Merge branch 'ak/corrected-commit-date'

The commit-graph learned to use corrected commit dates instead of
the generation number to help topological revision traversal.

* ak/corrected-commit-date:
  doc: add corrected commit date info
  commit-reach: use corrected commit dates in paint_down_to_common()
  commit-graph: use generation v2 only if entire chain does
  commit-graph: implement generation data chunk
  commit-graph: implement corrected commit date
  commit-graph: return 64-bit generation number
  commit-graph: add a slab to store topological levels
  t6600-test-reach: generalize *_three_modes
  commit-graph: consolidate fill_commit_graph_info
  revision: parse parent in indegree_walk_step()
  commit-graph: fix regression when computing Bloom filters

1 files changed, 204 insertions, 47 deletions

diff --git a/commit-graph.c b/commit-graph.c
index 6541060271..36e481c67e 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -38,11 +38,13 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */
 #define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */
 #define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */
+#define GRAPH_CHUNKID_GENERATION_DATA 0x47444154 /* "GDAT" */
+#define GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW 0x47444f56 /* "GDOV" */
 #define GRAPH_CHUNKID_EXTRAEDGES 0x45444745 /* "EDGE" */
 #define GRAPH_CHUNKID_BLOOMINDEXES 0x42494458 /* "BIDX" */
 #define GRAPH_CHUNKID_BLOOMDATA 0x42444154 /* "BDAT" */
 #define GRAPH_CHUNKID_BASE 0x42415345 /* "BASE" */
-#define MAX_NUM_CHUNKS 7
+#define MAX_NUM_CHUNKS 9
 
 #define GRAPH_DATA_WIDTH (the_hash_algo->rawsz + 16)
 
@@ -61,9 +63,13 @@ void git_test_write_commit_graph_or_die(void)
 #define GRAPH_MIN_SIZE (GRAPH_HEADER_SIZE + 4 * GRAPH_CHUNKLOOKUP_WIDTH \
 			+ GRAPH_FANOUT_SIZE + the_hash_algo->rawsz)
 
+#define CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW (1ULL << 31)
+
 /* Remember to update object flag allocation in object.h */
 #define REACHABLE       (1u<<15)
 
+define_commit_slab(topo_level_slab, uint32_t);
+
 /* Keep track of the order in which commits are added to our list. */
 define_commit_slab(commit_pos, int);
 static struct commit_pos commit_pos = COMMIT_SLAB_INIT(1, commit_pos);
@@ -99,7 +105,7 @@ uint32_t commit_graph_position(const struct commit *c)
 	return data ? data->graph_pos : COMMIT_NOT_FROM_GRAPH;
 }
 
-uint32_t commit_graph_generation(const struct commit *c)
+timestamp_t commit_graph_generation(const struct commit *c)
 {
 	struct commit_graph_data *data =
 		commit_graph_data_slab_peek(&commit_graph_data_slab, c);
@@ -139,13 +145,17 @@ static struct commit_graph_data *commit_graph_data_at(const struct commit *c)
 	return data;
 }
 
+/*
+ * Should be used only while writing commit-graph as it compares
+ * generation value of commits by directly accessing commit-slab.
+ */
 static int commit_gen_cmp(const void *va, const void *vb)
 {
 	const struct commit *a = *(const struct commit **)va;
 	const struct commit *b = *(const struct commit **)vb;
 
-	uint32_t generation_a = commit_graph_generation(a);
-	uint32_t generation_b = commit_graph_generation(b);
+	const timestamp_t generation_a = commit_graph_data_at(a)->generation;
+	const timestamp_t generation_b = commit_graph_data_at(b)->generation;
 	/* lower generation commits first */
 	if (generation_a < generation_b)
 		return -1;
@@ -388,6 +398,20 @@ struct commit_graph *parse_commit_graph(struct repository *r,
 				graph->chunk_commit_data = data + chunk_offset;
 			break;
 
+		case GRAPH_CHUNKID_GENERATION_DATA:
+			if (graph->chunk_generation_data)
+				chunk_repeated = 1;
+			else
+				graph->chunk_generation_data = data + chunk_offset;
+			break;
+
+		case GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW:
+			if (graph->chunk_generation_data_overflow)
+				chunk_repeated = 1;
+			else
+				graph->chunk_generation_data_overflow = data + chunk_offset;
+			break;
+
 		case GRAPH_CHUNKID_EXTRAEDGES:
 			if (graph->chunk_extra_edges)
 				chunk_repeated = 1;
@@ -590,6 +614,21 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r,
 	return graph_chain;
 }
 
