diff options
Diffstat (limited to 'builtin/pack-objects.c')
| -rw-r--r-- | builtin/pack-objects.c | 1351 |
1 files changed, 907 insertions, 444 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index e9d3cfb9e3..02aa6ee480 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" @@ -23,11 +24,29 @@ #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" +#include "trace2.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 [<options>...] [< <ref-list> | < <object-list>]"), @@ -43,7 +62,9 @@ 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 struct bitmap_index *bitmap_git; +static uint32_t write_layer; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@ -53,7 +74,8 @@ 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; @@ -63,22 +85,31 @@ static unsigned long pack_size_limit; static int depth = 50; static int delta_search_threads; static int pack_to_stdout; +static int sparse; +static int thin; static int num_preferred_base; static struct progress *progress_state; static struct packed_git *reuse_packfile; static uint32_t reuse_packfile_objects; -static off_t reuse_packfile_offset; +static struct bitmap *reuse_packfile_bitmap; static int use_bitmap_index_default = 1; static int use_bitmap_index = -1; -static int write_bitmap_index; -static uint16_t write_bitmap_options; +static int allow_pack_reuse = 1; +static enum { + WRITE_BITMAP_FALSE = 0, + WRITE_BITMAP_QUIET, + WRITE_BITMAP_TRUE, +} write_bitmap_index; +static uint16_t write_bitmap_options = BITMAP_OPT_HASH_CACHE; 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; @@ -122,18 +153,23 @@ 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); + 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 successfully computed this delta once but dropped it for + * memory reasons. Something is very wrong if this time we + * recompute and create a different delta. + */ + if (!delta_buf || delta_size != DELTA_SIZE(entry)) + BUG("delta size changed"); free(buf); free(base_buf); return delta_buf; @@ -263,15 +299,16 @@ 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(the_repository, &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 +320,15 @@ 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 +352,12 @@ 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 +369,19 @@ 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); @@ -367,28 +404,30 @@ 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); 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); @@ -398,20 +437,20 @@ 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)) { - 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; } @@ -420,16 +459,16 @@ 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 +504,29 @@ 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, @@ -529,7 +569,7 @@ static enum write_one_status write_one(struct hashfile *f, */ 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) { @@ -538,12 +578,12 @@ 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; @@ -563,7 +603,7 @@ static enum write_one_status write_one(struct hashfile *f, /* 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; } @@ -572,12 +612,12 @@ static int mark_tagged(const char *path, const struct object_id *oid, int flag, void *cb_data) { struct object_id peeled; - struct object_entry *entry = packlist_find(&to_pack, oid->hash, NULL); + struct object_entry *entry = packlist_find(&to_pack, oid); if (entry) entry->tagged = 1; if (!peel_ref(path, &peeled)) { - entry = packlist_find(&to_pack, peeled.hash, NULL); + entry = packlist_find(&to_pack, &peeled); if (entry) entry->tagged = 1; } @@ -588,7 +628,7 @@ static inline void add_to_write_order(struct object_entry **wo, 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; @@ -605,34 +645,34 @@ 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); } }; } @@ -643,53 +683,20 @@ 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); } -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; @@ -698,93 +705,267 @@ static struct object_entry **compute_write_order(void) */ 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; } -static off_t write_reused_pack(struct hashfile *f) + +/* + * A reused set of objects. All objects in a chunk have the same + * relative position in the original packfile and the generated + * packfile. + */ + +static struct reused_chunk { + /* The offset of the first object of this chunk in the original + * packfile. */ + off_t original; + /* The offset of the first object of this chunk in the