Merge branch 'tb/incremental-midx-part-2' into seen

Incremental updates of multi-pack index files.

* tb/incremental-midx-part-2:
  fixup! pack-bitmap.c: open and store incremental bitmap layers
  fixup! midx: implement writing incremental MIDX bitmaps
  midx: implement writing incremental MIDX bitmaps
  pack-bitmap.c: use `ewah_or_iterator` for type bitmap iterators
  pack-bitmap.c: keep track of each layer's type bitmaps
  ewah: implement `struct ewah_or_iterator`
  pack-bitmap.c: apply pseudo-merge commits with incremental MIDXs
  pack-bitmap.c: compute disk-usage with incremental MIDXs
  pack-bitmap.c: teach `rev-list --test-bitmap` about incremental MIDXs
  pack-bitmap.c: support bitmap pack-reuse with incremental MIDXs
  pack-bitmap.c: teach `show_objects_for_type()` about incremental MIDXs
  pack-bitmap.c: teach `bitmap_for_commit()` about incremental MIDXs
  pack-bitmap.c: open and store incremental bitmap layers
  pack-revindex: prepare for incremental MIDX bitmaps
  Documentation: describe incremental MIDX bitmaps

Author: gitster

Documentation/technical/multi-pack-index.txt

@@ -164,6 +164,70 @@ objects_nr($H2) + objects_nr($H1) + i
 (in the C implementation, this is often computed as `i +
 m->num_objects_in_base`).
 
+=== Pseudo-pack order for incremental MIDXs
+
+The original implementation of multi-pack reachability bitmaps defined
+the pseudo-pack order in linkgit:gitformat-pack[5] (see the section
+titled "multi-pack-index reverse indexes") roughly as follows:
+
+____
+In short, a MIDX's pseudo-pack is the de-duplicated concatenation of
+objects in packs stored by the MIDX, laid out in pack order, and the
+packs arranged in MIDX order (with the preferred pack coming first).
+____
+
+In the incremental MIDX design, we extend this definition to include
+objects from multiple layers of the MIDX chain. The pseudo-pack order
+for incremental MIDXs is determined by concatenating the pseudo-pack
+ordering for each layer of the MIDX chain in order. Formally two objects
+`o1` and `o2` are compared as follows:
+
+1. If `o1` appears in an earlier layer of the MIDX chain than `o2`, then
+  `o1` is considered less than `o2`.
+2. Otherwise, if `o1` and `o2` appear in the same MIDX layer, and that
+  MIDX layer has no base, then If one of `pack(o1)` and `pack(o2)` is
+  preferred and the other is not, then the preferred one sorts first. If
+  there is a base layer (i.e. the MIDX layer is not the first layer in
+  the chain), then if `pack(o1)` appears earlier in that MIDX layer's
+  pack order, than `o1` is less than `o2`. Likewise if `pack(o2)`
+  appears earlier, than the opposite is true.
+3. Otherwise, `o1` and `o2` appear in the same pack, and thus in the
+  same MIDX layer. Sort `o1` and `o2` by their offset within their
+  containing packfile.
+
+=== Reachability bitmaps and incremental MIDXs
+
+Each layer of an incremental MIDX chain may have its objects (and the
+objects from any previous layer in the same MIDX chain) represented in
+its own `*.bitmap` file.
+
+The structure of a `*.bitmap` file belonging to an incremental MIDX
+chain is identical to that of a non-incremental MIDX bitmap, or a
+classic single-pack bitmap. Since objects are added to the end of the
+incremental MIDX's pseudo-pack order (see: above), it is possible to
+extend a bitmap when appending to the end of a MIDX chain.
+
+(Note: it is possible likewise to compress a contiguous sequence of MIDX
+incremental layers, and their `*.bitmap`(s) into a single layer and
+`*.bitmap`, but this is not yet implemented.)
+
+The object positions used are global within the pseudo-pack order, so
+subsequent layers will have, for example, `m->num_objects_in_base`
+number of `0` bits in each of their four type bitmaps. This follows from
+the fact that we only write type bitmap entries for objects present in
+the layer immediately corresponding to the bitmap).
+
+Note also that only the bitmap pertaining to the most recent layer in an
+incremental MIDX chain is used to store reachability information about
+the interesting and uninteresting objects in a reachability query.
+Earlier bitmap layers are only used to look up commit and pseudo-merge
+bitmaps from that layer, as well as the type-level bitmaps for objects
+in that layer.
+
+To simplify the implementation, type-level bitmaps are iterated
+simultaneously, and their results are OR'd together to avoid recursively
+calling internal bitmap functions.
+
 Future Work
 -----------
 

