diff options
Diffstat (limited to 'builtin/repack.c')
-rw-r--r-- | builtin/repack.c | 940 |
1 files changed, 673 insertions, 267 deletions
diff --git a/builtin/repack.c b/builtin/repack.c index a5bacc7797..ede36328a3 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -1,29 +1,33 @@ #include "builtin.h" -#include "cache.h" #include "config.h" #include "dir.h" +#include "environment.h" +#include "gettext.h" +#include "hex.h" #include "parse-options.h" +#include "path.h" #include "run-command.h" -#include "sigchain.h" +#include "server-info.h" #include "strbuf.h" #include "string-list.h" #include "strvec.h" #include "midx.h" #include "packfile.h" #include "prune-packed.h" -#include "object-store.h" +#include "object-store-ll.h" #include "promisor-remote.h" #include "shallow.h" #include "pack.h" #include "pack-bitmap.h" #include "refs.h" +#include "list-objects-filter-options.h" #define ALL_INTO_ONE 1 #define LOOSEN_UNREACHABLE 2 #define PACK_CRUFT 4 #define DELETE_PACK 1 -#define CRUFT_PACK 2 +#define RETAIN_PACK 2 static int pack_everything; static int delta_base_offset = 1; @@ -32,7 +36,6 @@ static int write_bitmaps = -1; static int use_delta_islands; static int run_update_server_info = 1; static char *packdir, *packtmp_name, *packtmp; -static char *cruft_expiration; static const char *const git_repack_usage[] = { N_("git repack [<options>]"), @@ -49,14 +52,16 @@ struct pack_objects_args { const char *window_memory; const char *depth; const char *threads; - const char *max_pack_size; + unsigned long max_pack_size; int no_reuse_delta; int no_reuse_object; int quiet; int local; + struct list_objects_filter_options filter_options; }; -static int repack_config(const char *var, const char *value, void *cb) +static int repack_config(const char *var, const char *value, + const struct config_context *ctx, void *cb) { struct pack_objects_args *cruft_po_args = cb; if (!strcmp(var, "repack.usedeltabaseoffset")) { @@ -88,107 +93,185 @@ static int repack_config(const char *var, const char *value, void *cb) 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); + return git_default_config(var, value, ctx, cb); } -/* - * Remove temporary $GIT_OBJECT_DIRECTORY/pack/.tmp-$$-pack-* files. - */ -static void remove_temporary_files(void) +struct existing_packs { + struct string_list kept_packs; + struct string_list non_kept_packs; + struct string_list cruft_packs; +}; + +#define EXISTING_PACKS_INIT { \ + .kept_packs = STRING_LIST_INIT_DUP, \ + .non_kept_packs = STRING_LIST_INIT_DUP, \ + .cruft_packs = STRING_LIST_INIT_DUP, \ +} + +static int has_existing_non_kept_packs(const struct existing_packs *existing) { - struct strbuf buf = STRBUF_INIT; - size_t dirlen, prefixlen; - DIR *dir; - struct dirent *e; + return existing->non_kept_packs.nr || existing->cruft_packs.nr; +} - dir = opendir(packdir); - if (!dir) - return; +static void pack_mark_for_deletion(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util | DELETE_PACK); +} + +static void pack_unmark_for_deletion(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK); +} + +static int pack_is_marked_for_deletion(struct string_list_item *item) +{ + return (uintptr_t)item->util & DELETE_PACK; +} - /* 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; +static void pack_mark_retained(struct string_list_item *item) +{ + item->util = (void*)((uintptr_t)item->util | RETAIN_PACK); +} - while ((e = readdir(dir))) { - if (strncmp(e->d_name, buf.buf + dirlen, prefixlen)) +static int pack_is_retained(struct string_list_item *item) +{ + return (uintptr_t)item->util & RETAIN_PACK; +} + +static void mark_packs_for_deletion_1(struct string_list *names, + struct string_list *list) +{ + struct string_list_item *item; + const int hexsz = the_hash_algo->hexsz; + + for_each_string_list_item(item, list) { + char *sha1; + size_t len = strlen(item->string); + if (len < hexsz) continue; - strbuf_setlen(&buf, dirlen); - strbuf_addstr(&buf, e->d_name); - unlink(buf.buf); + sha1 = item->string + len - hexsz; + + if (pack_is_retained(item)) { + pack_unmark_for_deletion(item); + } else if (!string_list_has_string(names, sha1)) { + /* + * Mark this pack for deletion, which ensures + * that this pack won't be included in a MIDX + * (if `--write-midx` was given) and that we + * will actually delete this