Merge branch 'ac/bitmap-lookup-table'

The pack bitmap file gained a bitmap-lookup table to speed up
locating the necessary bitmap for a given commit.

* ac/bitmap-lookup-table:
  pack-bitmap-write: drop unused pack_idx_entry parameters
  bitmap-lookup-table: add performance tests for lookup table
  pack-bitmap: prepare to read lookup table extension
  pack-bitmap-write: learn pack.writeBitmapLookupTable and add tests
  pack-bitmap-write.c: write lookup table extension
  bitmap: move `get commit positions` code to `bitmap_writer_finish`
  Documentation/technical: describe bitmap lookup table extension

Author: gitster

Documentation/config/pack.txt

@@ -164,6 +164,13 @@ When writing a multi-pack reachability bitmap, no new namehashes are
 computed; instead, any namehashes stored in an existing bitmap are
 permuted into their appropriate location when writing a new bitmap.
 
+pack.writeBitmapLookupTable::
+	When true, Git will include a "lookup table" section in the
+	bitmap index (if one is written). This table is used to defer
+	loading individual bitmaps as late as possible. This can be
+	beneficial in repositories that have relatively large bitmap
+	indexes. Defaults to false.
+
 pack.writeReverseIndex::
 	When true, git will write a corresponding .rev file (see:
 	linkgit:gitformat-pack[5])

Documentation/technical/bitmap-format.txt

@@ -72,6 +72,17 @@ MIDXs, both the bit-cache and rev-cache extensions are required.
 	    pack/MIDX. The format and meaning of the name-hash is
 	    described below.
 
+		** {empty}
+		BITMAP_OPT_LOOKUP_TABLE (0x10): :::
+		If present, the end of the bitmap file contains a table
+		containing a list of `N` <commit_pos, offset, xor_row>
+		triplets. The format and meaning of the table is described
+		below.
++
+NOTE: Unlike the xor_offset used to compress an individual bitmap,
+`xor_row` stores an *absolute* index into the lookup table, not a location
+relative to the current entry.
+
 	4-byte entry count (network byte order): ::
 	    The total count of entries (bitmapped commits) in this bitmap index.
 
@@ -216,3 +227,31 @@ Note that this hashing scheme is tied to the BITMAP_OPT_HASH_CACHE flag.
 If implementations want to choose a different hashing scheme, they are
 free to do so, but MUST allocate a new header flag (because comparing
 hashes made under two different schemes would be pointless).
+
+Commit lookup table
+-------------------
+
+If the BITMAP_OPT_LOOKUP_TABLE flag is set, the last `N * (4 + 8 + 4)`
+bytes (preceding the name-hash cache and trailing hash) of the `.bitmap`
+file contains a lookup table specifying the information needed to get
+the desired bitmap from the entries without parsing previous unnecessary
+bitmaps.
+
+For a `.bitmap` containing `nr_entries` reachability bitmaps, the table
+contains a list of `nr_entries` <commit_pos, offset, xor_row> triplets
+(sorted in the ascending order of `commit_pos`). The content of i'th
+triplet is -
+
+	* {empty}
+	commit_pos (4 byte integer, network byte order): ::
+	It stores the object position of a commit (in the midx or pack
+	index).
+
+	* {empty}
+	offset (8 byte integer, network byte order): ::
+	The offset from which that commit's bitmap can be read.
+
+	* {empty}
+	xor_row (4 byte integer, network byte order): ::
+	The position of the triplet whose bitmap is used to compress
+	this one, or `0xffffffff` if no such bitmap exists.

builtin/multi-pack-index.c

@@ -87,6 +87,13 @@ static int git_multi_pack_index_write_config(const char *var, const char *value,
 			opts.flags &= ~MIDX_WRITE_BITMAP_HASH_CACHE;
 	}
 
