diff options
Diffstat (limited to 'midx.c')
-rw-r--r-- | midx.c | 470 |
1 files changed, 410 insertions, 60 deletions
@@ -13,6 +13,10 @@ #include "repository.h" #include "chunk-format.h" #include "pack.h" +#include "pack-bitmap.h" +#include "refs.h" +#include "revision.h" +#include "list-objects.h" #define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */ #define MIDX_VERSION 1 @@ -48,12 +52,12 @@ static uint8_t oid_version(void) } } -static const unsigned char *get_midx_checksum(struct multi_pack_index *m) +const unsigned char *get_midx_checksum(struct multi_pack_index *m) { return m->data + m->data_len - the_hash_algo->rawsz; } -static char *get_midx_filename(const char *object_dir) +char *get_midx_filename(const char *object_dir) { return xstrfmt("%s/pack/multi-pack-index", object_dir); } @@ -195,6 +199,8 @@ void close_midx(struct multi_pack_index *m) if (!m) return; + close_midx(m->next); + munmap((unsigned char *)m->data, m->data_len); for (i = 0; i < m->num_packs; i++) { @@ -203,6 +209,7 @@ void close_midx(struct multi_pack_index *m) } FREE_AND_NULL(m->packs); FREE_AND_NULL(m->pack_names); + free(m); } int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id) @@ -276,14 +283,18 @@ uint32_t nth_midxed_pack_int_id(struct multi_pack_index *m, uint32_t pos) (off_t)pos * MIDX_CHUNK_OFFSET_WIDTH); } -static int nth_midxed_pack_entry(struct repository *r, - struct multi_pack_index *m, - struct pack_entry *e, - uint32_t pos) +int fill_midx_entry(struct repository * r, + const struct object_id *oid, + struct pack_entry *e, + struct multi_pack_index *m) { + uint32_t pos; uint32_t pack_int_id; struct packed_git *p; + if (!bsearch_midx(oid, m, &pos)) + return 0; + if (pos >= m->num_objects) return 0; @@ -303,15 +314,9 @@ static int nth_midxed_pack_entry(struct repository *r, if (!is_pack_valid(p)) return 0; - if (p->num_bad_objects) { - uint32_t i; - struct object_id oid; - nth_midxed_object_oid(&oid, m, pos); - for (i = 0; i < p->num_bad_objects; i++) - if (hasheq(oid.hash, - p->bad_object_sha1 + the_hash_algo->rawsz * i)) - return 0; - } + if (oidset_size(&p->bad_objects) && + oidset_contains(&p->bad_objects, oid)) + return 0; e->offset = nth_midxed_offset(m, pos); e->p = p; @@ -319,19 +324,6 @@ static int nth_midxed_pack_entry(struct repository *r, return 1; } -int fill_midx_entry(struct repository * r, - const struct object_id *oid, - struct pack_entry *e, - struct multi_pack_index *m) -{ - uint32_t pos; - - if (!bsearch_midx(oid, m, &pos)) - return 0; - - return nth_midxed_pack_entry(r, m, e, pos); -} - /* Match "foo.idx" against either "foo.pack" _or_ "foo.idx". */ static int cmp_idx_or_pack_name(const char *idx_or_pack_name, const char *idx_name) @@ -468,6 +460,8 @@ struct write_midx_context { uint32_t num_large_offsets; int preferred_pack_idx; + + struct string_list *to_include; }; static void add_pack_to_midx(const char *full_path, size_t full_path_len, @@ -477,8 +471,26 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len, if (ends_with(file_name, ".idx")) { display_progress(ctx->progress, ++ctx->pack_paths_checked); + /* + * Note that at most one of ctx->m and ctx->to_include are set, + * so we are testing midx_contains_pack() and + * string_list_has_string() independently (guarded by the + * appropriate NULL checks). + * + * We could support passing to_include while reusing an existing + * MIDX, but don't currently since the reuse process drags + * forward all packs from an existing MIDX (without checking + * whether or not they appear in the to_include list). + * + * If we added support for that, these next two conditional + * should be performed independently (likely checking + * to_include before the existing MIDX). + */ if (ctx->m && midx_contains_pack(ctx->m, file_name)) return; + else if (ctx->to_include && + !string_list_has_string(ctx->to_include, file_name)) + return; ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); @@ -882,7 +894,7 @@ static void write_midx_reverse_index(char *midx_name, unsigned char *midx_hash, strbuf_release(&buf); } -static void clear_midx_files_ext(struct repository *r, const char *ext, +static void clear_midx_files_ext(const char *object_dir, const char *ext, unsigned char *keep_hash); static int midx_checksum_valid(struct multi_pack_index *m) @@ -890,9 +902,232 @@ static int midx_checksum_valid(struct multi_pack_index *m) return hashfile_checksum_valid(m->data, m->data_len); } -static int write_midx_internal(const char *object_dir, struct multi_pack_index *m, +static void prepare_midx_packing_data(struct packing_data *pdata, + struct write_midx_context *ctx) +{ + uint32_t i; + + memset(pdata, 0, sizeof(struct packing_data)); + prepare_packing_data(the_repository, pdata); + + for (i = 0; i < ctx->entries_nr; i++) { + struct pack_midx_entry *from = &ctx->entries[ctx->pack_order[i]]; + struct object_entry *to = packlist_alloc(pdata, &from->oid); + + oe_set_in_pack(pdata, to, + ctx->info[ctx->pack_perm[from->pack_int_id]].p); + } +} + +static int add_ref_to_pending(const char *refname, + const struct object_id *oid, + int flag, void *cb_data) +{ + struct rev_info *revs = (struct rev_info*)cb_data; + struct object *object; + + if ((flag & REF_ISSYMREF) && (flag & REF_ISBROKEN)) { + warning("symbolic ref is dangling: %s", refname); + return 0; + } + + object = parse_object_or_die(oid, refname); + if (object->type != OBJ_COMMIT) + return 0; + + add_pending_object(revs, object, ""); + if (bitmap_is_preferred_refname(revs->repo, refname)) + object->flags |= NEEDS_BITMAP; + return 0; +} + +struct bitmap_commit_cb { + struct commit **commits; + size_t commits_nr, commits_alloc; + + struct write_midx_context *ctx; +}; + +static const struct object_id *bitmap_oid_access(size_t index, + const void *_entries) +{ + const struct pack_midx_entry *entries = _entries; + return &entries[index].oid; +} + +static void bitmap_show_commit(struct commit *commit, void *_data) +{ + struct bitmap_commit_cb *data = _data; + int pos = oid_pos(&commit->object.oid, data->ctx->entries, + data->ctx->entries_nr, + bitmap_oid_access); + if (pos < 0) + return; + + ALLOC_GROW(data->commits, data->commits_nr + 1, data->commits_alloc); + data->commits[data->commits_nr++] = commit; +} + +static int read_refs_snapshot(const char *refs_snapshot, + struct rev_info *revs) +{ + struct strbuf buf = STRBUF_INIT; + struct object_id oid; + FILE *f = xfopen(refs_snapshot, "r"); + + while (strbuf_getline(&buf, f) != EOF) { + struct object *object; + int preferred = 0; + char *hex = buf.buf; + const char *end = NULL; + + if (buf.len && *buf.buf == '+') { + preferred = 1; + hex = &buf.buf[1]; + } + + if (parse_oid_hex(hex, &oid, &end) < 0) + die(_("could not parse line: %s"), buf.buf); + if (*end) + die(_("malformed line: %s"), buf.buf); + + object = parse_object_or_die(&oid, NULL); + if (preferred) + object->flags |= NEEDS_BITMAP; + + add_pending_object(revs, object, ""); + } + + fclose(f); + strbuf_release(&buf); + return 0; +} + +static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr_p, + const char *refs_snapshot, + struct write_midx_context *ctx) +{ + struct rev_info revs; + struct bitmap_commit_cb cb = {0}; + + cb.ctx = ctx; + + repo_init_revisions(the_repository, &revs, NULL); + if (refs_snapshot) { + read_refs_snapshot(refs_snapshot, &revs); + } else { + setup_revisions(0, NULL, &revs, NULL); + for_each_ref(add_ref_to_pending, &revs); + } + + /* + * Skipping promisor objects here is intentional, since it only excludes + * them from the list of reachable commits that we want to select from + * when computing the selection of MIDX'd commits to receive bitmaps. + * + * Reachability bitmaps do require that their objects be closed under + * reachability, but fetching any objects missing from promisors at this + * point is too late. But, if one of those objects can be reached