pack (if `-d` was + * given). + */ + pack_mark_for_deletion(item); + } } - closedir(dir); +} + +static void retain_cruft_pack(struct existing_packs *existing, + struct packed_git *cruft) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list_item *item; + + strbuf_addstr(&buf, pack_basename(cruft)); + strbuf_strip_suffix(&buf, ".pack"); + + item = string_list_lookup(&existing->cruft_packs, buf.buf); + if (!item) + BUG("could not find cruft pack '%s'", pack_basename(cruft)); + + pack_mark_retained(item); strbuf_release(&buf); } -static void remove_pack_on_signal(int signo) +static void mark_packs_for_deletion(struct existing_packs *existing, + struct string_list *names) + { - remove_temporary_files(); - sigchain_pop(signo); - raise(signo); + mark_packs_for_deletion_1(names, &existing->non_kept_packs); + mark_packs_for_deletion_1(names, &existing->cruft_packs); +} + +static void remove_redundant_pack(const char *dir_name, const char *base_name) +{ + struct strbuf buf = STRBUF_INIT; + struct multi_pack_index *m = get_local_multi_pack_index(the_repository); + strbuf_addf(&buf, "%s.pack", base_name); + if (m && midx_contains_pack(m, buf.buf)) + clear_midx_file(the_repository); + strbuf_insertf(&buf, 0, "%s/", dir_name); + unlink_pack_path(buf.buf, 1); + strbuf_release(&buf); +} + +static void remove_redundant_packs_1(struct string_list *packs) +{ + struct string_list_item *item; + for_each_string_list_item(item, packs) { + if (!pack_is_marked_for_deletion(item)) + continue; + remove_redundant_pack(packdir, item->string); + } +} + +static void remove_redundant_existing_packs(struct existing_packs *existing) +{ + remove_redundant_packs_1(&existing->non_kept_packs); + remove_redundant_packs_1(&existing->cruft_packs); +} + +static void existing_packs_release(struct existing_packs *existing) +{ + string_list_clear(&existing->kept_packs, 0); + string_list_clear(&existing->non_kept_packs, 0); + string_list_clear(&existing->cruft_packs, 0); } /* - * Adds all packs hex strings to either fname_nonkept_list or - * fname_kept_list based on whether each pack has a corresponding + * Adds all packs hex strings (pack-$HASH) to either packs->non_kept + * or packs->kept based on whether each pack has a corresponding * .keep file or not. Packs without a .keep file are not to be kept * if we are going to pack everything into one file. */ -static void collect_pack_filenames(struct string_list *fname_nonkept_list, - struct string_list *fname_kept_list, +static void collect_pack_filenames(struct existing_packs *existing, const struct string_list *extra_keep) { - DIR *dir; - struct dirent *e; - char *fname; - - if (!(dir = opendir(packdir))) - return; + struct packed_git *p; + struct strbuf buf = STRBUF_INIT; - while ((e = readdir(dir)) != NULL) { - size_t len; + for (p = get_all_packs(the_repository); p; p = p->next) { int i; + const char *base; - if (!strip_suffix(e->d_name, ".pack", &len)) + if (!p->pack_local) continue; + base = pack_basename(p); + for (i = 0; i < extra_keep->nr; i++) - if (!fspathcmp(e->d_name, extra_keep->items[i].string)) + if (!fspathcmp(base, extra_keep->items[i].string)) break; - fname = xmemdupz(e->d_name, len); + strbuf_reset(&buf); + strbuf_addstr(&buf, base); + strbuf_strip_suffix(&buf, ".pack"); - if ((extra_keep->nr > 0 && i < extra_keep->nr) || - (file_exists(mkpath("%s/%s.keep", packdir, fname)))) { - string_list_append_nodup(fname_kept_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; - } + if ((extra_keep->nr > 0 && i < extra_keep->nr) || p->pack_keep) + string_list_append(&existing->kept_packs, buf.buf); + else if (p->is_cruft) + string_list_append(&existing->cruft_packs, buf.buf); + else + string_list_append(&existing->non_kept_packs, buf.buf); } - closedir(dir); - - string_list_sort(fname_kept_list); -} -static void remove_redundant_pack(const char *dir_name, const char *base_name) -{ - struct strbuf buf = STRBUF_INIT; - struct multi_pack_index *m = get_local_multi_pack_index(the_repository); - strbuf_addf(&buf, "%s.pack", base_name); - if (m && midx_contains_pack(m, buf.buf)) - clear_midx_file(the_repository); - strbuf_insertf(&buf, 0, "%s/", dir_name); - unlink_pack_path(buf.buf, 1); + string_list_sort(&existing->kept_packs); + string_list_sort(&existing->non_kept_packs); + string_list_sort(&existing->cruft_packs); strbuf_release(&buf); } 