diff --git a/Documentation/git-multi-pack-index.adoc b/Documentation/git-multi-pack-index.adoc index 2f642697e9..458bb87363 100644 --- a/Documentation/git-multi-pack-index.adoc +++ b/Documentation/git-multi-pack-index.adoc @@ -9,7 +9,14 @@ git-multi-pack-index - Write and verify multi-pack-indexes SYNOPSIS -------- [verse] -'git multi-pack-index' [--object-dir=] [--[no-]bitmap] +'git multi-pack-index' [] write [--preferred-pack=] + [--[no-]bitmap] [--[no-]incremental] [--[no-]stdin-packs] + [--refs-snapshot=] +'git multi-pack-index' [] compact [--[no-]incremental] + [--[no-]bitmap] +'git multi-pack-index' [] verify +'git multi-pack-index' [] expire +'git multi-pack-index' [] repack [--batch-size=] DESCRIPTION ----------- @@ -18,6 +25,8 @@ Write or verify a multi-pack-index (MIDX) file. OPTIONS ------- +The following command-line options are applicable to all sub-commands: + --object-dir=:: Use given directory for the location of Git objects. We check `/packs/multi-pack-index` for the current MIDX file, and @@ -73,7 +82,18 @@ marker). Write an incremental MIDX file containing only objects and packs not present in an existing MIDX layer. Migrates non-incremental MIDXs to incremental ones when - necessary. Incompatible with `--bitmap`. + necessary. +-- + +compact:: + Write a new MIDX layer containing only objects and packs present + in the range `` to ``, where both arguments are + checksums of existing layers in the MIDX chain. ++ +-- + --incremental:: + Write the result to a MIDX chain instead of writing a + stand-alone MIDX. Incompatible with `--bitmap`. -- verify:: diff --git a/builtin/multi-pack-index.c b/builtin/multi-pack-index.c index 5f364aa816..40afa8f1ed 100644 --- a/builtin/multi-pack-index.c +++ b/builtin/multi-pack-index.c @@ -13,8 +13,13 @@ #include "repository.h" #define BUILTIN_MIDX_WRITE_USAGE \ - N_("git multi-pack-index [] write [--preferred-pack=]" \ - "[--refs-snapshot=]") + N_("git multi-pack-index [] write [--preferred-pack=]\n" \ + " [--[no-]bitmap] [--[no-]incremental] [--[no-]stdin-packs]\n" \ + " [--refs-snapshot=]") + +#define BUILTIN_MIDX_COMPACT_USAGE \ + N_("git multi-pack-index [] compact [--[no-]incremental]\n" \ + " [--[no-]bitmap] ") #define BUILTIN_MIDX_VERIFY_USAGE \ N_("git multi-pack-index [] verify") @@ -29,6 +34,10 @@ static char const * const builtin_multi_pack_index_write_usage[] = { BUILTIN_MIDX_WRITE_USAGE, NULL }; +static char const * const builtin_multi_pack_index_compact_usage[] = { + BUILTIN_MIDX_COMPACT_USAGE, + NULL +}; static char const * const builtin_multi_pack_index_verify_usage[] = { BUILTIN_MIDX_VERIFY_USAGE, NULL @@ -43,6 +52,7 @@ static char const * const builtin_multi_pack_index_repack_usage[] = { }; static char const * const builtin_multi_pack_index_usage[] = { BUILTIN_MIDX_WRITE_USAGE, + BUILTIN_MIDX_COMPACT_USAGE, BUILTIN_MIDX_VERIFY_USAGE, BUILTIN_MIDX_EXPIRE_USAGE, BUILTIN_MIDX_REPACK_USAGE, @@ -84,6 +94,8 @@ static struct option common_opts[] = { N_("directory"), N_("object directory containing set of packfile and pack-index pairs"), parse_object_dir), + OPT_BIT(0, "progress", &opts.flags, N_("force progress reporting"), + MIDX_PROGRESS), OPT_END(), }; @@ -138,8 +150,6 @@ static int cmd_multi_pack_index_write(int argc, const char **argv, N_("pack for reuse when computing a multi-pack bitmap")), OPT_BIT(0, "bitmap", &opts.flags, N_("write multi-pack bitmap"), MIDX_WRITE_BITMAP | MIDX_WRITE_REV_INDEX), - OPT_BIT(0, "progress", &opts.flags, - N_("force progress reporting"), MIDX_PROGRESS), OPT_BIT(0, "incremental", &opts.flags, N_("write a new incremental MIDX"), MIDX_WRITE_INCREMENTAL), OPT_BOOL(0, "stdin-packs", &opts.stdin_packs, @@ -194,14 +204,71 @@ static int cmd_multi_pack_index_write(int argc, const char **argv, return ret; } +static int cmd_multi_pack_index_compact(int argc, const char **argv, + const char *prefix, + struct repository *repo) +{ + struct multi_pack_index *m, *cur; + struct multi_pack_index *from_midx = NULL; + struct multi_pack_index *to_midx = NULL; + struct odb_source *source; + int ret; + + struct option *options; + static struct option builtin_multi_pack_index_compact_options[] = { + OPT_BIT(0, "bitmap", &opts.flags, N_("write multi-pack bitmap"), + MIDX_WRITE_BITMAP | MIDX_WRITE_REV_INDEX), + OPT_BIT(0, "incremental", &opts.flags, + N_("write a new incremental MIDX"), MIDX_WRITE_INCREMENTAL), + OPT_END(), + }; + + repo_config(repo, git_multi_pack_index_write_config, NULL); + + options = add_common_options(builtin_multi_pack_index_compact_options); + + trace2_cmd_mode(argv[0]); + + if (isatty(2)) + opts.flags |= MIDX_PROGRESS; + argc = parse_options(argc, argv, prefix, + options, builtin_multi_pack_index_compact_usage, + 0); + + if (argc != 2) + usage_with_options(builtin_multi_pack_index_compact_usage, + options); + source = handle_object_dir_option(the_repository); + + FREE_AND_NULL(options); + + m = get_multi_pack_index(source); + + for (cur = m; cur && !