diff options
Diffstat (limited to 'builtin/pack-objects.c')
| -rw-r--r-- | builtin/pack-objects.c | 663 |
1 files changed, 422 insertions, 241 deletions
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 06884c2a57..1c63f8f28c 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -14,10 +14,15 @@ #include "diff.h" #include "revision.h" #include "list-objects.h" +#include "pack-objects.h" #include "progress.h" #include "refs.h" #include "streaming.h" #include "thread-utils.h" +#include "pack-bitmap.h" +#include "reachable.h" +#include "sha1-array.h" +#include "argv-array.h" static const char *pack_usage[] = { N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"), @@ -25,41 +30,15 @@ static const char *pack_usage[] = { NULL }; -struct object_entry { - struct pack_idx_entry idx; - unsigned long size; /* uncompressed size */ - struct packed_git *in_pack; /* already in pack */ - off_t in_pack_offset; - struct object_entry *delta; /* delta base object */ - struct object_entry *delta_child; /* deltified objects who bases me */ - struct object_entry *delta_sibling; /* other deltified objects who - * uses the same base as me - */ - void *delta_data; /* cached delta (uncompressed) */ - unsigned long delta_size; /* delta data size (uncompressed) */ - unsigned long z_delta_size; /* delta data size (compressed) */ - unsigned int hash; /* name hint hash */ - enum object_type type; - enum object_type in_pack_type; /* could be delta */ - unsigned char in_pack_header_size; - unsigned char preferred_base; /* we do not pack this, but is available - * to be used as the base object to delta - * objects against. - */ - unsigned char no_try_delta; - unsigned char tagged; /* near the very tip of refs */ - unsigned char filled; /* assigned write-order */ -}; - /* - * Objects we are going to pack are collected in objects array (dynamically - * expanded). nr_objects & nr_alloc controls this array. They are stored - * in the order we see -- typically rev-list --objects order that gives us - * nice "minimum seek" order. + * Objects we are going to pack are collected in the `to_pack` structure. + * It contains an array (dynamically expanded) of the object data, and a map + * that can resolve SHA1s to their position in the array. */ -static struct object_entry *objects; +static struct packing_data to_pack; + static struct pack_idx_entry **written_list; -static uint32_t nr_objects, nr_alloc, nr_result, nr_written; +static uint32_t nr_result, nr_written; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@ -82,6 +61,14 @@ static struct progress *progress_state; static int pack_compression_level = Z_DEFAULT_COMPRESSION; static int pack_compression_seen; +static struct packed_git *reuse_packfile; +static uint32_t reuse_packfile_objects; +static off_t reuse_packfile_offset; + +static int use_bitmap_index = 1; +static int write_bitmap_index; +static uint16_t write_bitmap_options; + static unsigned long delta_cache_size = 0; static unsigned long max_delta_cache_size = 256 * 1024 * 1024; static unsigned long cache_max_small_delta_size = 1000; @@ -89,20 +76,27 @@ static unsigned long cache_max_small_delta_size = 1000; static unsigned long window_memory_limit = 0; /* - * The object names in objects array are hashed with this hashtable, - * to help looking up the entry by object name. - * This hashtable is built after all the objects are seen. - */ -static int *object_ix; -static int object_ix_hashsz; -static struct object_entry *locate_object_entry(const unsigned char *sha1); - -/* * stats */ static uint32_t written, written_delta; static uint32_t reused, reused_delta; +/* + * Indexed commits + */ +static struct commit **indexed_commits; +static unsigned int indexed_commits_nr; +static unsigned int indexed_commits_alloc; + +static void index_commit_for_bitmap(struct commit *commit) +{ + if (indexed_commits_nr >= indexed_commits_alloc) { + indexed_commits_alloc = (indexed_commits_alloc + 32) * 2; + REALLOC_ARRAY(indexed_commits, indexed_commits_alloc); + } + + indexed_commits[indexed_commits_nr++] = commit; +} static void *get_delta(struct object_entry *entry) { @@ -131,7 +125,6 @@ static unsigned long do_compress(void **pptr, unsigned long size) void *in, *out; unsigned long maxsize; - memset(&stream, 0, sizeof(stream)); git_deflate_init(&stream, pack_compression_level); maxsize = git_deflate_bound(&stream, size); @@ -159,7 +152,6 @@ static unsigned long write_large_blob_data(struct git_istream *st, struct sha1fi unsigned char obuf[1024 * 16]; unsigned long olen = 0; - memset(&stream, 0, sizeof(stream)); git_deflate_init(&stream, pack_compression_level); for (;;) { @@ -548,16 +540,16 @@ static enum write_one_status write_one(struct sha1file *f, return WRITE_ONE_WRITTEN; } -static int mark_tagged(const char *path, const unsigned char *sha1, int flag, +static int mark_tagged(const char *path, const struct object_id *oid, int flag, void *cb_data) { unsigned char peeled[20]; - struct object_entry *entry = locate_object_entry(sha1); + struct object_entry *entry = packlist_find(&to_pack, oid->hash, NULL); if (entry) entry->tagged = 1; if (!peel_ref(path, peeled)) { - entry = locate_object_entry(peeled); + entry = packlist_find(&to_pack, peeled, NULL); if (entry) entry->tagged = 1; } @@ -632,9 +624,10 @@ static struct object_entry **compute_write_order(void) { unsigned int i, wo_end, last_untagged; - struct object_entry **wo = xmalloc(nr_objects * sizeof(*wo)); + struct object_entry **wo = xmalloc(to_pack.nr_objects * sizeof(*wo)); + struct object_entry *objects = to_pack.objects; - for (i = 0; i < nr_objects; i++) { + for (i = 0; i < to_pack.nr_objects; i++) { objects[i].tagged = 0; objects[i].filled = 0; objects[i].delta_child = NULL; @@ -646,7 +639,7 @@ static struct object_entry **compute_write_order(void) * Make sure delta_sibling is sorted in the original * recency order. */ - for (i = nr_objects; i > 0;) { + for (i = to_pack.nr_objects; i > 0;) { struct object_entry *e = &objects[--i]; if (!e->delta) continue; @@ -664,7 +657,7 @@ static struct object_entry **compute_write_order(void) * Give the objects in the original recency order until * we see a tagged tip. */ - for (i = wo_end = 0; i < nr_objects; i++) { + 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]); @@ -674,7 +667,7 @@ static struct object_entry **compute_write_order(void) /* * Then fill all the tagged tips. */ - for (; i < nr_objects; i++) { + for (; i < to_pack.nr_objects; i++) { if (objects[i].tagged) add_to_write_order(wo, &wo_end, &objects[i]); } @@ -682,7 +675,7 @@ static struct object_entry **compute_write_order(void) /* * And then all remaining commits and tags. */ - for (i = last_untagged; i < nr_objects; i++) { + for (i = last_untagged; i < to_pack.nr_objects; i++) { if (objects[i].type != OBJ_COMMIT && objects[i].type != OBJ_TAG) continue; @@ -692,7 +685,7 @@ static struct object_entry **compute_write_order(void) /* * And then all the trees. */ - for (i = last_untagged; i < nr_objects; i++) { + for (i = last_untagged; i < to_pack.nr_objects; i++) { if (objects[i].type != OBJ_TREE) continue; add_to_write_order(wo, &wo_end, &objects[i]); @@ -701,17 +694,70 @@ static struct object_entry **compute_write_order(void) /* * Finally all the rest in really tight order */ - for (i = last_untagged; i < nr_objects; i++) { + 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 (wo_end != nr_objects) - die("ordered %u objects, expected %"PRIu32, wo_end, nr_objects); + if (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 sha1file *f) +{ + unsigned char buffer[8192]; + off_t to_write, total; + int fd; + + if (!is_pack_valid(reuse_packfile)) + die("packfile is invalid: %s", reuse_packfile->pack_name); + + fd = git_open_noatime(reuse_packfile->pack_name); + if (fd < 0) + 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"); + + if (reuse_packfile_offset < 0) + reuse_packfile_offset = reuse_packfile->pack_size - 20; + + total = to_write = reuse_packfile_offset - sizeof(struct pack_header); + + while (to_write) { + int read_pack = xread(fd, buffer, sizeof(buffer)); + + if (read_pack <= 0) + die_errno("unable to read from reused packfile"); + + if (read_pack > to_write) + read_pack = to_write; + + sha1write(f, buffer, read_pack); + to_write -= read_pack; + + /* + * 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); + } + + close(fd); + written = reuse_packfile_objects; + display_progress(progress_state, written); + return reuse_packfile_offset - sizeof(struct pack_header); +} + static void write_pack_file(void) { uint32_t i = 0, j; @@ -722,8 +768,8 @@ static void write_pack_file(void) struct object_entry **write_order; if (progress > pack_to_stdout) - progress_state = start_progress("Writing objects", nr_result); - written_list = xmalloc(nr_objects * sizeof(*written_list)); + progress_state = start_progress(_("Writing objects"), nr_result); + written_list = xmalloc(to_pack.nr_objects * sizeof(*written_list)); write_order = compute_write_order(); do { @@ -736,10 +782,17 @@ static void write_pack_file(void) f = create_tmp_packfile(&pack_tmp_name); offset = write_pack_header(f, nr_remaining); - if (!offset) - die_errno("unable to write pack header"); + + if (reuse_packfile) { + off_t packfile_size; + assert(pack_to_stdout); + + packfile_size = write_reused_pack(f); + offset += packfile_size; + } + nr_written = 0; - for (; i < nr_objects; i++) { + for (; i < to_pack.nr_objects; i++) { struct object_entry *e = write_order[i]; if (write_one(f, e, &offset) == WRITE_ONE_BREAK) break; @@ -759,11 +812,12 @@ static void write_pack_file(void) fixup_pack_header_footer(fd, sha1, pack_tmp_name, nr_written, sha1, offset); close(fd); + write_bitmap_index = 0; } if (!pack_to_stdout) { struct stat st; - char tmpname[PATH_MAX]; + struct strbuf tmpname = STRBUF_INIT; /* * Packs are runtime accessed in their mtime @@ -783,16 +837,35 @@ static void write_pack_file(void) utb.modtime = --last_mtime; if (utime(pack_tmp_name, &utb) < 0) warning("failed utime() on %s: %s", - tmpname, strerror(errno)); + pack_tmp_name, strerror(errno)); + } + + strbuf_addf(&tmpname, "%s-", base_name); + + if (write_bitmap_index) { + bitmap_writer_set_checksum(sha1); + bitmap_writer_build_type_index(written_list, nr_written); } - /* Enough space for "-<sha-1>.pack"? */ - if (sizeof(tmpname) <= strlen(base_name) + 50) - die("pack base name '%s' too long", base_name); - snprintf(tmpname, sizeof(tmpname), "%s-", base_name); - finish_tmp_packfile(tmpname, pack_tmp_name, + finish_tmp_packfile(&tmpname, pack_tmp_name, written_list, nr_written, &pack_idx_opts, sha1); + + if (write_bitmap_index) { + strbuf_addf(&tmpname, "%s.bitmap", sha1_to_hex(sha1)); + + stop_progress(&progress_state); + + bitmap_writer_show_progress(progress); + bitmap_writer_reuse_bitmaps(&to_pack); + bitmap_writer_select_commits(indexed_commits, indexed_commits_nr, -1); + bitmap_writer_build(&to_pack); + bitmap_writer_finish(written_list, nr_written, + tmpname.buf, write_bitmap_options); + write_bitmap_index = 0; + } + + strbuf_release(&tmpname); free(pack_tmp_name); puts(sha1_to_hex(sha1)); } @@ -802,7 +875,7 @@ static void write_pack_file(void) written_list[j]->offset = (off_t)-1; } nr_remaining -= nr_written; - } while (nr_remaining && i < nr_objects); + } while (nr_remaining && i < to_pack.nr_objects); free(written_list); free(write_order); @@ -812,73 +885,6 @@ static void write_pack_file(void) written, nr_result); } -static int locate_object_entry_hash(const unsigned char *sha1) -{ - int i; - unsigned int ui; - memcpy(&ui, sha1, sizeof(unsigned