midx: enable reachability bitmaps during MIDX compaction

Enable callers to generate reachability bitmaps when performing MIDX
layer compaction by combining all existing bitmaps from the compacted
layers.

Note that the because of the object/pack ordering described by the
previous commit, the pseudo-pack order for the compacted MIDX is the
same as concatenating the individual pseudo-pack orderings for each
layer in the compaction range.

As a result, the only non-test or documentation change necessary is to
treat all objects as non-preferred during compaction so as not to
disturb the object ordering.

In the future, we may want to adjust which commit(s) receive
reachability bitmaps when compacting multiple .bitmap files into one, or
even generate new bitmaps (e.g., if the references have moved
significantly since the .bitmap was generated). This commit only
implements combining all existing bitmaps in range together in order to
demonstrate and lay the groundwork for more exotic strategies.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: ttaylorr

Documentation/git-multi-pack-index.adoc

@@ -13,7 +13,7 @@ SYNOPSIS
 		         [--[no-]bitmap] [--[no-]incremental] [--[no-]stdin-packs]
 		         [--refs-snapshot=<path>]
 'git multi-pack-index' [<options>] compact [--[no-]incremental]
-		         <from> <to>
+		         [--[no-]bitmap] <from> <to>
 'git multi-pack-index' [<options>] verify
 'git multi-pack-index' [<options>] expire
 'git multi-pack-index' [<options>] repack [--batch-size=<size>]

builtin/multi-pack-index.c

@@ -19,7 +19,7 @@
 
 #define BUILTIN_MIDX_COMPACT_USAGE \
 	N_("git multi-pack-index [<options>] compact [--[no-]incremental]\n" \
-	   "  <from> <to>")
+	   "  [--[no-]bitmap] <from> <to>")
 
 #define BUILTIN_MIDX_VERIFY_USAGE \
 	N_("git multi-pack-index [<options>] verify")
@@ -216,6 +216,8 @@ static int cmd_multi_pack_index_compact(int argc, const char **argv,
 
 	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(),

midx-write.c

@@ -657,7 +657,7 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx)
 		struct pack_midx_entry *e = &ctx->entries[i];
 		data[i].nr = i;
 		data[i].pack = midx_pack_perm(ctx, e->pack_int_id);
-		if (!e->preferred)
+		if (!e->preferred || ctx->compact)
 			data[i].pack |= (1U << 31);
 		data[i].offset = e->offset;
 	}

t/t5335-compact-multi-pack-index.sh

@@ -65,7 +65,7 @@ test_expect_success 'MIDX compaction with lex-ordered pack names' '
 		write_packs A B C D E &&
 		test_line_count = 5 $midx_chain &&
 
-		git multi-pack-index compact --incremental \
+		git multi-pack-index compact --incremental --bitmap \
 			"$(nth_line 2 "$midx_chain")" \
 			"$(nth_line 4 "$midx_chain")" &&
 		test_line_count = 3 $midx_chain &&
@@ -86,7 +86,7 @@ test_expect_success 'MIDX compaction with non-lex-ordered pack names' '
 		write_packs D C A B E &&
 		test_line_count = 5 $midx_chain &&
 
-		git multi-pack-index compact --incremental \
+		git multi-pack-index compact --incremental --bitmap \
 			"$(nth_line 2 "$midx_chain")" \
 			"$(nth_line 4 "$midx_chain")" &&
 		test_line_count = 3 $midx_chain &&
@@ -99,4 +99,120 @@ test_expect_success 'MIDX compaction with non-lex-ordered pack names' '
 	)
 '
 
+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.info >AB.actual &&
+		midx_objs_by_pack <C.info >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