builtin/pack-objects.c

@@ -1370,7 +1370,8 @@ static void write_pack_file(void)
 
 			if (write_bitmap_index) {
 				bitmap_writer_init(&bitmap_writer,
-						   the_repository, &to_pack);
+						   the_repository, &to_pack,
+						   NULL);
 				bitmap_writer_set_checksum(&bitmap_writer, hash);
 				bitmap_writer_build_type_index(&bitmap_writer,
 							       written_list);

ewah/ewah_bitmap.c

@@ -372,6 +372,39 @@ void ewah_iterator_init(struct ewah_iterator *it, struct ewah_bitmap *parent)
 		read_new_rlw(it);
 }
 
+void ewah_or_iterator_init(struct ewah_or_iterator *it,
+			   struct ewah_bitmap **parents, size_t nr)
+{
+	size_t i;
+
+	memset(it, 0, sizeof(*it));
+
+	ALLOC_ARRAY(it->its, nr);
+	for (i = 0; i < nr; i++)
+		ewah_iterator_init(&it->its[it->nr++], parents[i]);
+}
+
+int ewah_or_iterator_next(eword_t *next, struct ewah_or_iterator *it)
+{
+	eword_t buf, out = 0;
+	size_t i;
+	int ret = 0;
+
+	for (i = 0; i < it->nr; i++)
+		if (ewah_iterator_next(&buf, &it->its[i])) {
+			out |= buf;
+			ret = 1;
+		}
+
+	*next = out;
+	return ret;
+}
+
+void ewah_or_iterator_free(struct ewah_or_iterator *it)
+{
+	free(it->its);
+}
+
 void ewah_xor(
 	struct ewah_bitmap *ewah_i,
 	struct ewah_bitmap *ewah_j,

ewah/ewok.h

@@ -148,6 +148,18 @@ void ewah_iterator_init(struct ewah_iterator *it, struct ewah_bitmap *parent);
  */
 int ewah_iterator_next(eword_t *next, struct ewah_iterator *it);
 
+struct ewah_or_iterator {
+	struct ewah_iterator *its;
+	size_t nr;
+};
+
+void ewah_or_iterator_init(struct ewah_or_iterator *it,
+			   struct ewah_bitmap **parents, size_t nr);
+
+int ewah_or_iterator_next(eword_t *next, struct ewah_or_iterator *it);
+
+void ewah_or_iterator_free(struct ewah_or_iterator *it);
+
 void ewah_xor(
 	struct ewah_bitmap *ewah_i,
 	struct ewah_bitmap *ewah_j,

midx-write.c

@@ -827,20 +827,26 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr
 	return cb.commits;
 }
 
-static int write_midx_bitmap(const char *midx_name,
+static int write_midx_bitmap(struct write_midx_context *ctx,
+			     const char *object_dir,
 			     const unsigned char *midx_hash,
 			     struct packing_data *pdata,
 			     struct commit **commits,
 			     uint32_t commits_nr,
-			     uint32_t *pack_order,
 			     unsigned flags)
 {
 	int ret, i;
 	uint16_t options = 0;
 	struct bitmap_writer writer;
 	struct pack_idx_entry **index;
-	char *bitmap_name = xstrfmt("%s-%s.bitmap", midx_name,
-					hash_to_hex(midx_hash));
+	struct strbuf bitmap_name = STRBUF_INIT;
+
+	if (ctx->incremental)
+		get_split_midx_filename_ext(&bitmap_name, object_dir, midx_hash,
+					    MIDX_EXT_BITMAP);
+	else
+		get_midx_filename_ext(&bitmap_name, object_dir, midx_hash,
+				      MIDX_EXT_BITMAP);
 
 	trace2_region_enter("midx", "write_midx_bitmap", the_repository);
 
@@ -859,7 +865,8 @@ static int write_midx_bitmap(const char *midx_name,
 	for (i = 0; i < pdata->nr_objects; i++)
 		index[i] = &pdata->objects[i].idx;
 
