From: Junio C Hamano Date: Tue, 6 Nov 2018 06:50:21 +0000 (+0900) Subject: Merge branch 'md/exclude-promisor-objects-fix' X-Git-Tag: v2.20.0-rc0~67 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/a29b8bcf624006cf66abe129c01c932ec75df9f7?hp=-c Merge branch 'md/exclude-promisor-objects-fix' Operations on promisor objects make sense in the context of only a small subset of the commands that internally use the revisions machinery, but the "--exclude-promisor-objects" option were taken and led to nonsense results by commands like "log", to which it didn't make much sense. This has been corrected. * md/exclude-promisor-objects-fix: exclude-promisor-objects: declare when option is allowed Documentation/git-log.txt: do not show --exclude-promisor-objects --- a29b8bcf624006cf66abe129c01c932ec75df9f7 diff --combined Documentation/rev-list-options.txt index 5f1672913b,21978ebbac..bab5f50b17 --- a/Documentation/rev-list-options.txt +++ b/Documentation/rev-list-options.txt @@@ -731,11 -731,6 +731,11 @@@ the requested refs + The form '--filter=sparse:path=' similarly uses a sparse-checkout specification contained in . ++ +The form '--filter=tree:' omits all blobs and trees whose depth +from the root tree is >= (minimum depth if an object is located +at multiple depths in the commits traversed). Currently, only =0 +is supported, which omits all blobs and trees. --no-filter:: Turn off any previous `--filter=` argument. @@@ -761,7 -756,6 +761,6 @@@ Unexpected missing objects will raise a + The form '--missing=print' is like 'allow-any', but will also print a list of the missing objects. Object IDs are prefixed with a ``?'' character. - endif::git-rev-list[] --exclude-promisor-objects:: (For internal use only.) Prefilter object traversal at @@@ -769,6 -763,7 +768,7 @@@ stronger than `--missing=allow-promisor` because it limits the traversal, rather than just silencing errors about missing objects. + endif::git-rev-list[] --no-walk[=(sorted|unsorted)]:: Only show the given commits, but do not traverse their ancestors. diff --combined builtin/pack-objects.c index e50c6cd1ff,8ac8ca1d26..c99ee79c31 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@@ -1,6 -1,5 +1,6 @@@ #include "builtin.h" #include "cache.h" +#include "repository.h" #include "config.h" #include "attr.h" #include "object.h" @@@ -24,28 -23,11 +24,28 @@@ #include "streaming.h" #include "thread-utils.h" #include "pack-bitmap.h" +#include "delta-islands.h" #include "reachable.h" #include "sha1-array.h" #include "argv-array.h" #include "list.h" #include "packfile.h" +#include "object-store.h" +#include "dir.h" +#include "midx.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_EXT(obj, oid) oe_set_delta_ext(&to_pack, obj, oid) +#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 [...] [< | < ]"), @@@ -61,9 -43,7 +61,9 @@@ 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 struct bitmap_index *bitmap_git; +static uint32_t write_layer; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@@ -73,8 -53,7 +73,8 @@@ 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; @@@ -84,7 -63,6 +84,7 @@@ static unsigned long pack_size_limit static int depth = 50; static int delta_search_threads; static int pack_to_stdout; +static int thin; static int num_preferred_base; static struct progress *progress_state; @@@ -99,10 -77,8 +99,10 @@@ static uint16_t write_bitmap_options static int exclude_promisor_objects; +static int use_delta_islands; + 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; @@@ -146,23 -122,18 +146,23 @@@ static void *get_delta(struct object_en 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); + die(_("unable to read %s"), oid_to_hex(&entry->idx.oid)); + 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) - die("delta size changed"); + /* + * We succesfully computed this delta once but dropped it for + * memory reasons. Something is very wrong if this time we + * recompute and create a different delta. + */ + if (!delta_buf || delta_size != DELTA_SIZE(entry)) + BUG("delta size changed"); free(buf); free(base_buf); return delta_buf; @@@ -292,15 -263,15 +292,15 @@@ static unsigned long write_no_reuse_obj 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)); @@@ -312,15 -283,15 +312,15 @@@ 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; } @@@ -344,12 -315,12 +344,12 @@@ * 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); @@@ -361,19 -332,19 +361,19 @@@ } 