generated + * packfile minus "original". */ + off_t difference; +} *reused_chunks; +static int reused_chunks_nr; +static int reused_chunks_alloc; + +static void record_reused_object(off_t where, off_t offset) +{ + if (reused_chunks_nr && reused_chunks[reused_chunks_nr-1].difference == offset) + return; + + ALLOC_GROW(reused_chunks, reused_chunks_nr + 1, + reused_chunks_alloc); + reused_chunks[reused_chunks_nr].original = where; + reused_chunks[reused_chunks_nr].difference = offset; + reused_chunks_nr++; +} + +/* + * Binary search to find the chunk that "where" is in. Note + * that we're not looking for an exact match, just the first + * chunk that contains it (which implicitly ends at the start + * of the next chunk. + */ +static off_t find_reused_offset(off_t where) +{ + int lo = 0, hi = reused_chunks_nr; + while (lo < hi) { + int mi = lo + ((hi - lo) / 2); + if (where == reused_chunks[mi].original) + return reused_chunks[mi].difference; + if (where < reused_chunks[mi].original) + hi = mi; + else + lo = mi + 1; + } + + /* + * The first chunk starts at zero, so we can't have gone below + * there. + */ + assert(lo); + return reused_chunks[lo-1].difference; +} + +static void write_reused_pack_one(size_t pos, struct hashfile *out, + struct pack_window **w_curs) { - unsigned char buffer[8192]; - off_t to_write, total; - int fd; + off_t offset, next, cur; + enum object_type type; + unsigned long size; + + offset = reuse_packfile->revindex[pos].offset; + next = reuse_packfile->revindex[pos + 1].offset; + + record_reused_object(offset, offset - hashfile_total(out)); - if (!is_pack_valid(reuse_packfile)) - die("packfile is invalid: %s", reuse_packfile->pack_name); + cur = offset; + type = unpack_object_header(reuse_packfile, w_curs, &cur, &size); + assert(type >= 0); - fd = git_open(reuse_packfile->pack_name); - if (fd < 0) - die_errno("unable to open packfile for reuse: %s", - reuse_packfile->pack_name); + if (type == OBJ_OFS_DELTA) { + off_t base_offset; + off_t fixup; - if (lseek(fd, sizeof(struct pack_header), SEEK_SET) == -1) - die_errno("unable to seek in reused packfile"); + unsigned char header[MAX_PACK_OBJECT_HEADER]; + unsigned len; - if (reuse_packfile_offset < 0) - reuse_packfile_offset = reuse_packfile->pack_size - 20; + base_offset = get_delta_base(reuse_packfile, w_curs, &cur, type, offset); + assert(base_offset != 0); - total = to_write = reuse_packfile_offset - sizeof(struct pack_header); + /* Convert to REF_DELTA if we must... */ + if (!allow_ofs_delta) { + int base_pos = find_revindex_position(reuse_packfile, base_offset); + struct object_id base_oid; - while (to_write) { - int read_pack = xread(fd, buffer, sizeof(buffer)); + nth_packed_object_id(&base_oid, reuse_packfile, + reuse_packfile->revindex[base_pos].nr); - if (read_pack <= 0) - die_errno("unable to read from reused packfile"); + len = encode_in_pack_object_header(header, sizeof(header), + OBJ_REF_DELTA, size); + hashwrite(out, header, len); + hashwrite(out, base_oid.hash, 20); + copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur); + return; + } - if (read_pack > to_write) - read_pack = to_write; + /* Otherwise see if we need to rewrite the offset... */ + fixup = find_reused_offset(offset) - + find_reused_offset(base_offset); + if (fixup) { + unsigned char ofs_header[10]; + unsigned i, ofs_len; + off_t ofs = offset - base_offset - fixup; - hashwrite(f, buffer, read_pack); - to_write -= read_pack; + len = encode_in_pack_object_header(header, sizeof(header), + OBJ_OFS_DELTA, size); + + i = sizeof(ofs_header) - 1; + ofs_header[i] = ofs & 127; + while (ofs >>= 7) + ofs_header[--i] = 128 | (--ofs & 127); + + ofs_len = sizeof(ofs_header) - i; + + hashwrite(out, header, len); + hashwrite(out, ofs_header + sizeof(ofs_header) - ofs_len, ofs_len); + copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur); + return; + } + + /* ...otherwise we have no fixup, and can write it verbatim */ + } + + copy_pack_data(out, reuse_packfile, w_curs, offset, next - offset); +} + +static size_t write_reused_pack_verbatim(struct hashfile *out, + struct pack_window **w_curs) +{ + size_t pos = 0; + + while (pos < reuse_packfile_bitmap->word_alloc && + reuse_packfile_bitmap->words[pos] == (eword_t)~0) + pos++; + + if (pos) { + off_t to_write; + + written = (pos * BITS_IN_EWORD); + to_write = reuse_packfile->revindex[written].offset + - sizeof(struct pack_header); + + /* We're recording one chunk, not one object. */ + record_reused_object(sizeof(struct pack_header), 0); + hashflush(out); + copy_pack_data(out, reuse_packfile, w_curs, + sizeof(struct pack_header), to_write); - /* - * We don't know the actual number of objects written, - * only how many bytes written, how many bytes total, and - * how many objects total. So we can fake it by pretending all - * objects we are writing are the same size. This gives us a - * smooth progress meter, and at the end it matches the true - * answer. - */ - written = reuse_packfile_objects * - (((double)(total - to_write)) / total); display_progress(progress_state, written); } + return pos; +} + +static void write_reused_pack(struct hashfile *f) +{ + size_t i = 0; + uint32_t offset; + struct pack_window *w_curs = NULL; - close(fd); - written = reuse_packfile_objects; - display_progress(progress_state, written); - return reuse_packfile_offset - sizeof(struct pack_header); + if (allow_ofs_delta) + i = write_reused_pack_verbatim(f, &w_curs); + + for (; i < reuse_packfile_bitmap->word_alloc; ++i) { + eword_t word = reuse_packfile_bitmap->words[i]; + size_t pos = (i * BITS_IN_EWORD); + + for (offset = 0; offset < BITS_IN_EWORD; ++offset) { + if ((word >> offset) == 0) + break; + + offset += ewah_bit_ctz64(word >> offset); + write_reused_pack_one(pos + offset, f, &w_curs); + display_progress(progress_state, ++written); + } + } + + unuse_pack(&w_curs); } static const char no_split_warning[] = N_( @@ -817,11 +998,9 @@ static void write_pack_file(void) offset = write_pack_header(f, nr_remaining); if (reuse_packfile) { - off_t packfile_size; assert(pack_to_stdout); - - packfile_size = write_reused_pack(f); - offset += packfile_size; + write_reused_pack(f); + offset = hashfile_total(f); } nr_written = 0; @@ -837,16 +1016,17 @@ 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); if (write_bitmap_index) { - warning(_(no_split_warning)); + if (write_bitmap_index != WRITE_BITMAP_QUIET) + warning(_(no_split_warning)); write_bitmap_index = 0; } } @@ -863,7 +1043,7 @@ static void write_pack_file(void) * 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 { @@ -871,14 +1051,15 @@ static void write_pack_file(void) 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, @@ -915,8 +1096,10 @@ static void write_pack_file(void) 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); + trace2_data_intmax("pack-objects", the_repository, + "write_pack_file/wrote", nr_result); } static int no_try_delta(const char *path) @@ -925,8 +1108,7 @@ static int no_try_delta(const char *path) if (!check) check = attr_check_initl("delta", NULL); - if (git_check_attr(path, check)) - return 0; + git_check_attr(the_repository->index, path, check); if (ATTR_FALSE(check->items[0].value)) return 1; return 0; @@ -943,12 +1125,15 @@ static int no_try_delta(const char *path) * few lines later when we want to add the new entry. */ static int have_duplicate_entry(const struct object_id *oid, - int exclude, - uint32_t *index_pos) + int exclude) { struct object_entry *entry; - entry = packlist_find(&to_pack, oid->hash, index_pos); + if (reuse_packfile_bitmap && + bitmap_walk_contains(bitmap_git, reuse_packfile_bitmap, oid)) + return 1; + + entry = packlist_find(&to_pack, oid); if (!entry) return 0; @@ -982,13 +1167,16 @@ 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 */ @@ -1011,8 +1199,9 @@ static int want_object_in_pack(const struct object_id *oid, { 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; /* @@ -1026,7 +1215,32 @@ static int want_object_in_pack(const struct object_id *oid, 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(the_repository, oid, &e, m)) { + struct packed_git *p = e.p; + off_t offset; + + if (p == *found_pack) + offset = *found_offset; + else + offset = find_pack_entry_one(oid->hash, p); + + if (offset) { + if (!*found_pack) { + if (!is_pack_valid(p)) + continue; + *found_offset = offset; + *found_pack = p; + } + want = want_found_object(exclude, p); + if (want != -1) + return want; + } + } + } + + 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 +1258,8 @@ 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; } @@ -1058,22 +1273,20 @@ static void create_object_entry(const struct object_id *oid, uint32_t hash, int exclude, int no_try_delta, - uint32_t index_pos, struct packed_git *found_pack, off_t found_offset) { struct object_entry *entry; - entry = packlist_alloc(&to_pack, oid->hash, index_pos); + entry = packlist_alloc(&to_pack, oid); 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; } @@ -1089,15 +1302,17 @@ static int add_object_entry(const struct object_id *oid, enum object_type type, { struct packed_git *found_pack = NULL; off_t found_offset = 0; - uint32_t index_pos; - if (have_duplicate_entry(oid, exclude, &index_pos)) + display_progress(progress_state, ++nr_seen); + + if (have_duplicate_entry(oid, exclude)) return 0; if (!want_object_in_pack(oid, exclude, &found_pack, &found_offset)) { /* The pack is missing an object, so it will not have closure */ if (write_bitmap_index) { - warning(_(no_closure_warning)); + if (write_bitmap_index != WRITE_BITMAP_QUIET) + warning(_(no_closure_warning)); write_bitmap_index = 0; } return 0; @@ -1105,9 +1320,7 @@ 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); + found_pack, found_offset); return 1; } @@ -1116,17 +1329,15 @@ static int add_object_entry_from_bitmap(const struct object_id *oid, int flags, uint32_t name_hash, struct packed_git *pack, off_t offset) { - uint32_t index_pos; + display_progress(progress_state, ++nr_seen); - if (have_duplicate_entry(oid, 0, &index_pos)) + if (have_duplicate_entry(oid, 0)) return 0; if (!want_object_in_pack(oid, 0, &pack, &offset)) return 0; - create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset); - - display_progress(progress_state, nr_result); + create_object_entry(oid, type, name_hash, 0, 0, pack, offset); return 1; } @@ -1174,7 +1385,7 @@ static struct pbase_tree_cache *pbase_tree_get(const struct object_id *oid) */ 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; } @@ -1190,7 +1401,7 @@ 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) { @@ -1261,7 +1472,7 @@ static void add_pbase_object(struct tree_desc *tree, if (cmp < 0) return; if (name[cmplen] != '/') { - add_object_entry(entry.oid, + add_object_entry(&entry.oid, object_type(entry.mode), fullname, 1); return; @@ -1272,7 +1483,7 @@ static void add_pbase_object(struct tree_desc *tree, const char *down = name+cmplen+1; int downlen = name_cmp_len(down); - tree = pbase_tree_get(entry.oid); + tree = pbase_tree_get(&entry.oid); if (!tree) return; init_tree_desc(&sub, tree->tree_data, tree->tree_size); @@ -1351,12 +1562,13 @@ 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(the_repository, 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; } @@ -1396,17 +1608,68 @@ 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 struct object_id *base_oid, + struct object_entry *delta, + struct object_entry **base_out) +{ + struct object_entry *base; + + /* + * First see if we're already sending the base (or it's explicitly in + * our "excluded" list). + */ + base = packlist_find(&to_pack, base_oid); + 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_oid_in_uninteresting(bitmap_git, base_oid)) { + if (use_delta_islands) { + 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; + int have_base = 0; + struct object_id base_ref; struct object_entry *base_entry; unsigned long used, used_0; 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 +1678,15 @@ 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 @@ -1428,17 +1695,22 @@ 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; case OBJ_REF_DELTA: - 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; + if (reuse_delta && !entry->preferred_base) { + oidread(&base_ref, + use_pack(p, &w_curs, + entry->in_pack_offset + used, + NULL)); + have_base = 1; + } + entry->in_pack_header_size = used + the_hash_algo->rawsz; break; case OBJ_OFS_DELTA: buf = use_pack(p, &w_curs, @@ -1449,7 +1721,7 @@ static void check_object(struct object_entry *entry) 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; } @@ -1458,7 +1730,7 @@ static void check_object(struct object_entry *entry) } 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; } @@ -1467,76 +1739,85 @@ static void check_object(struct object_entry *entry) revidx = find_pack_revindex(p, ofs); if (!revidx) goto give_up; - base_ref = nth_packed_object_sha1(p, revidx->nr); + if (!nth_packed_object_id(&base_ref, p, revidx->nr)) + have_base = 1; } entry->in_pack_header_size = used + used_0; 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 (have_base && + can_reuse_delta(&base_ref, entry, &base_entry)) { + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); /* delta size */ + SET_DELTA_SIZE(entry, in_pack_size); + + 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; } /* * No choice but to fall back to the recursive delta walk - * with sha1_object_info() to find about