /* * Deltas with a base reference contain - * an additional 20 bytes for the base sha1. + * additional bytes for the base object ID. */ - if (limit && hdrlen + 20 + datalen + 20 >= limit) { + if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, entry->delta->idx.oid.hash, 20); - hdrlen += 20; + hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { if (st) close_istream(st); free(buf); @@ -367,21 +383,23 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, unsigned long limit, int usable_delta) { - struct packed_git *p = entry->in_pack; + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; struct revindex_entry *revidx; off_t offset; - enum object_type type = entry->type; + enum object_type type = oe_type(entry); off_t datalen; unsigned char header[MAX_PACK_OBJECT_HEADER], dheader[MAX_PACK_OBJECT_HEADER]; unsigned hdrlen; + const unsigned hashsz = the_hash_algo->rawsz; + unsigned long entry_size = SIZE(entry); - if (entry->delta) - type = (allow_ofs_delta && entry->delta->idx.offset) ? + if (DELTA(entry)) + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; hdrlen = encode_in_pack_object_header(header, sizeof(header), - type, entry->size); + type, entry_size); offset = entry->in_pack_offset; revidx = find_pack_revindex(p, offset); @@ -398,7 +416,7 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, datalen -= entry->in_pack_header_size; if (!pack_to_stdout && p->index_version == 1 && - check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) { + check_pack_inflate(p, &w_curs, offset, datalen, entry_size)) { error("corrupt packed object for %s", oid_to_hex(&entry->idx.oid)); unuse_pack(&w_curs); @@ -406,12 +424,12 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, } if (type == OBJ_OFS_DELTA) { - off_t ofs = entry->idx.offset - entry->delta->idx.offset; + off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) dheader[--pos] = 128 | (--ofs & 127); - if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) { + if (limit && hdrlen + sizeof(dheader) - pos + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } @@ -420,16 +438,16 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, hdrlen += sizeof(dheader) - pos; reused_delta++; } else if (type == OBJ_REF_DELTA) { - if (limit && hdrlen + 20 + datalen + 20 >= limit) { + if (limit && hdrlen + hashsz + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, entry->delta->idx.oid.hash, 20); - hdrlen += 20; + hashwrite(f, DELTA(entry)->idx.oid.hash, hashsz); + hdrlen += hashsz; reused_delta++; } else { - if (limit && hdrlen + datalen + 20 >= limit) { + if (limit && hdrlen + datalen + hashsz >= limit) { unuse_pack(&w_curs); return 0; } @@ -465,28 +483,29 @@ static off_t write_object(struct hashfile *f, else limit = pack_size_limit - write_offset; - if (!entry->delta) + if (!DELTA(entry)) usable_delta = 0; /* no delta */ else if (!pack_size_limit) usable_delta = 1; /* unlimited packfile */ - else if (entry->delta->idx.offset == (off_t)-1) + else if (DELTA(entry)->idx.offset == (off_t)-1) usable_delta = 0; /* base was written to another pack */ - else if (entry->delta->idx.offset) + else if (DELTA(entry)->idx.offset) usable_delta = 1; /* base already exists in this pack */ else usable_delta = 0; /* base could end up in another pack */ if (!reuse_object) to_reuse = 0; /* explicit */ - else if (!entry->in_pack) + else if (!IN_PACK(entry)) to_reuse = 0; /* can't reuse what we don't have */ - else if (entry->type == OBJ_REF_DELTA || entry->type == OBJ_OFS_DELTA) + else if (oe_type(entry) == OBJ_REF_DELTA || + oe_type(entry) == OBJ_OFS_DELTA) /* check_object() decided it for us ... */ to_reuse = usable_delta; /* ... but pack split may override that */ - else if (entry->type != entry->in_pack_type) + else if (oe_type(entry) != entry->in_pack_type) to_reuse = 0; /* pack has delta which is unusable */ - else if (entry->delta) + else if (DELTA(entry)) to_reuse = 0; /* we want to pack afresh */ else to_reuse = 1; /* we have it in-pack undeltified, @@ -538,12 +557,12 @@ static enum write_one_status write_one(struct hashfile *f, } /* if we are deltified, write out base object first. */ - if (e->delta) { + if (DELTA(e)) { e->idx.offset = 1; /* now recurse */ - switch (write_one(f, e->delta, offset)) { + switch (write_one(f, DELTA(e), offset)) { case WRITE_ONE_RECURSIVE: /* we cannot depend on this one */ - e->delta = NULL; + SET_DELTA(e, NULL); break; default: break; @@ -605,34 +624,34 @@ static void add_descendants_to_write_order(struct object_entry **wo, /* add this node... */ add_to_write_order(wo, endp, e); /* all its siblings... */ - for (s = e->delta_sibling; s; s = s->delta_sibling) { + for (s = DELTA_SIBLING(e); s; s = DELTA_SIBLING(s)) { add_to_write_order(wo, endp, s); } } /* drop down a level to add left subtree nodes if possible */ - if (e->delta_child) { + if (DELTA_CHILD(e)) { add_to_order = 1; - e = e->delta_child; + e = DELTA_CHILD(e); } else { add_to_order = 0; /* our sibling might have some children, it is next */ - if (e->delta_sibling) { - e = e->delta_sibling; + if (DELTA_SIBLING(e)) { + e = DELTA_SIBLING(e); continue; } /* go back to our parent node */ - e = e->delta; - while (e && !e->delta_sibling) { + e = DELTA(e); + while (e && !DELTA_SIBLING(e)) { /* we're on the right side of a subtree, keep * going up until we can go right again */ - e = e->delta; + e = DELTA(e); } if (!e) { /* done- we hit our original root node */ return; } /* pass it off to sibling at this level */ - e = e->delta_sibling; + e = DELTA_SIBLING(e); } }; } @@ -643,7 +662,7 @@ static void add_family_to_write_order(struct object_entry **wo, { struct object_entry *root; - for (root = e; root->delta; root = root->delta) + for (root = e; DELTA(root); root = DELTA(root)) ; /* nothing */ add_descendants_to_write_order(wo, endp, root); } @@ -658,8 +677,8 @@ static struct object_entry **compute_write_order(void) for (i = 0; i < to_pack.nr_objects; i++) { objects[i].tagged = 0; objects[i].filled = 0; - objects[i].delta_child = NULL; - objects[i].delta_sibling = NULL; + SET_DELTA_CHILD(&objects[i], NULL); + SET_DELTA_SIBLING(&objects[i], NULL); } /* @@ -669,11 +688,11 @@ static struct object_entry **compute_write_order(void) */ for (i = to_pack.nr_objects; i > 0;) { struct object_entry *e = &objects[--i]; - if (!e->delta) + if (!DELTA(e)) continue; /* Mark me as the first child */ - e->delta_sibling = e->delta->delta_child; - e->delta->delta_child = e; + e->delta_sibling_idx = DELTA(e)->delta_child_idx; + SET_DELTA_CHILD(DELTA(e), e); } /* @@ -705,8 +724,8 @@ static struct object_entry **compute_write_order(void) * And then all remaining commits and tags. */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (objects[i].type != OBJ_COMMIT && - objects[i].type != OBJ_TAG) + if (oe_type(&objects[i]) != OBJ_COMMIT && + oe_type(&objects[i]) != OBJ_TAG) continue; add_to_write_order(wo, &wo_end, &objects[i]); } @@ -715,7 +734,7 @@ static struct object_entry **compute_write_order(void) * And then all the trees. */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (objects[i].type != OBJ_TREE) + if (oe_type(&objects[i]) != OBJ_TREE) continue; add_to_write_order(wo, &wo_end, &objects[i]); } @@ -752,7 +771,7 @@ static off_t write_reused_pack(struct hashfile *f) die_errno("unable to seek in reused packfile"); if (reuse_packfile_offset < 0) - reuse_packfile_offset = reuse_packfile->pack_size - 20; + reuse_packfile_offset = reuse_packfile->pack_size - the_hash_algo->rawsz; total = to_write = reuse_packfile_offset - sizeof(struct pack_header); @@ -837,11 +856,11 @@ static void write_pack_file(void) * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - hashclose(f, oid.hash, CSUM_CLOSE); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); } else if (nr_written == nr_remaining) { - hashclose(f, oid.hash, CSUM_FSYNC); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { - int fd = hashclose(f, oid.hash, 0); + int fd = finalize_hashfile(f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, pack_tmp_name, nr_written, oid.hash, offset); close(fd); @@ -878,7 +897,8 @@ static void write_pack_file(void) if (write_bitmap_index) { bitmap_writer_set_checksum(oid.hash); - bitmap_writer_build_type_index(written_list, nr_written); + bitmap_writer_build_type_index( + &to_pack, written_list, nr_written); } finish_tmp_packfile(&tmpname, pack_tmp_name, @@ -982,13 +1002,16 @@ static int want_found_object(int exclude, struct packed_git *p) * 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 && + if (!ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && (!local || !have_non_local_packs)) return 1; if (local && !p->pack_local) return 0; - if (ignore_packed_keep && p->pack_local && p->pack_keep) + if (p->pack_local && + ((ignore_packed_keep_on_disk && p->pack_keep) || + (ignore_packed_keep_in_core && p->pack_keep_in_core))) return 0; /* we don't know yet; keep looking for more packs */ @@ -1012,7 +1035,7 @@ static int want_object_in_pack(const struct object_id *oid, int want; struct list_head *pos; - if (!exclude && local && has_loose_object_nonlocal(oid->hash)) + if (!exclude && local && has_loose_object_nonlocal(oid)) return 0; /* @@ -1025,8 +1048,7 @@ static int want_object_in_pack(const struct object_id *oid, if (want != -1) return want; } - - list_for_each(pos, &packed_git_mru) { + list_for_each(pos, get_packed_git_mru(the_repository)) { struct packed_git *p = list_entry(pos, struct packed_git, mru); off_t offset; @@ -1044,7 +1066,8 @@ static int want_object_in_pack(const struct object_id *oid, } want = want_found_object(exclude, p); if (!exclude && want > 0) - list_move(&p->mru, &packed_git_mru); + list_move(&p->mru, + get_packed_git_mru(the_repository)); if (want != -1) return want; } @@ -1066,14 +1089,13 @@ static void create_object_entry(const struct object_id *oid, entry = packlist_alloc(&to_pack, oid->hash, index_pos); entry->hash = hash; - if (type) - entry->type = type; + oe_set_type(entry, type); if (exclude) entry->preferred_base = 1; else nr_result++; if (found_pack) { - entry->in_pack = found_pack; + oe_set_in_pack(&to_pack, entry, found_pack); entry->in_pack_offset = found_offset; } @@ -1091,6 +1113,8 @@ static int add_object_entry(const struct object_id *oid, enum object_type type, off_t found_offset = 0; uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, exclude, &index_pos)) return 0; @@ -1106,8 +1130,6 @@ static int add_object_entry(const struct object_id *oid, enum object_type type, create_object_entry(oid, type, pack_name_hash(name), exclude, name && no_try_delta(name), index_pos, found_pack, found_offset); - - display_progress(progress_state, nr_result); return 1; } @@ -1118,6 +1140,8 @@ static int add_object_entry_from_bitmap(const struct object_id *oid, { uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, 0, &index_pos)) return 0; @@ -1125,8 +1149,6 @@ static int add_object_entry_from_bitmap(const struct object_id *oid, return 0; create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset); - - display_progress(progress_state, nr_result); return 1; } @@ -1190,7 +1212,7 @@ 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_sha1_file(oid->hash, &type, &size); + data = read_object_file(oid, &type, &size); if (!data) return NULL; if (type != OBJ_TREE) { @@ -1351,7 +1373,7 @@ static void add_preferred_base(struct object_id *oid) if (window <= num_preferred_base++) return; - data = read_object_with_reference(oid->hash, tree_type, &size, tree_oid.hash); + data = read_object_with_reference(oid, tree_type, &size, &tree_oid); if (!data) return; @@ -1398,8 +1420,10 @@ static void cleanup_preferred_base(void) static void check_object(struct object_entry *entry) { - if (entry->in_pack) { - struct packed_git *p = entry->in_pack; + unsigned long 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; struct object_entry *base_entry; @@ -1407,6 +1431,8 @@ static void check_object(struct object_entry *entry) unsigned long avail; off_t ofs; unsigned char *buf, c; + enum object_type type; + unsigned long in_pack_size; buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail); @@ -1415,11 +1441,15 @@ static void check_object(struct object_entry *entry) * since non-delta representations could still be reused. */ used = unpack_object_header_buffer(buf, avail, - &entry->in_pack_type, - &entry->size); + &type, + &in_pack_size); if (used == 0) goto give_up; + if (type < 0) + BUG("invalid type %d", type); + entry->in_pack_type = type; + /* * Determine if this is a delta and if so whether we can * reuse it or not. Otherwise let's find out as cheaply as @@ -1428,9 +1458,10 @@ static void check_object(struct object_entry *entry) switch (entry->in_pack_type) { default: /* Not a delta hence we've already got all we need. */ - entry->type = entry->in_pack_type; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); entry->in_pack_header_size = used; - if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB) + if (oe_type(entry) < OBJ_COMMIT || oe_type(entry) > OBJ_BLOB) goto give_up; unuse_pack(&w_curs); return; @@ -1438,7 +1469,7 @@ static void check_object(struct object_entry *entry) if (reuse_delta && !entry->preferred_base) base_ref = use_pack(p, &w_curs, entry->in_pack_offset + used, NULL); - entry->in_pack_header_size = used + 20; + entry->in_pack_header_size = used + the_hash_algo->rawsz; break; case OBJ_OFS_DELTA: buf = use_pack(p, &w_curs, @@ -1484,25 +1515,29 @@ static void check_object(struct object_entry *entry) * deltify other objects against, in order to avoid * circular deltas. */ - entry->type = entry->in_pack_type; - entry->delta = base_entry; - entry->delta_size = entry->size; - entry->delta_sibling = base_entry->delta_child; - base_entry->delta_child = entry; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); /* delta size */ + SET_DELTA(entry, base_entry); + SET_DELTA_SIZE(entry, in_pack_size); + entry->delta_sibling_idx = base_entry->delta_child_idx; + SET_DELTA_CHILD(base_entry, entry); unuse_pack(&w_curs); return; } - if (entry->type) { + if (oe_type(entry)) { + off_t delta_pos; + /* * This must be a delta and we already know what the * final object type is. Let's extract the actual * object size from the delta header. */ - entry->size = get_size_from_delta(p, &w_curs, - entry->in_pack_offset + entry->in_pack_header_size); - if (entry->size == 0) + delta_pos = entry->in_pack_offset + entry->in_pack_header_size; + canonical_size = get_size_from_delta(p, &w_curs, delta_pos); + if (canonical_size == 0) goto give_up; + SET_SIZE(entry, canonical_size); unuse_pack(&w_curs); return; } @@ -1516,27 +1551,34 @@ static void check_object(struct object_entry *entry) unuse_pack(&w_curs); } - entry->type = sha1_object_info(entry->idx.oid.hash, &entry->size); - /* - * The error condition is checked in prepare_pack(). This is - * to permit a missing preferred base object to be ignored - * as a preferred base. Doing so can result in a larger - * pack file, but the transfer will still take place. - */ + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &canonical_size)); + if (entry->type_valid) { + SET_SIZE(entry, canonical_size); + } else { + /* + * Bad object type is checked in prepare_pack(). This is + * to permit a missing preferred base object to be ignored + * as a preferred base. Doing so can result in a larger + * pack file, but the transfer will still take place. + */ + } } static int pack_offset_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + const struct packed_git *a_in_pack = IN_PACK(a); + const struct packed_git *b_in_pack = IN_PACK(b); /* avoid filesystem trashing with loose objects */ - if (!a->in_pack && !b->in_pack) + if (!a_in_pack && !b_in_pack) return oidcmp(&a->idx.oid, &b->idx.oid); - if (a->in_pack < b->in_pack) + if (a_in_pack < b_in_pack) return -1; - if (a->in_pack > b->in_pack) + if (a_in_pack > b_in_pack) return 1; return a->in_pack_offset < b->in_pack_offset ? -1 : (a->in_pack_offset > b->in_pack_offset); @@ -1557,30 +1599,37 @@ static int pack_offset_sort(const void *_a, const void *_b) */ static void drop_reused_delta(struct object_entry *entry) { - struct object_entry **p = &entry->delta->delta_child; + unsigned *idx = &to_pack.objects[entry->delta_idx - 1].delta_child_idx; struct object_info oi = OBJECT_INFO_INIT; + enum object_type type; + unsigned long size; - while (*p) { - if (*p == entry) - *p = (*p)->delta_sibling; + while (*idx) { + struct object_entry *oe = &to_pack.objects[*idx - 1]; + + if (oe == entry) + *idx = oe->delta_sibling_idx; else - p = &(*p)->delta_sibling; + idx = &oe->delta_sibling_idx; } - entry->delta = NULL; + SET_DELTA(entry, NULL); entry->depth = 0; - oi.sizep = &entry->size; - oi.typep = &entry->type; - if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) { + oi.sizep = &size; + oi.typep = &type; + if (packed_object_info(the_repository, IN_PACK(entry), entry->in_pack_offset, &oi) < 0) { /* * We failed to get the info from this pack for some reason; * fall back to sha1_object_info, which may find another copy. - * And if that fails, the error will be recorded in entry->type + * And if that fails, the error will be recorded in oe_type(entry) * and dealt with in prepare_pack(). */ - entry->type = sha1_object_info(entry->idx.oid.hash, - &entry->size); + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &size)); + } else { + oe_set_type(entry, type); } + SET_SIZE(entry, size); } /* @@ -1604,7 +1653,7 @@ static void break_delta_chains(struct object_entry *entry) for (cur = entry, total_depth = 0; cur; - cur = cur->delta, total_depth++) { + cur = DELTA(cur), total_depth++) { if (cur->dfs_state == DFS_DONE) { /* * We've already seen this object and know it isn't @@ -1621,7 +1670,7 @@ static void break_delta_chains(struct