(from_midx && to_midx); cur = cur->base_midx) { + const char *midx_csum = get_midx_checksum(cur); + + if (!from_midx && !strcmp(midx_csum, argv[0])) + from_midx = cur; + if (!to_midx && !strcmp(midx_csum, argv[1])) + to_midx = cur; + } + + if (!from_midx) + die(_("could not find MIDX 'from': %s"), argv[0]); + if (!to_midx) + die(_("could not find MIDX 'to': %s"), argv[1]); + + ret = write_midx_file_compact(source, from_midx, to_midx, opts.flags); + + return ret; +} + static int cmd_multi_pack_index_verify(int argc, const char **argv, const char *prefix, struct repository *repo UNUSED) { struct option *options; static struct option builtin_multi_pack_index_verify_options[] = { - OPT_BIT(0, "progress", &opts.flags, - N_("force progress reporting"), MIDX_PROGRESS), OPT_END(), }; struct odb_source *source; @@ -231,8 +298,6 @@ static int cmd_multi_pack_index_expire(int argc, const char **argv, { struct option *options; static struct option builtin_multi_pack_index_expire_options[] = { - OPT_BIT(0, "progress", &opts.flags, - N_("force progress reporting"), MIDX_PROGRESS), OPT_END(), }; struct odb_source *source; @@ -264,8 +329,6 @@ static int cmd_multi_pack_index_repack(int argc, const char **argv, static struct option builtin_multi_pack_index_repack_options[] = { OPT_UNSIGNED(0, "batch-size", &opts.batch_size, N_("during repack, collect pack-files of smaller size into a batch that is larger than this size")), - OPT_BIT(0, "progress", &opts.flags, - N_("force progress reporting"), MIDX_PROGRESS), OPT_END(), }; struct odb_source *source; @@ -300,6 +363,7 @@ int cmd_multi_pack_index(int argc, struct option builtin_multi_pack_index_options[] = { OPT_SUBCOMMAND("repack", &fn, cmd_multi_pack_index_repack), OPT_SUBCOMMAND("write", &fn, cmd_multi_pack_index_write), + OPT_SUBCOMMAND("compact", &fn, cmd_multi_pack_index_compact), OPT_SUBCOMMAND("verify", &fn, cmd_multi_pack_index_verify), OPT_SUBCOMMAND("expire", &fn, cmd_multi_pack_index_expire), OPT_END(), diff --git a/git-compat-util.h b/git-compat-util.h index b0673d1a45..db62a6f25c 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -641,6 +641,14 @@ static inline int cast_size_t_to_int(size_t a) return (int)a; } +static inline uint32_t u32_add(uint32_t a, uint32_t b) +{ + if (unsigned_add_overflows(a, b)) + die("uint32_t overflow: %"PRIuMAX" + %"PRIuMAX, + (uintmax_t)a, (uintmax_t)b); + return a + b; +} + static inline uint64_t u64_mult(uint64_t a, uint64_t b) { if (unsigned_mult_overflows(a, b)) diff --git a/midx-write.c b/midx-write.c index ce459b02c3..66c125ccb0 100644 --- a/midx-write.c +++ b/midx-write.c @@ -108,12 +108,24 @@ struct write_midx_context { int incremental; uint32_t num_multi_pack_indexes_before; + struct multi_pack_index *compact_from; + struct multi_pack_index *compact_to; + int compact; + struct string_list *to_include; struct repository *repo; struct odb_source *source; }; +static uint32_t midx_pack_perm(struct write_midx_context *ctx, + uint32_t orig_pack_int_id) +{ + if (ctx->compact) + orig_pack_int_id -= ctx->compact_from->num_packs_in_base; + return ctx->pack_perm[orig_pack_int_id]; +} + static int should_include_pack(const struct write_midx_context *ctx, const char *file_name) { @@ -317,6 +329,45 @@ static void midx_fanout_add_pack_fanout(struct midx_fanout *fanout, } } +static void midx_fanout_add(struct midx_fanout *fanout, + struct write_midx_context *ctx, + uint32_t start_pack, + uint32_t cur_fanout) +{ + uint32_t cur_pack; + + if (ctx->m && !ctx->incremental) + midx_fanout_add_midx_fanout(fanout, ctx->m, cur_fanout, + ctx->preferred_pack_idx); + + for (cur_pack = start_pack; cur_pack < ctx->nr; cur_pack++) { + int preferred = cur_pack == ctx->preferred_pack_idx; + midx_fanout_add_pack_fanout(fanout, ctx->info, cur_pack, + preferred, cur_fanout); + } + + if (ctx->preferred_pack_idx != NO_PREFERRED_PACK && + ctx->preferred_pack_idx < start_pack) + midx_fanout_add_pack_fanout(fanout, ctx->info, + ctx->preferred_pack_idx, 1, + cur_fanout); +} + +static void midx_fanout_add_compact(struct midx_fanout *fanout, + struct write_midx_context *ctx, + uint32_t cur_fanout) +{ + struct multi_pack_index *m = ctx->compact_to; + + ASSERT(ctx->compact); + + while (m && m != ctx->compact_from->base_midx) { + midx_fanout_add_midx_fanout(fanout, m, cur_fanout, + NO_PREFERRED_PACK); + m = m->base_midx; + } +} + /* * It is possible to artificially get into a state where there are many * duplicate copies of objects. That can create high memory pressure if @@ -335,6 +386,9 @@ static void compute_sorted_entries(struct write_midx_context *ctx, size_t alloc_objects, total_objects = 0; struct midx_fanout fanout = { 0 }; + if (ctx->compact) + ASSERT(!start_pack); + for (cur_pack = start_pack; cur_pack < ctx->nr; cur_pack++) total_objects = st_add(total_objects, ctx->info[cur_pack].p->num_objects); @@ -353,23 +407,10 @@ static void compute_sorted_entries(struct write_midx_context *ctx, for (cur_fanout = 0; cur_fanout < 256; cur_fanout++) { fanout.nr = 0; - if (ctx->m && !ctx->incremental) - midx_fanout_add_midx_fanout(&fanout, ctx->m, cur_fanout, - ctx->preferred_pack_idx); - - for (cur_pack = start_pack; cur_pack < ctx->nr; cur_pack++) { - int preferred = cur_pack == ctx->preferred_pack_idx; - midx_fanout_add_pack_fanout(&fanout, - ctx->info, cur_pack, - preferred, cur_fanout); - } - - if (ctx->preferred_pack_idx != NO_PREFERRED_PACK && - ctx->preferred_pack_idx < start_pack) - midx_fanout_add_pack_fanout(&fanout, ctx->info, - ctx->preferred_pack_idx, 1, - cur_fanout); - + if (ctx->compact) + midx_fanout_add_compact(&fanout, ctx, cur_fanout); + else + midx_fanout_add(&fanout, ctx, start_pack, cur_fanout); midx_fanout_sort(&fanout); /* @@ -410,11 +451,6 @@ static int write_midx_pack_names(struct hashfile *f, void *data) if (ctx->info[i].expired) continue; - if (i && strcmp(ctx->info[i].pack_name, ctx->info[i - 1].pack_name) <= 0) - BUG("incorrect pack-file order: %s before %s", - ctx->info[i - 1].pack_name, - ctx->info[i].pack_name); - writelen = strlen(ctx->info[i].pack_name) + 1; hashwrite(f, ctx->info[i].pack_name, writelen); written += writelen; @@ -514,12 +550,12 @@ static int write_midx_object_offsets(struct hashfile *f, for (i = 0; i < ctx->entries_nr; i++) { struct pack_midx_entry *obj = list++; - if (ctx->pack_perm[obj->pack_int_id] == PACK_EXPIRED) + if (midx_pack_perm(ctx, obj->pack_int_id) == PACK_EXPIRED) BUG("object %s is in an expired pack with int-id %d", oid_to_hex(&obj->oid), obj->pack_int_id); - hashwrite_be32(f, ctx->pack_perm[obj->pack_int_id]); + hashwrite_be32(f, midx_pack_perm(ctx, obj->pack_int_id)); if (ctx->large_offsets_needed && obj->offset >> 31) hashwrite_be32(f, MIDX_LARGE_OFFSET_NEEDED | nr_large_offset++); @@ -620,8 +656,8 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx) for (i = 0; i < ctx->entries_nr; i++) { struct pack_midx_entry *e = &ctx->entries[i]; data[i].nr = i; - data[i].pack = ctx->pack_perm[e->pack_int_id]; - if (!e->preferred) + data[i].pack = midx_pack_perm(ctx, e->pack_int_id); + if (!e->preferred || ctx->compact) data[i].pack |= (1U << 31); data[i].offset = e->offset; } @@ -630,14 +666,14 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx) for (i = 0; i < ctx->entries_nr; i++) { struct pack_midx_entry *e = &ctx->entries[data[i].nr]; - struct pack_info *pack = &ctx->info[ctx->pack_perm[e->pack_int_id]]; + struct pack_info *pack = &ctx->info[midx_pack_perm(ctx, e->pack_int_id)]; if (pack->bitmap_pos == BITMAP_POS_UNKNOWN) pack->bitmap_pos = i + base_objects; pack->bitmap_nr++; pack_order[i] = data[i].nr; } for (i = 0; i < ctx->nr; i++) { - struct pack_info *pack = &ctx->info[ctx->pack_perm[i]]; + struct pack_info *pack = &ctx->info[i]; if (pack->bitmap_pos == BITMAP_POS_UNKNOWN) pack->bitmap_pos = 0; } @@ -691,7 +727,7 @@ static void prepare_midx_packing_data(struct packing_data *pdata, struct object_entry *to = packlist_alloc(pdata, &from->oid); oe_set_in_pack(pdata, to, - ctx->info[ctx->pack_perm[from->pack_int_id]].p); + ctx->info[midx_pack_perm(ctx, from->pack_int_id)].p); } trace2_region_leave("midx", "prepare_midx_packing_data", ctx->repo); @@ -909,6 +945,21 @@ cleanup: return ret; } +static int fill_pack_from_midx(struct pack_info *info, + struct multi_pack_index *m, + uint32_t pack_int_id) +{ + if (prepare_midx_pack(m, pack_int_id)) + return error(_("could not load pack %d"), pack_int_id); + + fill_pack_info(info, + m->packs[pack_int_id - m->num_packs_in_base], + m->pack_names[pack_int_id - m->num_packs_in_base], + pack_int_id); + + return 0; +} + static int fill_packs_from_midx(struct write_midx_context *ctx) { struct multi_pack_index *m; @@ -916,19 +967,85 @@ static int fill_packs_from_midx(struct write_midx_context *ctx) for (m = ctx->m; m; m = m->base_midx) { uint32_t i; - for (i = 0; i < m->num_packs; i++) { - if (prepare_midx_pack(m, m->num_packs_in_base + i)) - return error(_("could not load pack")); - + for (i = m->num_packs_in_base; + i < m->num_packs_in_base + m->num_packs; i++) { ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); - fill_pack_info(&ctx->info[ctx->nr++], m->packs[i], - m->pack_names[i], - m->num_packs_in_base + i); + + if (fill_pack_from_midx(&ctx->info[ctx->nr], m, i) < 0) + return -1; + + ctx->nr++; } } return 0; } +static uint32_t compactible_packs_between(const struct multi_pack_index *from, + const struct multi_pack_index *to) +{ + uint32_t nr; + + ASSERT(from && to); + + nr = u32_add(to->num_packs, to->num_packs_in_base); + if (nr < from->num_packs_in_base) + BUG("unexpected number of packs in base during compaction: " + "%"PRIu32" < %"PRIu32, nr, from->num_packs_in_base); + + return nr - from->num_packs_in_base; +} + +static int fill_packs_from_midx_range(struct write_midx_context *ctx, + int bitmap_order) +{ + struct multi_pack_index *m = ctx->compact_to; + uint32_t packs_nr; + + ASSERT(ctx->compact && !ctx->nr); + ASSERT(ctx->compact_from); + ASSERT(ctx->compact_to); + + packs_nr = compactible_packs_between(ctx->compact_from, + ctx->compact_to); + + ALLOC_GROW(ctx->info, packs_nr, ctx->alloc); + + while (m != ctx->compact_from->base_midx) { + uint32_t pack_int_id, preferred_pack_id; + uint32_t i; + + if (bitmap_order) { + if (midx_preferred_pack(m, &preferred_pack_id) < 0) + die(_("could not determine preferred pack")); + } else { + preferred_pack_id = m->num_packs_in_base; + } + + pack_int_id = m->num_packs_in_base - ctx->compact_from->num_packs_in_base; + + if (fill_pack_from_midx(&ctx->info[pack_int_id++], m, + preferred_pack_id) < 0) + return -1; + + for (i = m->num_packs_in_base; + i < m->num_packs_in_base + m->num_packs; i++) { + if (preferred_pack_id == i) + continue; + + if (fill_pack_from_midx(&ctx->info[pack_int_id++], m, + i) < 0) + return -1; + } + + ctx->nr += m->num_packs; + m = m->base_midx; + } + + ASSERT(ctx->nr == packs_nr); + + return 0; +} + static struct { const char *non_split; const char *split; @@ -955,7 +1072,7 @@ static int link_midx_to_chain(struct multi_pack_index *m) } for (i = 0; i < ARRAY_SIZE(midx_exts); i++) { - const unsigned char *hash = get_midx_checksum(m); + const unsigned char *hash = get_midx_hash(m); get_midx_filename_ext(m->source, &from, hash, midx_exts[i].non_split); @@ -1025,7 +1142,7 @@ static bool midx_needs_update(struct multi_pack_index *midx, struct write_midx_c * incremental update would be either empty (in which case we will bail * out later) or it would actually cover at least one new pack. */ - if (ctx->incremental) + if (ctx->incremental || ctx->compact) goto out; /* @@ -1073,14 +1190,30 @@ out: return needed; } -static int write_midx_internal(struct odb_source *source, - struct string_list *packs_to_include, - struct string_list *packs_to_drop, - const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags) +static int midx_hashcmp(const struct multi_pack_index *a, + const struct multi_pack_index *b, + const struct git_hash_algo *algop) { - struct repository *r = source->odb->repo; + return hashcmp(get_midx_hash(a), get_midx_hash(b), algop); +} + +struct write_midx_opts { + struct odb_source *source; + + struct string_list *packs_to_include; + struct string_list *packs_to_drop; + + struct multi_pack_index *compact_from; + struct multi_pack_index *compact_to; + + const char *preferred_pack_name; + const char *refs_snapshot; + unsigned flags; +}; + +static int write_midx_internal(struct write_midx_opts *opts) +{ + struct repository *r = opts->source->odb->repo; struct strbuf midx_name = STRBUF_INIT; unsigned char midx_hash[GIT_MAX_RAWSZ]; uint32_t start_pack; @@ -1096,27 +1229,39 @@ static int write_midx_internal(struct odb_source *source, int dropped_packs = 0; int result = -1; const char **keep_hashes = NULL; + size_t keep_hashes_nr = 0; struct chunkfile *cf; trace2_region_enter("midx", "write_midx_internal", r); ctx.repo = r; - ctx.source = source; + ctx.source = opts->source; - ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL); + ctx.incremental = !!