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) @@ -200,7 +283,7 @@ static void prepare_pack_objects(struct child_process *cmd, if (args->threads) strvec_pushf(&cmd->args, "--threads=%s", args->threads); if (args->max_pack_size) - strvec_pushf(&cmd->args, "--max-pack-size=%s", args->max_pack_size); + strvec_pushf(&cmd->args, "--max-pack-size=%lu", args->max_pack_size); if (args->no_reuse_delta) strvec_pushf(&cmd->args, "--no-reuse-delta"); if (args->no_reuse_object) @@ -211,7 +294,7 @@ 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; } @@ -220,8 +303,9 @@ static void prepare_pack_objects(struct child_process *cmd, * Write oid to the given struct child_process's stdin, starting it first if * necessary. */ -static int write_oid(const struct object_id *oid, struct packed_git *pack, - uint32_t pos, void *data) +static int write_oid(const struct object_id *oid, + struct packed_git *pack UNUSED, + uint32_t pos UNUSED, void *data) { struct child_process *cmd = data; @@ -247,11 +331,15 @@ static struct { {".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++) { @@ -261,11 +349,23 @@ 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 int has_pack_ext(const struct generated_pack_data *data, + const char *ext) +{ + int i; + for (i = 0; i < ARRAY_SIZE(exts); i++) { + if (strcmp(exts[i].name, ext)) + continue; + return !!data->tempfiles[i]; + } + BUG("unknown pack extension: '%s'", ext); } static void repack_promisor_objects(const struct pack_objects_args *args, @@ -275,7 +375,7 @@ 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; /* @@ -320,7 +420,7 @@ 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); } @@ -333,6 +433,8 @@ struct pack_geometry { struct packed_git **pack; uint32_t pack_nr, pack_alloc; uint32_t split; + + int split_factor; }; static uint32_t geometry_pack_weight(struct packed_git *p) @@ -354,36 +456,42 @@ static int geometry_cmp(const void *va, const void *vb) return 0; } -static void init_pack_geometry(struct pack_geometry **geometry_p, - struct string_list *existing_kept_packs) +static void init_pack_geometry(struct pack_geometry *geometry, + struct existing_packs *existing, + const struct pack_objects_args *args) { 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 (args->local && !p->pack_local) + /* + * When asked to only repack local packfiles we skip + * over any packfiles that are borrowed from alternate + * object directories. + */ + continue; + 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. + * 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. + * 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)) + if (string_list_has_string(&existing->kept_packs, buf.buf)) continue; } if (p->is_cruft) @@ -401,7 +509,7 @@ static void init_pack_geometry(struct pack_geometry **geometry_p, strbuf_release(&buf); } -static void split_pack_geometry(struct pack_geometry *geometry, int factor) +static void split_pack_geometry(struct pack_geometry *geometry) { uint32_t i; uint32_t split; @@ -420,12 +528,14 @@ static void split_pack_geometry(struct pack_geometry *geometry, int factor) struct packed_git *ours = geometry->pack[i]; struct packed_git *prev = geometry->pack[i - 1]; - if (unsigned_mult_overflows(factor, geometry_pack_weight(prev))) + if (unsigned_mult_overflows(geometry->split_factor, + geometry_pack_weight(prev))) die(_("pack %s too large to consider in geometric " "progression"), prev->pack_name); - if (geometry_pack_weight(ours) < factor * geometry_pack_weight(prev)) + if (geometry_pack_weight(ours) < + geometry->split_factor * geometry_pack_weight(prev)) break; } @@ -460,10 +570,12 @@ static void split_pack_geometry(struct pack_geometry *geometry, int factor) for (i = split; i < geometry->pack_nr; i++) { struct packed_git *ours = geometry->pack[i]; - if (unsigned_mult_overflows(factor, total_size)) + if (unsigned_mult_overflows(geometry->split_factor, + total_size)) die(_("pack %s too large to roll up"), ours->pack_name); - if (geometry_pack_weight(ours) < factor * total_size) { + if (geometry_pack_weight(ours) < + geometry->split_factor * total_size) { if (unsigned_add_overflows(total_size, geometry_pack_weight(ours))) die(_("pack %s too large to roll up"), @@ -478,8 +590,10 @@ static void split_pack_geometry(struct