diff options
Diffstat (limited to 'builtin/repack.c')
-rw-r--r-- | builtin/repack.c | 496 |
1 files changed, 328 insertions, 168 deletions
diff --git a/builtin/repack.c b/builtin/repack.c index f834b5551b..5f9bc74adc 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -7,16 +7,20 @@ #include "sigchain.h" #include "strbuf.h" #include "string-list.h" -#include "argv-array.h" +#include "strvec.h" #include "midx.h" #include "packfile.h" +#include "prune-packed.h" #include "object-store.h" +#include "promisor-remote.h" +#include "shallow.h" +#include "pack.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>]"), @@ -129,19 +133,13 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list, static void remove_redundant_pack(const char *dir_name, const char *base_name) { - const char *exts[] = {".pack", ".idx", ".keep", ".bitmap", ".promisor"}; - int i; struct strbuf buf = STRBUF_INIT; - size_t plen; - - strbuf_addf(&buf, "%s/%s", dir_name, base_name); - plen = buf.len; - - for (i = 0; i < ARRAY_SIZE(exts); i++) { - strbuf_setlen(&buf, plen); - strbuf_addstr(&buf, exts[i]); - unlink(buf.buf); - } + 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); } @@ -160,28 +158,28 @@ struct pack_objects_args { static void prepare_pack_objects(struct child_process *cmd, const struct pack_objects_args *args) { - argv_array_push(&cmd->args, "pack-objects"); + strvec_push(&cmd->args, "pack-objects"); if (args->window) - argv_array_pushf(&cmd->args, "--window=%s", args->window); + strvec_pushf(&cmd->args, "--window=%s", args->window); if (args->window_memory) - argv_array_pushf(&cmd->args, "--window-memory=%s", args->window_memory); + strvec_pushf(&cmd->args, "--window-memory=%s", args->window_memory); if (args->depth) - argv_array_pushf(&cmd->args, "--depth=%s", args->depth); + strvec_pushf(&cmd->args, "--depth=%s", args->depth); if (args->threads) - argv_array_pushf(&cmd->args, "--threads=%s", args->threads); + strvec_pushf(&cmd->args, "--threads=%s", args->threads); if (args->max_pack_size) - argv_array_pushf(&cmd->args, "--max-pack-size=%s", args->max_pack_size); + strvec_pushf(&cmd->args, "--max-pack-size=%s", args->max_pack_size); if (args->no_reuse_delta) - argv_array_pushf(&cmd->args, "--no-reuse-delta"); + strvec_pushf(&cmd->args, "--no-reuse-delta"); if (args->no_reuse_object) - argv_array_pushf(&cmd->args, "--no-reuse-object"); + strvec_pushf(&cmd->args, "--no-reuse-object"); if (args->local) - argv_array_push(&cmd->args, "--local"); + strvec_push(&cmd->args, "--local"); if (args->quiet) - argv_array_push(&cmd->args, "--quiet"); + strvec_push(&cmd->args, "--quiet"); if (delta_base_offset) - argv_array_push(&cmd->args, "--delta-base-offset"); - argv_array_push(&cmd->args, packtmp); + strvec_push(&cmd->args, "--delta-base-offset"); + strvec_push(&cmd->args, packtmp); cmd->git_cmd = 1; cmd->out = -1; } @@ -200,11 +198,43 @@ static int write_oid(const struct object_id *oid, struct packed_git *pack, die(_("could not start pack-objects to repack promisor objects")); } - xwrite(cmd->in, oid_to_hex(oid), GIT_SHA1_HEXSZ); + xwrite(cmd->in, oid_to_hex(oid), the_hash_algo->hexsz); xwrite(cmd->in, "\n", 1); return 0; } +static struct { + const char *name; + unsigned optional:1; +} exts[] = { + {".pack"}, + {".idx"}, + {".rev", 1}, + {".bitmap", 1}, + {".promisor", 1}, +}; + +static unsigned populate_pack_exts(char *name) +{ + struct stat statbuf; + struct strbuf path = STRBUF_INIT; + unsigned ret = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(exts); i++) { + strbuf_reset(&path); + strbuf_addf(&path, "%s-%s%s", packtmp, name, exts[i].name); + + if (stat(path.buf, &statbuf)) + continue; + + ret |= (1 << i); + } + + strbuf_release(&path); + return ret; +} + static void repack_promisor_objects(const struct pack_objects_args *args, struct string_list *names) { @@ -233,22 +263,30 @@ static void repack_promisor_objects(const struct pack_objects_args *args, out = xfdopen(cmd.out, "r"); while (strbuf_getline_lf(&line, out) != EOF) { + struct string_list_item *item; char *promisor_name; - int fd; + 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); /* * pack-objects creates the .pack and .idx files, but not the * .promisor file. Create the .promisor file, which is empty. + * + * NEEDSWORK: fetch-pack sometimes generates non-empty + * .promisor files containing the