(opts->flags & MIDX_WRITE_INCREMENTAL); + ctx.compact = !!(opts->flags & MIDX_WRITE_COMPACT); + + if (ctx.compact) { + if (!opts->compact_from) + BUG("expected non-NULL 'from' MIDX during compaction"); + if (!opts->compact_to) + BUG("expected non-NULL 'to' MIDX during compaction"); + + ctx.compact_from = opts->compact_from; + ctx.compact_to = opts->compact_to; + } if (ctx.incremental) strbuf_addf(&midx_name, "%s/pack/multi-pack-index.d/tmp_midx_XXXXXX", - source->path); + opts->source->path); else - get_midx_filename(source, &midx_name); + get_midx_filename(opts->source, &midx_name); if (safe_create_leading_directories(r, midx_name.buf)) die_errno(_("unable to create leading directories of %s"), midx_name.buf); - if (!packs_to_include || ctx.incremental) { - struct multi_pack_index *m = get_multi_pack_index(source); + if (!opts->packs_to_include || ctx.incremental) { + struct multi_pack_index *m = get_multi_pack_index(opts->source); if (m && !midx_checksum_valid(m)) { warning(_("ignoring existing multi-pack-index; checksum mismatch")); m = NULL; @@ -1131,11 +1276,18 @@ static int write_midx_internal(struct odb_source *source, */ if (ctx.incremental) ctx.base_midx = m; - else if (!packs_to_include) + if (!opts->packs_to_include) ctx.m = m; } } + /* + * If compacting MIDX layer(s) in the range [from, to], then the + * compacted MIDX will share the same base MIDX as 'from'. + */ + if (ctx.compact) + ctx.base_midx = ctx.compact_from->base_midx; + ctx.nr = 0; ctx.alloc = ctx.m ? ctx.m->num_packs + ctx.m->num_packs_in_base : 16; ctx.info = NULL; @@ -1144,34 +1296,42 @@ static int write_midx_internal(struct odb_source *source, if (ctx.incremental) { struct multi_pack_index *m = ctx.base_midx; while (m) { - if (flags & MIDX_WRITE_BITMAP && load_midx_revindex(m)) { + if (opts->flags & MIDX_WRITE_BITMAP && load_midx_revindex(m)) { error(_("could not load reverse index for MIDX %s"), - hash_to_hex_algop(get_midx_checksum(m), - m->source->odb->repo->hash_algo)); + get_midx_checksum(m)); goto cleanup; } ctx.num_multi_pack_indexes_before++; m = m->base_midx; } - } else if (ctx.m && fill_packs_from_midx(&ctx)) { + } else if (ctx.m && !ctx.compact && fill_packs_from_midx(&ctx)) { goto cleanup; } start_pack = ctx.nr; ctx.pack_paths_checked = 0; - if (flags & MIDX_PROGRESS) + if (opts->flags & MIDX_PROGRESS) ctx.progress = start_delayed_progress(r, _("Adding packfiles to multi-pack-index"), 0); else ctx.progress = NULL; - ctx.to_include = packs_to_include; + if (ctx.compact) { + int bitmap_order = 0; + if (opts->preferred_pack_name) + bitmap_order |= 1; + else if (opts->flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP)) + bitmap_order |= 1; - for_each_file_in_pack_dir(source->path, add_pack_to_midx, &ctx); + fill_packs_from_midx_range(&ctx, bitmap_order); + } else { + ctx.to_include = opts->packs_to_include; + for_each_file_in_pack_dir(opts->source->path, add_pack_to_midx, &ctx); + } stop_progress(&ctx.progress); - if (!packs_to_drop) { + if (!opts->packs_to_drop) { /* * If there is no MIDX then either it doesn't exist, or we're * doing a geometric repack. Try to load it from the source to @@ -1184,7 +1344,7 @@ static int write_midx_internal(struct odb_source *source, if (midx && !midx_needs_update(midx, &ctx)) { struct bitmap_index *bitmap_git; int bitmap_exists; - int want_bitmap = flags & MIDX_WRITE_BITMAP; + int want_bitmap = opts->flags & MIDX_WRITE_BITMAP; bitmap_git = prepare_midx_bitmap_git(midx); bitmap_exists = bitmap_git && bitmap_is_midx(bitmap_git); @@ -1196,7 +1356,8 @@ static int write_midx_internal(struct odb_source *source, * corresponding bitmap (or one wasn't requested). */ if (!want_bitmap) - clear_midx_files_ext(source, "bitmap", NULL); + clear_midx_files_ext(opts->source, + "bitmap", NULL); result = 0; goto cleanup; } @@ -1211,11 +1372,11 @@ static int write_midx_internal(struct odb_source *source, goto cleanup; /* nothing to do */ } - if (preferred_pack_name) { + if (opts->preferred_pack_name) { ctx.preferred_pack_idx = NO_PREFERRED_PACK; for (size_t i = 0; i < ctx.nr; i++) { - if (!cmp_idx_or_pack_name(preferred_pack_name, + if (!cmp_idx_or_pack_name(opts->preferred_pack_name, ctx.info[i].pack_name)) { ctx.preferred_pack_idx = i; break; @@ -1224,9 +1385,9 @@ static int write_midx_internal(struct odb_source *source, if (ctx.preferred_pack_idx == NO_PREFERRED_PACK) warning(_("unknown preferred pack: '%s'"), - preferred_pack_name); + opts->preferred_pack_name); } else if (ctx.nr && - (flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP))) { + (opts->flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP))) { struct packed_git *oldest = ctx.info[0].p; ctx.preferred_pack_idx = 0; @@ -1237,7 +1398,7 @@ static int write_midx_internal(struct odb_source *source, */ open_pack_index(oldest); - if (packs_to_drop && packs_to_drop->nr) + if (opts->packs_to_drop && opts->packs_to_drop->nr) BUG("cannot write a MIDX bitmap during expiration"); /* @@ -1297,22 +1458,26 @@ static int write_midx_internal(struct odb_source *source, ctx.large_offsets_needed = 1; } - QSORT(ctx.info, ctx.nr, pack_info_compare); + if (!ctx.compact) + QSORT(ctx.info, ctx.nr, pack_info_compare); - if (packs_to_drop && packs_to_drop->nr) { + if (opts->packs_to_drop && opts->packs_to_drop->nr) { size_t drop_index = 0; int missing_drops = 0; - for (size_t i = 0; i < ctx.nr && drop_index < packs_to_drop->nr; i++) { + ASSERT(!ctx.compact); + + for (size_t i = 0; + i < ctx.nr && drop_index < opts->packs_to_drop->nr; i++) { int cmp = strcmp(ctx.info[i].pack_name, - packs_to_drop->items[drop_index].string); + opts->packs_to_drop->items[drop_index].string); if (!cmp) { drop_index++; ctx.info[i].expired = 1; } else if (cmp > 0) { error(_("did not see pack-file %s to drop"), - packs_to_drop->items[drop_index].string); + opts->packs_to_drop->items[drop_index].string); drop_index++; missing_drops++; i--; @@ -1333,12 +1498,20 @@ static int write_midx_internal(struct odb_source *source, */ ALLOC_ARRAY(ctx.pack_perm, ctx.nr); for (size_t i = 0; i < ctx.nr; i++) { + uint32_t from = ctx.info[i].orig_pack_int_id; + uint32_t to; + if (ctx.info[i].expired) { + to = PACK_EXPIRED; dropped_packs++; - ctx.pack_perm[ctx.info[i].orig_pack_int_id] = PACK_EXPIRED; } else { - ctx.pack_perm[ctx.info[i].orig_pack_int_id] = i - dropped_packs; + to = i - dropped_packs; } + + if (ctx.compact) + from -= ctx.compact_from->num_packs_in_base; + + ctx.pack_perm[from] = to; } for (size_t i = 0; i < ctx.nr; i++) { @@ -1349,16 +1522,16 @@ static int write_midx_internal(struct odb_source *source, } /* Check that the preferred pack wasn't expired (if given). */ - if (preferred_pack_name) { - struct pack_info *preferred = bsearch(preferred_pack_name, + if (opts->preferred_pack_name) { + struct pack_info *preferred = bsearch(opts->preferred_pack_name, ctx.info, ctx.nr, sizeof(*ctx.info), idx_or_pack_name_cmp); if (preferred) { - uint32_t perm = ctx.pack_perm[preferred->orig_pack_int_id]; + uint32_t perm = midx_pack_perm(&ctx, preferred->orig_pack_int_id); if (perm == PACK_EXPIRED) warning(_("preferred pack '%s' is expired"), - preferred_pack_name); + opts->preferred_pack_name); } } @@ -1372,15 +1545,15 @@ static int write_midx_internal(struct odb_source *source, } if (!ctx.entries_nr) { - if (flags & MIDX_WRITE_BITMAP) + if (opts->flags & MIDX_WRITE_BITMAP) warning(_("refusing to write multi-pack .bitmap without any objects")); - flags &= ~(MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP); + opts->flags &= ~(MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP); } if (ctx.incremental) { struct strbuf lock_name = STRBUF_INIT; - get_midx_chain_filename(source, &lock_name); + get_midx_chain_filename(opts->source, &lock_name); hold_lock_file_for_update(&lk, lock_name.buf, LOCK_DIE_ON_ERROR); strbuf_release(&lock_name); @@ -1423,7 +1596,7 @@ static int write_midx_internal(struct odb_source *source, MIDX_CHUNK_LARGE_OFFSET_WIDTH), write_midx_large_offsets); - if (flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP)) { + if (opts->flags & (MIDX_WRITE_REV_INDEX | MIDX_WRITE_BITMAP)) { ctx.pack_order = midx_pack_order(&ctx); add_chunk(cf, MIDX_CHUNKID_REVINDEX, st_mult(ctx.entries_nr, sizeof(uint32_t)), @@ -1441,11 +1614,11 @@ static int write_midx_internal(struct odb_source *source, CSUM_FSYNC | CSUM_HASH_IN_STREAM); free_chunkfile(cf); - if (flags & MIDX_WRITE_REV_INDEX && + if (opts->flags & MIDX_WRITE_REV_INDEX && git_env_bool("GIT_TEST_MIDX_WRITE_REV", 0)) write_midx_reverse_index(&ctx, midx_hash); - if (flags & MIDX_WRITE_BITMAP) { + if (opts->flags & MIDX_WRITE_BITMAP) { struct packing_data pdata; struct commit **commits; uint32_t commits_nr; @@ -1455,7 +1628,7 @@ static int write_midx_internal(struct odb_source *source, prepare_midx_packing_data(&pdata, &ctx); - commits = find_commits_for_midx_bitmap(&commits_nr, refs_snapshot, &ctx); + commits = find_commits_for_midx_bitmap(&commits_nr, opts->refs_snapshot, &ctx); /* * The previous steps translated the information from @@ -1468,7 +1641,7 @@ static int write_midx_internal(struct odb_source *source, if (write_midx_bitmap(&ctx, midx_hash, &pdata, commits, commits_nr, - flags) < 0) { + opts->flags) < 0) { error(_("could not write multi-pack bitmap")); clear_packing_data(&pdata); free(commits); @@ -1486,7 +1659,24 @@ static int write_midx_internal(struct odb_source *source, if (ctx.num_multi_pack_indexes_before == UINT32_MAX) die(_("too many multi-pack-indexes")); - CALLOC_ARRAY(keep_hashes, ctx.num_multi_pack_indexes_before + 1); + if (ctx.compact) { + struct multi_pack_index *m; + + /* + * Keep all MIDX layers excluding those in the range [from, to]. + */ + for (m = ctx.base_midx; m; m = m->base_midx) + keep_hashes_nr++; + for (m = ctx.m; + m && midx_hashcmp(m, ctx.compact_to, r->hash_algo); + m = m->base_midx) + keep_hashes_nr++; + + keep_hashes_nr++; /* include the compacted layer */ + } else { + keep_hashes_nr = ctx.num_multi_pack_indexes_before + 1; + } + CALLOC_ARRAY(keep_hashes, keep_hashes_nr); if (ctx.incremental) { FILE *chainf = fdopen_lock_file(&lk, "w"); @@ -1501,7 +1691,7 @@ static int write_midx_internal(struct odb_source *source, if (link_midx_to_chain(ctx.base_midx) < 0) goto cleanup; - get_split_midx_filename_ext(source, &final_midx_name, + get_split_midx_filename_ext(opts->source, &final_midx_name, midx_hash, MIDX_EXT_MIDX); if (rename_tempfile(&incr, final_midx_name.buf) < 0) { @@ -1511,18 +1701,47 @@ static int write_midx_internal(struct odb_source *source, strbuf_release(&final_midx_name); - keep_hashes[ctx.num_multi_pack_indexes_before] = - xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo)); + if (ctx.compact) { + struct multi_pack_index *m; + uint32_t num_layers_before_from = 0; + uint32_t i; - for (uint32_t i = 0; i < ctx.num_multi_pack_indexes_before; i++) { - uint32_t j = ctx.num_multi_pack_indexes_before - i - 1; + for (m = ctx.base_midx; m; m = m->base_midx) + num_layers_before_from++; - keep_hashes[j] = xstrdup(hash_to_hex_algop(get_midx_checksum(m), + m = ctx.base_midx; + for (i = 0; i < num_layers_before_from; i++) { + uint32_t j = num_layers_before_from - i - 1; + + keep_hashes[j] = xstrdup(get_midx_checksum(m)); + m = m->base_midx; + } + + keep_hashes[i] = xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo)); - m = m->base_midx; + + i = 0; + for (m = ctx.m; + m && midx_hashcmp(m, ctx.compact_to, r->hash_algo); + m = m->base_midx) { + keep_hashes[keep_hashes_nr - i - 1] = + xstrdup(get_midx_checksum(m)); + i++; + } + } else { + keep_hashes[ctx.num_multi_pack_indexes_before] = + xstrdup(hash_to_hex_algop(midx_hash, + r->hash_algo)); + + for (uint32_t i = 0; i < ctx.num_multi_pack_indexes_before; i++) { + uint32_t j = ctx.num_multi_pack_indexes_before - i - 1; + + keep_hashes[j] = xstrdup(get_midx_checksum(m)); + m = m->base_midx; + } } - for (uint32_t i = 0; i <= ctx.num_multi_pack_indexes_before; i++) + for (uint32_t i = 0; i < keep_hashes_nr; i++) fprintf(get_lock_file_fp(&lk), "%s\n", keep_hashes[i]); } else { keep_hashes[ctx.num_multi_pack_indexes_before] = @@ -1535,8 +1754,7 @@ static int write_midx_internal(struct odb_source *source, if (commit_lock_file(&lk) < 0) die_errno(_("could not write multi-pack-index")); - clear_midx_files(source, keep_hashes, - ctx.num_multi_pack_indexes_before + 1, + clear_midx_files(opts->source, keep_hashes, keep_hashes_nr, ctx.incremental); result = 0; @@ -1554,7 +1772,7 @@ cleanup: free(ctx.pack_perm); free(ctx.pack_order); if (keep_hashes) { - for (uint32_t i = 0; i <= ctx.num_multi_pack_indexes_before; i++) + for (uint32_t i = 0; i < keep_hashes_nr; i++) free((char *)keep_hashes[i]); free(keep_hashes); } @@ -1570,9 +1788,14 @@ int write_midx_file(struct odb_source *source, const char *preferred_pack_name, const char *refs_snapshot, unsigned flags) { - return write_midx_internal(source, NULL, NULL, - preferred_pack_name, refs_snapshot, - flags); + struct write_midx_opts opts = { + .source = source, + .preferred_pack_name = preferred_pack_name, + .refs_snapshot = refs_snapshot, + .flags = flags, + }; + + return write_midx_internal(&opts); } int write_midx_file_only(struct odb_source *source, @@ -1580,8 +1803,30 @@ int write_midx_file_only(struct odb_source *source, const char *preferred_pack_name, const char *refs_snapshot, unsigned flags) { - return write_midx_internal(source, packs_to_include, NULL, - preferred_pack_name, refs_snapshot, flags); + struct write_midx_opts opts = { + .source = source, + .packs_to_include = packs_to_include, + .preferred_pack_name = preferred_pack_name, + .refs_snapshot = refs_snapshot, + .flags = flags, + }; + + return write_midx_internal(&opts); +} + +int write_midx_file_compact(struct odb_source *source, + struct multi_pack_index *from, + struct multi_pack_index *to, + unsigned flags) +{ + struct write_midx_opts opts = { + .source = source, + .compact_from = from, + .compact_to = to, + .flags = flags | MIDX_WRITE_COMPACT, + }; + + return write_midx_internal(&opts); } int expire_midx_packs(struct odb_source *source, unsigned flags) @@ -1641,8 +1886,11 @@ int expire_midx_packs(struct odb_source *source, unsigned flags) free(count); if (packs_to_drop.nr) - result = write_midx_internal(source, NULL, - &packs_to_drop, NULL, NULL, flags); + result = write_midx_internal(&(struct write_midx_opts) { + .source = source, + .packs_to_drop = &packs_to_drop, + .flags = flags & MIDX_PROGRESS, + }); string_list_clear(&packs_to_drop, 0); @@ -1849,8 +2097,10 @@ int midx_repack(struct odb_source *source, size_t batch_size, unsigned flags) goto cleanup; } - result = write_midx_internal(source, NULL, NULL, NULL, NULL, - flags); + result = write_midx_internal(&(struct write_midx_opts) { + .source = source, + .flags = flags, + }); cleanup: free(include_pack); diff --git a/midx.c b/midx.c index b681b18fc1..bbcce8783e 100644 --- a/midx.c +++ b/midx.c @@ -24,7 +24,13 @@ void clear_incremental_midx_files_ext(struct odb_source *source, const char *ext int cmp_idx_or_pack_name(const char *idx_or_pack_name, const char *idx_name); -const unsigned char *get_midx_checksum(struct multi_pack_index *m) +const char *get_midx_checksum(const struct multi_pack_index *m) +{ + return hash_to_hex_algop(get_midx_hash(m), + m->source->odb->repo->hash_algo); +} + +const unsigned char *get_midx_hash(const struct multi_pack_index *m) { return m->data + m->data_len - m->source->odb->repo->hash_algo->rawsz; } @@ -203,11 +209,6 @@ static struct multi_pack_index *load_multi_pack_index_one(struct odb_source *sou if (!end) die(_("multi-pack-index pack-name chunk is too short")); cur_pack_name = end + 1; - - if (i && strcmp(m->pack_names[i], m->pack_names[i - 1]) <= 0) - die(_("multi-pack-index pack names out of order: '%s' before '%s'"), - m->pack_names[i - 1], - m->pack_names[i]); } trace2_data_intmax("midx", r, "load/num_packs", m->num_packs); @@ -405,6 +406,7 @@ void close_midx(struct multi_pack_index *m) } FREE_AND_NULL(m->packs); FREE_AND_NULL(m->pack_names); + FREE_AND_NULL(m->pack_names_sorted); free(m); } @@ -650,17 +652,37 @@ int cmp_idx_or_pack_name(const char *idx_or_pack_name, return strcmp(idx_or_pack_name, idx_name); } + +static int midx_pack_names_cmp(const void *a, const void *b, void *m_) +{ + struct multi_pack_index *m = m_; + return strcmp(m->pack_names[*(const size_t *)a], + m->pack_names[*(const size_t *)b]); +} + static int midx_contains_pack_1(struct multi_pack_index *m, const char *idx_or_pack_name) { uint32_t first = 0, last = m->num_packs; + if (!m->pack_names_sorted) { + uint32_t i; + + ALLOC_ARRAY(m->pack_names_sorted, m->num_packs); + + for (i = 0; i < m->num_packs; i++) + m->pack_names_sorted[i] = i; + + QSORT_S(m->pack_names_sorted, m->num_packs, midx_pack_names_cmp, + m); + } + while (first < last) { uint32_t mid = first + (last - first) / 2; const char *current; int cmp; - current = m->pack_names[mid]; + current = m->pack_names[m->pack_names_sorted[mid]]; cmp = cmp_idx_or_pack_name(idx_or_pack_name, current); if (!cmp) return 1; diff --git a/midx.h b/midx.h index 6e54d73503..61f9809b8c 100644 --- a/midx.h +++ b/midx.h @@ -71,6 +71,7 @@ struct multi_pack_index { uint32_t num_packs_in_base; const char **pack_names; + size_t *pack_names_sorted; struct packed_git **packs; }; @@ -80,12 +81,14 @@ struct multi_pack_index { #define MIDX_WRITE_BITMAP_HASH_CACHE (1 << 3) #define MIDX_WRITE_BITMAP_LOOKUP_TABLE (1 << 4) #define MIDX_WRITE_INCREMENTAL (1 << 5) +#define MIDX_WRITE_COMPACT (1 << 6) #define MIDX_EXT_REV "rev" #define MIDX_EXT_BITMAP "bitmap" #define MIDX_EXT_MIDX "midx" -const unsigned char *get_midx_checksum(struct multi_pack_index *m); +const char *get_midx_checksum(const struct multi_pack_index *m) /* static buffer */; +const unsigned char *get_midx_hash(const struct multi_pack_index *m); void get_midx_filename(struct odb_source *source, struct strbuf *out); void get_midx_filename_ext(struct odb_source *source, struct strbuf *out, const unsigned char *hash, const char *ext); @@ -128,6 +131,10 @@ int write_midx_file_only(struct odb_source *source, struct string_list *packs_to_include, const char *preferred_pack_name, const char *refs_snapshot, unsigned flags); +int write_midx_file_compact(struct odb_source *source, + struct multi_pack_index *from, + struct multi_pack_index *to, + unsigned flags); void clear_midx_file(struct repository *r); int verify_midx_file(struct odb_source *source, unsigned flags); int expire_midx_packs(struct odb_source *source, unsigned flags); diff --git a/pack-bitmap.c b/pack-bitmap.c index 8ca79725b1..f466ed2ddc 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -441,11 +441,11 @@ char *midx_bitmap_filename(struct multi_pack_index *midx) struct strbuf buf = STRBUF_INIT; if (midx->has_chain) get_split_midx_filename_ext(midx->source, &buf, - get_midx_checksum(midx), + get_midx_hash(midx), MIDX_EXT_BITMAP); else get_midx_filename_ext(midx->source, &buf, - get_midx_checksum(midx), + get_midx_hash(midx), MIDX_EXT_BITMAP); return strbuf_detach(&buf, NULL); @@ -502,7 +502,7 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, if (load_bitmap_header(bitmap_git) < 0) goto cleanup; - if (!hasheq(get_midx_checksum(bitmap_git->midx), bitmap_git->checksum, + if (!hasheq(get_midx_hash(bitmap_git->midx), bitmap_git->checksum, bitmap_repo(bitmap_git)->hash_algo)) { error(_("checksum doesn't match in MIDX and bitmap")); goto cleanup; @@ -2820,8 +2820,7 @@ void test_bitmap_walk(struct rev_info *revs) if (bitmap_is_midx(found)) fprintf_ln(stderr, "Located via MIDX '%s'.", - hash_to_hex_algop(get_midx_checksum(found->midx), - revs->repo->hash_algo)); + get_midx_checksum(found->midx)); else fprintf_ln(stderr, "Located via pack '%s'.", hash_to_hex_algop(found->pack->hash, diff --git a/pack-revindex.c b/pack-revindex.c index 8598b941c8..e2646d682f 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -390,11 +390,11 @@ int load_midx_revindex(struct multi_pack_index *m) if (m->has_chain) get_split_midx_filename_ext(m->source, &revindex_name, - get_midx_checksum(m), + get_midx_hash(m), MIDX_EXT_REV); else get_midx_filename_ext(m->source, &revindex_name, - get_midx_checksum(m), + get_midx_hash(m), MIDX_EXT_REV); ret = load_revindex_from_disk(m->source->odb->repo->hash_algo, diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c index 6de5d1665a..6e03aabca7 100644 --- a/t/helper/test-read-midx.c +++ b/t/helper/test-read-midx.c @@ -26,18 +26,22 @@ static int read_midx_file(const char *object_dir, const char *checksum, int show_objects) { uint32_t i; - struct multi_pack_index *m; + struct multi_pack_index *m, *tip; + int ret = 0; - m = setup_midx(object_dir); + m = tip = setup_midx(object_dir); if (!m) return 1; if (checksum) { - while (m && strcmp(hash_to_hex(get_midx_checksum(m)), checksum)) + while (m && strcmp(get_midx_checksum(m), checksum)) m = m->base_midx; - if (!m) - return 1; + if (!m) { + ret = error(_("could not find MIDX with checksum %s"), + checksum); + goto out; + } } printf("header: %08x %d %d %d %d\n", @@ -82,9 +86,10 @@ static int read_midx_file(const char *object_dir, const char *checksum, } } - close_midx(m); +out: + close_midx(tip); - return 0; + return ret; } static int read_midx_checksum(const char *object_dir) @@ -94,7 +99,7 @@ static int read_midx_checksum(const char *object_dir) m = setup_midx(object_dir); if (!m) return 1; - printf("%s\n", hash_to_hex(get_midx_checksum(m))); + printf("%s\n", get_midx_checksum(m)); close_midx(m); return 0; diff --git a/t/meson.build b/t/meson.build index 38d5b6abdc..4ea2b0a669 100644 --- a/t/meson.build +++ b/t/meson.build @@ -617,6 +617,7 @@ integration_tests = [ 't5332-multi-pack-reuse.sh', 't5333-pseudo-merge-bitmaps.sh', 't5334-incremental-multi-pack-index.sh', + 't5335-compact-multi-pack-index.sh', 't5351-unpack-large-objects.sh', 't5400-send-pack.sh', 't5401-update-hooks.sh', diff --git a/t/t0450/adoc-help-mismatches b/t/t0450/adoc-help-mismatches index 8ee2d3f7c8..e8d6c13ccd 100644 --- a/t/t0450/adoc-help-mismatches +++ b/t/t0450/adoc-help-mismatches @@ -33,7 +33,6 @@ merge merge-file merge-index merge-one-file -multi-pack-index name-rev notes push diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh index 794f8b5ab4..a7e4f0c40c 100755 --- a/t/t5319-multi-pack-index.sh +++ b/t/t5319-multi-pack-index.sh @@ -514,12 +514,7 @@ test_expect_success 'verify invalid chunk offset' ' "improper chunk offset(s)" ' -test_expect_success 'verify packnames out of order' ' - corrupt_midx_and_verify $MIDX_BYTE_PACKNAME_ORDER "z" $objdir \ - "pack names out of order" -' - -test_expect_success 'verify packnames out of order' ' +test_expect_success 'verify missing pack' ' corrupt_midx_and_verify $MIDX_BYTE_PACKNAME_ORDER "a" $objdir \ "failed to load pack" ' diff --git a/t/t5335-compact-multi-pack-index.sh b/t/t5335-compact-multi-pack-index.sh new file mode 100755 index 0000000000..a306f50430 --- /dev/null +++ b/t/t5335-compact-multi-pack-index.sh @@ -0,0 +1,218 @@ +#!