+	if (!strcmp(var, "pack.writebitmaplookuptable")) {
+		if (git_config_bool(var, value))
+			opts.flags |= MIDX_WRITE_BITMAP_LOOKUP_TABLE;
+		else
+			opts.flags &= ~MIDX_WRITE_BITMAP_LOOKUP_TABLE;
+	}
+
 	/*
 	 * We should never make a fall-back call to 'git_default_config', since
 	 * this was already called in 'cmd_multi_pack_index()'.

builtin/pack-objects.c

@@ -3148,6 +3148,14 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 		else
 			write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE;
 	}
+
+	if (!strcmp(k, "pack.writebitmaplookuptable")) {
+		if (git_config_bool(k, v))
+			write_bitmap_options |= BITMAP_OPT_LOOKUP_TABLE;
+		else
+			write_bitmap_options &= ~BITMAP_OPT_LOOKUP_TABLE;
+	}
+
 	if (!strcmp(k, "pack.usebitmaps")) {
 		use_bitmap_index_default = git_config_bool(k, v);
 		return 0;

midx.c

@@ -1119,6 +1119,9 @@ static int write_midx_bitmap(const char *midx_name,
 	if (flags & MIDX_WRITE_BITMAP_HASH_CACHE)
 		options |= BITMAP_OPT_HASH_CACHE;
 
+	if (flags & MIDX_WRITE_BITMAP_LOOKUP_TABLE)
+		options |= BITMAP_OPT_LOOKUP_TABLE;
+
 	/*
 	 * Build the MIDX-order index based on pdata.objects (which is already
 	 * in MIDX order; c.f., 'midx_pack_order_cmp()' for the definition of

midx.h

@@ -47,6 +47,7 @@ struct multi_pack_index {
 #define MIDX_WRITE_REV_INDEX (1 << 1)
 #define MIDX_WRITE_BITMAP (1 << 2)
 #define MIDX_WRITE_BITMAP_HASH_CACHE (1 << 3)
+#define MIDX_WRITE_BITMAP_LOOKUP_TABLE (1 << 4)
 
 const unsigned char *get_midx_checksum(struct multi_pack_index *m);
 void get_midx_filename(struct strbuf *out, const char *object_dir);

pack-bitmap-write.c

@@ -649,28 +649,98 @@ static const struct object_id *oid_access(size_t pos, const void *table)
 }
 
 static void write_selected_commits_v1(struct hashfile *f,
-				      struct pack_idx_entry **index,
-				      uint32_t index_nr)
+				      uint32_t *commit_positions,
+				      off_t *offsets)
 {
 	int i;
 
 	for (i = 0; i < writer.selected_nr; ++i) {
 		struct bitmapped_commit *stored = &writer.selected[i];
 
-		int commit_pos =
-			oid_pos(&stored->commit->object.oid, index, index_nr, oid_access);
+		if (offsets)
+			offsets[i] = hashfile_total(f);
 
-		if (commit_pos < 0)
-			BUG("trying to write commit not in index");
-
-		hashwrite_be32(f, commit_pos);
+		hashwrite_be32(f, commit_positions[i]);
 		hashwrite_u8(f, stored->xor_offset);
 		hashwrite_u8(f, stored->flags);
 