the object type + * with oid_object_info() to find about the object type * at this point... */ give_up: 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 +1838,37 @@ 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 + * fall back to oid_object_info, which may find another copy. + * 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 +1892,7 @@ 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 +1909,7 @@ 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 +1917,7 @@ 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 +1940,7 @@ 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 +1955,7 @@ 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 +1966,7 @@ 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 +2000,10 @@ 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 +2012,12 @@ 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 +2042,14 @@ 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; + const enum object_type a_type = oe_type(a); + const enum object_type b_type = oe_type(b); + const unsigned long a_size = SIZE(a); + const 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 +2059,14 @@ 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 (use_delta_islands) { + const 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 */ } @@ -1790,30 +2094,65 @@ static int delta_cacheable(unsigned long src_size, unsigned long trg_size, return 0; } -#ifndef NO_PTHREADS - -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) -#else +/* + * 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. + */ -#define read_lock() (void)0 -#define read_unlock() (void)0 -#define cache_lock() (void)0 -#define cache_unlock() (void)0 -#define progress_lock() (void)0 -#define progress_unlock() (void)0 +/* + * 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) { + packing_data_lock(&to_pack); + if (oid_object_info(the_repository, &e->idx.oid, &size) < 0) + die(_("unable to get size of %s"), + oid_to_hex(&e->idx.oid)); + packing_data_unlock(&to_pack); + return size; + } + + p = oe_in_pack(pack, e); + if (!p) + BUG("when e->type is a delta, it must belong to a pack"); -#endif + packing_data_lock(&to_pack); + 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); + packing_data_unlock(&to_pack); + return size; +} static int try_delta(struct unpacked *trg, struct unpacked *src, unsigned max_depth, unsigned long *mem_usage) @@ -1826,7 +2165,7 @@ 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 +2176,8 @@ 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) @@ -1849,50 +2188,51 @@ 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; 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); - read_unlock(); + packing_data_lock(&to_pack); + trg->data = read_object_file(&trg_entry->idx.oid, &type, &sz); + packing_data_unlock(&to_pack); 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)", - oid_to_hex(&trg_entry->idx.oid), sz, - trg_size); + die(_("object %s inconsistent object length (%"PRIuMAX" vs %"PRIuMAX")"), + oid_to_hex(&trg_entry->idx.oid), (uintmax_t)sz, + (uintmax_t)trg_size); *mem_usage += sz; } if (!src->data) { - read_lock(); - src->data = read_sha1_file(src_entry->idx.oid.hash, &type, - &sz); - read_unlock(); + packing_data_lock(&to_pack); + src->data = read_object_file(&src_entry->idx.oid, &type, &sz); + packing_data_unlock(&to_pack); 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 @@ -1902,13 +2242,13 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, */ 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)", - oid_to_hex(&src_entry->idx.oid), sz, - src_size); + die(_("object %s inconsistent object length (%"PRIuMAX" vs %"PRIuMAX")"), + oid_to_hex(&src_entry->idx.oid), (uintmax_t)sz, + (uintmax_t)src_size); *mem_usage += sz; } if (!src->index) { @@ -1916,7 +2256,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, 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); @@ -1926,9 +2266,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, 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; @@ -1943,7 +2283,7 @@ 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 +2295,8 @@ 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 +2304,13 @@ 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); + const 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 +2321,7 @@ 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; @@ -2022,7 +2362,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, while (window_memory_limit && mem_usage > window_memory_limit && count > 1) { - uint32_t tail = (idx + window - count) % window; + const uint32_t tail = (idx + window - count) % window; mem_usage -= free_unpacked(array + tail); count--; } @@ -2039,7 +2379,7 @@ 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 +2417,26 @@ 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 +2444,7 @@ 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; @@ -2124,24 +2471,20 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, free(array); } -#ifndef NO_PTHREADS - -static void try_to_free_from_threads(size_t size) -{ - read_lock(); - release_pack_memory(size); - read_unlock(); -} - -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 { @@ -2165,18 +2508,14 @@ static pthread_cond_t progress_cond; */ static void init_threaded_search(void) { - init_recursive_mutex(&read_mutex); pthread_mutex_init(&cache_mutex, NULL); pthread_mutex_init(&progress_mutex, NULL); pthread_cond_init(&progress_cond, NULL); - old_try_to_free_routine = set_try_to_free_routine(try_to_free_from_threads); } static void cleanup_threaded_search(void) { - set_try_to_free_routine(old_try_to_free_routine); pthread_cond_destroy(&progress_cond); - pthread_mutex_destroy(&read_mutex); pthread_mutex_destroy(&cache_mutex); pthread_mutex_destroy(&progress_mutex); } @@ -2232,8 +2571,8 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, 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. */ @@ -2273,7 +2612,7 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, 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++; } @@ -2347,9 +2686,12 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, free(p); } -#else -#define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p) -#endif +static int obj_is_packed(const struct object_id *oid) +{ + return packlist_find(&to_pack, oid) || + (reuse_packfile_bitmap && + bitmap_walk_contains(bitmap_git, reuse_packfile_bitmap, oid)); +} static void add_tag_chain(const struct object_id *oid) { @@ -2362,13 +2704,13 @@ static void add_tag_chain(const struct object_id *oid) * it was included via bitmaps, we would not have parsed it * previously). */ - if (packlist_find(&to_pack, oid->hash, NULL)) + if (obj_is_packed(oid)) 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); @@ -2386,7 +2728,7 @@ static int add_ref_tag(const char *path, const struct object_id *oid, int flag, if (starts_with(path, "refs/tags/") && /* is a tag? */ !peel_ref(path, &peeled) && /* peelable? */ - packlist_find(&to_pack, peeled.hash, NULL)) /* object packed? */ + obj_is_packed(&peeled)) /* object packed? */ add_tag_chain(oid); return 0; } @@ -2397,6 +2739,9 @@ static void prepare_pack(int window, int depth) uint32_t i, nr_deltas; unsigned n; + if (use_delta_islands) + resolve_tree_islands(the_repository, progress, &to_pack); + get_object_details(); /* @@ -2418,13 +2763,14 @@ 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 +2778,11 @@ static void prepare_pack(int window, int depth) 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. @@ -2450,6 +2796,7 @@ static void prepare_pack(int window, int depth) if (nr_deltas && n > 1) { unsigned nr_done = 0; + if (progress) progress_state = start_progress(_("Compressing objects"), nr_deltas); @@ -2457,7 +2804,7 @@ static void prepare_pack(int window, int depth) 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); } @@ -2494,23 +2841,25 @@ static int git_pack_config(const char *k, const char *v, void *cb) use_bitmap_index_default = git_config_bool(k, v); return 0; } + if (!strcmp(k, "pack.allowpackreuse")) { + allow_pack_reuse = git_config_bool(k, v); + return 0; + } if (!strcmp(k, "pack.threads")) { delta_search_threads = git_config_int(k, v); if (delta_search_threads < 0) - 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); + if (!HAVE_THREADS && delta_search_threads != 1) { + warning(_("no threads support, ignoring %s"), k); delta_search_threads = 0; } -#endif return 0; } 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; } @@ -2528,7 +2877,7 @@ static void read_object_list_from_stdin(void) 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); @@ -2536,16 +2885,16 @@ static void read_object_list_from_stdin(void) } 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); } } @@ -2559,6 +2908,9 @@ static void show_commit(struct commit *commit, void *data) 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) @@ -2566,6 +2918,21 @@ static void show_object(struct object *obj, const char *name, void *data) add_preferred_base_object(name); add_object_entry(&obj->oid, obj->type, name, 0); obj->flags |= OBJECT_ADDED; + + if (use_delta_islands) { + const char *p; + unsigned depth; + struct object_entry *ent; + + /* the empty string is a root tree, which is depth 0 */ + depth = *name ? 