+static void validate_mixed_generation_chain(struct commit_graph *g)
+{
+	int read_generation_data;
+
+	if (!g)
+		return;
+
+	read_generation_data = !!g->chunk_generation_data;
+
+	while (g) {
+		g->read_generation_data = read_generation_data;
+		g = g->base_graph;
+	}
+}
+
 struct commit_graph *read_commit_graph_one(struct repository *r,
 					   struct object_directory *odb)
 {
@@ -598,6 +637,8 @@ struct commit_graph *read_commit_graph_one(struct repository *r,
 	if (!g)
 		g = load_commit_graph_chain(r, odb);
 
+	validate_mixed_generation_chain(g);
+
 	return g;
 }
 
@@ -673,6 +714,20 @@ int generation_numbers_enabled(struct repository *r)
 	return !!first_generation;
 }
 
+int corrected_commit_dates_enabled(struct repository *r)
+{
+	struct commit_graph *g;
+	if (!prepare_commit_graph(r))
+		return 0;
+
+	g = r->objects->commit_graph;
+
+	if (!g->num_commits)
+		return 0;
+
+	return g->read_generation_data;
+}
+
 struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
 {
 	struct commit_graph *g = r->objects->commit_graph;
@@ -748,17 +803,41 @@ static void fill_commit_graph_info(struct commit *item, struct commit_graph *g,
 {
 	const unsigned char *commit_data;
 	struct commit_graph_data *graph_data;
-	uint32_t lex_index;
+	uint32_t lex_index, offset_pos;
+	uint64_t date_high, date_low, offset;
 
 	while (pos < g->num_commits_in_base)
 		g = g->base_graph;
 
+	if (pos >= g->num_commits + g->num_commits_in_base)
+		die(_("invalid commit position. commit-graph is likely corrupt"));
+
 	lex_index = pos - g->num_commits_in_base;
 	commit_data = g->chunk_commit_data + GRAPH_DATA_WIDTH * lex_index;
 
 	graph_data = commit_graph_data_at(item);
 	graph_data->graph_pos = pos;
-	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+
+	date_high = get_be32(commit_data + g->hash_len + 8) & 0x3;
+	date_low = get_be32(commit_data + g->hash_len + 12);
+	item->date = (timestamp_t)((date_high << 32) | date_low);
+
+	if (g->read_generation_data) {
+		offset = (timestamp_t)get_be32(g->chunk_generation_data + sizeof(uint32_t) * lex_index);
+
+		if (offset & CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW) {
+			if (!g->chunk_generation_data_overflow)
+				die(_("commit-graph requires overflow generation data but has none"));
+
+			offset_pos = offset ^ CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW;
+			graph_data->generation = get_be64(g->chunk_generation_data_overflow + 8 * offset_pos);
+		} else
+			graph_data->generation = item->date + offset;
+	} else
+		graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
+
+	if (g->topo_levels)
+		*topo_level_slab_at(g->topo_levels, item) = get_be32(commit_data + g->hash_len + 8) >> 2;
 }
 
 static inline void set_commit_tree(struct commit *c, struct tree *t)
@@ -772,38 +851,22 @@ static int fill_commit_in_graph(struct repository *r,
 {
 	uint32_t edge_value;
 	uint32_t *parent_data_ptr;
-	uint64_t date_low, date_high;
 	struct commit_list **pptr;
-	struct commit_graph_data *graph_data;
 	const unsigned char *commit_data;
 	uint32_t lex_index;
 
 	while (pos < g->num_commits_in_base)
 		g = g->base_graph;
 
-	if (pos >= g->num_commits + g->num_commits_in_base)
-		die(_("invalid commit position. commit-graph is likely corrupt"));
+	fill_commit_graph_info(item, g, pos);
 
-	/*
-	 * Store the "full" position, but then use the
-	 * "local" position for the rest of the calculation.
-	 */
-	graph_data = commit_graph_data_at(item);
-	graph_data->graph_pos = pos;
 	lex_index = pos - g->num_commits_in_base;
-
 	commit_data = g->chunk_commit_data + (g->hash_len + 16) * lex_index;
 
 	item->object.parsed = 1;
 
 	set_commit_tree(item, NULL);
 