int)); - i = ui % object_ix_hashsz; - while (0 < object_ix[i]) { - if (!hashcmp(sha1, objects[object_ix[i] - 1].idx.sha1)) - return i; - if (++i == object_ix_hashsz) - i = 0; - } - return -1 - i; -} - -static struct object_entry *locate_object_entry(const unsigned char *sha1) -{ - int i; - - if (!object_ix_hashsz) - return NULL; - - i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; -} - -static void rehash_objects(void) -{ - uint32_t i; - struct object_entry *oe; - - object_ix_hashsz = nr_objects * 3; - if (object_ix_hashsz < 1024) - object_ix_hashsz = 1024; - object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz); - memset(object_ix, 0, sizeof(int) * object_ix_hashsz); - for (i = 0, oe = objects; i < nr_objects; i++, oe++) { - int ix = locate_object_entry_hash(oe->idx.sha1); - if (0 <= ix) - continue; - ix = -1 - ix; - object_ix[ix] = i + 1; - } -} - -static unsigned name_hash(const char *name) -{ - unsigned c, hash = 0; - - if (!name) - return 0; - - /* - * This effectively just creates a sortable number from the - * last sixteen non-whitespace characters. Last characters - * count "most", so things that end in ".c" sort together. - */ - while ((c = *name++) != 0) { - if (isspace(c)) - continue; - hash = (hash >> 2) + (c << 24); - } - return hash; -} - static void setup_delta_attr_check(struct git_attr_check *check) { static struct git_attr *attr_delta; @@ -901,42 +907,67 @@ static int no_try_delta(const char *path) return 0; } -static int add_object_entry(const unsigned char *sha1, enum object_type type, - const char *name, int exclude) +/* + * When adding an object, check whether we have already added it + * to our packing list. If so, we can skip. However, if we are + * being asked to excludei t, but the previous mention was to include + * it, make sure to adjust its flags and tweak our numbers accordingly. + * + * As an optimization, we pass out the index position where we would have + * found the item, since that saves us from having to look it up again a + * few lines later when we want to add the new entry. + */ +static int have_duplicate_entry(const unsigned char *sha1, + int exclude, + uint32_t *index_pos) { struct object_entry *entry; - struct packed_git *p, *found_pack = NULL; - off_t found_offset = 0; - int ix; - unsigned hash = name_hash(name); - - ix = nr_objects ? locate_object_entry_hash(sha1) : -1; - if (ix >= 0) { - if (exclude) { - entry = objects + object_ix[ix] - 1; - if (!entry->preferred_base) - nr_result--; - entry->preferred_base = 1; - } + + entry = packlist_find(&to_pack, sha1, index_pos); + if (!entry) return 0; + + if (exclude) { + if (!entry->preferred_base) + nr_result--; + entry->preferred_base = 1; } + return 1; +} + +/* + * Check whether we want the object in the pack (e.g., we do not want + * objects found in non-local stores if the "--local" option was used). + * + * As a side effect of this check, we will find the packed version of this + * object, if any. We therefore pass out the pack information to avoid having + * to look it up again later. + */ +static int want_object_in_pack(const unsigned char *sha1, + int exclude, + struct packed_git **found_pack, + off_t *found_offset) +{ + struct packed_git *p; + if (!exclude && local && has_loose_object_nonlocal(sha1)) return 0; + *found_pack = NULL; + *found_offset = 0; + for (p = packed_git; p; p = p->next) { off_t offset = find_pack_entry_one(sha1, p); if (offset) { - if (!found_pack) { - if (!is_pack_valid(p)) { - warning("packfile %s cannot be accessed", p->pack_name); + if (!