pack-bitmap-write.c: write lookup table extension

The bitmap lookup table extension was documented by an earlier
change, but Git does not yet know how to write that extension.

Teach Git to write bitmap lookup table extension. The table contains
the list of `N` <commit_pos, offset, xor_row>` triplets. These
triplets are sorted according to their commit pos (ascending order).
The meaning of each data in the i'th triplet is given below:

  - commit_pos stores commit position (in the pack-index or midx).
    It is a 4 byte network byte order unsigned integer.

  - offset is the position (in the bitmap file) from which that
    commit's bitmap can be read.

  - xor_row is the position of the triplet in the lookup table
    whose bitmap is used to compress this bitmap, or `0xffffffff`
    if no such bitmap exists.

Mentored-by: Taylor Blau <[email protected]>
Co-mentored-by: Kaartic Sivaraam <[email protected]>
Co-authored-by: Taylor Blau <[email protected]>
Signed-off-by: Abhradeep Chakraborty <[email protected]>
Reviewed-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: 2 people

pack-bitmap-write.c

@@ -651,13 +651,17 @@ 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)
+				      uint32_t *commit_positions,
+				      off_t *offsets)
 {
 	int i;
 
 	for (i = 0; i < writer.selected_nr; ++i) {
 		struct bitmapped_commit *stored = &writer.selected[i];
 
+		if (offsets)
+			offsets[i] = hashfile_total(f);
+
 		hashwrite_be32(f, commit_positions[i]);
 		hashwrite_u8(f, stored->xor_offset);
 		hashwrite_u8(f, stored->flags);
@@ -666,6 +670,81 @@ static void write_selected_commits_v1(struct hashfile *f,
 	}
 }
 
+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,
+			       struct pack_idx_entry **index,
+			       uint32_t index_nr,
+			       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)
@@ -693,6 +772,7 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 	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;
@@ -713,6 +793,9 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 	dump_bitmap(f, writer.blobs);
 	dump_bitmap(f, writer.tags);
 
+	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++) {
@@ -725,7 +808,10 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 		commit_positions[i] = commit_pos;
 	}
 
-	write_selected_commits_v1(f, index, index_nr, commit_positions);
+	write_selected_commits_v1(f, index, index_nr, commit_positions, offsets);
+
+	if (options & BITMAP_OPT_LOOKUP_TABLE)
+		write_lookup_table(f, index, index_nr, commit_positions, offsets);
 
 	if (options & BITMAP_OPT_HASH_CACHE)
 		write_hash_cache(f, index, index_nr);
@@ -741,4 +827,5 @@ void bitmap_writer_finish(struct pack_idx_entry **index,
 
 	strbuf_release(&tmp_file);
 	free(commit_positions);
+	free(offsets);
 }

pack-bitmap.h

@@ -24,8 +24,9 @@ struct bitmap_disk_header {
 #define NEEDS_BITMAP (1u<<22)
 
 enum pack_bitmap_opts {
-	BITMAP_OPT_FULL_DAG = 1,
-	BITMAP_OPT_HASH_CACHE = 4,
+	BITMAP_OPT_FULL_DAG = 0x1,
+	BITMAP_OPT_HASH_CACHE = 0x4,
+	BITMAP_OPT_LOOKUP_TABLE = 0x10,
 };
 
 enum pack_bitmap_flags {