pack_geometry *geometry, int factor) geometry->split = split; } -static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry) +static struct packed_git *get_preferred_pack(struct pack_geometry *geometry) { + uint32_t i; + if (!geometry) { /* * No geometry means either an all-into-one repack (in which @@ -494,18 +608,55 @@ static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry } if (geometry->split == geometry->pack_nr) return NULL; - return geometry->pack[geometry->pack_nr - 1]; + + /* + * The preferred pack is the largest pack above the split line. In + * other words, it is the largest pack that does not get rolled up in + * the geometric repack. + */ + for (i = geometry->pack_nr; i > geometry->split; i--) + /* + * A pack that is not local would never be included in a + * multi-pack index. We thus skip over any non-local packs. + */ + if (geometry->pack[i - 1]->pack_local) + return geometry->pack[i - 1]; + + return NULL; +} + +static void geometry_remove_redundant_packs(struct pack_geometry *geometry, + struct string_list *names, + struct existing_packs *existing) +{ + struct strbuf buf = STRBUF_INIT; + uint32_t i; + + for (i = 0; i < geometry->split; i++) { + struct packed_git *p = geometry->pack[i]; + if (string_list_has_string(names, hash_to_hex(p->hash))) + continue; + + strbuf_reset(&buf); + 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); } -static void clear_pack_geometry(struct pack_geometry *geometry) +static void free_pack_geometry(struct pack_geometry *geometry) { if (!geometry) return; free(geometry->pack); - geometry->pack_nr = 0; - geometry->pack_alloc = 0; - geometry->split = 0; } struct midx_snapshot_ref_data { @@ -571,57 +722,76 @@ static void midx_snapshot_refs(struct tempfile *f) } static void midx_included_packs(struct string_list *include, - struct string_list *existing_nonkept_packs, - struct string_list *existing_kept_packs, + struct existing_packs *existing, struct string_list *names, struct pack_geometry *geometry) { struct string_list_item *item; - for_each_string_list_item(item, existing_kept_packs) + for_each_string_list_item(item, &existing->kept_packs) string_list_insert(include, xstrfmt("%s.idx", item->string)); for_each_string_list_item(item, names) string_list_insert(include, xstrfmt("pack-%s.idx", item->string)); - if (geometry) { + if (geometry->split_factor) { struct strbuf buf = STRBUF_INIT; uint32_t i; for (i = geometry->split; i < geometry->pack_nr; i++) { struct packed_git *p = geometry->pack[i]; + /* + * The multi-pack index never refers to packfiles part + * of an alternate object database, so we skip these. + * While git-multi-pack-index(1) would silently ignore + * them anyway, this allows us to skip executing the + * command completely when we have only non-local + * packfiles. + */ + if (!p->pack_local) + continue; + strbuf_addstr(&buf, pack_basename(p)); strbuf_strip_suffix(&buf, ".pack"); strbuf_addstr(&buf, ".idx"); 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 ((uintptr_t)item->util & DELETE_PACK) + for_each_string_list_item(item, &existing->non_kept_packs) { + if (pack_is_marked_for_deletion(item)) continue; string_list_insert(include, xstrfmt("%s.idx", item->string)); } } + + for_each_string_list_item(item, &existing->cruft_packs) { + /* + * When doing a --geometric repack, there is no need to check + * for deleted packs, since we're by definition not doing an + * ALL_INTO_ONE repack (hence no packs will be deleted). + * Otherwise we must check for and exclude any packs which are + * enqueued for deletion. + * + * So we could omit the conditional below in the --geometric + * case, but doing so is unnecessary since no packs are marked + * as pending deletion (since we only call + * `mark_packs_for_deletion()` when doing an all-into-one + * repack). + */ + if (pack_is_marked_for_deletion(item)) + continue; + string_list_insert(include, xstrfmt("%s.idx", item->string)); + } } static int write_midx_included_packs(struct string_list *include, struct pack_geometry *geometry, + struct string_list *names, const char *refs_snapshot, int show_progress, int write_bitmaps) { struct child_process cmd = CHILD_PROCESS_INIT; struct string_list_item *item; - struct packed_git *largest = get_largest_active_pack(geometry); + struct packed_git *preferred = get_preferred_pack(geometry); FILE *in; int ret; @@ -642,9 +812,41 @@ static int write_midx_included_packs(struct string_list *include, if (write_bitmaps) strvec_push(&cmd.args, "--bitmap"); - if (largest) + if (preferred) strvec_pushf(&cmd.args, "--preferred-pack=%s", - pack_basename(largest)); + pack_basename(preferred)); + else if (names->nr) { + /* The largest pack was repacked, meaning that either + * one or two packs exist depending on whether the + * repository has a cruft pack or not. + * + * Select the non-cruft one as preferred to encourage + * pack-reuse among packs containing reachable objects + * over unreachable ones. + * + * (Note we could write multiple packs here if + * `--max-pack-size` was given, but any one of them + * will suffice, so pick the first one.) + */ + for_each_string_list_item(item, names) { + struct generated_pack_data *data = item->util; + if (has_pack_ext(data, ".mtimes")) + continue; + + strvec_pushf(&cmd.args, "--preferred-pack=pack-%s.pack", + item->string); + break; + } + } else { + /* + * No packs were kept, and no packs were written. The + * only thing remaining are .keep packs (unless + * --pack-kept-objects was given). + * + * Set the `--preferred-pack` arbitrarily here. + */ + ; + } if (refs_snapshot) strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot); @@ -661,19 +863,197 @@ 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 finish_pack_objects_cmd(struct child_process *cmd, + struct string_list *names, + int local) +{ + FILE *out; + struct strbuf line = STRBUF_INIT; + + 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); +} + +static int write_filtered_pack(const struct pack_objects_args *args, + const char *destination, + const char *pack_prefix, + struct existing_packs *existing, + struct string_list *names) +{ + struct child_process cmd = CHILD_PROCESS_INIT; + struct string_list_item *item; + FILE *in; + int ret; + const char *caret; + const char *scratch; + int local = skip_prefix(destination, packdir, &scratch); + + prepare_pack_objects(&cmd, args, destination); + + strvec_push(&cmd.args, "--stdin-packs"); + + if (!pack_kept_objects) + strvec_push(&cmd.args, "--honor-pack-keep"); + for_each_string_list_item(item, &existing->kept_packs) + strvec_pushf(&cmd.args, "--keep-pack=%s", item->string); + + cmd.in = -1; + + ret = start_command(&cmd); + if (ret) + return ret; + + /* + * Here 'names' contains only the pack(s) that were just + * written, which is exactly the packs we want to keep. Also + * 'existing_kept_packs' already contains the packs in + * 'keep_pack_list'. + */ + 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->non_kept_packs) + fprintf(in, "%s.pack\n", item->string); + for_each_string_list_item(item, &existing->cruft_packs) + fprintf(in, "%s.pack\n", item->string); + caret = pack_kept_objects ? "" : "^"; + for_each_string_list_item(item, &existing->kept_packs) + fprintf(in, "%s%s.pack\n", caret, item->string); + fclose(in); + + return finish_pack_objects_cmd(&cmd, names, local); +} + +static int existing_cruft_pack_cmp(const void *va, const void *vb) +{ + struct packed_git *a = *(struct packed_git **)va; + struct packed_git *b = *(struct packed_git **)vb; + + if (a->pack_size < b->pack_size) + return -1; + if (a->pack_size > b->pack_size) + return 1; + return 0; +} + +static void collapse_small_cruft_packs(FILE *in, size_t max_size, + struct existing_packs *existing) +{ + struct packed_git **existing_cruft, *p; + struct strbuf buf = STRBUF_INIT; + size_t total_size = 0; + size_t existing_cruft_nr = 0; + size_t i; + + ALLOC_ARRAY(existing_cruft, existing->cruft_packs.nr); + + for (p = get_all_packs(the_repository); p; p = p->next) { + if (!