*found_pack) { + if (!is_pack_valid(p)) continue; - } - found_offset = offset; - found_pack = p; + *found_offset = offset; + *found_pack = p; } if (exclude) - break; + return 1; if (incremental) return 0; if (local && !p->pack_local) @@ -946,14 +977,21 @@ static int add_object_entry(const unsigned char *sha1, enum object_type type, } } - if (nr_objects >= nr_alloc) { - nr_alloc = (nr_alloc + 1024) * 3 / 2; - objects = xrealloc(objects, nr_alloc * sizeof(*entry)); - } + return 1; +} + +static void create_object_entry(const unsigned char *sha1, + enum object_type type, + 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 = objects + nr_objects++; - memset(entry, 0, sizeof(*entry)); - hashcpy(entry->idx.sha1, sha1); + entry = packlist_alloc(&to_pack, sha1, index_pos); entry->hash = hash; if (type) entry->type = type; @@ -966,16 +1004,53 @@ static int add_object_entry(const unsigned char *sha1, enum object_type type, entry->in_pack_offset = found_offset; } - if (object_ix_hashsz * 3 <= nr_objects * 4) - rehash_objects(); - else - object_ix[-1 - ix] = nr_objects; + entry->no_try_delta = no_try_delta; +} + +static const char no_closure_warning[] = N_( +"disabling bitmap writing, as some objects are not being packed" +); + +static int add_object_entry(const unsigned char *sha1, enum object_type type, + const char *name, int exclude) +{ + struct packed_git *found_pack; + off_t found_offset; + uint32_t index_pos; + + if (have_duplicate_entry(sha1, exclude, &index_pos)) + return 0; + + if (!want_object_in_pack(sha1, 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)); + write_bitmap_index = 0; + } + return 0; + } + + create_object_entry(sha1, 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; +} + +static int add_object_entry_from_bitmap(const unsigned char *sha1, + enum object_type type, + int flags, uint32_t name_hash, + struct packed_git *pack, off_t offset) +{ + uint32_t index_pos; - display_progress(progress_state, nr_objects); + if (have_duplicate_entry(sha1, 0, &index_pos)) + return 0; - if (name && no_try_delta(name)) - entry->no_try_delta = 1; + create_object_entry(sha1, type, name_hash, 0, 0, index_pos, pack, offset); + display_progress(progress_state, nr_result); return 1; } @@ -1000,7 +1075,7 @@ static int pbase_tree_cache_ix_incr(int ix) static struct pbase_tree { struct pbase_tree *next; /* This is a phony "cache" entry; we are not - * going to evict it nor find it through _get() + * going to evict it or find it through _get() * mechanism -- this is for the toplevel node that * would almost always change with any commit. */ @@ -1157,12 +1232,9 @@ static int check_pbase_path(unsigned hash) if (0 <= pos) return 1; pos = -pos - 1; - if (done_pbase_paths_alloc <= done_pbase_paths_num) { - done_pbase_paths_alloc = alloc_nr(done_pbase_paths_alloc); - done_pbase_paths = xrealloc(done_pbase_paths, - done_pbase_paths_alloc * - sizeof(unsigned)); - } + ALLOC_GROW(done_pbase_paths, + done_pbase_paths_num + 1, + done_pbase_paths_alloc); done_pbase_paths_num++; if (pos < done_pbase_paths_num) memmove(done_pbase_paths + pos + 1, @@ -1176,7 +1248,7 @@ static void add_preferred_base_object(const char *name) { struct pbase_tree *it; int cmplen; - unsigned hash = name_hash(name); + unsigned hash = pack_name_hash(name); if (!num_preferred_base || check_pbase_path(hash)) return; @@ -1328,7 +1400,7 @@ static void check_object(struct object_entry *entry) break; } - if (base_ref && (base_entry = locate_object_entry(base_ref))) { + 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 @@ -1402,12 +1474,12 @@ static void get_object_details(void) uint32_t i; struct object_entry **sorted_by_offset; - sorted_by_offset = xcalloc(nr_objects, sizeof(struct object_entry *)); - for (i = 0; i < nr_objects; i++) - sorted_by_offset[i] = objects + i; - qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort); + 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; + qsort(sorted_by_offset, to_pack.nr_objects, sizeof(*sorted_by_offset), pack_offset_sort); - for (i = 0; i < nr_objects; i++) { + 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) @@ -1809,7 +1881,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, static