From: Junio C Hamano Date: Tue, 9 Jul 2019 22:25:36 +0000 (-0700) Subject: Merge branch 'ds/commit-graph-write-refactor' X-Git-Tag: v2.23.0-rc0~86 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/e1168940ce11878261ece4602a7d8b8ee9a8c77e?hp=-c Merge branch 'ds/commit-graph-write-refactor' Renamed from commit-graph-format-v2 and changed scope. * ds/commit-graph-write-refactor: commit-graph: extract write_commit_graph_file() commit-graph: extract copy_oids_to_commits() commit-graph: extract count_distinct_commits() commit-graph: extract fill_oids_from_all_packs() commit-graph: extract fill_oids_from_commit_hex() commit-graph: extract fill_oids_from_packs() commit-graph: create write_commit_graph_context commit-graph: remove Future Work section commit-graph: collapse parameters into flags commit-graph: return with errors during write commit-graph: fix the_repository reference --- e1168940ce11878261ece4602a7d8b8ee9a8c77e diff --combined builtin/commit.c index 1c9e8e2228,b001ef565d..1921401117 --- a/builtin/commit.c +++ b/builtin/commit.c @@@ -235,7 -235,7 +235,7 @@@ static int commit_index_files(void * and return the paths that match the given pattern in list. */ static int list_paths(struct string_list *list, const char *with_tree, - const char *prefix, const struct pathspec *pattern) + const struct pathspec *pattern) { int i, ret; char *m; @@@ -264,7 -264,7 +264,7 @@@ item->util = item; /* better a valid pointer than a fake one */ } - ret = report_path_error(m, pattern, prefix); + ret = report_path_error(m, pattern); free(m); return ret; } @@@ -454,7 -454,7 +454,7 @@@ static const char *prepare_index(int ar die(_("cannot do a partial commit during a cherry-pick.")); } - if (list_paths(&partial, !current_head ? NULL : "HEAD", prefix, &pathspec)) + if (list_paths(&partial, !current_head ? NULL : "HEAD", &pathspec)) exit(1); discard_cache(); @@@ -609,8 -609,7 +609,8 @@@ static void determine_author_info(struc set_ident_var(&date, strbuf_detach(&date_buf, NULL)); } - strbuf_addstr(author_ident, fmt_ident(name, email, date, IDENT_STRICT)); + strbuf_addstr(author_ident, fmt_ident(name, email, WANT_AUTHOR_IDENT, date, + IDENT_STRICT)); assert_split_ident(&author, author_ident); export_one("GIT_AUTHOR_NAME", author.name_begin, author.name_end, 0); export_one("GIT_AUTHOR_EMAIL", author.mail_begin, author.mail_end, 0); @@@ -668,7 -667,6 +668,7 @@@ static int prepare_to_commit(const cha const char *hook_arg2 = NULL; int clean_message_contents = (cleanup_mode != COMMIT_MSG_CLEANUP_NONE); int old_display_comment_prefix; + int merge_contains_scissors = 0; /* This checks and barfs if author is badly specified */ determine_author_info(author_ident); @@@ -729,8 -727,6 +729,8 @@@ strbuf_addbuf(&sb, &message); hook_arg1 = "message"; } else if (!stat(git_path_merge_msg(the_repository), &statbuf)) { + size_t merge_msg_start; + /* * prepend SQUASH_MSG here if it exists and a * "merge --squash" was originally performed @@@ -741,16 -737,8 +741,16 @@@ hook_arg1 = "squash"; } else hook_arg1 = "merge"; + + merge_msg_start = sb.len; if (strbuf_read_file(&sb, git_path_merge_msg(the_repository), 0) < 0) die_errno(_("could not read MERGE_MSG")); + + if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS && + wt_status_locate_end(sb.buf + merge_msg_start, + sb.len - merge_msg_start) < + sb.len - merge_msg_start) + merge_contains_scissors = 1; } else if (!stat(git_path_squash_msg(the_repository), &statbuf)) { if (strbuf_read_file(&sb, git_path_squash_msg(the_repository), 0) < 0) die_errno(_("could not read SQUASH_MSG")); @@@ -818,8 -806,7 +818,8 @@@ struct ident_split ci, ai; if (whence != FROM_COMMIT) { - if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS) + if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS && + !merge_contains_scissors) wt_status_add_cut_line(s->fp); status_printf_ln(s, GIT_COLOR_NORMAL, whence == FROM_MERGE @@@ -844,10 -831,10 +844,10 @@@ _("Please enter the commit message for your changes." " Lines starting\nwith '%c' will be ignored, and an empty" " message aborts the commit.\n"), comment_line_char); - else if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS && - whence == FROM_COMMIT) - wt_status_add_cut_line(s->fp); - else /* COMMIT_MSG_CLEANUP_SPACE, that is. */ + else if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS) { + if (whence == FROM_COMMIT && !merge_contains_scissors) + wt_status_add_cut_line(s->fp); + } else /* COMMIT_MSG_CLEANUP_SPACE, that is. */ status_printf(s, GIT_COLOR_NORMAL, _("Please enter the commit message for your changes." " Lines starting\n" @@@ -1051,10 -1038,6 +1051,10 @@@ static void handle_untracked_files_arg( s->show_untracked_files = SHOW_NORMAL_UNTRACKED_FILES; else if (!strcmp(untracked_files_arg, "all")) s->show_untracked_files = SHOW_ALL_UNTRACKED_FILES; + /* + * Please update $__git_untracked_file_modes in + * git-completion.bash when you add new options + */ else die(_("Invalid untracked files mode '%s'"), untracked_files_arg); } @@@ -1184,13 -1167,25 +1184,13 @@@ static int parse_and_validate_options(i die(_("Only one of --include/--only/--all/--interactive/--patch can be used.")); if (argc == 0 && (also || (only && !amend && !allow_empty))) die(_("No paths with --include/--only does not make sense.")); - if (!cleanup_arg || !strcmp(cleanup_arg, "default")) - cleanup_mode = use_editor ? COMMIT_MSG_CLEANUP_ALL : - COMMIT_MSG_CLEANUP_SPACE; - else if (!strcmp(cleanup_arg, "verbatim")) - cleanup_mode = COMMIT_MSG_CLEANUP_NONE; - else if (!strcmp(cleanup_arg, "whitespace")) - cleanup_mode = COMMIT_MSG_CLEANUP_SPACE; - else if (!strcmp(cleanup_arg, "strip")) - cleanup_mode = COMMIT_MSG_CLEANUP_ALL; - else if (!strcmp(cleanup_arg, "scissors")) - cleanup_mode = use_editor ? COMMIT_MSG_CLEANUP_SCISSORS : - COMMIT_MSG_CLEANUP_SPACE; - else - die(_("Invalid cleanup mode %s"), cleanup_arg); + cleanup_mode = get_cleanup_mode(cleanup_arg, use_editor); handle_untracked_files_arg(s); if (all && argc > 0) - die(_("Paths with -a does not make sense.")); + die(_("paths '%s ...' with -a does not make sense"), + argv[0]); if (status_format != STATUS_FORMAT_NONE) dry_run = 1; @@@ -1486,7 -1481,7 +1486,7 @@@ int cmd_commit(int argc, const char **a OPT_BOOL('s', "signoff", &signoff, N_("add Signed-off-by:")), OPT_FILENAME('t', "template", &template_file, N_("use specified template file")), OPT_BOOL('e', "edit", &edit_flag, N_("force edit of commit")), - OPT_STRING(0, "cleanup", &cleanup_arg, N_("default"), N_("how to strip spaces and #comments from message")), + OPT_CLEANUP(&cleanup_arg), OPT_BOOL(0, "status", &include_status, N_("include status in commit message template")), { OPTION_STRING, 'S', "gpg-sign", &sign_commit, N_("key-id"), N_("GPG sign commit"), PARSE_OPT_OPTARG, NULL, (intptr_t) "" }, @@@ -1622,7 -1617,11 +1622,7 @@@ die(_("could not read commit message: %s"), strerror(saved_errno)); } - if (verbose || /* Truncate the message just before the diff, if any. */ - cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS) - strbuf_setlen(&sb, wt_status_locate_end(sb.buf, sb.len)); - if (cleanup_mode != COMMIT_MSG_CLEANUP_NONE) - strbuf_stripspace(&sb, cleanup_mode == COMMIT_MSG_CLEANUP_ALL); + cleanup_message(&sb, cleanup_mode, verbose); if (message_is_empty(&sb, cleanup_mode) && !allow_empty_message) { rollback_index_files(); @@@ -1658,7 -1657,8 +1658,7 @@@ die("%s", err.buf); } - unlink(git_path_cherry_pick_head(the_repository)); - unlink(git_path_revert_head(the_repository)); + sequencer_post_commit_cleanup(the_repository); unlink(git_path_merge_head(the_repository)); unlink(git_path_merge_msg(the_repository)); unlink(git_path_merge_mode(the_repository)); @@@ -1669,8 -1669,9 +1669,9 @@@ "new_index file. Check that disk is not full and quota is\n" "not exceeded, and then \"git reset HEAD\" to recover.")); - if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0)) - write_commit_graph_reachable(get_object_directory(), 0, 0); + if (git_env_bool(GIT_TEST_COMMIT_GRAPH, 0) && + write_commit_graph_reachable(get_object_directory(), 0)) + return 1; repo_rerere(the_repository, 0); run_command_v_opt(argv_gc_auto, RUN_GIT_CMD); diff --combined builtin/gc.c index 8943bcc300,df2573f124..8ba9bd2472 --- a/builtin/gc.c +++ b/builtin/gc.c @@@ -116,19 -116,6 +116,19 @@@ static void process_log_file_on_signal( raise(signo); } +static int gc_config_is_timestamp_never(const char *var) +{ + const char *value; + timestamp_t expire; + + if (!git_config_get_value(var, &value) && value) { + if (parse_expiry_date(value, &expire)) + die(_("failed to parse '%s' value '%s'"), var, value); + return expire == 0; + } + return 0; +} + static void gc_config(void) { const char *value; @@@ -140,10 -127,6 +140,10 @@@ pack_refs = git_config_bool("gc.packrefs", value); } + if (gc_config_is_timestamp_never("gc.reflogexpire") && + gc_config_is_timestamp_never("gc.reflogexpireunreachable")) + prune_reflogs = 0; + git_config_get_int("gc.aggressivewindow", &aggressive_window); git_config_get_int("gc.aggressivedepth", &aggressive_depth); git_config_get_int("gc.auto", &gc_auto_threshold); @@@ -173,7 -156,9 +173,7 @@@ static int too_many_loose_objects(void int auto_threshold; int num_loose = 0; int needed = 0; - - if (gc_auto_threshold <= 0) - return 0; + const unsigned hexsz_loose = the_hash_algo->hexsz - 2; dir = opendir(git_path("objects/17")); if (!dir) @@@ -181,8 -166,8 +181,8 @@@ auto_threshold = DIV_ROUND_UP(gc_auto_threshold, 256); while ((ent = readdir(dir)) != NULL) { - if (strspn(ent->d_name, "0123456789abcdef") != 38 || - ent->d_name[38] != '\0') + if (strspn(ent->d_name, "0123456789abcdef") != hexsz_loose || + ent->d_name[hexsz_loose] != '\0') continue; if (++num_loose > auto_threshold) { needed = 1; @@@ -506,20 -491,14 +506,20 @@@ done static void gc_before_repack(void) { + /* + * We may be called twice, as both the pre- and + * post-daemonized phases will call us, but running these + * commands more than once is pointless and wasteful. + */ + static int done = 0; + if (done++) + return; + if (pack_refs && run_command_v_opt(pack_refs_cmd.argv, RUN_GIT_CMD)) die(FAILED_RUN, pack_refs_cmd.argv[0]); if (prune_reflogs && run_command_v_opt(reflog.argv, RUN_GIT_CMD)) die(FAILED_RUN, reflog.argv[0]); - - pack_refs = 0; - prune_reflogs = 0; } int cmd_gc(int argc, const char **argv, const char *prefix) @@@ -685,9 -664,10 +685,10 @@@ clean_pack_garbage(); } - if (gc_write_commit_graph) - write_commit_graph_reachable(get_object_directory(), 0, - !quiet && !daemonized); + if (gc_write_commit_graph && + write_commit_graph_reachable(get_object_directory(), + !quiet && !daemonized ? COMMIT_GRAPH_PROGRESS : 0)) + return 1; if (auto_gc && too_many_loose_objects()) warning(_("There are too many unreachable loose objects; " diff --combined commit-graph.c index 7c5e54875f,9d2c72f5b4..89c4b982dd --- a/commit-graph.c +++ b/commit-graph.c @@@ -267,10 -267,8 +267,10 @@@ struct commit_graph *parse_commit_graph last_chunk_offset = chunk_offset; } - if (verify_commit_graph_lite(graph)) + if (verify_commit_graph_lite(graph)) { + free(graph); return NULL; + } return graph; } @@@ -399,11 -397,6 +399,11 @@@ static void fill_commit_graph_info(stru item->generation = get_be32(commit_data + g->hash_len + 8) >> 2; } +static inline void set_commit_tree(struct commit *c, struct tree *t) +{ + c->maybe_tree = t; +} + static int fill_commit_in_graph(struct repository *r, struct commit *item, struct commit_graph *g, uint32_t pos) @@@ -417,7 -410,7 +417,7 @@@ item->object.parsed = 1; item->graph_pos = pos; - item->maybe_tree = NULL; + set_commit_tree(item, NULL); date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; date_low = get_be32(commit_data + g->hash_len + 12); @@@ -503,7 -496,7 +503,7 @@@ static struct tree *load_tree_for_commi GRAPH_DATA_WIDTH * (c->graph_pos); hashcpy(oid.hash, commit_data); - c->maybe_tree = lookup_tree(r, &oid); + set_commit_tree(c, lookup_tree(r, &oid)); return c->maybe_tree; } @@@ -525,14 -518,38 +525,38 @@@ struct tree *get_commit_tree_in_graph(s return get_commit_tree_in_graph_one(r, r->objects->commit_graph, c); } + struct packed_commit_list { + struct commit **list; + int nr; + int alloc; + }; + + struct packed_oid_list { + struct object_id *list; + int nr; + int alloc; + }; + + struct write_commit_graph_context { + struct repository *r; + const char *obj_dir; + char *graph_name; + struct packed_oid_list oids; + struct packed_commit_list commits; + int num_extra_edges; + unsigned long approx_nr_objects; + struct progress *progress; + int progress_done; + uint64_t progress_cnt; + unsigned append:1, + report_progress:1; + }; + static void write_graph_chunk_fanout(struct hashfile *f, - struct commit **commits, - int nr_commits, - struct progress *progress, - uint64_t *progress_cnt) + struct write_commit_graph_context *ctx) { int i, count = 0; - struct commit **list = commits; + struct commit **list = ctx->commits.list; /* * Write the first-level table (the list is sorted, @@@ -540,10 -557,10 +564,10 @@@ * having to do eight extra binary search iterations). */ for (i = 0; i < 256; i++) { - while (count < nr_commits) { + while (count < ctx->commits.nr) { if ((*list)->object.oid.hash[0] != i) break; - display_progress(progress, ++*progress_cnt); + display_progress(ctx->progress, ++ctx->progress_cnt); count++; list++; } @@@ -553,14 -570,12 +577,12 @@@ } static void write_graph_chunk_oids(struct hashfile *f, int hash_len, - struct commit **commits, int nr_commits, - struct progress *progress, - uint64_t *progress_cnt) + struct write_commit_graph_context *ctx) { - struct commit **list = commits; + struct commit **list = ctx->commits.list; int count; - for (count = 0; count < nr_commits; count++, list++) { - display_progress(progress, ++*progress_cnt); + for (count = 0; count < ctx->commits.nr; count++, list++) { + display_progress(ctx->progress, ++ctx->progress_cnt); hashwrite(f, (*list)->object.oid.hash, (int)hash_len); } } @@@ -572,19 -587,17 +594,17 @@@ static const unsigned char *commit_to_s } static void write_graph_chunk_data(struct hashfile *f, int hash_len, - struct commit **commits, int nr_commits, - struct progress *progress, - uint64_t *progress_cnt) + struct write_commit_graph_context *ctx) { - struct commit **list = commits; - struct commit **last = commits + nr_commits; + struct commit **list = ctx->commits.list; + struct commit **last = ctx->commits.list + ctx->commits.nr; uint32_t num_extra_edges = 0; while (list < last) { struct commit_list *parent; int edge_value; uint32_t packedDate[2]; - display_progress(progress, ++*progress_cnt); + display_progress(ctx->progress, ++ctx->progress_cnt); parse_commit_no_graph(*list); hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len); @@@ -595,8 -608,8 +615,8 @@@ edge_value = GRAPH_PARENT_NONE; else { edge_value = sha1_pos(parent->item->object.oid.hash, - commits, - nr_commits, + ctx->commits.list, + ctx->commits.nr, commit_to_sha1); if (edge_value < 0) @@@ -616,8 -629,8 +636,8 @@@ edge_value = GRAPH_EXTRA_EDGES_NEEDED | num_extra_edges; else { edge_value = sha1_pos(parent->item->object.oid.hash, - commits, - nr_commits, + ctx->commits.list, + ctx->commits.nr, commit_to_sha1); if (edge_value < 0) BUG("missing parent %s for commit %s", @@@ -649,19 -662,16 +669,16 @@@ } static void write_graph_chunk_extra_edges(struct hashfile *f, - struct commit **commits, - int nr_commits, - struct progress *progress, - uint64_t *progress_cnt) + struct write_commit_graph_context *ctx) { - struct commit **list = commits; - struct commit **last = commits + nr_commits; + struct commit **list = ctx->commits.list; + struct commit **last = ctx->commits.list + ctx->commits.nr; struct commit_list *parent; while (list < last) { int num_parents = 0; - display_progress(progress, ++*progress_cnt); + display_progress(ctx->progress, ++ctx->progress_cnt); for (parent = (*list)->parents; num_parents < 3 && parent; parent = parent->next) @@@ -675,8 -685,8 +692,8 @@@ /* Since num_parents > 2, this initializer is safe. */ for (parent = (*list)->parents->next; parent; parent = parent->next) { int edge_value = sha1_pos(parent->item->object.oid.hash, - commits, - nr_commits, + ctx->commits.list, + ctx->commits.nr, commit_to_sha1); if (edge_value < 0) @@@ -700,125 -710,111 +717,111 @@@ static int commit_compare(const void *_ return oidcmp(a, b); } - struct packed_commit_list { - struct commit **list; - int nr; - int alloc; - }; - - struct packed_oid_list { - struct object_id *list; - int nr; - int alloc; - struct progress *progress; - int progress_done; - }; - static int add_packed_commits(const struct object_id *oid, struct packed_git *pack, uint32_t pos, void *data) { - struct packed_oid_list *list = (struct packed_oid_list*)data; + struct write_commit_graph_context *ctx = (struct write_commit_graph_context*)data; enum object_type type; off_t offset = nth_packed_object_offset(pack, pos); struct object_info oi = OBJECT_INFO_INIT; - if (list->progress) - display_progress(list->progress, ++list->progress_done); + if (ctx->progress) + display_progress(ctx->progress, ++ctx->progress_done); oi.typep = &type; - if (packed_object_info(the_repository, pack, offset, &oi) < 0) + if (packed_object_info(ctx->r, pack, offset, &oi) < 0) die(_("unable to get type of object %s"), oid_to_hex(oid)); if (type != OBJ_COMMIT) return 0; - ALLOC_GROW(list->list, list->nr + 1, list->alloc); - oidcpy(&(list->list[list->nr]), oid); - list->nr++; + ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); + oidcpy(&(ctx->oids.list[ctx->oids.nr]), oid); + ctx->oids.nr++; return 0; } - static void add_missing_parents(struct packed_oid_list *oids, struct commit *commit) + static void add_missing_parents(struct write_commit_graph_context *ctx, struct commit *commit) { struct commit_list *parent; for (parent = commit->parents; parent; parent = parent->next) { if (!(parent->item->object.flags & UNINTERESTING)) { - ALLOC_GROW(oids->list, oids->nr + 1, oids->alloc); - oidcpy(&oids->list[oids->nr], &(parent->item->object.oid)); - oids->nr++; + ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); + oidcpy(&ctx->oids.list[ctx->oids.nr], &(parent->item->object.oid)); + ctx->oids.nr++; parent->item->object.flags |= UNINTERESTING; } } } - static void close_reachable(struct packed_oid_list *oids, int report_progress) + static void close_reachable(struct write_commit_graph_context *ctx) { int i; struct commit *commit; - struct progress *progress = NULL; - if (report_progress) - progress = start_delayed_progress( - _("Loading known commits in commit graph"), oids->nr); - for (i = 0; i < oids->nr; i++) { - display_progress(progress, i + 1); - commit = lookup_commit(the_repository, &oids->list[i]); + if (ctx->report_progress) + ctx->progress = start_delayed_progress( + _("Loading known commits in commit graph"), + ctx->oids.nr); + for (i = 0; i < ctx->oids.nr; i++) { + display_progress(ctx->progress, i + 1); + commit = lookup_commit(ctx->r, &ctx->oids.list[i]); if (commit) commit->object.flags |= UNINTERESTING; } - stop_progress(&progress); + stop_progress(&ctx->progress); /* - * As this loop runs, oids->nr may grow, but not more + * As this loop runs, ctx->oids.nr may grow, but not more * than the number of missing commits in the reachable * closure. */ - if (report_progress) - progress = start_delayed_progress( - _("Expanding reachable commits in commit graph"), oids->nr); - for (i = 0; i < oids->nr; i++) { - display_progress(progress, i + 1); - commit = lookup_commit(the_repository, &oids->list[i]); + if (ctx->report_progress) + ctx->progress = start_delayed_progress( + _("Expanding reachable commits in commit graph"), + ctx->oids.nr); + for (i = 0; i < ctx->oids.nr; i++) { + display_progress(ctx->progress, i + 1); + commit = lookup_commit(ctx->r, &ctx->oids.list[i]); if (commit && !parse_commit_no_graph(commit)) - add_missing_parents(oids, commit); + add_missing_parents(ctx, commit); } - stop_progress(&progress); + stop_progress(&ctx->progress); - if (report_progress) - progress = start_delayed_progress( - _("Clearing commit marks in commit graph"), oids->nr); - for (i = 0; i < oids->nr; i++) { - display_progress(progress, i + 1); - commit = lookup_commit(the_repository, &oids->list[i]); + if (ctx->report_progress) + ctx->progress = start_delayed_progress( + _("Clearing commit marks in commit graph"), + ctx->oids.nr); + for (i = 0; i < ctx->oids.nr; i++) { + display_progress(ctx->progress, i + 1); + commit = lookup_commit(ctx->r, &ctx->oids.list[i]); if (commit) commit->object.flags &= ~UNINTERESTING; } - stop_progress(&progress); + stop_progress(&ctx->progress); } - static void compute_generation_numbers(struct packed_commit_list* commits, - int report_progress) + static void compute_generation_numbers(struct write_commit_graph_context *ctx) { int i; struct commit_list *list = NULL; - struct progress *progress = NULL; - if (report_progress) - progress = start_progress( - _("Computing commit graph generation numbers"), - commits->nr); - for (i = 0; i < commits->nr; i++) { - display_progress(progress, i + 1); - if (commits->list[i]->generation != GENERATION_NUMBER_INFINITY && - commits->list[i]->generation != GENERATION_NUMBER_ZERO) + if (ctx->report_progress) + ctx->progress = start_progress( + _("Computing commit graph generation numbers"), + ctx->commits.nr); + for (i = 0; i < ctx->commits.nr; i++) { + display_progress(ctx->progress, i + 1); + if (ctx->commits.list[i]->generation != GENERATION_NUMBER_INFINITY && + ctx->commits.list[i]->generation != GENERATION_NUMBER_ZERO) continue; - commit_list_insert(commits->list[i], &list); + commit_list_insert(ctx->commits.list[i], &list); while (list) { struct commit *current = list->item; struct commit_list *parent; @@@ -845,7 -841,7 +848,7 @@@ } } } - stop_progress(&progress); + stop_progress(&ctx->progress); } static int add_ref_to_list(const char *refname, @@@ -858,207 -854,187 +861,187 @@@ return 0; } - void write_commit_graph_reachable(const char *obj_dir, int append, - int report_progress) + int write_commit_graph_reachable(const char *obj_dir, unsigned int flags) { struct string_list list = STRING_LIST_INIT_DUP; + int result; for_each_ref(add_ref_to_list, &list); - write_commit_graph(obj_dir, NULL, &list, append, report_progress); + result = write_commit_graph(obj_dir, NULL, &list, + flags); string_list_clear(&list, 0); + return result; } - void write_commit_graph(const char *obj_dir, - struct string_list *pack_indexes, - struct string_list *commit_hex, - int append, int report_progress) + static int fill_oids_from_packs(struct write_commit_graph_context *ctx, + struct string_list *pack_indexes) { - struct packed_oid_list oids; - struct packed_commit_list commits; - struct hashfile *f; - uint32_t i, count_distinct = 0; - char *graph_name; - struct lock_file lk = LOCK_INIT; - uint32_t chunk_ids[5]; - uint64_t chunk_offsets[5]; - int num_chunks; - int num_extra_edges; - struct commit_list *parent; - struct progress *progress = NULL; - const unsigned hashsz = the_hash_algo->rawsz; - uint64_t progress_cnt = 0; + uint32_t i; struct strbuf progress_title = STRBUF_INIT; - unsigned long approx_nr_objects; - - if (!commit_graph_compatible(the_repository)) - return; - - oids.nr = 0; - approx_nr_objects = approximate_object_count(); - oids.alloc = approx_nr_objects / 32; - oids.progress = NULL; - oids.progress_done = 0; + struct strbuf packname = STRBUF_INIT; + int dirlen; - if (append) { - prepare_commit_graph_one(the_repository, obj_dir); - if (the_repository->objects->commit_graph) - oids.alloc += the_repository->objects->commit_graph->num_commits; + strbuf_addf(&packname, "%s/pack/", ctx->obj_dir); + dirlen = packname.len; + if (ctx->report_progress) { + strbuf_addf(&progress_title, + Q_("Finding commits for commit graph in %d pack", + "Finding commits for commit graph in %d packs", + pack_indexes->nr), + pack_indexes->nr); + ctx->progress = start_delayed_progress(progress_title.buf, 0); + ctx->progress_done = 0; } - - if (oids.alloc < 1024) - oids.alloc = 1024; - ALLOC_ARRAY(oids.list, oids.alloc); - - if (append && the_repository->objects->commit_graph) { - struct commit_graph *commit_graph = - the_repository->objects->commit_graph; - for (i = 0; i < commit_graph->num_commits; i++) { - const unsigned char *hash = commit_graph->chunk_oid_lookup + - commit_graph->hash_len * i; - hashcpy(oids.list[oids.nr++].hash, hash); + for (i = 0; i < pack_indexes->nr; i++) { + struct packed_git *p; + strbuf_setlen(&packname, dirlen); + strbuf_addstr(&packname, pack_indexes->items[i].string); + p = add_packed_git(packname.buf, packname.len, 1); + if (!p) { + error(_("error adding pack %s"), packname.buf); + return -1; } + if (open_pack_index(p)) { + error(_("error opening index for %s"), packname.buf); + return -1; + } + for_each_object_in_pack(p, add_packed_commits, ctx, + FOR_EACH_OBJECT_PACK_ORDER); + close_pack(p); + free(p); } - if (pack_indexes) { - struct strbuf packname = STRBUF_INIT; - int dirlen; - strbuf_addf(&packname, "%s/pack/", obj_dir); - dirlen = packname.len; - if (report_progress) { - strbuf_addf(&progress_title, - Q_("Finding commits for commit graph in %d pack", - "Finding commits for commit graph in %d packs", - pack_indexes->nr), - pack_indexes->nr); - oids.progress = start_delayed_progress(progress_title.buf, 0); - oids.progress_done = 0; - } - for (i = 0; i < pack_indexes->nr; i++) { - struct packed_git *p; - strbuf_setlen(&packname, dirlen); - strbuf_addstr(&packname, pack_indexes->items[i].string); - p = add_packed_git(packname.buf, packname.len, 1); - if (!p) - die(_("error adding pack %s"), packname.buf); - if (open_pack_index(p)) - die(_("error opening index for %s"), packname.buf); - for_each_object_in_pack(p, add_packed_commits, &oids, - FOR_EACH_OBJECT_PACK_ORDER); - close_pack(p); - free(p); - } - stop_progress(&oids.progress); - strbuf_reset(&progress_title); - strbuf_release(&packname); + stop_progress(&ctx->progress); + strbuf_reset(&progress_title); + strbuf_release(&packname); + + return 0; + } + + static void fill_oids_from_commit_hex(struct write_commit_graph_context *ctx, + struct string_list *commit_hex) + { + uint32_t i; + struct strbuf progress_title = STRBUF_INIT; + + if (ctx->report_progress) { + strbuf_addf(&progress_title, + Q_("Finding commits for commit graph from %d ref", + "Finding commits for commit graph from %d refs", + commit_hex->nr), + commit_hex->nr); + ctx->progress = start_delayed_progress( + progress_title.buf, + commit_hex->nr); } + for (i = 0; i < commit_hex->nr; i++) { + const char *end; + struct object_id oid; + struct commit *result; + + display_progress(ctx->progress, i + 1); + if (commit_hex->items[i].string && + parse_oid_hex(commit_hex->items[i].string, &oid, &end)) + continue; - if (commit_hex) { - if (report_progress) { - strbuf_addf(&progress_title, - Q_("Finding commits for commit graph from %d ref", - "Finding commits for commit graph from %d refs", - commit_hex->nr), - commit_hex->nr); - progress = start_delayed_progress(progress_title.buf, - commit_hex->nr); - } - for (i = 0; i < commit_hex->nr; i++) { - const char *end; - struct object_id oid; - struct commit *result; - - display_progress(progress, i + 1); - if (commit_hex->items[i].string && - parse_oid_hex(commit_hex->items[i].string, &oid, &end)) - continue; - - result = lookup_commit_reference_gently(the_repository, &oid, 1); - - if (result) { - ALLOC_GROW(oids.list, oids.nr + 1, oids.alloc); - oidcpy(&oids.list[oids.nr], &(result->object.oid)); - oids.nr++; - } + result = lookup_commit_reference_gently(ctx->r, &oid, 1); + + if (result) { + ALLOC_GROW(ctx->oids.list, ctx->oids.nr + 1, ctx->oids.alloc); + oidcpy(&ctx->oids.list[ctx->oids.nr], &(result->object.oid)); + ctx->oids.nr++; } - stop_progress(&progress); - strbuf_reset(&progress_title); } + stop_progress(&ctx->progress); + strbuf_release(&progress_title); + } - if (!pack_indexes && !commit_hex) { - if (report_progress) - oids.progress = start_delayed_progress( - _("Finding commits for commit graph among packed objects"), - approx_nr_objects); - for_each_packed_object(add_packed_commits, &oids, - FOR_EACH_OBJECT_PACK_ORDER); - if (oids.progress_done < approx_nr_objects) - display_progress(oids.progress, approx_nr_objects); - stop_progress(&oids.progress); - } + static void fill_oids_from_all_packs(struct write_commit_graph_context *ctx) + { + if (ctx->report_progress) + ctx->progress = start_delayed_progress( + _("Finding commits for commit graph among packed objects"), + ctx->approx_nr_objects); + for_each_packed_object(add_packed_commits, ctx, + FOR_EACH_OBJECT_PACK_ORDER); + if (ctx->progress_done < ctx->approx_nr_objects) + display_progress(ctx->progress, ctx->approx_nr_objects); + stop_progress(&ctx->progress); + } - close_reachable(&oids, report_progress); + static uint32_t count_distinct_commits(struct write_commit_graph_context *ctx) + { + uint32_t i, count_distinct = 1; - if (report_progress) - progress = start_delayed_progress( + if (ctx->report_progress) + ctx->progress = start_delayed_progress( _("Counting distinct commits in commit graph"), - oids.nr); - display_progress(progress, 0); /* TODO: Measure QSORT() progress */ - QSORT(oids.list, oids.nr, commit_compare); - count_distinct = 1; - for (i = 1; i < oids.nr; i++) { - display_progress(progress, i + 1); - if (!oideq(&oids.list[i - 1], &oids.list[i])) + ctx->oids.nr); + display_progress(ctx->progress, 0); /* TODO: Measure QSORT() progress */ + QSORT(ctx->oids.list, ctx->oids.nr, commit_compare); + + for (i = 1; i < ctx->oids.nr; i++) { + display_progress(ctx->progress, i + 1); + if (!oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i])) count_distinct++; } - stop_progress(&progress); + stop_progress(&ctx->progress); - if (count_distinct >= GRAPH_EDGE_LAST_MASK) - die(_("the commit graph format cannot write %d commits"), count_distinct); + return count_distinct; + } - commits.nr = 0; - commits.alloc = count_distinct; - ALLOC_ARRAY(commits.list, commits.alloc); + static void copy_oids_to_commits(struct write_commit_graph_context *ctx) + { + uint32_t i; + struct commit_list *parent; - num_extra_edges = 0; - if (report_progress) - progress = start_delayed_progress( + ctx->num_extra_edges = 0; + if (ctx->report_progress) + ctx->progress = start_delayed_progress( _("Finding extra edges in commit graph"), - oids.nr); - for (i = 0; i < oids.nr; i++) { + ctx->oids.nr); + for (i = 0; i < ctx->oids.nr; i++) { int num_parents = 0; - display_progress(progress, i + 1); - if (i > 0 && oideq(&oids.list[i - 1], &oids.list[i])) + display_progress(ctx->progress, i + 1); + if (i > 0 && oideq(&ctx->oids.list[i - 1], &ctx->oids.list[i])) continue; - commits.list[commits.nr] = lookup_commit(the_repository, &oids.list[i]); - parse_commit_no_graph(commits.list[commits.nr]); + ctx->commits.list[ctx->commits.nr] = lookup_commit(ctx->r, &ctx->oids.list[i]); + parse_commit_no_graph(ctx->commits.list[ctx->commits.nr]); - for (parent = commits.list[commits.nr]->parents; + for (parent = ctx->commits.list[ctx->commits.nr]->parents; parent; parent = parent->next) num_parents++; if (num_parents > 2) - num_extra_edges += num_parents - 1; + ctx->num_extra_edges += num_parents - 1; - commits.nr++; + ctx->commits.nr++; } - num_chunks = num_extra_edges ? 4 : 3; - stop_progress(&progress); - - if (commits.nr >= GRAPH_EDGE_LAST_MASK) - die(_("too many commits to write graph")); - - compute_generation_numbers(&commits, report_progress); + stop_progress(&ctx->progress); + } - graph_name = get_commit_graph_filename(obj_dir); - if (safe_create_leading_directories(graph_name)) { - UNLEAK(graph_name); - die_errno(_("unable to create leading directories of %s"), - graph_name); + static int write_commit_graph_file(struct write_commit_graph_context *ctx) + { + uint32_t i; + struct hashfile *f; + struct lock_file lk = LOCK_INIT; + uint32_t chunk_ids[5]; + uint64_t chunk_offsets[5]; + const unsigned hashsz = the_hash_algo->rawsz; + struct strbuf progress_title = STRBUF_INIT; + int num_chunks = ctx->num_extra_edges ? 4 : 3; + + ctx->graph_name = get_commit_graph_filename(ctx->obj_dir); + if (safe_create_leading_directories(ctx->graph_name)) { + UNLEAK(ctx->graph_name); + error(_("unable to create leading directories of %s"), + ctx->graph_name); + return -1; } - hold_lock_file_for_update(&lk, graph_name, LOCK_DIE_ON_ERROR); + hold_lock_file_for_update(&lk, ctx->graph_name, LOCK_DIE_ON_ERROR); f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf); hashwrite_be32(f, GRAPH_SIGNATURE); @@@ -1071,7 -1047,7 +1054,7 @@@ chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT; chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP; chunk_ids[2] = GRAPH_CHUNKID_DATA; - if (num_extra_edges) + if (ctx->num_extra_edges) chunk_ids[3] = GRAPH_CHUNKID_EXTRAEDGES; else chunk_ids[3] = 0; @@@ -1079,9 -1055,9 +1062,9 @@@ chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH; chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE; - chunk_offsets[2] = chunk_offsets[1] + hashsz * commits.nr; - chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * commits.nr; - chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges; + chunk_offsets[2] = chunk_offsets[1] + hashsz * ctx->commits.nr; + chunk_offsets[3] = chunk_offsets[2] + (hashsz + 16) * ctx->commits.nr; + chunk_offsets[4] = chunk_offsets[3] + 4 * ctx->num_extra_edges; for (i = 0; i <= num_chunks; i++) { uint32_t chunk_write[3]; @@@ -1092,31 -1068,113 +1075,113 @@@ hashwrite(f, chunk_write, 12); } - if (report_progress) { + if (ctx->report_progress) { strbuf_addf(&progress_title, Q_("Writing out commit graph in %d pass", "Writing out commit graph in %d passes", num_chunks), num_chunks); - progress = start_delayed_progress( + ctx->progress = start_delayed_progress( progress_title.buf, - num_chunks * commits.nr); + num_chunks * ctx->commits.nr); } - write_graph_chunk_fanout(f, commits.list, commits.nr, progress, &progress_cnt); - write_graph_chunk_oids(f, hashsz, commits.list, commits.nr, progress, &progress_cnt); - write_graph_chunk_data(f, hashsz, commits.list, commits.nr, progress, &progress_cnt); - if (num_extra_edges) - write_graph_chunk_extra_edges(f, commits.list, commits.nr, progress, &progress_cnt); - stop_progress(&progress); + write_graph_chunk_fanout(f, ctx); + write_graph_chunk_oids(f, hashsz, ctx); + write_graph_chunk_data(f, hashsz, ctx); + if (ctx->num_extra_edges) + write_graph_chunk_extra_edges(f, ctx); + stop_progress(&ctx->progress); strbuf_release(&progress_title); - close_commit_graph(the_repository); + close_commit_graph(ctx->r); finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC); commit_lock_file(&lk); - free(graph_name); - free(commits.list); - free(oids.list); + return 0; + } + + int write_commit_graph(const char *obj_dir, + struct string_list *pack_indexes, + struct string_list *commit_hex, + unsigned int flags) + { + struct write_commit_graph_context *ctx; + uint32_t i, count_distinct = 0; + int res = 0; + + if (!commit_graph_compatible(the_repository)) + return 0; + + ctx = xcalloc(1, sizeof(struct write_commit_graph_context)); + ctx->r = the_repository; + ctx->obj_dir = obj_dir; + ctx->append = flags & COMMIT_GRAPH_APPEND ? 