object_entry *entry) * is a bug. */ if (cur->dfs_state != DFS_NONE) - die("BUG: confusing delta dfs state in first pass: %d", + BUG("confusing delta dfs state in first pass: %d", cur->dfs_state); /* @@ -1629,7 +1678,7 @@ static void break_delta_chains(struct object_entry *entry) * it's not a delta, we're done traversing, but we'll mark it * done to save time on future traversals. */ - if (!cur->delta) { + if (!DELTA(cur)) { cur->dfs_state = DFS_DONE; break; } @@ -1652,7 +1701,7 @@ static void break_delta_chains(struct object_entry *entry) * We keep all commits in the chain that we examined. */ cur->dfs_state = DFS_ACTIVE; - if (cur->delta->dfs_state == DFS_ACTIVE) { + if (DELTA(cur)->dfs_state == DFS_ACTIVE) { drop_reused_delta(cur); cur->dfs_state = DFS_DONE; break; @@ -1667,7 +1716,7 @@ static void break_delta_chains(struct object_entry *entry) * an extra "next" pointer to keep going after we reset cur->delta. */ for (cur = entry; cur; cur = next) { - next = cur->delta; + next = DELTA(cur); /* * We should have a chain of zero or more ACTIVE states down to @@ -1678,7 +1727,7 @@ static void break_delta_chains(struct object_entry *entry) if (cur->dfs_state == DFS_DONE) break; else if (cur->dfs_state != DFS_ACTIVE) - die("BUG: confusing delta dfs state in second pass: %d", + BUG("confusing delta dfs state in second pass: %d", cur->dfs_state); /* @@ -1712,6 +1761,10 @@ static void get_object_details(void) uint32_t i; struct object_entry **sorted_by_offset; + if (progress) + progress_state = start_progress(_("Counting objects"), + to_pack.nr_objects); + sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *)); for (i = 0; i < to_pack.nr_objects; i++) sorted_by_offset[i] = to_pack.objects + i; @@ -1720,9 +1773,12 @@ static void get_object_details(void) for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = sorted_by_offset[i]; check_object(entry); - if (big_file_threshold < entry->size) + if (entry->type_valid && + oe_size_greater_than(&to_pack, entry, big_file_threshold)) entry->no_try_delta = 1; + display_progress(progress_state, i + 1); } + stop_progress(&progress_state); /* * This must happen in a second pass, since we rely on the delta @@ -1747,10 +1803,14 @@ static int type_size_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + enum object_type a_type = oe_type(a); + enum object_type b_type = oe_type(b); + unsigned long a_size = SIZE(a); + unsigned long b_size = SIZE(b); - if (a->type > b->type) + if (a_type > b_type) return -1; - if (a->type < b->type) + if (a_type < b_type) return 1; if (a->hash > b->hash) return -1; @@ -1760,9 +1820,9 @@ static int type_size_sort(const void *_a, const void *_b) return -1; if (a->preferred_base < b->preferred_base) return 1; - if (a->size > b->size) + if (a_size > b_size) return -1; - if (a->size < b->size) + if (a_size < b_size) return 1; return a < b ? -1 : (a > b); /* newest first */ } @@ -1815,6 +1875,46 @@ static pthread_mutex_t progress_mutex; #endif +/* + * Return the size of the object without doing any delta + * reconstruction (so non-deltas are true object sizes, but deltas + * return the size of the delta data). + */ +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e) +{ + struct packed_git *p; + struct pack_window *w_curs; + unsigned char *buf; + enum object_type type; + unsigned long used, avail, size; + + if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) { + read_lock(); + if (oid_object_info(the_repository, &e->idx.oid, &size) < 0) + die(_("unable to get size of %s"), + oid_to_hex(&e->idx.oid)); + read_unlock(); + return size; + } + + p = oe_in_pack(pack, e); + if (!p) + BUG("when e->type is a delta, it must belong to a pack"); + + read_lock(); + w_curs = NULL; + buf = use_pack(p, &w_curs, e->in_pack_offset, &avail); + used = unpack_object_header_buffer(buf, avail, &type, &size); + if (used == 0) + die(_("unable to parse object header of %s"), + oid_to_hex(&e->idx.oid)); + + unuse_pack(&w_curs); + read_unlock(); + return size; +} + static int try_delta(struct unpacked *trg, struct unpacked *src, unsigned max_depth, unsigned long *mem_usage) { @@ -1826,7 +1926,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, void *delta_buf; /* Don't bother doing diffs between different types */ - if (trg_entry->type != src_entry->type) + if (oe_type(trg_entry) != oe_type(src_entry)) return -1; /* @@ -1837,8 +1937,8 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, * it, we