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); @@@ -396,30 -367,28 +396,30 @@@ 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); datalen = revidx[1].offset - offset; if (!pack_to_stdout && p->index_version > 1 && check_pack_crc(p, &w_curs, offset, datalen, revidx->nr)) { - error("bad packed object CRC for %s", + error(_("bad packed object CRC for %s"), oid_to_hex(&entry->idx.oid)); unuse_pack(&w_curs); return write_no_reuse_object(f, entry, limit, usable_delta); @@@ -429,20 -398,20 +429,20 @@@ datalen -= entry->in_pack_header_size; if (!pack_to_stdout && p->index_version == 1 && - check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) { - error("corrupt packed object for %s", + 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); return write_no_reuse_object(f, entry, limit, usable_delta); } 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; } @@@ -451,16 -420,16 +451,16 @@@ 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; } @@@ -496,29 -465,28 +496,29 @@@ static off_t write_object(struct hashfi 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, @@@ -561,7 -529,7 +561,7 @@@ static enum write_one_status write_one( */ recursing = (e->idx.offset == 1); if (recursing) { - warning("recursive delta detected for object %s", + warning(_("recursive delta detected for object %s"), oid_to_hex(&e->idx.oid)); return WRITE_ONE_RECURSIVE; } else if (e->idx.offset || e->preferred_base) { @@@ -570,12 -538,12 +570,12 @@@ } /* 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; @@@ -595,7 -563,7 +595,7 @@@ /* make sure off_t is sufficiently large not to wrap */ if (signed_add_overflows(*offset, size)) - die("pack too large for current definition of off_t"); + die(_("pack too large for current definition of off_t")); *offset += size; return WRITE_ONE_WRITTEN; } @@@ -620,7 -588,7 +620,7 @@@ static inline void add_to_write_order(s unsigned int *endp, struct object_entry *e) { - if (e->filled) + if (e->filled || oe_layer(&to_pack, e) != write_layer) return; wo[(*endp)++] = e; e->filled = 1; @@@ -637,34 -605,34 +637,34 @@@ static void add_descendants_to_write_or /* 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); } }; } @@@ -675,20 -643,53 +675,20 @@@ static void add_family_to_write_order(s { 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); } -static struct object_entry **compute_write_order(void) +static void compute_layer_order(struct object_entry **wo, unsigned int *wo_end) { - unsigned int i, wo_end, last_untagged; - - struct object_entry **wo; + unsigned int i, last_untagged; struct object_entry *objects = to_pack.objects; 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; - } - - /* - * Fully connect delta_child/delta_sibling network. - * Make sure delta_sibling is sorted in the original - * recency order. - */ - for (i = to_pack.nr_objects; i > 0;) { - struct object_entry *e = &objects[--i]; - if (!e->delta) - continue; - /* Mark me as the first child */ - e->delta_sibling = e->delta->delta_child; - e->delta->delta_child = e; - } - - /* - * Mark objects that are at the tip of tags. - */ - for_each_tag_ref(mark_tagged, NULL); - - /* - * Give the objects in the original recency order until - * we see a tagged tip. - */ - ALLOC_ARRAY(wo, to_pack.nr_objects); - for (i = wo_end = 0; i < to_pack.nr_objects; i++) { if (objects[i].tagged) break; - add_to_write_order(wo, &wo_end, &objects[i]); + add_to_write_order(wo, wo_end, &objects[i]); } last_untagged = i; @@@ -697,83 -698,38 +697,83 @@@ */ for (; i < to_pack.nr_objects; i++) { if (objects[i].tagged) - add_to_write_order(wo, &wo_end, &objects[i]); + add_to_write_order(wo, wo_end, &objects[i]); } /* * 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]); + add_to_write_order(wo, wo_end, &objects[i]); } /* * 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]); + add_to_write_order(wo, wo_end, &objects[i]); } /* * Finally all the rest in really tight order */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (!objects[i].filled) - add_family_to_write_order(wo, &wo_end, &objects[i]); + if (!objects[i].filled && oe_layer(&to_pack, &objects[i]) == write_layer) + add_family_to_write_order(wo, wo_end, &objects[i]); + } +} + +static struct object_entry **compute_write_order(void) +{ + uint32_t max_layers = 1; + unsigned int i, wo_end; + + struct object_entry **wo; + struct object_entry *objects = to_pack.objects; + + for (i = 0; i < to_pack.nr_objects; i++) { + objects[i].tagged = 0; + objects[i].filled = 0; + SET_DELTA_CHILD(&objects[i], NULL); + SET_DELTA_SIBLING(&objects[i], NULL); + } + + /* + * Fully connect delta_child/delta_sibling network. + * Make sure delta_sibling is sorted in the original + * recency order. + */ + for (i = to_pack.nr_objects; i > 0;) { + struct object_entry *e = &objects[--i]; + if (!DELTA(e)) + continue; + /* Mark me as the first child */ + e->delta_sibling_idx = DELTA(e)->delta_child_idx; + SET_DELTA_CHILD(DELTA(e), e); } + /* + * Mark objects that are at the tip of tags. + */ + for_each_tag_ref(mark_tagged, NULL); + + if (use_delta_islands) + max_layers = compute_pack_layers(&to_pack); + + ALLOC_ARRAY(wo, to_pack.nr_objects); + wo_end = 0; + + for (; write_layer < max_layers; ++write_layer) + compute_layer_order(wo, &wo_end); + if (wo_end != to_pack.nr_objects) - die("ordered %u objects, expected %"PRIu32, wo_end, to_pack.nr_objects); + die(_("ordered %u objects, expected %"PRIu32), + wo_end, to_pack.nr_objects); return wo; } @@@ -785,18 -741,18 +785,18 @@@ static off_t write_reused_pack(struct h int fd; if (!is_pack_valid(reuse_packfile)) - die("packfile is invalid: %s", reuse_packfile->pack_name); + die(_("packfile is invalid: %s"), reuse_packfile->pack_name); fd = git_open(reuse_packfile->pack_name); if (fd < 0) - die_errno("unable to open packfile for reuse: %s", + die_errno(_("unable to open packfile for reuse: %s"), reuse_packfile->pack_name); if (lseek(fd, sizeof(struct pack_header), SEEK_SET) == -1) - die_errno("unable to seek in reused packfile"); + 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); @@@ -804,7 -760,7 +804,7 @@@ int read_pack = xread(fd, buffer, sizeof(buffer)); if (read_pack <= 0) - die_errno("unable to read from reused packfile"); + die_errno(_("unable to read from reused packfile")); if (read_pack > to_write) read_pack = to_write; @@@ -881,11 -837,11 +881,11 @@@ 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); @@@ -907,7 -863,7 +907,7 @@@ * to preserve this property. */ if (stat(pack_tmp_name, &st) < 0) { - warning_errno("failed to stat %s", pack_tmp_name); + warning_errno(_("failed to stat %s"), pack_tmp_name); } else if (!last_mtime) { last_mtime = st.st_mtime; } else { @@@ -915,15 -871,14 +915,15 @@@ utb.actime = st.st_atime; utb.modtime = --last_mtime; if (utime(pack_tmp_name, &utb) < 0) - warning_errno("failed utime() on %s", pack_tmp_name); + warning_errno(_("failed utime() on %s"), pack_tmp_name); } strbuf_addf(&tmpname, "%s-", base_name); 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, @@@ -960,8 -915,8 +960,8 @@@ free(write_order); stop_progress(&progress_state); if (written != nr_result) - die("wrote %"PRIu32" objects while expecting %"PRIu32, - written, nr_result); + die(_("wrote %"PRIu32" objects while expecting %"PRIu32), + written, nr_result); } static int no_try_delta(const char *path) @@@ -970,7 -925,8 +970,7 @@@ if (!check) check = attr_check_initl("delta", NULL); - if (git_check_attr(path, check)) - return 0; + git_check_attr(&the_index, path, check); if (ATTR_FALSE(check->items[0].value)) return 1; return 0; @@@ -1026,16 -982,13 +1026,16 @@@ static int want_found_object(int exclud * 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 */ @@@ -1058,9 -1011,8 +1058,9 @@@ static int want_object_in_pack(const st { int want; struct list_head *pos; + struct multi_pack_index *m; - if (!exclude && local && has_loose_object_nonlocal(oid->hash)) + if (!exclude && local && has_loose_object_nonlocal(oid)) return 0; /* @@@ -1074,32 -1026,7 +1074,32 @@@ return want; } - list_for_each(pos, &packed_git_mru) { + for (m = get_multi_pack_index(the_repository); m; m = m->next) { + struct pack_entry e; + if (fill_midx_entry(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; + } + } + } + + list_for_each(pos, get_packed_git_mru(the_repository)) { struct packed_git *p = list_entry(pos, struct packed_git, mru); off_t offset; @@@ -1117,8 -1044,7 +1117,8 @@@ } 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; } @@@ -1140,13 -1066,14 +1140,13 @@@ static void create_object_entry(const s 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; } @@@ -1164,8 -1091,6 +1164,8 @@@ static int add_object_entry(const struc 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; @@@ -1181,6 -1106,8 +1181,6 @@@ 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; } @@@ -1191,8 -1118,6 +1191,8 @@@ static int add_object_entry_from_bitmap { uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, 