-	bitmap_writer_init(&writer, the_repository, pdata);
+	bitmap_writer_init(&writer, the_repository, pdata,
+			   ctx->incremental ? ctx->base_midx : NULL);
 	bitmap_writer_show_progress(&writer, flags & MIDX_PROGRESS);
 	bitmap_writer_build_type_index(&writer, index);
 
@@ -877,19 +884,19 @@ static int write_midx_bitmap(const char *midx_name,
 	 * bitmap_writer_finish().
 	 */
 	for (i = 0; i < pdata->nr_objects; i++)
-		index[pack_order[i]] = &pdata->objects[i].idx;
+		index[ctx->pack_order[i]] = &pdata->objects[i].idx;
 
 	bitmap_writer_select_commits(&writer, commits, commits_nr);
 	ret = bitmap_writer_build(&writer);
 	if (ret < 0)
 		goto cleanup;
 
 	bitmap_writer_set_checksum(&writer, midx_hash);
-	bitmap_writer_finish(&writer, index, bitmap_name, options);
+	bitmap_writer_finish(&writer, index, bitmap_name.buf, options);
 
 cleanup:
 	free(index);
-	free(bitmap_name);
+	strbuf_release(&bitmap_name);
 	bitmap_writer_free(&writer);
 
 	trace2_region_leave("midx", "write_midx_bitmap", the_repository);
@@ -1073,8 +1080,6 @@ static int write_midx_internal(const char *object_dir,
 	trace2_region_enter("midx", "write_midx_internal", the_repository);
 
 	ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL);
-	if (ctx.incremental && (flags & MIDX_WRITE_BITMAP))
-		die(_("cannot write incremental MIDX with bitmap"));
 
 	if (ctx.incremental)
 		strbuf_addf(&midx_name,
@@ -1116,6 +1121,12 @@ static int write_midx_internal(const char *object_dir,
 	if (ctx.incremental) {
 		struct multi_pack_index *m = ctx.base_midx;
 		while (m) {
+			if (flags & MIDX_WRITE_BITMAP && load_midx_revindex(m)) {
+				error(_("could not load reverse index for MIDX %s"),
+				      hash_to_hex(get_midx_checksum(m)));
+				result = 1;
+				goto cleanup;
+			}
 			ctx.num_multi_pack_indexes_before++;
 			m = m->base_midx;
 		}
@@ -1405,8 +1416,8 @@ static int write_midx_internal(const char *object_dir,
 		FREE_AND_NULL(ctx.entries);
 		ctx.entries_nr = 0;
 
-		if (write_midx_bitmap(midx_name.buf, midx_hash, &pdata,
-				      commits, commits_nr, ctx.pack_order,
+		if (write_midx_bitmap(&ctx, object_dir,
+				      midx_hash, &pdata, commits, commits_nr,
 				      flags) < 0) {
 			error(_("could not write multi-pack bitmap"));
 			result = 1;

pack-bitmap-write.c

@@ -25,6 +25,8 @@
 #include "alloc.h"
 #include "refs.h"
 #include "strmap.h"
+#include "midx.h"
+#include "pack-revindex.h"
 
 struct bitmapped_commit {
 	struct commit *commit;
@@ -42,14 +44,16 @@ static inline int bitmap_writer_nr_selected_commits(struct bitmap_writer *writer
 }
 
 void bitmap_writer_init(struct bitmap_writer *writer, struct repository *r,
-			struct packing_data *pdata)
+			struct packing_data *pdata,
+			struct multi_pack_index *midx)
 {
 	memset(writer, 0, sizeof(struct bitmap_writer));
 	if (writer->bitmaps)
 		BUG("bitmap writer already initialized");
 	writer->bitmaps = kh_init_oid_map();
 	writer->pseudo_merge_commits = kh_init_oid_map();
 	writer->to_pack = pdata;
+	writer->midx = midx;
 
 	string_list_init_dup(&writer->pseudo_merge_groups);
 