will still save the transfer cost, as we already know * the other side has it and we won't send src_entry at all. */ - if (reuse_delta && trg_entry->in_pack && - trg_entry->in_pack == src_entry->in_pack && + if (reuse_delta && IN_PACK(trg_entry) && + IN_PACK(trg_entry) == IN_PACK(src_entry) && !src_entry->preferred_base && trg_entry->in_pack_type != OBJ_REF_DELTA && trg_entry->in_pack_type != OBJ_OFS_DELTA) @@ -1849,19 +1949,19 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, return 0; /* Now some size filtering heuristics. */ - trg_size = trg_entry->size; - if (!trg_entry->delta) { - max_size = trg_size/2 - 20; + trg_size = SIZE(trg_entry); + if (!DELTA(trg_entry)) { + max_size = trg_size/2 - the_hash_algo->rawsz; ref_depth = 1; } else { - max_size = trg_entry->delta_size; + max_size = DELTA_SIZE(trg_entry); ref_depth = trg->depth; } max_size = (uint64_t)max_size * (max_depth - src->depth) / (max_depth - ref_depth + 1); if (max_size == 0) return 0; - src_size = src_entry->size; + src_size = SIZE(src_entry); sizediff = src_size < trg_size ? trg_size - src_size : 0; if (sizediff >= max_size) return 0; @@ -1871,8 +1971,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, /* Load data if not already done */ if (!trg->data) { read_lock(); - trg->data = read_sha1_file(trg_entry->idx.oid.hash, &type, - &sz); + trg->data = read_object_file(&trg_entry->idx.oid, &type, &sz); read_unlock(); if (!trg->data) die("object %s cannot be read", @@ -1885,8 +1984,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, } if (!src->data) { read_lock(); - src->data = read_sha1_file(src_entry->idx.oid.hash, &type, - &sz); + src->data = read_object_file(&src_entry->idx.oid, &type, &sz); read_unlock(); if (!src->data) { if (src_entry->preferred_base) { @@ -1925,10 +2023,14 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size); if (!delta_buf) return 0; + if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) { + free(delta_buf); + return 0; + } - if (trg_entry->delta) { + if (DELTA(trg_entry)) { /* Prefer only shallower same-sized deltas. */ - if (delta_size == trg_entry->delta_size && + if (delta_size == DELTA_SIZE(trg_entry) && src->depth + 1 >= trg->depth) { free(delta_buf); return 0; @@ -1943,7 +2045,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, free(trg_entry->delta_data); cache_lock(); if (trg_entry->delta_data) { - delta_cache_size -= trg_entry->delta_size; + delta_cache_size -= DELTA_SIZE(trg_entry); trg_entry->delta_data = NULL; } if (delta_cacheable(src_size, trg_size, delta_size)) { @@ -1955,8 +2057,8 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, free(delta_buf); } - trg_entry->delta = src_entry; - trg_entry->delta_size = delta_size; + SET_DELTA(trg_entry, src_entry); + SET_DELTA_SIZE(trg_entry, delta_size); trg->depth = src->depth + 1; return 1; @@ -1964,13 +2066,13 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) { - struct object_entry *child = me->delta_child; + struct object_entry *child = DELTA_CHILD(me); unsigned int m = n; while (child) { unsigned int c = check_delta_limit(child, n + 1); if (m < c) m = c; - child = child->delta_sibling; + child = DELTA_SIBLING(child); } return m; } @@ -1981,7 +2083,7 @@ static unsigned long free_unpacked(struct unpacked *n) free_delta_index(n->index); n->index = NULL; if (n->data) { - freed_mem += n->entry->size; + freed_mem += SIZE(n->entry); FREE_AND_NULL(n->data); } n->entry = NULL; @@ -2039,7 +2141,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * otherwise they would become too deep. */ max_depth = depth; - if (entry->delta_child) { + if (DELTA_CHILD(entry)) { max_depth -= check_delta_limit(entry, 0); if (max_depth <= 0) goto next; @@ -2077,19 +2179,26 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * between writes at that moment. */ if (entry->delta_data && !pack_to_stdout) { - entry->z_delta_size = do_compress(&entry->delta_data, - entry->delta_size); - cache_lock(); - delta_cache_size -= entry->delta_size; - delta_cache_size += entry->z_delta_size; - cache_unlock(); + unsigned long size; + + size = do_compress(&entry->delta_data, DELTA_SIZE(entry)); + if (size < (1U << OE_Z_DELTA_BITS)) { + entry->z_delta_size = size; + cache_lock(); + delta_cache_size -= DELTA_SIZE(entry); + delta_cache_size += entry->z_delta_size; + cache_unlock(); + } else { + FREE_AND_NULL(entry->delta_data); + entry->z_delta_size = 0; + } } /* if we made n a delta, and if n is already