diff --git a/midx-write.c b/midx-write.c index 55a6b63bac..0125aa4dc9 100644 --- a/midx-write.c +++ b/midx-write.c @@ -101,13 +101,27 @@ struct write_midx_context { }; static int should_include_pack(const struct write_midx_context *ctx, - const char *file_name, - int exclude_from_midx) + const char *file_name) { - if (exclude_from_midx && ctx->m && midx_contains_pack(ctx->m, file_name)) + /* + * Note that at most one of ctx->m and ctx->to_include are set, + * so we are testing midx_contains_pack() and + * string_list_has_string() independently (guarded by the + * appropriate NULL checks). + * + * We could support passing to_include while reusing an existing + * MIDX, but don't currently since the reuse process drags + * forward all packs from an existing MIDX (without checking + * whether or not they appear in the to_include list). + * + * If we added support for that, these next two conditional + * should be performed independently (likely checking + * to_include before the existing MIDX). + */ + if (ctx->m && midx_contains_pack(ctx->m, file_name)) return 0; - if (ctx->to_include && !string_list_has_string(ctx->to_include, - file_name)) + else if (ctx->to_include && + !string_list_has_string(ctx->to_include, file_name)) return 0; return 1; } @@ -121,7 +135,7 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len, if (ends_with(file_name, ".idx")) { display_progress(ctx->progress, ++ctx->pack_paths_checked); - if (!should_include_pack(ctx, file_name, 1)) + if (!should_include_pack(ctx, file_name)) return; ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); @@ -880,9 +894,6 @@ static int fill_packs_from_midx(struct write_midx_context *ctx, uint32_t i; for (i = 0; i < ctx->m->num_packs; i++) { - if (!should_include_pack(ctx, ctx->m->pack_names[i], 0)) - continue; - ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); if (flags & MIDX_WRITE_REV_INDEX || preferred_pack_name) { @@ -937,7 +948,15 @@ static int write_midx_internal(const char *object_dir, die_errno(_("unable to create leading directories of %s"), midx_name.buf); - ctx.m = lookup_multi_pack_index(the_repository, object_dir); + if (!packs_to_include) { + /* + * Only reference an existing MIDX when not filtering which + * packs to include, since all packs and objects are copied + * blindly from an existing MIDX if one is present. + */ + ctx.m = lookup_multi_pack_index(the_repository, object_dir); + } + if (ctx.m && !midx_checksum_valid(ctx.m)) { warning(_("ignoring existing multi-pack-index; checksum mismatch")); ctx.m = NULL; @@ -946,7 +965,6 @@ static int write_midx_internal(const char *object_dir, ctx.nr = 0; ctx.alloc = ctx.m ? ctx.m->num_packs : 16; ctx.info = NULL; - ctx.to_include = packs_to_include; ALLOC_ARRAY(ctx.info, ctx.alloc); if (ctx.m && fill_packs_from_midx(&ctx, preferred_pack_name, @@ -963,6 +981,8 @@ static int write_midx_internal(const char *object_dir, else ctx.progress = NULL; + ctx.to_include = packs_to_include; + for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &ctx); stop_progress(&ctx.progress); diff --git a/pack-bitmap.c b/pack-bitmap.c index fe8e8a51d3..1d6b7f2826 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -2073,6 +2073,7 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git, QSORT(packs, packs_nr, bitmapped_pack_cmp); } else { struct packed_git *pack; + uint32_t pack_int_id; if (bitmap_is_midx(bitmap_git)) { uint32_t preferred_pack_pos; @@ -2083,12 +2084,24 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git, } pack = bitmap_git->midx->packs[preferred_pack_pos]; + pack_int_id = preferred_pack_pos; } else { pack = bitmap_git->pack; + /* + * Any value for 'pack_int_id' will do here. When we + * process the pack via try_partial_reuse(), we won't + * use the `pack_int_id` field since we have a non-MIDX + * bitmap. + * + * Use '-1' as a sentinel value to make it clear + * that we do not expect to read this field. + */ + pack_int_id = -1; } ALLOC_GROW(packs, packs_nr + 1, packs_alloc); packs[packs_nr].p = pack; + packs[packs_nr].pack_int_id = pack_int_id; packs[packs_nr].bitmap_nr = pack->num_objects; packs[packs_nr].bitmap_pos = 0; diff --git a/pack-revindex.c b/pack-revindex.c index fc63aa76a2..93ffca7731 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -527,6 +527,9 @@ static int midx_key_to_pack_pos(struct multi_pack_index *m, { uint32_t *found; + if (key->pack >= m->num_packs) + BUG("MIDX pack lookup out of bounds (%"PRIu32" >= %"PRIu32")", + key->pack, m->num_packs); /* * The preferred pack sorts first, so determine its identifier by * looking at the first object in pseudo-pack order. diff --git a/t/t5326-multi-pack-bitmaps.sh b/t/t5326-multi-pack-bitmaps.sh index cc7220b6c0..916da389b6 100755 --- a/t/t5326-multi-pack-bitmaps.sh +++ b/t/t5326-multi-pack-bitmaps.sh @@ -551,4 +551,34 @@ do ' done +test_expect_success 'remove one packfile between MIDX bitmap writes' ' + git init remove-pack-between-writes && + ( + cd remove-pack-between-writes && + + test_commit A && + test_commit B && + test_commit C && + + # Create packs with the prefix "pack-A", "pack-B", + # "pack-C" to impose a lexicographic order on these + # packs so the pack being removed is always from the + # middle. + packdir=.git/objects/pack && + A="$(echo A | git pack-objects $packdir/pack-A --revs)" && + B="$(echo B | git pack-objects $packdir/pack-B --revs)" && + C="$(echo C | git pack-objects $packdir/pack-C --revs)" && + + git multi-pack-index write --bitmap && + + cat >in <<-EOF && + pack-A-$A.idx + pack-C-$C.idx + EOF + git multi-pack-index write --bitmap --stdin-packs p1.objects <<-EOF && + $(git rev-parse $base) + ^$(git rev-parse $delta^) + EOF + cat >p2.objects <<-EOF && + $(git rev-parse F) + EOF + + p1="$(git pack-objects --revs $packdir/pack in <<-EOF && + pack-$p1.idx + pack-$p2.idx + EOF + git multi-pack-index write --bitmap --stdin-packs \ + --preferred-pack=pack-$p1.pack expect && + + test_pack_objects_reused_all $(wc -l