diff options
Diffstat (limited to 'builtin/repack.c')
| -rw-r--r-- | builtin/repack.c | 422 |
1 files changed, 319 insertions, 103 deletions
diff --git a/builtin/repack.c b/builtin/repack.c index d1a563d5b6..c1402ad038 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -18,6 +18,14 @@ #include "pack-bitmap.h" #include "refs.h" +#define ALL_INTO_ONE 1 +#define LOOSEN_UNREACHABLE 2 +#define PACK_CRUFT 4 + +#define DELETE_PACK 1 +#define CRUFT_PACK 2 + +static int pack_everything; static int delta_base_offset = 1; static int pack_kept_objects = -1; static int write_bitmaps = -1; @@ -32,12 +40,24 @@ static const char *const git_repack_usage[] = { static const char incremental_bitmap_conflict_error[] = N_( "Incremental repacks are incompatible with bitmap indexes. Use\n" -"--no-write-bitmap-index or disable the pack.writebitmaps configuration." +"--no-write-bitmap-index or disable the pack.writeBitmaps configuration." ); +struct pack_objects_args { + const char *window; + const char *window_memory; + const char *depth; + const char *threads; + const char *max_pack_size; + int no_reuse_delta; + int no_reuse_object; + int quiet; + int local; +}; static int repack_config(const char *var, const char *value, void *cb) { + struct pack_objects_args *cruft_po_args = cb; if (!strcmp(var, "repack.usedeltabaseoffset")) { delta_base_offset = git_config_bool(var, value); return 0; @@ -59,48 +79,18 @@ static int repack_config(const char *var, const char *value, void *cb) run_update_server_info = git_config_bool(var, value); return 0; } + if (!strcmp(var, "repack.cruftwindow")) + return git_config_string(&cruft_po_args->window, var, value); + if (!strcmp(var, "repack.cruftwindowmemory")) + return git_config_string(&cruft_po_args->window_memory, var, value); + if (!strcmp(var, "repack.cruftdepth")) + return git_config_string(&cruft_po_args->depth, var, value); + if (!strcmp(var, "repack.cruftthreads")) + return git_config_string(&cruft_po_args->threads, var, value); return git_default_config(var, value, cb); } /* - * Remove temporary $GIT_OBJECT_DIRECTORY/pack/.tmp-$$-pack-* files. - */ -static void remove_temporary_files(void) -{ - struct strbuf buf = STRBUF_INIT; - size_t dirlen, prefixlen; - DIR *dir; - struct dirent *e; - - dir = opendir(packdir); - if (!dir) - return; - - /* Point at the slash at the end of ".../objects/pack/" */ - dirlen = strlen(packdir) + 1; - strbuf_addstr(&buf, packtmp); - /* Hold the length of ".tmp-%d-pack-" */ - prefixlen = buf.len - dirlen; - - while ((e = readdir(dir))) { - if (strncmp(e->d_name, buf.buf + dirlen, prefixlen)) - continue; - strbuf_setlen(&buf, dirlen); - strbuf_addstr(&buf, e->d_name); - unlink(buf.buf); - } - closedir(dir); - strbuf_release(&buf); -} - -static void remove_pack_on_signal(int signo) -{ - remove_temporary_files(); - sigchain_pop(signo); - raise(signo); -} - -/* * Adds all packs hex strings to either fname_nonkept_list or * fname_kept_list based on whether each pack has a corresponding * .keep file or not. Packs without a .keep file are not to be kept @@ -131,12 +121,19 @@ static void collect_pack_filenames(struct string_list *fname_nonkept_list, fname = xmemdupz(e->d_name, len); if ((extra_keep->nr > 0 && i < extra_keep->nr) || - (file_exists(mkpath("%s/%s.keep", packdir, fname)))) + (file_exists(mkpath("%s/%s.keep", packdir, fname)))) { string_list_append_nodup(fname_kept_list, fname); - else - string_list_append_nodup(fname_nonkept_list, fname); + } else { + struct string_list_item *item; + item = string_list_append_nodup(fname_nonkept_list, + fname); + if (file_exists(mkpath("%s/%s.mtimes", packdir, fname))) + item->util = (void*)(uintptr_t)CRUFT_PACK; + } } closedir(dir); + + string_list_sort(fname_kept_list); } static