void try_to_free_from_threads(size_t size) { read_lock(); - release_pack_memory(size, -1); + release_pack_memory(size); read_unlock(); } @@ -1900,8 +1972,6 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, init_threaded_search(); - if (!delta_search_threads) /* --threads=0 means autodetect */ - delta_search_threads = online_cpus(); if (delta_search_threads <= 1) { find_deltas(list, &list_size, window, depth, processed); cleanup_threaded_search(); @@ -2027,15 +2097,14 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size, #define ll_find_deltas(l, s, w, d, p) find_deltas(l, &s, w, d, p) #endif -static int add_ref_tag(const char *path, const unsigned char *sha1, int flag, void *cb_data) +static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data) { - unsigned char peeled[20]; + struct object_id peeled; - if (!prefixcmp(path, "refs/tags/") && /* is a tag? */ - !peel_ref(path, peeled) && /* peelable? */ - !is_null_sha1(peeled) && /* annotated tag? */ - locate_object_entry(peeled)) /* object packed? */ - add_object_entry(sha1, OBJ_TAG, NULL, 0); + if (starts_with(path, "refs/tags/") && /* is a tag? */ + !peel_ref(path, peeled.hash) && /* peelable? */ + packlist_find(&to_pack, peeled.hash, NULL)) /* object packed? */ + add_object_entry(oid->hash, OBJ_TAG, NULL, 0); return 0; } @@ -2057,14 +2126,14 @@ static void prepare_pack(int window, int depth) if (!pack_to_stdout) do_check_packed_object_crc = 1; - if (!nr_objects || !window || !depth) + if (!to_pack.nr_objects || !window || !depth) return; - delta_list = xmalloc(nr_objects * sizeof(*delta_list)); + delta_list = xmalloc(to_pack.nr_objects * sizeof(*delta_list)); nr_deltas = n = 0; - for (i = 0; i < nr_objects; i++) { - struct object_entry *entry = objects + i; + for (i = 0; i < to_pack.nr_objects; i++) { + struct object_entry *entry = to_pack.objects + i; if (entry->delta) /* This happens if we decided to reuse existing @@ -2099,7 +2168,7 @@ 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", + progress_state = start_progress(_("Compressing objects"), nr_deltas); qsort(delta_list, n, sizeof(*delta_list), type_size_sort); ll_find_deltas(delta_list, n, window+1, depth, &nr_done); @@ -2142,6 +2211,16 @@ static int git_pack_config(const char *k, const char *v, void *cb) cache_max_small_delta_size = git_config_int(k, v); return 0; } + if (!strcmp(k, "pack.writebitmaphashcache")) { + if (git_config_bool(k, v)) + write_bitmap_options |= BITMAP_OPT_HASH_CACHE; + else + write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE; + } + if (!strcmp(k, "pack.usebitmaps")) { + use_bitmap_index = 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) @@ -2200,6 +2279,9 @@ static void show_commit(struct commit *commit, void *data) { add_object_entry(commit->object.sha1, OBJ_COMMIT, NULL, 0); commit->object.flags |= OBJECT_ADDED; + + if (write_bitmap_index) + index_commit_for_bitmap(commit); } static void show_object(struct object *obj, @@ -2323,6 +2405,27 @@ static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1) return 0; } +/* + * Store a list of sha1s that are should not be discarded + * because they are either written too recently, or are + * reachable from another object that was. + * + * This is filled by get_object_list. + */ +static struct sha1_array recent_objects; + +static int loosened_object_can_be_discarded(const unsigned char *sha1, + unsigned long mtime) +{ + if (!unpack_unreachable_expiration) + return 0; + if (mtime > unpack_unreachable_expiration) + return 0; + if (sha1_array_lookup(&recent_objects, sha1) >= 0) + return 0; + return 1; +} + static void loosen_unused_packed_objects(struct rev_info *revs) { struct packed_git *p; @@ -2333,23 +2436,62 @@ static void loosen_unused_packed_objects(struct rev_info *revs) if (!p->pack_local || p->pack_keep) continue; - if (unpack_unreachable_expiration && - p->mtime < unpack_unreachable_expiration) - continue; - if (open_pack_index(p)) die("cannot open pack index"); for (i = 0; i < p->num_objects; i++) { sha1 = nth_packed_object_sha1(p, i); - if (!locate_object_entry(sha1) && - !has_sha1_pack_kept_or_nonlocal(sha1)) + if (!packlist_find(&to_pack, sha1, NULL) && + !has_sha1_pack_kept_or_nonlocal(sha1) && + !loosened_object_can_be_discarded(sha1, p->mtime)) if (force_object_loose(sha1, p->mtime)) die("unable to force loose object"); } } } +/* + * This tracks any options which a reader of the pack might + * not understand, and which would therefore prevent blind reuse + * of what we have on disk. + */ +static int pack_options_allow_reuse(void) +{ + return allow_ofs_delta; +} + +static int get_object_list_from_bitmap(struct rev_info *revs) +{ + if (prepare_bitmap_walk(revs) < 0) + return -1; + + if (pack_options_allow_reuse() && + !reuse_partial_packfile_from_bitmap( + &reuse_packfile, + &reuse_packfile_objects, + &reuse_packfile_offset)) { + assert(reuse_packfile_objects); + nr_result += reuse_packfile_objects; + display_progress(progress_state, nr_result); + } + + traverse_bitmap_commit_list(&add_object_entry_from_bitmap); + return 0; +} + +static void record_recent_object(struct object *obj, + const struct name_path *path, + const char *last, + void *data) +{ + sha1_array_append(&recent_objects, obj->sha1); +} + +static void record_recent_commit(struct commit *commit, void *data) +{ + sha1_array_append(&recent_objects, commit->object.sha1); +} + static void get_object_list(int ac, const char **av) { struct rev_info revs; @@ -2360,6 +2502,9 @@ static void get_object_list(int ac, const char **av) save_commit_buffer = 0; setup_revisions(ac, av, &revs, NULL); + /* make sure shallows are read */ + is_repository_shallow(); + while (fgets(line, sizeof(line), stdin) != NULL) { int len = strlen(line); if (len && line[len - 1] == '\n') @@ -2369,6 +2514,15 @@ static void get_object_list(int ac, const char **av) if (*line == '-') { if (!strcmp(line, "--not")) { flags ^= UNINTERESTING; + write_bitmap_index = 0; + continue; + } + if (starts_with(line, "--shallow ")) { + unsigned char sha1[20]; + if (get_sha1_hex(line + 10, sha1)) + die("not an SHA-1 '%s'", line + 10); + register_shallow(sha1); + use_bitmap_index = 0; continue; } die("not a rev '%s'", line); @@ -2377,15 +2531,31 @@ static void get_object_list(int ac, const char **av) die("bad revision '%s'", line); } + if (use_bitmap_index && !get_object_list_from_bitmap(&revs)) + return; + if (prepare_revision_walk(&revs)) die("revision walk setup failed"); - mark_edges_uninteresting(revs.commits, &revs, show_edge); + mark_edges_uninteresting(&revs, show_edge); traverse_commit_list(&revs, show_commit, show_object, NULL); + if (unpack_unreachable_expiration) { + revs.ignore_missing_links = 1; + if (add_unseen_recent_objects_to_traversal(&revs, + unpack_unreachable_expiration)) + die("unable to add recent objects"); + if (prepare_revision_walk(&revs)) + 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); if (unpack_unreachable) loosen_unused_packed_objects(&revs); + + sha1_array_clear(&recent_objects); } static int option_parse_index_version(const struct option *opt, @@ -2418,31 +2588,15 @@ static int option_parse_unpack_unreachable(const struct option *opt, return 0; } -static int option_parse_ulong(const struct option *opt, - const char *arg, int unset) -{ - if (unset) - die(_("option %s does not accept negative form"), - opt->long_name); - - if (!git_parse_ulong(arg, opt->value)) - die(_("unable to parse value '%s' for option %s"), - arg, opt->long_name); - return 0; -} - -#define OPT_ULONG(s, l, v, h) \ - { OPTION_CALLBACK, (s), (l), (v), "n", (h), \ - PARSE_OPT_NONEG, option_parse_ulong } - 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; - const