at max * depth, leaving it in the window is pointless. we * should evict it first. */ - if (entry->delta && max_depth <= n->depth) + if (DELTA(entry) && max_depth <= n->depth) continue; /* @@ -2097,7 +2206,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * currently deltified object, to keep it longer. It will * be the first base object to be attempted next. */ - if (entry->delta) { + if (DELTA(entry)) { struct unpacked swap = array[best_base]; int dist = (window + idx - best_base) % window; int dst = best_base; @@ -2418,13 +2527,14 @@ static void prepare_pack(int window, int depth) for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = to_pack.objects + i; - if (entry->delta) + if (DELTA(entry)) /* This happens if we decided to reuse existing * delta from a pack. "reuse_delta &&" is implied. */ continue; - if (entry->size < 50) + if (!entry->type_valid || + oe_size_less_than(&to_pack, entry, 50)) continue; if (entry->no_try_delta) @@ -2432,11 +2542,11 @@ static void prepare_pack(int window, int depth) if (!entry->preferred_base) { nr_deltas++; - if (entry->type < 0) + if (oe_type(entry) < 0) die("unable to get type of object %s", oid_to_hex(&entry->idx.oid)); } else { - if (entry->type < 0) { + if (oe_type(entry) < 0) { /* * This object is not found, but we * don't have to include it anyway. @@ -2545,7 +2655,7 @@ static void read_object_list_from_stdin(void) die("expected object ID, got garbage:\n %s", line); add_preferred_base_object(p + 1); - add_object_entry(&oid, 0, p + 1, 0); + add_object_entry(&oid, OBJ_NONE, p + 1, 0); } } @@ -2674,11 +2784,11 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs) memset(&in_pack, 0, sizeof(in_pack)); - for (p = packed_git; p; p = p->next) { + for (p = get_packed_git(the_repository); p; p = p->next) { struct object_id oid; struct object *o; - if (!p->pack_local || p->pack_keep) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) die("cannot open pack index"); @@ -2709,7 +2819,7 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs) static int add_loose_object(const struct object_id *oid, const char *path, void *data) { - enum object_type type = sha1_object_info(oid->hash, NULL); + enum object_type type = oid_object_info(the_repository, oid, NULL); if (type < 0) { warning("loose object at %s could not be examined", path); @@ -2737,16 +2847,18 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid) static struct packed_git *last_found = (void *)1; struct packed_git *p; - p = (last_found != (void *)1) ? last_found : packed_git; + p = (last_found != (void *)1) ? last_found : + get_packed_git(the_repository); while (p) { - if ((!p->pack_local || p->pack_keep) && + if ((!p->pack_local || p->pack_keep || + p->pack_keep_in_core) && find_pack_entry_one(oid->hash, p)) { last_found = p; return 1; } if (p == last_found) - p = packed_git; + p = get_packed_git(the_repository); else p = p->next; if (p == last_found) @@ -2782,8 +2894,8 @@ static void loosen_unused_packed_objects(struct rev_info *revs) uint32_t i; struct object_id oid; - for (p = packed_git; p; p = p->next) { - if (!p->pack_local || p->pack_keep) + for (p = get_packed_git(the_repository); p; p = p->next) { + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) @@ -2809,7 +2921,8 @@ static int pack_options_allow_reuse(void) { return pack_to_stdout && allow_ofs_delta && - !ignore_packed_keep && + !ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && (!local || !have_non_local_packs) && !incremental; } @@ -2918,6 +3031,32 @@ static void get_object_list(int ac, const char **av) oid_array_clear(&recent_objects); } +static void add_extra_kept_packs(const struct string_list *names) +{ + struct packed_git *p; + + if (!names->nr) + return; + + for (p = get_packed_git(the_repository); p; p = p->next) { + const char *name = basename(p->pack_name); + int i; + + if (!p->pack_local) + continue; + + for (i = 0; i < names->nr; i++) + if (!fspathcmp(name, names->items[i].string)) + break; + + if (i < names->nr) { + p->pack_keep_in_core = 1; + ignore_packed_keep_in_core = 1; + continue; + } + } +} + static int option_parse_index_version(const struct option *opt, const char *arg, int unset) { @@ -2957,6 +3096,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) struct argv_array rp = ARGV_ARRAY_INIT; int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0; int rev_list_index = 0; + struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; struct