1 : 0; + ctx->report_progress = flags & COMMIT_GRAPH_PROGRESS ? 1 : 0; + + ctx->approx_nr_objects = approximate_object_count(); + ctx->oids.alloc = ctx->approx_nr_objects / 32; + + if (ctx->append) { + prepare_commit_graph_one(ctx->r, ctx->obj_dir); + if (ctx->r->objects->commit_graph) + ctx->oids.alloc += ctx->r->objects->commit_graph->num_commits; + } + + if (ctx->oids.alloc < 1024) + ctx->oids.alloc = 1024; + ALLOC_ARRAY(ctx->oids.list, ctx->oids.alloc); + + if (ctx->append && ctx->r->objects->commit_graph) { + struct commit_graph *g = ctx->r->objects->commit_graph; + for (i = 0; i < g->num_commits; i++) { + const unsigned char *hash = g->chunk_oid_lookup + g->hash_len * i; + hashcpy(ctx->oids.list[ctx->oids.nr++].hash, hash); + } + } + + if (pack_indexes) { + if ((res = fill_oids_from_packs(ctx, pack_indexes))) + goto cleanup; + } + + if (commit_hex) + fill_oids_from_commit_hex(ctx, commit_hex); + + if (!pack_indexes && !commit_hex) + fill_oids_from_all_packs(ctx); + + close_reachable(ctx); + + count_distinct = count_distinct_commits(ctx); + + if (count_distinct >= GRAPH_EDGE_LAST_MASK) { + error(_("the commit graph format cannot write %d commits"), count_distinct); + res = -1; + goto cleanup; + } + + ctx->commits.alloc = count_distinct; + ALLOC_ARRAY(ctx->commits.list, ctx->commits.alloc); + + copy_oids_to_commits(ctx); + + if (ctx->commits.nr >= GRAPH_EDGE_LAST_MASK) { + error(_("too many commits to write graph")); + res = -1; + goto cleanup; + } + + compute_generation_numbers(ctx); + + res = write_commit_graph_file(ctx); + + cleanup: + free(ctx->graph_name); + free(ctx->commits.list); + free(ctx->oids.list); + free(ctx); + + return res; } #define VERIFY_COMMIT_GRAPH_ERROR_HASH 2 diff --combined commit.c index 8fa1883c61,e4d1233226..26ce0770f6 --- a/commit.c +++ b/commit.c @@@ -340,21 -340,15 +340,21 @@@ void free_commit_buffer(struct parsed_o } } -struct tree *get_commit_tree(const struct commit *commit) +static inline void set_commit_tree(struct commit *c, struct tree *t) +{ + c->maybe_tree = t; +} + +struct tree *repo_get_commit_tree(struct repository *r, + const struct commit *commit) { if (commit->maybe_tree || !commit->object.parsed) return commit->maybe_tree; - if (commit->graph_pos == COMMIT_NOT_FROM_GRAPH) - BUG("commit has NULL tree, but was not loaded from commit-graph"); + if (commit->graph_pos != COMMIT_NOT_FROM_GRAPH) + return get_commit_tree_in_graph(r, commit); - return get_commit_tree_in_graph(the_repository, commit); + return NULL; } struct object_id *get_commit_tree_oid(const struct commit *commit) @@@ -364,7 -358,7 +364,7 @@@ void release_commit_memory(struct parsed_object_pool *pool, struct commit *c) { - c->maybe_tree = NULL; + set_commit_tree(c, NULL); c->index = 0; free_commit_buffer(pool, c); free_commit_list(c->parents); @@@ -412,7 -406,7 +412,7 @@@ int parse_commit_buffer(struct reposito if (get_oid_hex(bufptr + 5, &parent) < 0) return error("bad tree pointer in commit %s", oid_to_hex(&item->object.oid)); - item->maybe_tree = lookup_tree(r, &parent); + set_commit_tree(item, lookup_tree(r, &parent)); bufptr += tree_entry_len + 1; /* "tree " + "hex sha1" + "\n" */ pptr = &item->parents; @@@ -449,7 -443,7 +449,7 @@@ item->date = parse_commit_date(bufptr, tail); if (check_graph) - load_commit_graph_info(the_repository, item); + load_commit_graph_info(r, item); return 0; } diff --combined t/t5318-commit-graph.sh index 840ad4d8ac,3b6fd0d728..5267c4be20 --- a/t/t5318-commit-graph.sh +++ b/t/t5318-commit-graph.sh @@@ -23,6 -23,14 +23,14 @@@ test_expect_success 'write graph with n test_path_is_file info/commit-graph ' + test_expect_success 'close with correct error on bad input' ' + cd "$TRASH_DIRECTORY/full" && + echo doesnotexist >in && + { git commit-graph write --stdin-packs stderr; ret=$?; } && + test "$ret" = 1 && + test_i18ngrep "error adding pack" stderr + ' + test_expect_success 'create commits and repack' ' cd "$TRASH_DIRECTORY/full" && for i in $(test_seq 3) @@@ -75,7 -83,7 +83,7 @@@ graph_read_expect() test_expect_success 'write graph' ' cd "$TRASH_DIRECTORY/full" && - graph1=$(git commit-graph write) && + git commit-graph write && test_path_is_file $objdir/info/commit-graph && graph_read_expect "3" ' @@@ -400,7 -408,7 +408,7 @@@ corrupt_graph_and_verify() orig_size=$(wc -c < $objdir/info/commit-graph) && zero_pos=${4:-${orig_size}} && printf "$data" | dd of="$objdir/info/commit-graph" bs=1 seek="$pos" conv=notrunc && - dd of="$objdir/info/commit-graph" bs=1 seek="$zero_pos" count=0 && + dd of="$objdir/info/commit-graph" bs=1 seek="$zero_pos" if=/dev/null && generate_zero_bytes $(($orig_size - $zero_pos)) >>"$objdir/info/commit-graph" && corrupt_graph_verify "$grepstr"