1 : 0; + for (p = strchr(name, '/'); p; p = strchr(p + 1, '/')) + depth++; + + ent = packlist_find(&to_pack, &obj->oid); + 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) @@ -2666,7 +3033,7 @@ static int ofscmp(const void *a_, const void *b_) return oidcmp(&a->object->oid, &b->object->oid); } -static void add_objects_in_unpacked_packs(struct rev_info *revs) +static void add_objects_in_unpacked_packs(void) { struct packed_git *p; struct in_pack in_pack; @@ -2674,22 +3041,22 @@ 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_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, in_pack.alloc); for (i = 0; i < p->num_objects; i++) { - nth_packed_object_oid(&oid, p, i); - o = lookup_unknown_object(oid.hash); + nth_packed_object_id(&oid, p, i); + o = lookup_unknown_object(&oid); if (!(o->flags & OBJECT_ADDED)) mark_in_pack_object(o, p, &in_pack); o->flags |= OBJECT_ADDED; @@ -2709,10 +3076,10 @@ 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); + warning(_("loose object at %s could not be examined"), path); return 0; } @@ -2737,16 +3104,18 @@ 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_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) @@ -2776,26 +3145,26 @@ static int loosened_object_can_be_discarded(const struct object_id *oid, return 1; } -static void loosen_unused_packed_objects(struct rev_info *revs) +static void loosen_unused_packed_objects(void) { struct packed_git *p; 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); - if (!packlist_find(&to_pack, oid.hash, NULL) && + nth_packed_object_id(&oid, p, i); + if (!packlist_find(&to_pack, &oid) && !has_sha1_pack_kept_or_nonlocal(&oid) && !loosened_object_can_be_discarded(&oid, p->mtime)) if (force_object_loose(&oid, p->mtime)) - die("unable to force loose object"); + die(_("unable to force loose object")); } } } @@ -2807,29 +3176,32 @@ static void loosen_unused_packed_objects(struct rev_info *revs) */ static int pack_options_allow_reuse(void) { - return pack_to_stdout && - allow_ofs_delta && - !ignore_packed_keep && + return allow_pack_reuse && + pack_to_stdout && + !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, &filter_options))) return -1; if (pack_options_allow_reuse() && !reuse_partial_packfile_from_bitmap( + bitmap_git, &reuse_packfile, &reuse_packfile_objects, - &reuse_packfile_offset)) { + &reuse_packfile_bitmap)) { assert(reuse_packfile_objects); nr_result += reuse_packfile_objects; display_progress(progress_state, nr_result); } - traverse_bitmap_commit_list(&add_object_entry_from_bitmap); + traverse_bitmap_commit_list(bitmap_git, revs, + &add_object_entry_from_bitmap); return 0; } @@ -2848,15 +3220,22 @@ static void record_recent_commit(struct commit *commit, void *data) static void get_object_list(int ac, const char **av) { struct rev_info revs; + struct setup_revision_opt s_r_opt = { + .allow_exclude_promisor_objects = 1, + }; char line[1000]; int flags = 0; + int save_warning; - init_revisions(&revs, NULL); + repo_init_revisions(the_repository, &revs, NULL); save_commit_buffer = 0; - setup_revisions(ac, av, &revs, NULL); + setup_revisions(ac, av, &revs, &s_r_opt); /* make sure shallows are read */ - is_repository_shallow(); + is_repository_shallow(the_repository); + + save_warning = warn_on_object_refname_ambiguity; + warn_on_object_refname_ambiguity = 0; while (fgets(line, sizeof(line), stdin) != NULL) { int len = strlen(line); @@ -2874,22 +3253,27 @@ static void get_object_list(int ac, const char **av) 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); } + warn_on_object_refname_ambiguity = save_warning; + if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) return; + if (use_delta_islands) + load_delta_islands(the_repository, progress); + if (prepare_revision_walk(&revs)) - die("revision walk setup failed"); - mark_edges_uninteresting(&revs, show_edge); + die(_("revision walk setup failed")); + mark_edges_uninteresting(&revs, show_edge, sparse); if (!fn_show_object) fn_show_object = show_object; @@ -2901,28 +3285,57 @@ static void get_object_list(int ac, const char **av) 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); } if (keep_unreachable) - add_objects_in_unpacked_packs(&revs); + add_objects_in_unpacked_packs(); if (pack_loose_unreachable) add_unreachable_loose_objects(); if (unpack_unreachable) - loosen_unused_packed_objects(&revs); + loosen_unused_packed_objects(); 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) { char *c; const char *val = arg; + + BUG_ON_OPT_NEG(unset); + pack_idx_opts.version = strtoul(val, &c, 10); if (pack_idx_opts.version > 2) die(_("unsupported index version %s"), val); @@ -2951,12 +3364,12 @@ static int option_parse_unpack_unreachable(const struct option *opt, 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), @@ -2967,9 +3380,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) OPT_BOOL(0, "all-progress-implied", &all_progress_implied, N_("similar to --all-progress when progress meter is shown")), - { OPTION_CALLBACK, 0, "index-version", NULL, N_("version[,offset]"), + { OPTION_CALLBACK, 0, "index-version", NULL, N_("<version>[,<offset>]"), N_("write the pack index file in the specified idx format version"), - 0, option_parse_index_version }, + PARSE_OPT_NONEG, option_parse_index_version }, OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit, N_("maximum size of each output pack file")), OPT_BOOL(0, "local", &local, @@ -2994,18 +3407,18 @@ 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, @@ -3017,30 +3430,49 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) { OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"), N_("unpack unreachable objects newer than <time>"), PARSE_OPT_OPTARG, option_parse_unpack_unreachable }, + OPT_BOOL(0, "sparse", &sparse, + N_("use the sparse reachability algorithm")), OPT_BOOL(0, "thin", &thin, 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, N_("do not hide commits by grafts"), 0), OPT_BOOL(0, "use-bitmap-index", &use_bitmap_index, N_("use a bitmap index if available to speed up counting objects")), - OPT_BOOL(0, "write-bitmap-index", &write_bitmap_index, - N_("write a bitmap index together with the pack index")), + OPT_SET_INT(0, "write-bitmap-index", &write_bitmap_index, + N_("write a bitmap index together with the pack index"), + WRITE_BITMAP_TRUE), + OPT_SET_INT_F(0, "write-bitmap-index-quiet", + &write_bitmap_index, + N_("write a bitmap index if possible"), + WRITE_BITMAP_QUIET, PARSE_OPT_HIDDEN), OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options), { OPTION_CALLBACK, 0, "missing", NULL, N_("action"), N_("handling for missing objects"), PARSE_OPT_NONEG, 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; + + sparse = git_env_bool("GIT_TEST_PACK_SPARSE", 0); + prepare_repo_settings(the_repository); + if (!sparse && the_repository->settings.pack_use_sparse != -1) + sparse = the_repository->settings.pack_use_sparse; reset_pack_idx_option(&pack_idx_opts); git_config(git_pack_config, NULL); @@ -3056,6 +3488,17 @@ 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; @@ -3087,42 +3530,41 @@ 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; 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"); -#endif + if (!HAVE_THREADS && delta_search_threads != 1) + warning(_("no threads support, ignoring --threads")); 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."); - use_bitmap_index = 0; + die(_("cannot use --filter without --stdout")); } /* @@ -3141,32 +3583,35 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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; @@ -3174,8 +3619,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) } } + trace2_region_enter("pack-objects", "enumerate-objects", + the_repository); + prepare_packing_data(the_repository, &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 { @@ -3186,15 +3635,29 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (include_tag && nr_result) for_each_ref(add_ref_tag, NULL); stop_progress(&progress_state); + trace2_region_leave("pack-objects", "enumerate-objects", + the_repository); if (non_empty && !nr_result) return 0; - if (nr_result) + if (nr_result) { + trace2_region_enter("pack-objects", "prepare-pack", + the_repository); prepare_pack(window, depth); + trace2_region_leave("pack-objects", "prepare-pack", + the_repository); + } + + trace2_region_enter("pack-objects", "write-pack-file", the_repository); write_pack_file(); + trace2_region_leave("pack-objects", "write-pack-file", the_repository); + 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")," + " pack-reused %"PRIu32), + written, written_delta, reused, reused_delta, + reuse_packfile_objects); return 0; } |