@@ -112,6 +116,11 @@ void bitmap_writer_build_type_index(struct bitmap_writer *writer,
 				    struct pack_idx_entry **index)
 {
 	uint32_t i;
+	uint32_t base_objects = 0;
+
+	if (writer->midx)
+		base_objects = writer->midx->num_objects +
+			writer->midx->num_objects_in_base;
 
 	writer->commits = ewah_new();
 	writer->trees = ewah_new();
@@ -141,19 +150,19 @@ void bitmap_writer_build_type_index(struct bitmap_writer *writer,
 
 		switch (real_type) {
 		case OBJ_COMMIT:
-			ewah_set(writer->commits, i);
+			ewah_set(writer->commits, i + base_objects);
 			break;
 
 		case OBJ_TREE:
-			ewah_set(writer->trees, i);
+			ewah_set(writer->trees, i + base_objects);
 			break;
 
 		case OBJ_BLOB:
-			ewah_set(writer->blobs, i);
+			ewah_set(writer->blobs, i + base_objects);
 			break;
 
 		case OBJ_TAG:
-			ewah_set(writer->tags, i);
+			ewah_set(writer->tags, i + base_objects);
 			break;
 
 		default:
@@ -206,19 +215,37 @@ void bitmap_writer_push_commit(struct bitmap_writer *writer,
 static uint32_t find_object_pos(struct bitmap_writer *writer,
 				const struct object_id *oid, int *found)
 {
-	struct object_entry *entry = packlist_find(writer->to_pack, oid);
+	struct object_entry *entry;
+
+	entry = packlist_find(writer->to_pack, oid);
+	if (entry) {
+		uint32_t base_objects = 0;
+		if (writer->midx)
+			base_objects = writer->midx->num_objects +
+				writer->midx->num_objects_in_base;
 
-	if (!entry) {
 		if (found)
-			*found = 0;
-		warning("Failed to write bitmap index. Packfile doesn't have full closure "
-			"(object %s is missing)", oid_to_hex(oid));
-		return 0;
+			*found = 1;
+		return oe_in_pack_pos(writer->to_pack, entry) + base_objects;
+	} else if (writer->midx) {
+		uint32_t at, pos;
+
+		if (!bsearch_midx(oid, writer->midx, &at))
+			goto missing;
+		if (midx_to_pack_pos(writer->midx, at, &pos) < 0)
+			goto missing;
+
+		if (found)
+			*found = 1;
+		return pos;
 	}
 
+missing:
 	if (found)
-		*found = 1;
-	return oe_in_pack_pos(writer->to_pack, entry);
+		*found = 0;
+	warning("Failed to write bitmap index. Packfile doesn't have full closure "
+		"(object %s is missing)", oid_to_hex(oid));
+	return 0;
 }
 
 static void compute_xor_offsets(struct bitmap_writer *writer)
@@ -585,7 +612,7 @@ int bitmap_writer_build(struct bitmap_writer *writer)
 	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
 	struct prio_queue tree_queue = { NULL };
 	struct bitmap_index *old_bitmap;
-	uint32_t *mapping;
+	uint32_t *mapping = NULL;
 	int closed = 1; /* until proven otherwise */
 
 	if (writer->show_progress)
@@ -1018,7 +1045,7 @@ void bitmap_writer_finish(struct bitmap_writer *writer,
 	struct strbuf tmp_file = STRBUF_INIT;
 	struct hashfile *f;
 	off_t *offsets = NULL;
-	uint32_t i;
+	uint32_t i, base_objects;
 
 	struct bitmap_disk_header header;
 
@@ -1044,6 +1071,12 @@ void bitmap_writer_finish(struct bitmap_writer *writer,
 	if (options & BITMAP_OPT_LOOKUP_TABLE)
 		CALLOC_ARRAY(offsets, writer->to_pack->nr_objects);
 
+	if (writer->midx)
+		base_objects = writer->midx->num_objects +
+			writer->midx->num_objects_in_base;
+	else
+		base_objects = 0;
+
 	for (i = 0; i < bitmap_writer_nr_selected_commits(writer); i++) {
 		struct bitmapped_commit *stored = &writer->selected[i];
 		int commit_pos = oid_pos(&stored->commit->object.oid, index,
@@ -1052,7 +1085,7 @@ void bitmap_writer_finish(struct bitmap_writer *writer,
 
 		if (commit_pos < 0)
 			BUG(_("trying to write commit not in index"));
-		stored->commit_pos = commit_pos;
+		stored->commit_pos = commit_pos + base_objects;
 	}
 
 	write_selected_commits_v1(writer, f, offsets);