(p->is_cruft && p->pack_local)) + continue; + + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + if (!string_list_has_string(&existing->cruft_packs, buf.buf)) + continue; + + if (existing_cruft_nr >= existing->cruft_packs.nr) + BUG("too many cruft packs (found %"PRIuMAX", but knew " + "of %"PRIuMAX")", + (uintmax_t)existing_cruft_nr + 1, + (uintmax_t)existing->cruft_packs.nr); + existing_cruft[existing_cruft_nr++] = p; + } + + QSORT(existing_cruft, existing_cruft_nr, existing_cruft_pack_cmp); + + for (i = 0; i < existing_cruft_nr; i++) { + size_t proposed; + + p = existing_cruft[i]; + proposed = st_add(total_size, p->pack_size); + + if (proposed <= max_size) { + total_size = proposed; + fprintf(in, "-%s\n", pack_basename(p)); + } else { + retain_cruft_pack(existing, p); + fprintf(in, "%s\n", pack_basename(p)); + } + } + + for (i = 0; i < existing->non_kept_packs.nr; i++) + fprintf(in, "-%s.pack\n", + existing->non_kept_packs.items[i].string); + + strbuf_release(&buf); + free(existing_cruft); +} + 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 existing_packs *existing) { struct child_process cmd = CHILD_PROCESS_INIT; - struct strbuf line = STRBUF_INIT; struct string_list_item *item; - FILE *in, *out; + FILE *in; int ret; + const char *scratch; + int local = skip_prefix(destination, packdir, &scratch); - prepare_pack_objects(&cmd, args); + prepare_pack_objects(&cmd, args, destination); strvec_push(&cmd.args, "--cruft"); if (cruft_expiration) @@ -682,7 +1062,6 @@ static int write_cruft_pack(const struct pack_objects_args *args, strvec_push(&cmd.args, "--honor-pack-keep"); strvec_push(&cmd.args, "--non-empty"); - strvec_push(&cmd.args, "--max-pack-size=0"); cmd.in = -1; @@ -698,28 +1077,38 @@ static int write_cruft_pack(const struct pack_objects_args *args, * 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) + if (args->max_pack_size && !cruft_expiration) { + collapse_small_cruft_packs(in, args->max_pack_size, existing); + } else { + for_each_string_list_item(item, &existing->non_kept_packs) + fprintf(in, "-%s.pack\n", item->string); + for_each_string_list_item(item, &existing->cruft_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) { - 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); - } - fclose(out); - - strbuf_release(&line); + return finish_pack_objects_cmd(&cmd, names, local); +} - return finish_command(&cmd); +static const char *find_pack_prefix(const char *packdir, const char *packtmp) +{ + 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++; + return pack_prefix; } int cmd_repack(int argc, const char **argv, const char *prefix) @@ -727,13 +1116,10 @@ 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 existing_nonkept_packs = STRING_LIST_INIT_DUP; - struct string_list existing_kept_packs = STRING_LIST_INIT_DUP; - struct pack_geometry *geometry = NULL; - struct strbuf line = STRBUF_INIT; + struct existing_packs existing = EXISTING_PACKS_INIT; + struct pack_geometry geometry = { 0 }; struct tempfile *refs_snapshot = NULL; int i, ext, ret; - FILE *out; int show_progress; /* variables to be filled by option parsing */ @@ -743,8 +1129,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix) 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; + const char *filter_to = NULL; struct option builtin_repack_options[] = { OPT_BIT('a', NULL, &pack_everything, @@ -756,7 +1144,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix) 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")), + N_("with --cruft, expire objects older than this")), + OPT_MAGNITUDE(0, "max-cruft-size", &cruft_po_args.max_pack_size, + N_("with --cruft, limit the size of new cruft packs")), OPT_BOOL('d', NULL, &delete_redundant, N_("remove redundant packs, and run git-prune-packed")), OPT_BOOL('f', NULL, &po_args.no_reuse_delta, @@ -784,19 +1174,26 @@ int cmd_repack(int argc, const char **argv, const char *prefix) N_("limits the maximum delta depth")), OPT_STRING(0, "threads", &po_args.threads, N_("n"), N_("limits the maximum number of threads")), - OPT_STRING(0, "max-pack-size", &po_args.max_pack_size, N_("bytes"), + OPT_MAGNITUDE(0, "max-pack-size", &po_args.max_pack_size, N_("maximum size of each packfile")), + OPT_PARSE_LIST_OBJECTS_FILTER(&po_args.filter_options), OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects, N_("repack objects in packs marked with .keep")), OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"), N_("do not repack this pack")), - OPT_INTEGER('g', "geometric", &geometric_factor, + OPT_INTEGER('g', "geometric", &geometry.split_factor, 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_STRING(0, "filter-to", &filter_to, N_("dir"), + N_("pack prefix to store a pack containing filtered out objects")), OPT_END() }; + list_objects_filter_init(&po_args.filter_options); + git_config(repack_config, &cruft_po_args); argc = parse_options(argc, argv, prefix, builtin_repack_options, @@ -805,19 +1202,13 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (delete_redundant && repository_format_precious_objects) die(_("cannot delete packs in a precious-objects repo")); - if (keep_unreachable && - (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE))) - die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "-A"); + die_for_incompatible_opt3(unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE), "-A", + keep_unreachable, "-k/--keep-unreachable", + pack_everything & PACK_CRUFT, "--cruft"); - if (pack_everything & PACK_CRUFT) { + 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())) @@ -833,6 +1224,18 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (write_bitmaps && !(pack_everything & ALL_INTO_ONE) && !write_midx) die(_(incremental_bitmap_conflict_error)); + if (write_bitmaps && po_args.local && has_alt_odb(the_repository)) { + /* + * When asked to do a local repack, but we have + * packfiles that are inherited from an alternate, then + * we cannot guarantee that the multi-pack-index would + * have full coverage of all objects. We thus disable + * writing bitmaps in that case. + */ + warning(_("disabling bitmap writing, as some objects are not being packed")); + write_bitmaps = 0; + } + if (write_midx && write_bitmaps) { struct strbuf path = STRBUF_INIT; @@ -849,19 +1252,16 @@ int cmd_repack(int argc, const char **argv, const char *prefix) 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); + collect_pack_filenames(&existing, &keep_pack_list); - if (geometric_factor) { + if (geometry.split_factor) { if (pack_everything) die(_("options '%s' and '%s' cannot be used together"), "--geometric", "-A/-a"); - init_pack_geometry(&geometry, &existing_kept_packs); - split_pack_geometry(geometry, geometric_factor); + init_pack_geometry(&geometry, &existing, &po_args); + split_pack_geometry(&geometry); } - 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); @@ -872,7 +1272,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) strvec_pushf(&cmd.args, "--keep-pack=%s", keep_pack_list.items[i].string); strvec_push(&cmd.args, "--non-empty"); - if (!geometry) { + if (!geometry.split_factor) { /* * We need to grab all reachable objects, including those that * are reachable from reflogs and the index. @@ -887,7 +1287,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) strvec_push(&cmd.args, "--reflog"); strvec_push(&cmd.args, "--indexed-objects"); } - if (has_promisor_remote()) + if (repo_has_promisor_remote(the_repository)) strvec_push(&cmd.args, "--exclude-promisor-objects"); if (!write_midx) { if (write_bitmaps > 0) @@ -901,7 +1301,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (pack_everything & ALL_INTO_ONE) { repack_promisor_objects(&po_args, &names); - if (existing_nonkept_packs.nr && delete_redundant && + if (has_existing_non_kept_packs(&existing) && + delete_redundant && !(pack_everything & PACK_CRUFT)) { for_each_string_list_item(item, &names) { strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack", @@ -919,7 +1320,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) strvec_push(&cmd.args, "--pack-loose-unreachable"); } } - } else if (geometry) { + } else if (geometry.split_factor) { strvec_push(&cmd.args, "--stdin-packs"); strvec_push(&cmd.args, "--unpacked"); } else { @@ -927,50 +1328,44 @@ int cmd_repack(int argc, const char **argv, const char *prefix) strvec_push(&cmd.args, "--incremental"); } - if (geometry) + if (po_args.filter_options.choice) + strvec_pushf(&cmd.args, "--filter=%s", + expand_list_objects_filter_spec(&po_args.filter_options)); + else if (filter_to) + die(_("option '%s' can only be used along with '%s'"), "--filter-to", "--filter"); + + if (geometry.split_factor) cmd.in = -1; else cmd.no_stdin = 1; ret = start_command(&cmd); if (ret) - return ret; + goto cleanup; - if (geometry) { + if (geometry.split_factor) { FILE *in = xfdopen(cmd.in, "w"); /* * The resulting pack should contain all objects in packs that * are going to be rolled up, but exclude objects in packs which * are being left alone. */ - for (i = 0; i < geometry->split; i++) - fprintf(in, "%s\n", pack_basename(geometry->pack[i])); - for (i = geometry->split; i < geometry->pack_nr; i++) - fprintf(in, "^%s\n", pack_basename(geometry->pack[i])); + for (i = 0; i < geometry.split; i++) + fprintf(in, "%s\n", pack_basename(geometry.pack[i])); + for (i = geometry.split; i < geometry.pack_nr; i++) + fprintf(in, "^%s\n", pack_basename(geometry.pack[i])); fclose(in); } - out = xfdopen(cmd.out, "r"); - while (strbuf_getline_lf(&line, out) != EOF) { - 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); - } - fclose(out); - ret = finish_command(&cmd); + ret = finish_pack_objects_cmd(&cmd, &names, 1); if (ret) - return ret; + goto cleanup; if (!names.nr && !po_args.quiet) printf_ln(_("Nothing new to pack.")); 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++; + const char *pack_prefix = find_pack_prefix(packdir, packtmp); if (!cruft_po_args.window) cruft_po_args.window = po_args.window; @@ -980,119 +1375,131 @@ int cmd_repack(int argc, const char **argv, const char *prefix) cruft_po_args.depth = po_args.depth; if (!cruft_po_args.threads) cruft_po_args.threads = po_args.threads; + if (!cruft_po_args.max_pack_size) + cruft_po_args.max_pack_size = po_args.max_pack_size; cruft_po_args.local = po_args.local; cruft_po_args.quiet = po_args.quiet; - ret = write_cruft_pack(&cruft_po_args, pack_prefix, &names, - &existing_nonkept_packs, - &existing_kept_packs); + ret = write_cruft_pack(&cruft_po_args, packtmp, pack_prefix, + cruft_expiration, &names, + &existing); if (ret) - return ret; + goto cleanup; + + 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); + if (ret) + goto cleanup; + } } - string_list_sort(&names); + if (po_args.filter_options.choice) { + if (!filter_to) + filter_to = packtmp; - for_each_string_list_item(item, &names) { - item->util = (void *)(uintptr_t)populate_pack_exts(item->string); + ret = write_filtered_pack(&po_args, + filter_to, + find_pack_prefix(packdir, packtmp), + &existing, + &names); + if (ret) + goto cleanup; } + 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; - for_each_string_list_item(item, &existing_nonkept_packs) { - char *sha1; - size_t len = strlen(item->string); - if (len < hexsz) - continue; - sha1 = item->string + len - hexsz; - /* - * Mark this pack for deletion, which ensures that this - * pack won't be included in a MIDX (if `--write-midx` - * was given) and that we will actually delete this pack - * (if `-d` was given). - */ - if (!string_list_has_string(&names, sha1)) - item->util = (void*)(uintptr_t)((size_t)item->util | DELETE_PACK); - } - } + if (delete_redundant && pack_everything & ALL_INTO_ONE) + mark_packs_for_deletion(&existing, &names); if (write_midx) { struct string_list include = STRING_LIST_INIT_NODUP; - midx_included_packs(&include, &existing_nonkept_packs, - &existing_kept_packs, &names, geometry); + midx_included_packs(&include, &existing, &names, &geometry); - ret = write_midx_included_packs(&include, geometry, + ret = write_midx_included_packs(&include, &geometry, &names, 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) - return ret; + goto cleanup; } reprepare_packed_git(the_repository); if (delete_redundant) { int opts = 0; - for_each_string_list_item(item, &existing_nonkept_packs) { - if (!((uintptr_t)item->util & DELETE_PACK)) - continue; - remove_redundant_pack(packdir, item->string); - } - - if (geometry) { - struct strbuf buf = STRBUF_INIT; - - uint32_t i; - for (i = 0; i < geometry->split; i++) { - struct packed_git *p = geometry->pack[i]; - if (string_list_has_string(&names, - hash_to_hex(p->hash))) - continue; + remove_redundant_existing_packs(&existing); - strbuf_reset(&buf); - strbuf_addstr(&buf, pack_basename(p)); - strbuf_strip_suffix(&buf, ".pack"); - - remove_redundant_pack(packdir, buf.buf); - } - strbuf_release(&buf); - } + if (geometry.split_factor) + geometry_remove_redundant_packs(&geometry, &names, + &existing); if (show_progress) opts |= PRUNE_PACKED_VERBOSE; prune_packed_objects(opts); @@ -1106,7 +1513,6 @@ 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; @@ -1115,11 +1521,11 @@ 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(&existing_nonkept_packs, 0); - string_list_clear(&existing_kept_packs, 0); - clear_pack_geometry(geometry); - strbuf_release(&line); +cleanup: + string_list_clear(&names, 1); + existing_packs_release(&existing); + free_pack_geometry(&geometry); + list_objects_filter_release(&po_args.filter_options); - return 0; + return ret; } |