option pack_objects_options[] = { OPT_SET_INT('q', "quiet", &progress, N_("do not show progress meter"), 0), @@ -2994,18 +3134,18 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("do not create an empty pack output")), OPT_BOOL(0, "revs", &use_internal_rev_list, N_("read revision arguments from standard input")), - { OPTION_SET_INT, 0, "unpacked", &rev_list_unpacked, NULL, - N_("limit the objects to those that are not yet packed"), - PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, - { OPTION_SET_INT, 0, "all", &rev_list_all, NULL, - N_("include objects reachable from any reference"), - PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, - { OPTION_SET_INT, 0, "reflog", &rev_list_reflog, NULL, - N_("include objects referred by reflog entries"), - PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, - { OPTION_SET_INT, 0, "indexed-objects", &rev_list_index, NULL, - N_("include objects referred to by the index"), - PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 }, + OPT_SET_INT_F(0, "unpacked", &rev_list_unpacked, + N_("limit the objects to those that are not yet packed"), + 1, PARSE_OPT_NONEG), + OPT_SET_INT_F(0, "all", &rev_list_all, + N_("include objects reachable from any reference"), + 1, PARSE_OPT_NONEG), + OPT_SET_INT_F(0, "reflog", &rev_list_reflog, + N_("include objects referred by reflog entries"), + 1, PARSE_OPT_NONEG), + 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, "stdout", &pack_to_stdout, N_("output pack to stdout")), OPT_BOOL(0, "include-tag", &include_tag, @@ -3021,8 +3161,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("create thin packs")), OPT_BOOL(0, "shallow", &shallow, N_("create packs suitable for shallow fetches")), - OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep, + OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk, N_("ignore packs that have companion .keep file")), + OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"), + 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, @@ -3040,6 +3182,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) OPT_END(), }; + if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS)) + BUG("too many dfs states, increase OE_DFS_STATE_BITS"); + check_replace_refs = 0; reset_pack_idx_option(&pack_idx_opts); @@ -3056,6 +3201,17 @@ 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 >= (1 << OE_DEPTH_BITS)) { + warning(_("delta chain depth %d is too deep, forcing %d"), + depth, (1 << OE_DEPTH_BITS) - 1); + depth = (1 << OE_DEPTH_BITS) - 1; + } + if (cache_max_small_delta_size >= (1U << OE_Z_DELTA_BITS)) { + warning(_("pack.deltaCacheLimit is too high, forcing %d"), + (1U << OE_Z_DELTA_BITS) - 1); + cache_max_small_delta_size = (1U << OE_Z_DELTA_BITS) - 1; + } + argv_array_push(&rp, "pack-objects"); if (thin) { use_internal_rev_list = 1; @@ -3087,6 +3243,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) fetch_if_missing = 0; argv_array_push(&rp, "--exclude-promisor-objects"); } + if (unpack_unreachable || keep_unreachable || pack_loose_unreachable) + use_internal_rev_list = 1; if (!reuse_object) reuse_delta = 0; @@ -3150,23 +3308,23 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (progress && all_progress_implied) progress = 2; - prepare_packed_git(); - if (ignore_packed_keep) { + add_extra_kept_packs(&keep_pack_list); + if (ignore_packed_keep_on_disk) { struct packed_git *p; - for (p = packed_git; p; p = p->next) + for (p = get_packed_git(the_repository); p; p = p->next) if (p->pack_local && p->pack_keep) break; if (!p) /* no keep-able packs found */ - ignore_packed_keep = 0; + ignore_packed_keep_on_disk = 0; } if (local) { /* - * unlike ignore_packed_keep above, we do not want to - * unset "local" based on looking at packs, as it - * also covers non-local objects + * unlike ignore_packed_keep_on_disk above, we do not + * want to unset "local" based on looking at packs, as + * it also covers non-local objects */ struct packed_git *p; - for (p = packed_git; p; p = p->next) { + for (p = get_packed_git(the_repository); p; p = p->next) { if (!p->pack_local) { have_non_local_packs = 1; break; @@ -3174,8 +3332,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) } } + prepare_packing_data(&to_pack); + if (progress) - progress_state = start_progress(_("Counting objects"), 0); + progress_state = start_progress(_("Enumerating objects"), 0); if (!use_internal_rev_list) read_object_list_from_stdin(); else { |