 		dump_bitmap(f, stored->write_as);
 	}
 }
 
+static int table_cmp(const void *_va, const void *_vb, void *_data)
+{
+	uint32_t *commit_positions = _data;
+	uint32_t a = commit_positions[*(uint32_t *)_va];
+	uint32_t b = commit_positions[*(uint32_t *)_vb];
+
+	if (a > b)
+		return 1;
+	else if (a < b)
+		return -1;
+
+	return 0;
+}
+
+static void write_lookup_table(struct hashfile *f,
+			       uint32_t *commit_positions,
+			       off_t *offsets)
+{
+	uint32_t i;
+	uint32_t *table, *table_inv;
+
+	ALLOC_ARRAY(table, writer.selected_nr);
+	ALLOC_ARRAY(table_inv, writer.selected_nr);
+
+	for (i = 0; i < writer.selected_nr; i++)
+		table[i] = i;
+
+	/*
+	 * At the end of this sort table[j] = i means that the i'th
+	 * bitmap corresponds to j'th bitmapped commit (among the selected
+	 * commits) in lex order of OIDs.
+	 */
+	QSORT_S(table, writer.selected_nr, table_cmp, commit_positions);
+
+	/* table_inv helps us discover that relationship (i'th bitmap
+	 * to j'th commit by j = table_inv[i])
+	 */
+	for (i = 0; i < writer.selected_nr; i++)
+		table_inv[table[i]] = i;
+
+	trace2_region_enter("pack-bitmap-write", "writing_lookup_table", the_repository);
+	for (i = 0; i < writer.selected_nr; i++) {
+		struct bitmapped_commit *selected = &writer.selected[table[i]];
+		uint32_t xor_offset = selected->xor_offset;
+		uint32_t xor_row;
+
+		if (xor_offset) {
+			/*
+			 * xor_index stores the index (in the bitmap entries)
+			 * of the corresponding xor bitmap. But we need to convert
+			 * this index into lookup table's index. So, table_inv[xor_index]
+			 * gives us the index position w.r.t. the lookup table.
+			 *
+			 * If "k = table[i] - xor_offset" then the xor base is the k'th
+			 * bitmap. `table_inv[k]` gives us the position of that bitmap
+			 * in the lookup table.
+			 */
+			uint32_t xor_index = table[i] - xor_offset;
+			xor_row = table_inv[xor_index];
+		} else {
+			xor_row = 0xffffffff;
+		}
+
+		hashwrite_be32(f, commit_positions[table[i]]);
+		hashwrite_be64(f, (uint64_t)offsets[table[i]]);
+		hashwrite_be32(f, xor_row);
+	}
+	trace2_region_leave("pack-bitmap-write", "writing_lookup_table", the_repository);
+
+	free(table);
+	free(table_inv);
+}
+
 static void write_hash_cache(struct hashfile *f,
 			     struct pack_idx_entry **index,
 			     uint32_t index_nr)
@@ -697,6 +767,9 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 	static uint16_t flags = BITMAP_OPT_FULL_DAG;
 	struct strbuf tmp_file = STRBUF_INIT;
 	struct hashfile *f;
+	uint32_t *commit_positions = NULL;
+	off_t *offsets = NULL;
+	uint32_t i;
 
 	struct bitmap_disk_header header;
 
@@ -715,7 +788,26 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 	dump_bitmap(f, writer.trees);
 	dump_bitmap(f, writer.blobs);
 	dump_bitmap(f, writer.tags);
-	write_selected_commits_v1(f, index, index_nr);
+
+	if (options & BITMAP_OPT_LOOKUP_TABLE)
+		CALLOC_ARRAY(offsets, index_nr);
+
+	ALLOC_ARRAY(commit_positions, writer.selected_nr);
+
+	for (i = 0; i < writer.selected_nr; i++) {
+		struct bitmapped_commit *stored = &writer.selected[i];
+		int commit_pos = oid_pos(&stored->commit->object.oid, index, index_nr, oid_access);
+
+		if (commit_pos < 0)
+			BUG(_("trying to write commit not in index"));
+
+		commit_positions[i] = commit_pos;
+	}
+
+	write_selected_commits_v1(f, commit_positions, offsets);
+
+	if (options & BITMAP_OPT_LOOKUP_TABLE)
+		write_lookup_table(f, commit_positions, offsets);
 
 	if (options & BITMAP_OPT_HASH_CACHE)
 		write_hash_cache(f, index, index_nr);
@@ -730,4 +822,6 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 		die_errno("unable to rename temporary bitmap file to '%s'", filename);
 
 	strbuf_release(&tmp_file);
+	free(commit_positions);
+	free(offsets);
 }