diff options
Diffstat (limited to 'builtin/repack.c')
-rw-r--r-- | builtin/repack.c | 520 |
1 files changed, 473 insertions, 47 deletions
diff --git a/builtin/repack.c b/builtin/repack.c index 2158b48f4c..9b0be6a6ab 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -15,12 +15,14 @@ #include "promisor-remote.h" #include "shallow.h" #include "pack.h" +#include "pack-bitmap.h" +#include "refs.h" static int delta_base_offset = 1; static int pack_kept_objects = -1; static int write_bitmaps = -1; static int use_delta_islands; -static char *packdir, *packtmp; +static char *packdir, *packtmp_name, *packtmp; static const char *const git_repack_usage[] = { N_("git repack [<options>]"), @@ -94,12 +96,14 @@ static void remove_pack_on_signal(int signo) } /* - * Adds all packs hex strings to the fname list, which do not - * have a corresponding .keep file. These packs are not to - * be kept if we are going to pack everything into one file. + * 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 + * if we are going to pack everything into one file. */ -static void get_non_kept_pack_filenames(struct string_list *fname_list, - const struct string_list *extra_keep) +static void collect_pack_filenames(struct string_list *fname_nonkept_list, + struct string_list *fname_kept_list, + const struct string_list *extra_keep) { DIR *dir; struct dirent *e; @@ -112,21 +116,20 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list, size_t len; int i; + if (!strip_suffix(e->d_name, ".pack", &len)) + continue; + for (i = 0; i < extra_keep->nr; i++) if (!fspathcmp(e->d_name, extra_keep->items[i].string)) break; - if (extra_keep->nr > 0 && i < extra_keep->nr) - continue; - - if (!strip_suffix(e->d_name, ".pack", &len)) - continue; fname = xmemdupz(e->d_name, len); - if (!file_exists(mkpath("%s/%s.keep", packdir, fname))) - string_list_append_nodup(fname_list, fname); + 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 - free(fname); + string_list_append_nodup(fname_nonkept_list, fname); } closedir(dir); } @@ -208,9 +211,10 @@ static struct { unsigned optional:1; } exts[] = { {".pack"}, - {".idx"}, + {".rev", 1}, {".bitmap", 1}, {".promisor", 1}, + {".idx"}, }; static unsigned populate_pack_exts(char *name) @@ -254,9 +258,11 @@ static void repack_promisor_objects(const struct pack_objects_args *args, for_each_packed_object(write_oid, &cmd, FOR_EACH_OBJECT_PROMISOR_ONLY); - if (cmd.in == -1) + if (cmd.in == -1) { /* No packed objects; cmd was never started */ + child_process_clear(&cmd); return; + } close(cmd.in); @@ -296,16 +302,317 @@ static void repack_promisor_objects(const struct pack_objects_args *args, #define ALL_INTO_ONE 1 #define LOOSEN_UNREACHABLE 2 +struct pack_geometry { + struct packed_git **pack; + uint32_t pack_nr, pack_alloc; + uint32_t split; +}; + +static uint32_t geometry_pack_weight(struct packed_git *p) +{ + if (open_pack_index(p)) + die(_("cannot open index for %s"), p->pack_name); + return p->num_objects; +} + +static int geometry_cmp(const void *va, const void *vb) +{ + uint32_t aw = geometry_pack_weight(*(struct packed_git **)va), + bw = geometry_pack_weight(*(struct packed_git **)vb); + + if (aw < bw) + return -1; + if (aw > bw) + return 1; + return 0; +} + +static void init_pack_geometry(struct pack_geometry **geometry_p) +{ + struct packed_git *p; + struct pack_geometry *geometry; + + *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) + continue; + + ALLOC_GROW(geometry->pack, + geometry->pack_nr + 1, + geometry->pack_alloc); + + geometry->pack[geometry->pack_nr] = p; + geometry->pack_nr++; + } + + QSORT(geometry->pack, geometry->pack_nr, geometry_cmp); +} + +static void split_pack_geometry(struct pack_geometry *geometry, int factor) +{ + uint32_t i; + uint32_t split; + off_t total_size = 0; + + if (!geometry->pack_nr) { + geometry->split = geometry->pack_nr; + return; + } + + /* + * First, count the number of packs (in descending order of size) which + * already form a geometric progression. + */ + for (i = geometry->pack_nr - 1; i > 0; i--) { + struct packed_git *ours = geometry->pack[i]; + struct packed_git *prev = geometry->pack[i - 1]; + + if (unsigned_mult_overflows(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)) + break; + } + + split = i; + + if (split) { + /* + * Move the split one to the right, since the top element in the + * last-compared pair can't be in the progression. Only do this + * when we split in the middle of the array (otherwise if we got + * to the end, then the split is in the right place). + */ + split++; + } + + /* + * Then, anything to the left of 'split' must be in a new pack. But, + * creating that new pack may cause packs in the heavy half to no longer + * form a geometric progression. + * + * Compute an expected size of the new pack, and then determine how many + * packs in the heavy half need to be joined into it (if any) to restore + * the geometric progression. + */ + for (i = 0; i < split; i++) { + struct packed_git *p = geometry->pack[i]; + + if (unsigned_add_overflows(total_size, geometry_pack_weight(p))) + die(_("pack %s too large to roll up"), p->pack_name); + total_size += geometry_pack_weight(p); + } + for (i = split; i < geometry->pack_nr; i++) { + struct packed_git *ours = geometry->pack[i]; + + if (unsigned_mult_overflows(factor, total_size)) + die(_("pack %s too large to roll up"), ours->pack_name); + + if (geometry_pack_weight(ours) < factor * total_size) { + if (unsigned_add_overflows(total_size, + geometry_pack_weight(ours))) + die(_("pack %s too large to roll up"), + ours->pack_name); + + split++; + total_size += geometry_pack_weight(ours); + } else + break; + } + + geometry->split = split; +} + +static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry) +{ + if (!geometry) { + /* + * No geometry means either an all-into-one repack (in which + * case there is only one pack left and it is the largest) or an + * incremental one. + * + * If repacking incrementally, then we could check the size of + * all packs to determine which should be preferred, but leave + * this for later. + */ + return NULL; + } + if (geometry->split == geometry->pack_nr) + return NULL; + return geometry->pack[geometry->pack_nr - 1]; +} + +static void clear_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 { + struct tempfile *f; + struct oidset seen; + int preferred; +}; + +static int midx_snapshot_ref_one(const char *refname, + const struct object_id *oid, + int flag, void *_data) +{ + struct midx_snapshot_ref_data *data = _data; + struct object_id peeled; + + if (!peel_iterated_oid(oid, &peeled)) + oid = &peeled; + + if (oidset_insert(&data->seen, oid)) + return 0; /* already seen */ + + if (oid_object_info(the_repository, oid, NULL) != OBJ_COMMIT) + return 0; + + fprintf(data->f->fp, "%s%s\n", data->preferred ? "+" : "", + oid_to_hex(oid)); + + return 0; +} + +static void midx_snapshot_refs(struct tempfile *f) +{ + struct midx_snapshot_ref_data data; + const struct string_list *preferred = bitmap_preferred_tips(the_repository); + + data.f = f; + data.preferred = 0; + oidset_init(&data.seen, 0); + + if (!fdopen_tempfile(f, "w")) + die(_("could not open tempfile %s for writing"), + get_tempfile_path(f)); + + if (preferred) { + struct string_list_item *item; + + data.preferred = 1; + for_each_string_list_item(item, preferred) + for_each_ref_in(item->string, midx_snapshot_ref_one, &data); + data.preferred = 0; + } + + for_each_ref(midx_snapshot_ref_one, &data); + + if (close_tempfile_gently(f)) { + int save_errno = errno; + delete_tempfile(&f); + errno = save_errno; + die_errno(_("could not close refs snapshot tempfile")); + } + + oidset_clear(&data.seen); +} + +static void midx_included_packs(struct string_list *include, + struct string_list *existing_nonkept_packs, + struct string_list *existing_kept_packs, + struct string_list *names, + struct pack_geometry *geometry) +{ + struct string_list_item *item; + + 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) { + struct strbuf buf = STRBUF_INIT; + uint32_t i; + for (i = geometry->split; i < geometry->pack_nr; i++) { + struct packed_git *p = geometry->pack[i]; + + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + strbuf_addstr(&buf, ".idx"); + + string_list_insert(include, strbuf_detach(&buf, NULL)); + } + } else { + for_each_string_list_item(item, existing_nonkept_packs) { + if (item->util) + continue; + string_list_insert(include, xstrfmt("%s.idx", item->string)); + } + } +} + +static int write_midx_included_packs(struct string_list *include, + struct pack_geometry *geometry, + 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); + FILE *in; + int ret; + + if (!include->nr) + return 0; + + cmd.in = -1; + cmd.git_cmd = 1; + + strvec_push(&cmd.args, "multi-pack-index"); + strvec_pushl(&cmd.args, "write", "--stdin-packs", NULL); + + if (show_progress) + strvec_push(&cmd.args, "--progress"); + else + strvec_push(&cmd.args, "--no-progress"); + + if (write_bitmaps) + strvec_push(&cmd.args, "--bitmap"); + + if (largest) + strvec_pushf(&cmd.args, "--preferred-pack=%s", + pack_basename(largest)); + + if (refs_snapshot) + strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot); + + ret = start_command(&cmd); + if (ret) + return ret; + + in = xfdopen(cmd.in, "w"); + for_each_string_list_item(item, include) + fprintf(in, "%s\n", item->string); + fclose(in); + + 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_packs = 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 tempfile *refs_snapshot = NULL; int i, ext, ret; FILE *out; + int show_progress = isatty(2); /* variables to be filled by option parsing */ int pack_everything = 0; @@ -315,6 +622,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; int no_update_server_info = 0; struct pack_objects_args po_args = {NULL}; + int geometric_factor = 0; + int write_midx = 0; struct option builtin_repack_options[] = { OPT_BIT('a', NULL, &pack_everything, @@ -355,6 +664,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix) 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, + 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_END() }; @@ -371,18 +684,42 @@ int cmd_repack(int argc, const char **argv, const char *prefix) die(_("--keep-unreachable and -A are incompatible")); if (write_bitmaps < 0) { - if (!(pack_everything & ALL_INTO_ONE) || - !is_bare_repository()) + if (!write_midx && + (!(pack_everything & ALL_INTO_ONE) || !is_bare_repository())) write_bitmaps = 0; + } else if (write_bitmaps && + git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0) && + git_env_bool(GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP, 0)) { + write_bitmaps = 0; } if (pack_kept_objects < 0) pack_kept_objects = write_bitmaps > 0; - if (write_bitmaps && !(pack_everything & ALL_INTO_ONE)) + if (write_bitmaps && !(pack_everything & ALL_INTO_ONE) && !write_midx) die(_(incremental_bitmap_conflict_error)); + if (write_midx && write_bitmaps) { + struct strbuf path = STRBUF_INIT; + + strbuf_addf(&path, "%s/%s_XXXXXX", get_object_directory(), + "bitmap-ref-tips"); + + refs_snapshot = xmks_tempfile(path.buf); + midx_snapshot_refs(refs_snapshot); + + strbuf_release(&path); + } + + if (geometric_factor) { + if (pack_everything) + die(_("--geometric is incompatible with -A, -a")); + init_pack_geometry(&geometry); + split_pack_geometry(geometry, geometric_factor); + } + packdir = mkpathdup("%s/pack", get_object_directory()); - packtmp = mkpathdup("%s/.tmp-%d-pack", packdir, (int)getpid()); + packtmp_name = xstrfmt(".tmp-%d-pack", (int)getpid()); + packtmp = mkpathdup("%s/%s", packdir, packtmp_name); sigchain_push_common(remove_pack_on_signal); @@ -395,50 +732,86 @@ 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"); - strvec_push(&cmd.args, "--all"); - strvec_push(&cmd.args, "--reflog"); - strvec_push(&cmd.args, "--indexed-objects"); + if (!geometry) { + /* + * We need to grab all reachable objects, including those that + * are reachable from reflogs and the index. + * + * When repacking into a geometric progression of packs, + * however, we ask 'git pack-objects --stdin-packs', and it is + * not about packing objects based on reachability but about + * repacking all the objects in specified packs and loose ones + * (indeed, --stdin-packs is incompatible with these options). + */ + strvec_push(&cmd.args, "--all"); + strvec_push(&cmd.args, "--reflog"); + strvec_push(&cmd.args, "--indexed-objects"); + } if (has_promisor_remote()) strvec_push(&cmd.args, "--exclude-promisor-objects"); - if (write_bitmaps > 0) - strvec_push(&cmd.args, "--write-bitmap-index"); - else if (write_bitmaps < 0) - strvec_push(&cmd.args, "--write-bitmap-index-quiet"); + if (!write_midx) { + if (write_bitmaps > 0) + strvec_push(&cmd.args, "--write-bitmap-index"); + else if (write_bitmaps < 