void remove_redundant_pack(const char *dir_name, const char *base_name) @@ -151,20 +148,9 @@ static void remove_redundant_pack(const char *dir_name, const char *base_name) strbuf_release(&buf); } -struct pack_objects_args { - const char *window; - const char *window_memory; - const char *depth; - const char *threads; - const char *max_pack_size; - int no_reuse_delta; - int no_reuse_object; - int quiet; - int local; -}; - static void prepare_pack_objects(struct child_process *cmd, - const struct pack_objects_args *args) + const struct pack_objects_args *args, + const char *out) { strvec_push(&cmd->args, "pack-objects"); if (args->window) @@ -187,7 +173,7 @@ static void prepare_pack_objects(struct child_process *cmd, strvec_push(&cmd->args, "--quiet"); if (delta_base_offset) strvec_push(&cmd->args, "--delta-base-offset"); - strvec_push(&cmd->args, packtmp); + strvec_push(&cmd->args, out); cmd->git_cmd = 1; cmd->out = -1; } @@ -217,16 +203,21 @@ static struct { } exts[] = { {".pack"}, {".rev", 1}, + {".mtimes", 1}, {".bitmap", 1}, {".promisor", 1}, {".idx"}, }; -static unsigned populate_pack_exts(char *name) +struct generated_pack_data { + struct tempfile *tempfiles[ARRAY_SIZE(exts)]; +}; + +static struct generated_pack_data *populate_pack_exts(const char *name) { struct stat statbuf; struct strbuf path = STRBUF_INIT; - unsigned ret = 0; + struct generated_pack_data *data = xcalloc(1, sizeof(*data)); int i; for (i = 0; i < ARRAY_SIZE(exts); i++) { @@ -236,11 +227,11 @@ static unsigned populate_pack_exts(char *name) if (stat(path.buf, &statbuf)) continue; - ret |= (1 << i); + data->tempfiles[i] = register_tempfile(path.buf); } strbuf_release(&path); - return ret; + return data; } static void repack_promisor_objects(const struct pack_objects_args *args, @@ -250,7 +241,7 @@ static void repack_promisor_objects(const struct pack_objects_args *args, FILE *out; struct strbuf line = STRBUF_INIT; - prepare_pack_objects(&cmd, args); + prepare_pack_objects(&cmd, args, packtmp); cmd.in = -1; /* @@ -295,7 +286,7 @@ static void repack_promisor_objects(const struct pack_objects_args *args, line.buf); write_promisor_file(promisor_name, NULL, 0); - item->util = (void *)(uintptr_t)populate_pack_exts(item->string); + item->util = populate_pack_exts(item->string); free(promisor_name); } @@ -304,9 +295,6 @@ static void repack_promisor_objects(const struct pack_objects_args *args, die(_("could not finish pack-objects to repack promisor objects")); } -#define ALL_INTO_ONE 1 -#define LOOSEN_UNREACHABLE 2 - struct pack_geometry { struct packed_git **pack; uint32_t pack_nr, pack_alloc; @@ -332,16 +320,39 @@ static int geometry_cmp(const void *va, const void *vb) return 0; } -static void init_pack_geometry(struct pack_geometry **geometry_p) +static void init_pack_geometry(struct pack_geometry **geometry_p, + struct string_list *existing_kept_packs) { struct packed_git *p; struct pack_geometry *geometry; + struct strbuf buf = STRBUF_INIT; *geometry_p = xcalloc(1, sizeof(struct pack_geometry)); geometry = *geometry_p; for (p = get_all_packs(the_repository); p; p = p->next) { - if (!pack_kept_objects && p->pack_keep) + if (!pack_kept_objects) { + /* + * Any pack that has its pack_keep bit set will appear + * in existing_kept_packs below, but this saves us from + * doing a more expensive check. + */ + if (p->pack_keep) + continue; + + /* + * The pack may be kept via the --keep-pack option; + * check 'existing_kept_packs' to determine whether to + * ignore it. + */ + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + if (string_list_has_string(existing_kept_packs, buf.buf)) + continue; + } + if (p->is_cruft) continue; ALLOC_GROW(geometry->pack, @@ -353,6 +364,7 @@ static void init_pack_geometry(struct pack_geometry **geometry_p) } QSORT(geometry->pack, geometry->pack_nr, geometry_cmp); + strbuf_release(&buf); } static void split_pack_geometry(struct pack_geometry *geometry, int factor) @@ -468,9 +480,9 @@ struct midx_snapshot_ref_data { int preferred; }; -static int midx_snapshot_ref_one(const char *refname, +static int midx_snapshot_ref_one(const char *refname UNUSED, const struct object_id *oid, - int flag, void *_data) + int flag UNUSED, void *_data) { struct midx_snapshot_ref_data *data = _data; struct object_id peeled; @@ -548,9 +560,20 @@ static void midx_included_packs(struct string_list *include, string_list_insert(include, strbuf_detach(&buf, NULL)); } + + for_each_string_list_item(item, existing_nonkept_packs) { + if (!((uintptr_t)item->util & CRUFT_PACK)) { + /* + * no need to check DELETE_PACK, since we're not + * doing an ALL_INTO_ONE repack + */ + continue; + } + string_list_insert(include, xstrfmt("%s.idx", item->string)); + } } else { for_each_string_list_item(item, existing_nonkept_packs) { - if (item->util) + if ((uintptr_t)item->util & DELETE_PACK) continue; string_list_insert(include, xstrfmt("%s.idx", item->string)); } @@ -604,12 +627,118 @@ static int write_midx_included_packs(struct string_list *include, return finish_command(&cmd); } +static void remove_redundant_bitmaps(struct string_list *include, + const char *packdir) +{ + struct strbuf path = STRBUF_INIT; + struct string_list_item *item; + size_t packdir_len; + + strbuf_addstr(&path, packdir); + strbuf_addch(&path, '/'); + packdir_len = path.len; + + /* + * Remove any pack bitmaps corresponding to packs which are now + * included in the MIDX. + */ + for_each_string_list_item(item, include) { + strbuf_addstr(&path, item->string); + strbuf_strip_suffix(&path, ".idx"); + strbuf_addstr(&path, ".bitmap"); + + if (unlink(path.buf) && errno != ENOENT) + warning_errno(_("could not remove stale bitmap: %s"), + path.buf); + + strbuf_setlen(&path, packdir_len); + } + strbuf_release(&path); +} + +static int write_cruft_pack(const struct pack_objects_args *args, + const char *destination, + const char *pack_prefix, + const char *cruft_expiration, + struct string_list *names, + struct string_list *existing_packs, + struct string_list *existing_kept_packs) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + struct strbuf line = STRBUF_INIT; + struct string_list_item *item; + FILE *in, *out; + int ret; + const char *scratch; + int local = skip_prefix(destination, packdir, &scratch); + + prepare_pack_objects(&cmd, args, destination); + + strvec_push(&cmd.args, "--cruft"); + if (cruft_expiration) + strvec_pushf(&cmd.args, "--cruft-expiration=%s", + cruft_expiration); + + strvec_push(&cmd.args, "--honor-pack-keep"); + strvec_push(&cmd.args, "--non-empty"); + strvec_push(&cmd.args, "--max-pack-size=0"); + + cmd.in = -1; + + ret = start_command(&cmd); + if (ret) + return ret; + + /* + * names has a confusing double use: it both provides the list + * of just-written new packs, and accepts the name of the cruft + * pack we are writing. + * + * By the time it is read here, it contains only the pack(s) + * that were just written, which is exactly the set of packs we + * want to consider kept. + * + * If `--expire-to` is given, the double-use served by `names` + * ensures that the pack written to `--expire-to` excludes any + * objects contained in the cruft pack. + */ + in = xfdopen(cmd.in, "w"); + for_each_string_list_item(item, names) + fprintf(in, "%s-%s.pack\n", pack_prefix, item->string); + for_each_string_list_item(item, existing_packs) + fprintf(in, "-%s.pack\n", item->string); + for_each_string_list_item(item, existing_kept_packs) + fprintf(in, "%s.pack\n", item->string); + fclose(in); + + out = xfdopen(cmd.out, "r"); + while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; + + if (line.len != the_hash_algo->hexsz) + die(_("repack: Expecting full hex object ID lines only " + "from pack-objects.")); + /* + * avoid putting packs written outside of the repository in the + * list of names + */ + if (local) { + item = string_list_append(names, line.buf); + item->util = populate_pack_exts(line.buf); + } + } + fclose(out); + + strbuf_release(&line); + + return finish_command(&cmd); +} + int cmd_repack(int argc, const char **argv, const char *prefix) { struct child_process cmd = CHILD_PROCESS_INIT; struct string_list_item *item; struct string_list names = STRING_LIST_INIT_DUP; - struct string_list rollback = STRING_LIST_INIT_NODUP; struct string_list existing_nonkept_packs = STRING_LIST_INIT_DUP; struct string_list existing_kept_packs = STRING_LIST_INIT_DUP; struct pack_geometry *geometry = NULL; @@ -620,14 +749,16 @@ int cmd_repack(int argc, const char **argv, const char *prefix) int show_progress; /* variables to be filled by option parsing */ - int pack_everything = 0; int delete_redundant = 0; const char *unpack_unreachable = NULL; int keep_unreachable = 0; struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; struct pack_objects_args po_args = {NULL}; + struct pack_objects_args cruft_po_args = {NULL}; int geometric_factor = 0; int write_midx = 0; + const char *cruft_expiration = NULL; + const char *expire_to = NULL; struct option builtin_repack_options[] = { OPT_BIT('a', NULL, &pack_everything, @@ -635,6 +766,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix) OPT_BIT('A', NULL, &pack_everything, N_("same as -a, and turn unreachable objects loose"), LOOSEN_UNREACHABLE | ALL_INTO_ONE), + OPT_BIT(0, "cruft", &pack_everything, + N_("same as -a, pack unreachable cruft objects separately"), + PACK_CRUFT), + OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"), + N_("with -C, expire objects older than this")), OPT_BOOL('d', NULL, &delete_redundant, N_("remove redundant packs, and run git-prune-packed")), OPT_BOOL('f', NULL, &po_args.no_reuse_delta, @@ -672,10 +808,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix) N_("find a geometric progression with factor <N>")), OPT_BOOL('m', "write-midx", &write_midx, N_("write a multi-pack index of the resulting packs")), + OPT_STRING(0, "expire-to", &expire_to, N_("dir"), + N_("pack prefix to store a pack containing pruned objects")), OPT_END() }; - git_config(repack_config, NULL); + git_config(repack_config, &cruft_po_args); argc = parse_options(argc, argv, prefix, builtin_repack_options, git_repack_usage, 0); @@ -687,6 +825,15 @@ int cmd_repack(int argc, const char **argv, const char *prefix) (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE))) die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "-A"); + if (pack_everything & PACK_CRUFT) { + pack_everything |= ALL_INTO_ONE; + + if (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)) + die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-A"); + if (keep_unreachable) + die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-k"); + } + if (write_bitmaps < 0) { if (!write_midx && (!