ref names and associated + * hashes at the point of generation of the corresponding + * packfile, but this would not preserve their contents. Maybe + * concatenate the contents of all .promisor files instead of + * just creating a new empty file. */ promisor_name = mkpathdup("%s-%s.promisor", packtmp, line.buf); - fd = open(promisor_name, O_CREAT|O_EXCL|O_WRONLY, 0600); - if (fd < 0) - die_errno(_("unable to create '%s'"), promisor_name); - close(fd); + write_promisor_file(promisor_name, NULL, 0); + + item->util = (void *)(uintptr_t)populate_pack_exts(item->string); + free(promisor_name); } fclose(out); @@ -259,24 +297,152 @@ 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 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; +} + int cmd_repack(int argc, const char **argv, const char *prefix) { - struct { - const char *name; - unsigned optional:1; - } exts[] = { - {".pack"}, - {".idx"}, - {".bitmap", 1}, - {".promisor", 1}, - }; 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 pack_geometry *geometry = NULL; struct strbuf line = STRBUF_INIT; - int i, ext, ret, failed; + int i, ext, ret; FILE *out; /* variables to be filled by option parsing */ @@ -286,8 +452,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) int keep_unreachable = 0; struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; int no_update_server_info = 0; - int midx_cleared = 0; struct pack_objects_args po_args = {NULL}; + int geometric_factor = 0; struct option builtin_repack_options[] = { OPT_BIT('a', NULL, &pack_everything, @@ -328,6 +494,8 @@ 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_END() }; @@ -343,38 +511,62 @@ int cmd_repack(int argc, const char **argv, const char *prefix) (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE))) die(_("--keep-unreachable and -A are incompatible")); - if (write_bitmaps < 0) - write_bitmaps = (pack_everything & ALL_INTO_ONE) && - is_bare_repository(); + if (write_bitmaps < 0) { + if (!(pack_everything & ALL_INTO_ONE) || + !is_bare_repository()) + write_bitmaps = 0; + } if (pack_kept_objects < 0) - pack_kept_objects = write_bitmaps; + pack_kept_objects = write_bitmaps > 0; if (write_bitmaps && !(pack_everything & ALL_INTO_ONE)) die(_(incremental_bitmap_conflict_error)); + 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); prepare_pack_objects(&cmd, &po_args); - argv_array_push(&cmd.args, "--keep-true-parents"); + strvec_push(&cmd.args, "--keep-true-parents"); if (!pack_kept_objects) - argv_array_push(&cmd.args, "--honor-pack-keep"); + strvec_push(&cmd.args, "--honor-pack-keep"); for (i = 0; i < keep_pack_list.nr; i++) - argv_array_pushf(&cmd.args, "--keep-pack=%s", - keep_pack_list.items[i].string); - argv_array_push(&cmd.args, "--non-empty"); - argv_array_push(&cmd.args, "--all"); - argv_array_push(&cmd.args, "--reflog"); - argv_array_push(&cmd.args, "--indexed-objects"); - if (repository_format_partial_clone) - argv_array_push(&cmd.args, "--exclude-promisor-objects"); - if (write_bitmaps) - argv_array_push(&cmd.args, "--write-bitmap-index"); + strvec_pushf(&cmd.args, "--keep-pack=%s", + keep_pack_list.items[i].string); + strvec_push(&cmd.args, "--non-empty"); + 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 (use_delta_islands) - argv_array_push(&cmd.args, "--delta-islands"); + strvec_push(&cmd.args, "--delta-islands"); if (pack_everything & ALL_INTO_ONE) { get_non_kept_pack_filenames(&existing_packs, &keep_pack_list); @@ -382,32 +574,56 @@ int cmd_repack(int argc, const char **argv, const char *prefix) repack_promisor_objects(&po_args, &names); if (existing_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) { - argv_array_pushf(&cmd.args, - "--unpack-unreachable=%s", - unpack_unreachable); - argv_array_push(&cmd.env_array, "GIT_REF_PARANOIA=1"); + strvec_pushf(&cmd.args, + "--unpack-unreachable=%s", + unpack_unreachable); + strvec_push(&cmd.env_array, "GIT_REF_PARANOIA=1"); } else if (pack_everything & LOOSEN_UNREACHABLE) { - argv_array_push(&cmd.args, - "--unpack-unreachable"); + strvec_push(&cmd.args, + "--unpack-unreachable"); } else if (keep_unreachable) { - argv_array_push(&cmd.args, "--keep-unreachable"); - argv_array_push(&cmd.args, "--pack-loose-unreachable"); + strvec_push(&cmd.args, "--keep-unreachable"); + strvec_push(&cmd.args, "--pack-loose-unreachable"); } else { - argv_array_push(&cmd.env_array, "GIT_REF_PARANOIA=1"); + strvec_push(&cmd.env_array, "GIT_REF_PARANOIA=1"); } } + } else if (geometry) { + strvec_push(&cmd.args, "--stdin-packs"); + strvec_push(&cmd.args, "--unpacked"); } else { - argv_array_push(&cmd.args, "--unpacked"); - argv_array_push(&cmd.args, "--incremental"); + 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) @@ -422,118 +638,42 @@ 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); + } + close_object_store(the_repository->objects); /* * Ok we have prepared all new packfiles. - * First see if there are packs of the same name and if so - * if we can move them out of the way (this can happen if we - * repacked immediately after packing fully. */ - failed = 0; for_each_string_list_item(item, &names) { for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { char *fname, *fname_old; - if (!midx_cleared) { - clear_midx_file(the_repository); - midx_cleared = 1; - } - - fname = mkpathdup("%s/pack-%s%s", packdir, - item->string, exts[ext].name); - if (!file_exists(fname)) { - free(fname); - continue; - } - - fname_old = mkpathdup("%s/old-%s%s", packdir, - item->string, exts[ext].name); - if (file_exists(fname_old)) - if (unlink(fname_old)) - failed = 1; - - if (!failed && rename(fname, fname_old)) { - free(fname); - free(fname_old); - failed = 1; - break; - } else { - string_list_append(&rollback, fname); - free(fname_old); - } - } - if (failed) - break; - } - if (failed) { - struct string_list rollback_failure = STRING_LIST_INIT_DUP; - for_each_string_list_item(item, &rollback) { - char *fname, *fname_old; - fname = mkpathdup("%s/%s", packdir, item->string); - fname_old = mkpathdup("%s/old-%s", packdir, item->string); - if (rename(fname_old, fname)) - string_list_append(&rollback_failure, fname); - free(fname); - free(fname_old); - } - - if (rollback_failure.nr) { - int i; - fprintf(stderr, - _("WARNING: Some packs in use have been renamed by\n" - "WARNING: prefixing old- to their name, in order to\n" - "WARNING: replace them with the new version of the\n" - "WARNING: file. But the operation failed, and the\n" - "WARNING: attempt to rename them back to their\n" - "WARNING: original names also failed.\n" - "WARNING: Please rename them in %s manually:\n"), packdir); - for (i = 0; i < rollback_failure.nr; i++) - fprintf(stderr, "WARNING: old-%s -> %s\n", - rollback_failure.items[i].string, - rollback_failure.items[i].string); - } - exit(1); - } - - /* Now the ones with the same name are out of the way... */ - for_each_string_list_item(item, &names) { - for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { - char *fname, *fname_old; - struct stat statbuffer; - int exists = 0; 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 (!stat(fname_old, &statbuffer)) { - statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH); - chmod(fname_old, statbuffer.st_mode); - exists = 1; - } - if (exists || !exts[ext].optional) { + + if (((uintptr_t)item->util) & (1 << 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); - } - free(fname); - free(fname_old); - } - } + } else if (!exts[ext].optional) + die(_("missing required file: %s"), fname_old); + else if (unlink(fname) < 0 && errno != ENOENT) + die_errno(_("could not unlink: %s"), fname); - /* Remove the "old-" files */ - for_each_string_list_item(item, &names) { - for (ext = 0; ext < ARRAY_SIZE(exts); ext++) { - char *fname; - fname = mkpathdup("%s/old-%s%s", - packdir, - item->string, - exts[ext].name); - if (remove_path(fname)) - warning(_("failed to remove '%s'"), fname); free(fname); + free(fname_old); } } - /* End of pack replacement. */ reprepare_packed_git(the_repository); @@ -551,6 +691,25 @@ int cmd_repack(int argc, const char **argv, const char *prefix) if (!string_list_has_string(&names, sha1)) 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 && isatty(2)) opts |= PRUNE_PACKED_VERBOSE; prune_packed_objects(opts); @@ -567,11 +726,12 @@ int cmd_repack(int argc, const char **argv, const char *prefix) remove_temporary_files(); if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) - write_midx_file(get_object_directory()); + write_midx_file(get_object_directory(), NULL, 0); string_list_clear(&names, 0); string_list_clear(&rollback, 0); string_list_clear(&existing_packs, 0); + clear_pack_geometry(geometry); strbuf_release(&line); return 0; |