char *rp_av[6]; - int rp_ac = 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 option pack_objects_options[] = { OPT_SET_INT('q', "quiet", &progress, N_("do not show progress meter"), 0), @@ -2456,16 +2610,16 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) { 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 }, - OPT_ULONG(0, "max-pack-size", &pack_size_limit, - N_("maximum size of each output pack file")), + OPT_MAGNITUDE(0, "max-pack-size", &pack_size_limit, + N_("maximum size of each output pack file")), OPT_BOOL(0, "local", &local, N_("ignore borrowed objects from alternate object store")), OPT_BOOL(0, "incremental", &incremental, N_("ignore packed objects")), OPT_INTEGER(0, "window", &window, N_("limit pack window by objects")), - OPT_ULONG(0, "window-memory", &window_memory_limit, - N_("limit pack window by memory in addition to object limit")), + OPT_MAGNITUDE(0, "window-memory", &window_memory_limit, + N_("limit pack window by memory in addition to object limit")), OPT_INTEGER(0, "depth", &depth, N_("maximum length of delta chain allowed in the resulting pack")), OPT_BOOL(0, "reuse-delta", &reuse_delta, @@ -2489,6 +2643,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) { 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_BOOL(0, "stdout", &pack_to_stdout, N_("output pack to stdout")), OPT_BOOL(0, "include-tag", &include_tag, @@ -2500,16 +2657,22 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) PARSE_OPT_OPTARG, option_parse_unpack_unreachable }, 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, N_("ignore packs that have companion .keep file")), 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_END(), }; - read_replace_refs = 0; + check_replace_refs = 0; reset_pack_idx_option(&pack_idx_opts); git_config(git_pack_config, NULL); @@ -2527,24 +2690,30 @@ 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); - rp_av[rp_ac++] = "pack-objects"; + argv_array_push(&rp, "pack-objects"); if (thin) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--objects-edge"; + argv_array_push(&rp, shallow + ? "--objects-edge-aggressive" + : "--objects-edge"); } else - rp_av[rp_ac++] = "--objects"; + argv_array_push(&rp, "--objects"); if (rev_list_all) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--all"; + argv_array_push(&rp, "--all"); } if (rev_list_reflog) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--reflog"; + argv_array_push(&rp, "--reflog"); + } + if (rev_list_index) { + use_internal_rev_list = 1; + argv_array_push(&rp, "--indexed-objects"); } if (rev_list_unpacked) { use_internal_rev_list = 1; - rp_av[rp_ac++] = "--unpacked"; + argv_array_push(&rp, "--unpacked"); } if (!reuse_object) @@ -2553,6 +2722,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) 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); + + 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"); @@ -2571,6 +2744,14 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (keep_unreachable && unpack_unreachable) die("--keep-unreachable and --unpack-unreachable are incompatible."); + if (!rev_list_all || !rev_list_reflog || !rev_list_index) + unpack_unreachable_expiration = 0; + + if (!use_internal_rev_list || !pack_to_stdout || is_repository_shallow()) + use_bitmap_index = 0; + + if (pack_to_stdout || !rev_list_all) + write_bitmap_index = 0; if (progress && all_progress_implied) progress = 2; @@ -2578,12 +2759,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) prepare_packed_git(); if (progress) - progress_state = start_progress("Counting objects", 0); + progress_state = start_progress(_("Counting objects"), 0); if (!use_internal_rev_list) read_object_list_from_stdin(); else { - rp_av[rp_ac] = NULL; - get_object_list(rp_ac, rp_av); + get_object_list(rp.argc, rp.argv); + argv_array_clear(&rp); } cleanup_preferred_base(); if (include_tag && nr_result) |