0, &index_pos)) return 0; @@@ -1200,6 -1125,8 +1200,6 @@@ return 0; create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset); - - display_progress(progress_state, nr_result); return 1; } @@@ -1247,7 -1174,7 +1247,7 @@@ static struct pbase_tree_cache *pbase_t */ for (neigh = 0; neigh < 8; neigh++) { ent = pbase_tree_cache[my_ix]; - if (ent && !oidcmp(&ent->oid, oid)) { + if (ent && oideq(&ent->oid, oid)) { ent->ref++; return ent; } @@@ -1263,7 -1190,7 +1263,7 @@@ /* 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) { @@@ -1424,12 -1351,12 +1424,12 @@@ static void add_preferred_base(struct o 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; for (it = pbase_tree; it; it = it->next) { - if (!oidcmp(&it->pcache.oid, &tree_oid)) { + if (oideq(&it->pcache.oid, &tree_oid)) { free(data); return; } @@@ -1469,63 -1396,10 +1469,63 @@@ static void cleanup_preferred_base(void done_pbase_paths_num = done_pbase_paths_alloc = 0; } +/* + * Return 1 iff the object specified by "delta" can be sent + * literally as a delta against the base in "base_sha1". If + * so, then *base_out will point to the entry in our packing + * list, or NULL if we must use the external-base list. + * + * Depth value does not matter - find_deltas() will + * never consider reused delta as the base object to + * deltify other objects against, in order to avoid + * circular deltas. + */ +static int can_reuse_delta(const unsigned char *base_sha1, + struct object_entry *delta, + struct object_entry **base_out) +{ + struct object_entry *base; + + if (!base_sha1) + return 0; + + /* + * First see if we're already sending the base (or it's explicitly in + * our "excluded" list). + */ + base = packlist_find(&to_pack, base_sha1, NULL); + if (base) { + if (!in_same_island(&delta->idx.oid, &base->idx.oid)) + return 0; + *base_out = base; + return 1; + } + + /* + * Otherwise, reachability bitmaps may tell us if the receiver has it, + * even if it was buried too deep in history to make it into the + * packing list. + */ + if (thin && bitmap_has_sha1_in_uninteresting(bitmap_git, base_sha1)) { + if (use_delta_islands) { + struct object_id base_oid; + hashcpy(base_oid.hash, base_sha1); + if (!in_same_island(&delta->idx.oid, &base_oid)) + return 0; + } + *base_out = NULL; + return 1; + } + + return 0; +} + 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; @@@ -1533,8 -1407,6 +1533,8 @@@ 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); @@@ -1543,15 -1415,11 +1543,15 @@@ * 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 @@@ -1560,10 -1428,9 +1560,10 @@@ 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; @@@ -1571,7 -1438,7 +1571,7 @@@ 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, @@@ -1582,7 -1449,7 +1582,7 @@@ while (c & 128) { ofs += 1; if (!ofs || MSB(ofs, 7)) { - error("delta base offset overflow in pack for %s", + error(_("delta base offset overflow in pack for %s"), oid_to_hex(&entry->idx.oid)); goto give_up; } @@@ -1591,7 -1458,7 +1591,7 @@@ } ofs = entry->in_pack_offset - ofs; if (ofs <= 0 || ofs >= entry->in_pack_offset) { - error("delta base offset out of bound for %s", + error(_("delta base offset out of bound for %s"), oid_to_hex(&entry->idx.oid)); goto give_up; } @@@ -1606,36 -1473,36 +1606,36 @@@ break; } - if (base_ref && (base_entry = packlist_find(&to_pack, base_ref, NULL))) { - /* - * If base_ref was set above that means we wish to - * reuse delta data, and we even found that base - * in the list of objects we want to pack. Goodie! - * - * Depth value does not matter - find_deltas() will - * never consider reused delta as the base object to - * 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; + if (can_reuse_delta(base_ref, entry, &base_entry)) { + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); /* delta size */ + SET_DELTA_SIZE(entry, in_pack_size); + + if (base_entry) { + SET_DELTA(entry, base_entry); + entry->delta_sibling_idx = base_entry->delta_child_idx; + SET_DELTA_CHILD(base_entry, entry); + } else { + SET_DELTA_EXT(entry, base_ref); + } + 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; } @@@ -1649,34 -1516,27 +1649,34 @@@ 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); @@@ -1697,37 -1557,30 +1697,37 @@@ */ 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); } /* @@@ -1751,7 -1604,7 +1751,7 @@@ static void break_delta_chains(struct o 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 @@@ -1768,7 -1621,7 +1768,7 @@@ * 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); /* @@@ -1776,7 -1629,7 +1776,7 @@@ * 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; } @@@ -1799,7 -1652,7 +1799,7 @@@ * 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; @@@ -1814,7 -1667,7 +1814,7 @@@ * 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 @@@ -1825,7 -1678,7 +1825,7 @@@ 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); /* @@@ -1859,10 -1712,6 +1859,10 @@@ 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; @@@ -1871,12 -1720,9 +1871,12 @@@ 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 @@@ -1901,14 -1747,10 +1901,14 @@@ static int type_size_sort(const void *_ { 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; @@@ -1918,14 -1760,9 +1918,14 @@@ return -1; if (a->preferred_base < b->preferred_base) return 1; - if (a->size > b->size) + if (use_delta_islands) { + int island_cmp = island_delta_cmp(&a->idx.oid, &b->idx.oid); + if (island_cmp) + return island_cmp; + } + 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 */ } @@@ -1955,30 -1792,18 +1955,30 @@@ static int delta_cacheable(unsigned lon #ifndef NO_PTHREADS +/* Protect access to object database */ static pthread_mutex_t read_mutex; #define read_lock() pthread_mutex_lock(&read_mutex) #define read_unlock() pthread_mutex_unlock(&read_mutex) +/* Protect delta_cache_size */ static pthread_mutex_t cache_mutex; #define cache_lock() pthread_mutex_lock(&cache_mutex) #define cache_unlock() pthread_mutex_unlock(&cache_mutex) +/* + * Protect object list partitioning (e.g. struct thread_param) and + * progress_state + */ static pthread_mutex_t progress_mutex; #define progress_lock() pthread_mutex_lock(&progress_mutex) #define progress_unlock() pthread_mutex_unlock(&progress_mutex) +/* + * Access to struct object_entry is unprotected since each thread owns + * a portion of the main object list. Just don't access object entries + * ahead in the list because they can be stolen and would need + * progress_mutex for protection. + */ #else #define read_lock() (void)0 @@@ -1990,46 -1815,6 +1990,46 @@@ #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) { @@@ -2041,7 -1826,7 +2041,7 @@@ 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; /* @@@ -2052,8 -1837,8 +2052,8 @@@ * 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) @@@ -2064,51 -1849,50 +2064,51 @@@ 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; if (trg_size < src_size / 32) return 0; + if (!in_same_island(&trg->entry->idx.oid, &src->entry->idx.oid)) + return 0; + /* 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", + die(_("object %s cannot be read"), oid_to_hex(&trg_entry->idx.oid)); if (sz != trg_size) - die("object %s inconsistent object length (%lu vs %lu)", + die(_("object %s inconsistent object length (%lu vs %lu)"), oid_to_hex(&trg_entry->idx.oid), sz, trg_size); *mem_usage += sz; } 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) { static int warned = 0; if (!warned++) - warning("object %s cannot be read", + warning(_("object %s cannot be read"), oid_to_hex(&src_entry->idx.oid)); /* * Those objects are not included in the @@@ -2118,11 -1902,11 +2118,11 @@@ */ return 0; } - die("object %s cannot be read", + die(_("object %s cannot be read"), oid_to_hex(&src_entry->idx.oid)); } if (sz != src_size) - die("object %s inconsistent object length (%lu vs %lu)", + die(_("object %s inconsistent object length (%lu vs %lu)"), oid_to_hex(&src_entry->idx.oid), sz, src_size); *mem_usage += sz; @@@ -2132,7 -1916,7 +2132,7 @@@ if (!src->index) { static int warned = 0; if (!warned++) - warning("suboptimal pack - out of memory"); + warning(_("suboptimal pack - out of memory")); return 0; } *mem_usage += sizeof_delta_index(src->index); @@@ -2142,9 -1926,9 +2142,9 @@@ if (!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; @@@ -2159,7 -1943,7 +2159,7 @@@ 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)) { @@@ -2171,8 -1955,8 +2171,8 @@@ 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; @@@ -2180,13 -1964,13 +2180,13 @@@ 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; } @@@ -2197,7 -1981,7 +2197,7 @@@ static unsigned long free_unpacked(stru 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; @@@ -2255,7 -2039,7 +2255,7 @@@ static void find_deltas(struct object_e * 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; @@@ -2293,26 -2077,19 +2293,26 @@@ * 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; /* @@@ -2320,7 -2097,7 +2320,7 @@@ * 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; @@@ -2359,19 -2136,12 +2359,19 @@@ static void try_to_free_from_threads(si static try_to_free_t old_try_to_free_routine; /* + * The main object list is split into smaller lists, each is handed to + * one worker. + * * The main thread waits on the condition that (at least) one of the workers * has stopped working (which is indicated in the .working member of * struct thread_params). + * * When a work thread has completed its work, it sets .working to 0 and * signals the main thread and waits on the condition that .data_ready * becomes 1. + * + * The main thread steals half of the work from the worker that has + * most work left to hand it to the idle worker. */ struct thread_params { @@@ -2462,8 -2232,8 +2462,8 @@@ static void ll_find_deltas(struct objec return; } if (progress > pack_to_stdout) - fprintf(stderr, "Delta compression using up to %d threads.\n", - delta_search_threads); + fprintf_ln(stderr, _("Delta compression using up to %d threads"), + delta_search_threads); p = xcalloc(delta_search_threads, sizeof(*p)); /* Partition the work amongst work threads. */ @@@ -2503,7 -2273,7 +2503,7 @@@ ret = pthread_create(&p[i].thread, NULL, threaded_find_deltas, &p[i]); if (ret) - die("unable to create thread: %s", strerror(ret)); + die(_("unable to create thread: %s"), strerror(ret)); active_threads++; } @@@ -2595,10 -2365,10 +2595,10 @@@ static void add_tag_chain(const struct if (packlist_find(&to_pack, oid->hash, NULL)) return; - tag = lookup_tag(oid); + tag = lookup_tag(the_repository, oid); while (1) { if (!tag || parse_tag(tag) || !tag->tagged) - die("unable to pack objects reachable from tag %s", + die(_("unable to pack objects reachable from tag %s"), oid_to_hex(oid)); add_object_entry(&tag->object.oid, OBJ_TAG, NULL, 0); @@@ -2627,9 -2397,6 +2627,9 @@@ static void prepare_pack(int window, in uint32_t i, nr_deltas; unsigned n; + if (use_delta_islands) + resolve_tree_islands(progress, &to_pack); + get_object_details(); /* @@@ -2651,14 -2418,13 +2651,14 @@@ 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) @@@ -2666,11 -2432,11 +2666,11 @@@ if (!entry->preferred_base) { nr_deltas++; - if (entry->type < 0) - die("unable to get type of object %s", + 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. @@@ -2691,7 -2457,7 +2691,7 @@@ ll_find_deltas(delta_list, n, window+1, depth, &nr_done); stop_progress(&progress_state); if (nr_done != nr_deltas) - die("inconsistency with delta count"); + die(_("inconsistency with delta count")); } free(delta_list); } @@@ -2731,11 -2497,11 +2731,11 @@@ static int git_pack_config(const char * if (!strcmp(k, "pack.threads")) { delta_search_threads = git_config_int(k, v); if (delta_search_threads < 0) - die("invalid number of threads specified (%d)", + die(_("invalid number of threads specified (%d)"), delta_search_threads); #ifdef NO_PTHREADS if (delta_search_threads != 1) { - warning("no threads support, ignoring %s", k); + warning(_("no threads support, ignoring %s"), k); delta_search_threads = 0; } #endif @@@ -2744,7 -2510,7 +2744,7 @@@ if (!strcmp(k, "pack.indexversion")) { pack_idx_opts.version = git_config_int(k, v); if (pack_idx_opts.version > 2) - die("bad pack.indexversion=%"PRIu32, + die(_("bad pack.indexversion=%"PRIu32), pack_idx_opts.version); return 0; } @@@ -2762,7 -2528,7 +2762,7 @@@ static void read_object_list_from_stdin if (feof(stdin)) break; if (!ferror(stdin)) - die("fgets returned NULL, not EOF, not error!"); + die("BUG: fgets returned NULL, not EOF, not error!"); if (errno != EINTR) die_errno("fgets"); clearerr(stdin); @@@ -2770,16 -2536,16 +2770,16 @@@ } if (line[0] == '-') { if (get_oid_hex(line+1, &oid)) - die("expected edge object ID, got garbage:\n %s", + die(_("expected edge object ID, got garbage:\n %s"), line); add_preferred_base(&oid); continue; } if (parse_oid_hex(line, &oid, &p)) - die("expected object ID, got garbage:\n %s", line); + 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); } } @@@ -2793,9 -2559,6 +2793,9 @@@ static void show_commit(struct commit * if (write_bitmap_index) index_commit_for_bitmap(commit); + + if (use_delta_islands) + propagate_island_marks(commit); } static void show_object(struct object *obj, const char *name, void *data) @@@ -2803,19 -2566,6 +2803,19 @@@ 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; + unsigned depth = 0; + struct object_entry *ent; + + for (p = strchr(name, '/'); p; p = strchr(p + 1, '/')) + depth++; + + ent = packlist_find(&to_pack, obj->oid.hash, NULL); + if (ent && depth > oe_tree_depth(&to_pack, ent)) + oe_set_tree_depth(&to_pack, ent, depth); + } } static void show_object__ma_allow_any(struct object *obj, const char *name, void *data) @@@ -2924,14 -2674,14 +2924,14 @@@ static void add_objects_in_unpacked_pac memset(&in_pack, 0, sizeof(in_pack)); - for (p = packed_git; p; p = p->next) { + 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) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) - die("cannot open pack index"); + die(_("cannot open pack index")); ALLOC_GROW(in_pack.array, in_pack.nr + p->num_objects, @@@ -2959,10 -2709,10 +2959,10 @@@ 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); + warning(_("loose object at %s could not be examined"), path); return 0; } @@@ -2987,18 -2737,16 +2987,18 @@@ static int has_sha1_pack_kept_or_nonloc 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_all_packs(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_all_packs(the_repository); else p = p->next; if (p == last_found) @@@ -3034,12 -2782,12 +3034,12 @@@ static void loosen_unused_packed_object 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_all_packs(the_repository); p; p = p->next) { + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) - die("cannot open pack index"); + die(_("cannot open pack index")); for (i = 0; i < p->num_objects; i++) { nth_packed_object_oid(&oid, p, i); @@@ -3047,7 -2795,7 +3047,7 @@@ !has_sha1_pack_kept_or_nonlocal(&oid) && !loosened_object_can_be_discarded(&oid, p->mtime)) if (force_object_loose(&oid, p->mtime)) - die("unable to force loose object"); + die(_("unable to force loose object")); } } } @@@ -3061,20 -2809,18 +3061,20 @@@ static int pack_options_allow_reuse(voi { 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; } static int get_object_list_from_bitmap(struct rev_info *revs) { - if (prepare_bitmap_walk(revs) < 0) + if (!(bitmap_git = prepare_bitmap_walk(revs))) return -1; if (pack_options_allow_reuse() && !reuse_partial_packfile_from_bitmap( + bitmap_git, &reuse_packfile, &reuse_packfile_objects, &reuse_packfile_offset)) { @@@ -3083,7 -2829,7 +3083,7 @@@ display_progress(progress_state, nr_result); } - traverse_bitmap_commit_list(&add_object_entry_from_bitmap); + traverse_bitmap_commit_list(bitmap_git, &add_object_entry_from_bitmap); return 0; } @@@ -3105,12 -2851,13 +3105,13 @@@ static void get_object_list(int ac, con char line[1000]; int flags = 0; - init_revisions(&revs, NULL); + repo_init_revisions(the_repository, &revs, NULL); save_commit_buffer = 0; + revs.allow_exclude_promisor_objects_opt = 1; setup_revisions(ac, av, &revs, NULL); /* make sure shallows are read */ - is_repository_shallow(); + is_repository_shallow(the_repository); while (fgets(line, sizeof(line), stdin) != NULL) { int len = strlen(line); @@@ -3128,24 -2875,21 +3129,24 @@@ struct object_id oid; if (get_oid_hex(line + 10, &oid)) die("not an SHA-1 '%s'", line + 10); - register_shallow(&oid); + register_shallow(the_repository, &oid); use_bitmap_index = 0; continue; } - die("not a rev '%s'", line); + die(_("not a rev '%s'"), line); } if (handle_revision_arg(line, &revs, flags, REVARG_CANNOT_BE_FILENAME)) - die("bad revision '%s'", line); + die(_("bad revision '%s'"), line); } if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) return; + if (use_delta_islands) + load_delta_islands(); + if (prepare_revision_walk(&revs)) - die("revision walk setup failed"); + die(_("revision walk setup failed")); mark_edges_uninteresting(&revs, show_edge); if (!fn_show_object) @@@ -3158,9 -2902,9 +3159,9 @@@ revs.ignore_missing_links = 1; if (add_unseen_recent_objects_to_traversal(&revs, unpack_unreachable_expiration)) - die("unable to add recent objects"); + die(_("unable to add recent objects")); if (prepare_revision_walk(&revs)) - die("revision walk setup failed"); + die(_("revision walk setup failed")); traverse_commit_list(&revs, record_recent_commit, record_recent_object, NULL); } @@@ -3175,32 -2919,6 +3176,32 @@@ 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_all_packs(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) { @@@ -3234,12 -2952,12 +3235,12 @@@ static int option_parse_unpack_unreacha int cmd_pack_objects(int argc, const char **argv, const char *prefix) { int use_internal_rev_list = 0; - int thin = 0; int shallow = 0; int all_progress_implied = 0; 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), @@@ -3250,7 -2968,7 +3251,7 @@@ OPT_BOOL(0, "all-progress-implied", &all_progress_implied, N_("similar to --all-progress when progress meter is shown")), - { OPTION_CALLBACK, 0, "index-version", NULL, N_("version[,offset]"), + { OPTION_CALLBACK, 0, "index-version", NULL, N_("[,]"), N_("write the pack index file in the specified idx format version"), 0, option_parse_index_version }, OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit, @@@ -3277,18 -2995,18 +3278,18 @@@ 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, @@@ -3304,10 -3022,8 +3305,10 @@@ 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, @@@ -3322,15 -3038,10 +3323,15 @@@ option_parse_missing_action }, OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects, N_("do not pack objects in promisor packfiles")), + OPT_BOOL(0, "delta-islands", &use_delta_islands, + N_("respect islands during delta compression")), OPT_END(), }; - check_replace_refs = 0; + if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS)) + BUG("too many dfs states, increase OE_DFS_STATE_BITS"); + + read_replace_refs = 0; reset_pack_idx_option(&pack_idx_opts); git_config(git_pack_config, NULL); @@@ -3346,17 -3057,6 +3347,17 @@@ 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; @@@ -3388,43 -3088,41 +3389,43 @@@ 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; if (pack_compression_level == -1) pack_compression_level = Z_DEFAULT_COMPRESSION; else if (pack_compression_level < 0 || pack_compression_level > Z_BEST_COMPRESSION) - die("bad pack compression level %d", pack_compression_level); + die(_("bad pack compression level %d"), pack_compression_level); if (!delta_search_threads) /* --threads=0 means autodetect */ delta_search_threads = online_cpus(); #ifdef NO_PTHREADS if (delta_search_threads != 1) - warning("no threads support, ignoring --threads"); + warning(_("no threads support, ignoring --threads")); #endif if (!pack_to_stdout && !pack_size_limit) pack_size_limit = pack_size_limit_cfg; if (pack_to_stdout && pack_size_limit) - die("--max-pack-size cannot be used to build a pack for transfer."); + die(_("--max-pack-size cannot be used to build a pack for transfer")); if (pack_size_limit && pack_size_limit < 1024*1024) { - warning("minimum pack size limit is 1 MiB"); + warning(_("minimum pack size limit is 1 MiB")); pack_size_limit = 1024*1024; } if (!pack_to_stdout && thin) - die("--thin cannot be used to build an indexable pack."); + die(_("--thin cannot be used to build an indexable pack")); if (keep_unreachable && unpack_unreachable) - die("--keep-unreachable and --unpack-unreachable are incompatible."); + die(_("--keep-unreachable and --unpack-unreachable are incompatible")); 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."); + die(_("cannot use --filter without --stdout")); use_bitmap_index = 0; } @@@ -3444,35 -3142,32 +3445,35 @@@ use_bitmap_index = use_bitmap_index_default; /* "hard" reasons not to use bitmaps; these just won't work at all */ - if (!use_internal_rev_list || (!pack_to_stdout && write_bitmap_index) || is_repository_shallow()) + if (!use_internal_rev_list || (!pack_to_stdout && write_bitmap_index) || is_repository_shallow(the_repository)) use_bitmap_index = 0; if (pack_to_stdout || !rev_list_all) write_bitmap_index = 0; + if (use_delta_islands) + argv_array_push(&rp, "--topo-order"); + 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_all_packs(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_all_packs(the_repository); p; p = p->next) { if (!p->pack_local) { have_non_local_packs = 1; break; @@@ -3480,10 -3175,8 +3481,10 @@@ } } + 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 { @@@ -3501,9 -3194,8 +3502,9 @@@ prepare_pack(window, depth); write_pack_file(); if (progress) - fprintf(stderr, "Total %"PRIu32" (delta %"PRIu32")," - " reused %"PRIu32" (delta %"PRIu32")\n", - written, written_delta, reused, reused_delta); + fprintf_ln(stderr, + _("Total %"PRIu32" (delta %"PRIu32")," + " reused %"PRIu32" (delta %"PRIu32")"), + written, written_delta, reused, reused_delta); return 0; } diff --combined builtin/prune.c index 1ec9ddd751,a5c784749e..e42653b99c --- a/builtin/prune.c +++ b/builtin/prune.c @@@ -6,7 -6,6 +6,7 @@@ #include "reachable.h" #include "parse-options.h" #include "progress.h" +#include "object-store.h" static const char * const prune_usage[] = { N_("git prune [-n] [-v] [--progress] [--expire