0) + strvec_push(&cmd.args, "--write-bitmap-index-quiet"); + } if (use_delta_islands) strvec_push(&cmd.args, "--delta-islands"); - if (pack_everything & ALL_INTO_ONE) { - get_non_kept_pack_filenames(&existing_packs, &keep_pack_list); + 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_packs.nr && delete_redundant) { + if (existing_nonkept_packs.nr && delete_redundant) { + for_each_string_list_item(item, &names) { + strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack", + packtmp_name, item->string); + } if (unpack_unreachable) { strvec_pushf(&cmd.args, "--unpack-unreachable=%s", unpack_unreachable); - strvec_push(&cmd.env_array, "GIT_REF_PARANOIA=1"); } else if (pack_everything & LOOSEN_UNREACHABLE) { strvec_push(&cmd.args, "--unpack-unreachable"); } else if (keep_unreachable) { strvec_push(&cmd.args, "--keep-unreachable"); strvec_push(&cmd.args, "--pack-loose-unreachable"); - } else { - strvec_push(&cmd.env_array, "GIT_REF_PARANOIA=1"); } } + } else if (geometry) { + strvec_push(&cmd.args, "--stdin-packs"); + strvec_push(&cmd.args, "--unpacked"); } else { strvec_push(&cmd.args, "--unpacked"); strvec_push(&cmd.args, "--incremental"); } - cmd.no_stdin = 1; + if (geometry) + cmd.in = -1; + else + cmd.no_stdin = 1; ret = start_command(&cmd); if (ret) return ret; + if (geometry) { + 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])); + fclose(in); + } + out = xfdopen(cmd.out, "r"); while (strbuf_getline_lf(&line, out) != EOF) { if (line.len != the_hash_algo->hexsz) @@ -471,7 +844,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) fname_old = mkpathdup("%s-%s%s", packtmp, item->string, exts[ext].name); - if (((uintptr_t)item->util) & (1 << ext)) { + if (((uintptr_t)item->util) & ((uintptr_t)1 << ext)) { struct stat statbuffer; if (!stat(fname_old, &statbuffer)) { statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); @@ -491,22 +864,69 @@ int cmd_repack(int argc, const char **argv, const char *prefix) } /* End of pack replacement. */ - reprepare_packed_git(the_repository); - - if (delete_redundant) { + if (delete_redundant && pack_everything & ALL_INTO_ONE) { const int hexsz = the_hash_algo->hexsz; - int opts = 0; string_list_sort(&names); - for_each_string_list_item(item, &existing_packs) { + 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; - if (!string_list_has_string(&names, sha1)) - remove_redundant_pack(packdir, item->string); + /* + * 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). + */ + item->util = (void*)(intptr_t)!string_list_has_string(&names, sha1); } - if (!po_args.quiet && isatty(2)) + } + + if (write_midx) { + struct string_list include = STRING_LIST_INIT_NODUP; + midx_included_packs(&include, &existing_nonkept_packs, + &existing_kept_packs, &names, geometry); + + ret = write_midx_included_packs(&include, geometry, + refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL, + show_progress, write_bitmaps > 0); + + string_list_clear(&include, 0); + + if (ret) + return ret; + } + + reprepare_packed_git(the_repository); + + if (delete_redundant) { + int opts = 0; + for_each_string_list_item(item, &existing_nonkept_packs) { + if (!item->util) + 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; + + strbuf_reset(&buf); + strbuf_addstr(&buf, pack_basename(p)); + strbuf_strip_suffix(&buf, ".pack"); + + remove_redundant_pack(packdir, buf.buf); + } + strbuf_release(&buf); + } + if (!po_args.quiet && show_progress) opts |= PRUNE_PACKED_VERBOSE; prune_packed_objects(opts); @@ -521,12 +941,18 @@ int cmd_repack(int argc, const char **argv, const char *prefix) update_server_info(0); remove_temporary_files(); - if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) - write_midx_file(get_object_directory(), 0); + if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) { + unsigned flags = 0; + if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP, 0)) + flags |= MIDX_WRITE_BITMAP | MIDX_WRITE_REV_INDEX; + write_midx_file(get_object_directory(), NULL, NULL, flags); + } string_list_clear(&names, 0); string_list_clear(&rollback, 0); - string_list_clear(&existing_packs, 0); + string_list_clear(&existing_nonkept_packs, 0); + string_list_clear(&existing_kept_packs, 0); + clear_pack_geometry(geometry); strbuf_release(&line); return 0; |