from + * an another object that is included in the bitmap, then we will + * complain later that we don't have reachability closure (and fail + * appropriately). + */ + fetch_if_missing = 0; + revs.exclude_promisor_objects = 1; + + if (prepare_revision_walk(&revs)) + die(_("revision walk setup failed")); + + traverse_commit_list(&revs, bitmap_show_commit, NULL, &cb); + if (indexed_commits_nr_p) + *indexed_commits_nr_p = cb.commits_nr; + + return cb.commits; +} + +static int write_midx_bitmap(char *midx_name, unsigned char *midx_hash, + struct write_midx_context *ctx, + const char *refs_snapshot, + unsigned flags) +{ + struct packing_data pdata; + struct pack_idx_entry **index; + struct commit **commits = NULL; + uint32_t i, commits_nr; + uint16_t options = 0; + char *bitmap_name = xstrfmt("%s-%s.bitmap", midx_name, hash_to_hex(midx_hash)); + int ret; + + if (flags & MIDX_WRITE_BITMAP_HASH_CACHE) + options |= BITMAP_OPT_HASH_CACHE; + + prepare_midx_packing_data(&pdata, ctx); + + commits = find_commits_for_midx_bitmap(&commits_nr, refs_snapshot, ctx); + + /* + * Build the MIDX-order index based on pdata.objects (which is already + * in MIDX order; c.f., 'midx_pack_order_cmp()' for the definition of + * this order). + */ + ALLOC_ARRAY(index, pdata.nr_objects); + for (i = 0; i < pdata.nr_objects; i++) + index[i] = &pdata.objects[i].idx; + + bitmap_writer_show_progress(flags & MIDX_PROGRESS); + bitmap_writer_build_type_index(&pdata, index, pdata.nr_objects); + + /* + * bitmap_writer_finish expects objects in lex order, but pack_order + * gives us exactly that. use it directly instead of re-sorting the + * array. + * + * This changes the order of objects in 'index' between + * bitmap_writer_build_type_index and bitmap_writer_finish. + * + * The same re-ordering takes place in the single-pack bitmap code via + * write_idx_file(), which is called by finish_tmp_packfile(), which + * happens between bitmap_writer_build_type_index() and + * bitmap_writer_finish(). + */ + for (i = 0; i < pdata.nr_objects; i++) + index[ctx->pack_order[i]] = &pdata.objects[i].idx; + + bitmap_writer_select_commits(commits, commits_nr, -1); + ret = bitmap_writer_build(&pdata); + if (ret < 0) + goto cleanup; + + bitmap_writer_set_checksum(midx_hash); + bitmap_writer_finish(index, pdata.nr_objects, bitmap_name, options); + +cleanup: + free(index); + free(bitmap_name); + return ret; +} + +static struct multi_pack_index *lookup_multi_pack_index(struct repository *r, + const char *object_dir) +{ + struct multi_pack_index *cur; + + /* Ensure the given object_dir is local, or a known alternate. */ + find_odb(r, object_dir); + + for (cur = get_multi_pack_index(r); cur; cur = cur->next) { + if (!strcmp(object_dir, cur->object_dir)) + return cur; + } + + return NULL; +} + +static int write_midx_internal(const char *object_dir, + struct string_list *packs_to_include, struct string_list *packs_to_drop, const char *preferred_pack_name, + const char *refs_snapshot, unsigned flags) { char *midx_name; @@ -911,10 +1146,14 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index * die_errno(_("unable to create leading directories of %s"), midx_name); - if (m) - ctx.m = m; - else - ctx.m = load_multi_pack_index(object_dir, 1); + if (!packs_to_include) { + /* + * Only reference an existing MIDX when not filtering which + * packs to include, since all packs and objects are copied + * blindly from an existing MIDX if one is present. + */ + ctx.m = lookup_multi_pack_index(the_repository, object_dir); + } if (ctx.m && !midx_checksum_valid(ctx.m)) { warning(_("ignoring existing multi-pack-index; checksum mismatch")); @@ -932,8 +1171,27 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index * ctx.info[ctx.nr].orig_pack_int_id = i; ctx.info[ctx.nr].pack_name = xstrdup(ctx.m->pack_names[i]); - ctx.info[ctx.nr].p = NULL; + ctx.info[ctx.nr].p = ctx.m->packs[i]; ctx.info[ctx.nr].expired = 0; + + if (flags & MIDX_WRITE_REV_INDEX) { + /* + * If generating a reverse index, need to have + * packed_git's loaded to compare their + * mtimes and object count. + */ + if (prepare_midx_pack(the_repository, ctx.m, i)) { + error(_("could not load pack")); + result = 1; + goto cleanup; + } + + if (open_pack_index(ctx.m->packs[i])) + die(_("could not open index for %s"), + ctx.m->packs[i]->pack_name); + ctx.info[ctx.nr].p = ctx.m->packs[i]; + } + ctx.nr++; } } @@ -944,21 +1202,95 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index * else ctx.progress = NULL; + ctx.to_include = packs_to_include; + for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &ctx); stop_progress(&ctx.progress); - if (ctx.m && ctx.nr == ctx.m->num_packs && !packs_to_drop) - goto cleanup; + if ((ctx.m && ctx.nr == ctx.m->num_packs) && + !(packs_to_include || packs_to_drop)) { + struct bitmap_index *bitmap_git; + int bitmap_exists; + int want_bitmap = flags & MIDX_WRITE_BITMAP; + + bitmap_git = prepare_midx_bitmap_git(ctx.m); + bitmap_exists = bitmap_git && bitmap_is_midx(bitmap_git); + free_bitmap_index(bitmap_git); + + if (bitmap_exists || !want_bitmap) { + /* + * The correct MIDX already exists, and so does a + * corresponding bitmap (or one wasn't requested). + */ + if (!want_bitmap) + clear_midx_files_ext(object_dir, ".bitmap", + NULL); + goto cleanup; + } + } - ctx.preferred_pack_idx = -1; if (preferred_pack_name) { + int found = 0; for (i = 0; i < ctx.nr; i++) { if (!cmp_idx_or_pack_name(preferred_pack_name, ctx.info[i].pack_name)) { ctx.preferred_pack_idx = i; + found = 1; break; } } + + if (!found) + warning(_("unknown preferred pack: '%s'"), + preferred_pack_name); + } else if (ctx.nr && + (flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP))) { + struct packed_git *oldest = ctx.info[ctx.preferred_pack_idx].p; + ctx.preferred_pack_idx = 0; + + if (packs_to_drop && packs_to_drop->nr) + BUG("cannot write a MIDX bitmap during expiration"); + + /* + * set a preferred pack when writing a bitmap to ensure that + * the pack from which the first object is selected in pseudo + * pack-order has all of its objects selected from that pack + * (and not another pack containing a duplicate) + */ + for (i = 1; i < ctx.nr; i++) { + struct packed_git *p = ctx.info[i].p; + + if (!oldest->num_objects || p->mtime < oldest->mtime) { + oldest = p; + ctx.preferred_pack_idx = i; + } + } + + if (!oldest->num_objects) { + /* + * If all packs are empty; unset the preferred index. + * This is acceptable since there will be no duplicate + * objects to resolve, so the preferred value doesn't + * matter. + */ + ctx.preferred_pack_idx = -1; + } + } else { + /* + * otherwise don't mark any pack as preferred to avoid + * interfering with expiration logic below + */ + ctx.preferred_pack_idx = -1; + } + + if (ctx.preferred_pack_idx > -1) { + struct packed_git *preferred = ctx.info[ctx.preferred_pack_idx].p; + if (!preferred->num_objects) { + error(_("cannot select preferred pack %s with no objects"), + preferred->pack_name); + result = 1; + goto cleanup; + } } ctx.entries = get_sorted_entries(ctx.m, ctx.info, ctx.nr, &ctx.entries_nr, @@ -1029,11 +1361,7 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index * ctx.info, ctx.nr, sizeof(*ctx.info), idx_or_pack_name_cmp); - - if (!preferred) - warning(_("unknown preferred pack: '%s'"), - preferred_pack_name); - else { + if (preferred) { uint32_t perm = ctx.pack_perm[preferred->orig_pack_int_id]; if (perm == PACK_EXPIRED) warning(_("preferred pack '%s' is expired"), @@ -1048,9 +1376,6 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index * hold_lock_file_for_update(&lk, midx_name, LOCK_DIE_ON_ERROR); f = hashfd(get_lock_file_fd(&lk), get_lock_file_path(&lk)); - if (ctx.m) - close_midx(ctx.m); - if (ctx.nr - dropped_packs == 0) { error(_("no pack files to index.")); result = 1; @@ -1081,14 +1406,28 @@ static int write_midx_internal(const char *object_dir, struct multi_pack_index * finalize_hashfile(f, midx_hash, CSUM_FSYNC | CSUM_HASH_IN_STREAM); free_chunkfile(cf); - if (flags & MIDX_WRITE_REV_INDEX) + if (flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP)) ctx.pack_order = midx_pack_order(&ctx); if (flags & MIDX_WRITE_REV_INDEX) write_midx_reverse_index(midx_name, midx_hash, &ctx); - clear_midx_files_ext(the_repository, ".rev", midx_hash); + if (flags & MIDX_WRITE_BITMAP) { + if (write_midx_bitmap(midx_name, midx_hash, &ctx, + refs_snapshot, flags) < 0) { + error(_("could not write multi-pack bitmap")); + result = 1; + goto cleanup; + } + } - commit_lock_file(&lk); + if (ctx.m) + close_object_store(the_repository->objects); + + if (commit_lock_file(&lk) < 0) + die_errno(_("could not write multi-pack-index")); + + clear_midx_files_ext(object_dir, ".bitmap", midx_hash); + clear_midx_files_ext(object_dir, ".rev", midx_hash); cleanup: for (i = 0; i < ctx.nr; i++) { @@ -1104,15 +1443,27 @@ cleanup: free(ctx.pack_perm); free(ctx.pack_order); free(midx_name); + return result; } int write_midx_file(const char *object_dir, const char *preferred_pack_name, + const char *refs_snapshot, unsigned flags) { return write_midx_internal(object_dir, NULL, NULL, preferred_pack_name, - flags); + refs_snapshot, flags); +} + +int write_midx_file_only(const char *object_dir, + struct string_list *packs_to_include, + const char *preferred_pack_name, + const char *refs_snapshot, + unsigned flags) +{ + return write_midx_internal(object_dir, packs_to_include, NULL, + preferred_pack_name, refs_snapshot, flags); } struct clear_midx_data { @@ -1135,7 +1486,7 @@ static void clear_midx_file_ext(const char *full_path, size_t full_path_len, die_errno(_("failed to remove %s"), full_path); } -static void clear_midx_files_ext(struct repository *r, const char *ext, +static void clear_midx_files_ext(const char *object_dir, const char *ext, unsigned char *keep_hash) { struct clear_midx_data data; @@ -1146,7 +1497,7 @@ static void clear_midx_files_ext(struct repository *r, const char *ext, hash_to_hex(keep_hash), ext); data.ext = ext; - for_each_file_in_pack_dir(r->objects->odb->path, + for_each_file_in_pack_dir(object_dir, clear_midx_file_ext, &data); @@ -1165,7 +1516,8 @@ void clear_midx_file(struct repository *r) if (remove_path(midx)) die(_("failed to clear multi-pack-index at %s"), midx); - clear_midx_files_ext(r, ".rev", NULL); + clear_midx_files_ext(r->objects->odb->path, ".bitmap", NULL); + clear_midx_files_ext(r->objects->odb->path, ".rev", NULL); free(midx); } @@ -1345,7 +1697,7 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla { uint32_t i, *count, result = 0; struct string_list packs_to_drop = STRING_LIST_INIT_DUP; - struct multi_pack_index *m = load_multi_pack_index(object_dir, 1); + struct multi_pack_index *m = lookup_multi_pack_index(r, object_dir); struct progress *progress = NULL; if (!m) @@ -1391,9 +1743,10 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla free(count); if (packs_to_drop.nr) - result = write_midx_internal(object_dir, m, &packs_to_drop, NULL, flags); + result = write_midx_internal(object_dir, NULL, &packs_to_drop, NULL, NULL, flags); string_list_clear(&packs_to_drop, 0); + return result; } @@ -1509,7 +1862,7 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size, struct child_process cmd = CHILD_PROCESS_INIT; FILE *cmd_in; struct strbuf base_name = STRBUF_INIT; - struct multi_pack_index *m = load_multi_pack_index(object_dir, 1); + struct multi_pack_index *m = lookup_multi_pack_index(r, object_dir); /* * When updating the default for these configuration @@ -1580,12 +1933,9 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size, goto cleanup; } - result = write_midx_internal(object_dir, m, NULL, NULL, flags); - m = NULL; + result = write_midx_internal(object_dir, NULL, NULL, NULL, NULL, flags); cleanup: - if (m) - close_midx(m); free(include_pack); return result; } |