/bin/sh + +test_description='multi-pack-index compaction' + +. ./test-lib.sh + +GIT_TEST_MULTI_PACK_INDEX=0 +GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 +GIT_TEST_MULTI_PACK_INDEX_WRITE_INCREMENTAL=0 + +objdir=.git/objects +packdir=$objdir/pack +midxdir=$packdir/multi-pack-index.d +midx_chain=$midxdir/multi-pack-index-chain + +nth_line() { + local n="$1" + shift + awk "NR==$n" "$@" +} + +write_packs () { + for c in "$@" + do + test_commit "$c" && + + git pack-objects --all --unpacked $packdir/pack-$c && + git prune-packed && + + git multi-pack-index write --incremental --bitmap || return 1 + done +} + +test_midx_layer_packs () { + local checksum="$1" && + shift && + + test-tool read-midx $objdir "$checksum" >out && + + printf "%s\n" "$@" >expect && + # NOTE: do *not* pipe through sort here, we want to ensure the + # order of packs is preserved during compaction. + grep "^pack-" out | cut -d"-" -f2 >actual && + + test_cmp expect actual +} + +test_midx_layer_object_uniqueness () { + : >objs.all + while read layer + do + test-tool read-midx --show-objects $objdir "$layer" >out && + grep "\.pack$" out | cut -d" " -f1 | sort >objs.layer && + test_stdout_line_count = 0 comm -12 objs.all objs.layer && + cat objs.all objs.layer | sort >objs.tmp && + mv objs.tmp objs.all || return 1 + done <$midx_chain +} + +test_expect_success 'MIDX compaction with lex-ordered pack names' ' + git init midx-compact-lex-order && + ( + cd midx-compact-lex-order && + + write_packs A B C D E && + test_line_count = 5 $midx_chain && + + git multi-pack-index compact --incremental --bitmap \ + "$(nth_line 2 "$midx_chain")" \ + "$(nth_line 4 "$midx_chain")" && + test_line_count = 3 $midx_chain && + + test_midx_layer_packs "$(nth_line 1 "$midx_chain")" A && + test_midx_layer_packs "$(nth_line 2 "$midx_chain")" B C D && + test_midx_layer_packs "$(nth_line 3 "$midx_chain")" E && + + test_midx_layer_object_uniqueness + ) +' + +test_expect_success 'MIDX compaction with non-lex-ordered pack names' ' + git init midx-compact-non-lex-order && + ( + cd midx-compact-non-lex-order && + + write_packs D C A B E && + test_line_count = 5 $midx_chain && + + git multi-pack-index compact --incremental --bitmap \ + "$(nth_line 2 "$midx_chain")" \ + "$(nth_line 4 "$midx_chain")" && + test_line_count = 3 $midx_chain && + + test_midx_layer_packs "$(nth_line 1 "$midx_chain")" D && + test_midx_layer_packs "$(nth_line 2 "$midx_chain")" C A B && + test_midx_layer_packs "$(nth_line 3 "$midx_chain")" E && + + test_midx_layer_object_uniqueness + ) +' + +midx_objs_by_pack () { + awk '/\.pack$/ { split($3, a, "-"); print a[2], $1 }' | sort +} + +tag_objs_from_pack () { + objs="$(git rev-list --objects --no-object-names "$2")" && + printf "$1 %s\n" $objs | sort +} + +test_expect_success 'MIDX compaction preserves pack object selection' ' + git init midx-compact-preserve-selection && + ( + cd midx-compact-preserve-selection && + + test_commit A && + test_commit B && + + # Create two packs, one containing just the objects from + # A, and another containing all objects from the + # repository. + p1="$(echo A | git pack-objects --revs --delta-base-offset \ + $packdir/pack-1)" && + p0="$(echo B | git pack-objects --revs --delta-base-offset \ + $packdir/pack-0)" && + + echo "pack-1-$p1.idx" | git multi-pack-index write \ + --incremental --bitmap --stdin-packs && + echo "pack-0-$p0.idx" | git multi-pack-index write \ + --incremental --bitmap --stdin-packs && + + write_packs C && + + git multi-pack-index compact --incremental --bitmap \ + "$(nth_line 1 "$midx_chain")" \ + "$(nth_line 2 "$midx_chain")" && + + + test-tool read-midx --show-objects $objdir \ + "$(nth_line 1 "$midx_chain")" >AB.info && + test-tool read-midx --show-objects $objdir \ + "$(nth_line 2 "$midx_chain")" >C.info && + + midx_objs_by_pack AB.actual && + midx_objs_by_pack C.actual && + + { + tag_objs_from_pack 1 A && + tag_objs_from_pack 0 A..B + } | sort >AB.expect && + tag_objs_from_pack C B..C >C.expect && + + test_cmp AB.expect AB.actual && + test_cmp C.expect C.actual + ) +' + +test_expect_success 'MIDX compaction with bitmaps' ' + git init midx-compact-with-bitmaps && + ( + cd midx-compact-with-bitmaps && + + write_packs foo bar baz quux woot && + + test-tool read-midx --bitmap $objdir >bitmap.expect && + git multi-pack-index compact --incremental --bitmap \ + "$(nth_line 2 "$midx_chain")" \ + "$(nth_line 4 "$midx_chain")" && + test-tool read-midx --bitmap $objdir >bitmap.actual && + + test_cmp bitmap.expect bitmap.actual && + + true + ) +' + +test_expect_success 'MIDX compaction with bitmaps (non-trivial)' ' + git init midx-compact-with-bitmaps-non-trivial && + ( + cd midx-compact-with-bitmaps-non-trivial && + + git branch -m main && + + # D(4) + # / + # A(1) --- B(2) --- C(3) --- G(7) + # \ + # E(5) --- F(6) + write_packs A B C && + git checkout -b side && + write_packs D && + git checkout -b other B && + write_packs E F && + git checkout main && + write_packs G && + + cat $midx_chain && + + # Compact layers 2-4, leaving us with: + # + # [A, [B, C, D], E, F, G] + git multi-pack-index compact --incremental --bitmap \ + "$(nth_line 2 "$midx_chain")" \ + "$(nth_line 4 "$midx_chain")" && + + # Then compact the top two layers, condensing the above + # such that the new 4th layer contains F and G. + # + # [A, [B, C, D], E, [F, G]] + git multi-pack-index compact --incremental --bitmap \ + "$(nth_line 4 "$midx_chain")" \ + "$(nth_line 5 "$midx_chain")" && + + cat $midx_chain + ) +' + +test_done