(pack_everything & ALL_INTO_ONE) || !is_bare_repository())) @@ -714,20 +861,21 @@ int cmd_repack(int argc, const char **argv, const char *prefix) strbuf_release(&path); } + packdir = mkpathdup("%s/pack", get_object_directory()); + packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid()); + packtmp = mkpathdup("%s/%s", packdir, packtmp_name); + + collect_pack_filenames(&existing_nonkept_packs, &existing_kept_packs, + &keep_pack_list); + if (geometric_factor) { if (pack_everything) die(_("options '%s' and '%s' cannot be used together"), "--geometric", "-A/-a"); - init_pack_geometry(&geometry); + init_pack_geometry(&geometry, &existing_kept_packs); split_pack_geometry(geometry, geometric_factor); } - packdir = mkpathdup("%s/pack", get_object_directory()); - packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid()); - packtmp = mkpathdup("%s/%s", packdir, packtmp_name); - - sigchain_push_common(remove_pack_on_signal); - - prepare_pack_objects(&cmd, &po_args); + prepare_pack_objects(&cmd, &po_args, packtmp); show_progress = !po_args.quiet && isatty(2); @@ -764,13 +912,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (use_delta_islands) strvec_push(&cmd.args, "--delta-islands"); - collect_pack_filenames(&existing_nonkept_packs, &existing_kept_packs, - &keep_pack_list); - if (pack_everything & ALL_INTO_ONE) { repack_promisor_objects(&po_args, &names); - if (existing_nonkept_packs.nr && delete_redundant) { + if (existing_nonkept_packs.nr && delete_redundant && + !(pack_everything & PACK_CRUFT)) { for_each_string_list_item(item, &names) { strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack", packtmp_name, item->string); @@ -820,10 +966,14 @@ int cmd_repack(int argc, const char **argv, const char *prefix) out = xfdopen(cmd.out, "r"); while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; + if (line.len != the_hash_algo->hexsz) die(_("repack: Expecting full hex object ID lines only from pack-objects.")); - string_list_append(&names, line.buf); + item = string_list_append(&names, line.buf); + item->util = populate_pack_exts(item->string); } + strbuf_release(&line); fclose(out); ret = finish_command(&cmd); if (ret) @@ -832,47 +982,107 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (!names.nr && !po_args.quiet) printf_ln(_("Nothing new to pack.")); - for_each_string_list_item(item, &names) { - item->util = (void *)(uintptr_t)populate_pack_exts(item->string); + if (pack_everything & PACK_CRUFT) { + const char *pack_prefix; + if (!skip_prefix(packtmp, packdir, &pack_prefix)) + die(_("pack prefix %s does not begin with objdir %s"), + packtmp, packdir); + if (*pack_prefix == '/') + pack_prefix++; + + if (!cruft_po_args.window) + cruft_po_args.window = po_args.window; + if (!cruft_po_args.window_memory) + cruft_po_args.window_memory = po_args.window_memory; + if (!cruft_po_args.depth) + cruft_po_args.depth = po_args.depth; + if (!cruft_po_args.threads) + cruft_po_args.threads = po_args.threads; + + cruft_po_args.local = po_args.local; + cruft_po_args.quiet = po_args.quiet; + + ret = write_cruft_pack(&cruft_po_args, packtmp, pack_prefix, + cruft_expiration, &names, + &existing_nonkept_packs, + &existing_kept_packs); + if (ret) + return ret; + + if (delete_redundant && expire_to) { + /* + * If `--expire-to` is given with `-d`, it's possible + * that we're about to prune some objects. With cruft + * packs, pruning is implicit: any objects from existing + * packs that weren't picked up by new packs are removed + * when their packs are deleted. + * + * Generate an additional cruft pack, with one twist: + * `names` now includes the name of the cruft pack + * written in the previous step. So the contents of + * _this_ cruft pack exclude everything contained in the + * existing cruft pack (that is, all of the unreachable + * objects which are no older than + * `--cruft-expiration`). + * + * To make this work, cruft_expiration must become NULL + * so that this cruft pack doesn't actually prune any + * objects. If it were non-NULL, this call would always + * generate an empty pack (since every object not in the + * cruft pack generated above will have an mtime older + * than the expiration). + */ + ret = write_cruft_pack(&cruft_po_args, expire_to, + pack_prefix, + NULL, + &names, + &existing_nonkept_packs, + &existing_kept_packs); + if (ret) + return ret; + } } + string_list_sort(&names); + close_object_store(the_repository->objects); /* * Ok we have prepared all new packfiles. */ for_each_string_list_item(item, &names) { + struct generated_pack_data *data = item->util; + for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { - char *fname, *fname_old; + char *fname; fname = mkpathdup("%s/pack-%s%s", packdir, item->string, exts[ext].name); - fname_old = mkpathdup("%s-%s%s", - packtmp, item->string, exts[ext].name); - if (((uintptr_t)item->util) & ((uintptr_t)1 << ext)) { + if (data->tempfiles[ext]) { + const char *fname_old = get_tempfile_path(data->tempfiles[ext]); struct stat statbuffer; + if (!stat(fname_old, &statbuffer)) { statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); chmod(fname_old, statbuffer.st_mode); } - if (rename(fname_old, fname)) - die_errno(_("renaming '%s' failed"), fname_old); + if (rename_tempfile(&data->tempfiles[ext], fname)) + die_errno(_("renaming pack to '%s' failed"), fname); } else if (!exts[ext].optional) - die(_("missing required file: %s"), fname_old); + die(_("pack-objects did not write a '%s' file for pack %s-%s"), + exts[ext].name, packtmp, item->string); else if (unlink(fname) < 0 && errno != ENOENT) die_errno(_("could not unlink: %s"), fname); free(fname); - free(fname_old); } } /* End of pack replacement. */ if (delete_redundant && pack_everything & ALL_INTO_ONE) { const int hexsz = the_hash_algo->hexsz; - string_list_sort(&names); for_each_string_list_item(item, &existing_nonkept_packs) { char *sha1; size_t len = strlen(item->string); @@ -885,7 +1095,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) * was given) and that we will actually delete this pack * (if `-d` was given). */ - item->util = (void*)(intptr_t)!string_list_has_string(&names, sha1); + if (!string_list_has_string(&names, sha1)) + item->util = (void*)(uintptr_t)((size_t)item->util | DELETE_PACK); } } @@ -898,6 +1109,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix) refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL, show_progress, write_bitmaps > 0); + if (!ret && write_bitmaps) + remove_redundant_bitmaps(&include, packdir); + string_list_clear(&include, 0); if (ret) @@ -909,7 +1123,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (delete_redundant) { int opts = 0; for_each_string_list_item(item, &existing_nonkept_packs) { - if (!item->util) + if (!((uintptr_t)item->util & DELETE_PACK)) continue; remove_redundant_pack(packdir, item->string); } @@ -928,6 +1142,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix) strbuf_addstr(&buf, pack_basename(p)); strbuf_strip_suffix(&buf, ".pack"); + if ((p->pack_keep) || + (string_list_has_string(&existing_kept_packs, + buf.buf))) + continue; + remove_redundant_pack(packdir, buf.buf); } strbuf_release(&buf); @@ -945,7 +1164,6 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (run_update_server_info) update_server_info(0); - remove_temporary_files(); if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) { unsigned flags = 0; @@ -954,12 +1172,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix) write_midx_file(get_object_directory(), NULL, NULL, flags); } - string_list_clear(&names, 0); - string_list_clear(&rollback, 0); + string_list_clear(&names, 1); string_list_clear(&existing_nonkept_packs, 0); string_list_clear(&existing_kept_packs, 0); clear_pack_geometry(geometry); - strbuf_release(&line); return 0; } |