-	date_high = get_be32(commit_data + g->hash_len + 8) & 0x3;
-	date_low = get_be32(commit_data + g->hash_len + 12);
-	item->date = (timestamp_t)((date_high << 32) | date_low);
-
-	graph_data->generation = get_be32(commit_data + g->hash_len + 8) >> 2;
-
 	pptr = &item->parents;
 
 	edge_value = get_be32(commit_data + g->hash_len);
@@ -943,6 +1006,7 @@ struct write_commit_graph_context {
 	struct oid_array oids;
 	struct packed_commit_list commits;
 	int num_extra_edges;
+	int num_generation_data_overflows;
 	unsigned long approx_nr_objects;
 	struct progress *progress;
 	int progress_done;
@@ -961,8 +1025,10 @@ struct write_commit_graph_context {
 		 report_progress:1,
 		 split:1,
 		 changed_paths:1,
-		 order_by_pack:1;
+		 order_by_pack:1,
+		 write_generation_data:1;
 
+	struct topo_level_slab *topo_levels;
 	const struct commit_graph_opts *opts;
 	size_t total_bloom_filter_data_size;
 	const struct bloom_filter_settings *bloom_settings;
@@ -1109,7 +1175,7 @@ static int write_graph_chunk_data(struct hashfile *f,
 		else
 			packedDate[0] = 0;
 
-		packedDate[0] |= htonl(commit_graph_data_at(*list)->generation << 2);
+		packedDate[0] |= htonl(*topo_level_slab_at(ctx->topo_levels, *list) << 2);
 
 		packedDate[1] = htonl((*list)->date);
 		hashwrite(f, packedDate, 8);
@@ -1120,6 +1186,45 @@ static int write_graph_chunk_data(struct hashfile *f,
 	return 0;
 }
 
+static int write_graph_chunk_generation_data(struct hashfile *f,
+					      struct write_commit_graph_context *ctx)
+{
+	int i, num_generation_data_overflows = 0;
+
+	for (i = 0; i < ctx->commits.nr; i++) {
+		struct commit *c = ctx->commits.list[i];
+		timestamp_t offset = commit_graph_data_at(c)->generation - c->date;
+		display_progress(ctx->progress, ++ctx->progress_cnt);
+
+		if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) {
+			offset = CORRECTED_COMMIT_DATE_OFFSET_OVERFLOW | num_generation_data_overflows;
+			num_generation_data_overflows++;
+		}
+
+		hashwrite_be32(f, offset);
+	}
+
+	return 0;
+}
+
+static int write_graph_chunk_generation_data_overflow(struct hashfile *f,
+						       struct write_commit_graph_context *ctx)
+{
+	int i;
+	for (i = 0; i < ctx->commits.nr; i++) {
+		struct commit *c = ctx->commits.list[i];
+		timestamp_t offset = commit_graph_data_at(c)->generation - c->date;
+		display_progress(ctx->progress, ++ctx->progress_cnt);
+
+		if (offset > GENERATION_NUMBER_V2_OFFSET_MAX) {
+			hashwrite_be32(f, offset >> 32);
+			hashwrite_be32(f, (uint32_t) offset);
+		}
+	}
+
+	return 0;
+}
+
 static int write_graph_chunk_extra_edges(struct hashfile *f,
 					 struct write_commit_graph_context *ctx)
 {
@@ -1339,11 +1444,12 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 					_("Computing commit graph generation numbers"),
 					ctx->commits.nr);
 	for (i = 0; i < ctx->commits.nr; i++) {
-		uint32_t generation = commit_graph_data_at(ctx->commits.list[i])->generation;
+		uint32_t level = *topo_level_slab_at(ctx->topo_levels, ctx->commits.list[i]);
+		timestamp_t corrected_commit_date = commit_graph_data_at(ctx->commits.list[i])->generation;
 
 		display_progress(ctx->progress, i + 1);
-		if (generation != GENERATION_NUMBER_INFINITY &&
-		    generation != GENERATION_NUMBER_ZERO)
+		if (level != GENERATION_NUMBER_ZERO &&
+		    corrected_commit_date != GENERATION_NUMBER_ZERO)
 			continue;
 
 		commit_list_insert(ctx->commits.list[i], &list);
@@ -1351,29 +1457,40 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 			struct commit *current = list->item;
 			struct commit_list *parent;
 			int all_parents_computed = 1;
-			uint32_t max_generation = 0;
+			uint32_t max_level = 0;
+			timestamp_t max_corrected_commit_date = 0;
 
 			for (parent = current->parents; parent; parent = parent->next) {
-				generation = commit_graph_data_at(parent->item)->generation;
+				level = *topo_level_slab_at(ctx->topo_levels, parent->item);
+				corrected_commit_date = commit_graph_data_at(parent->item)->generation;
 
-				if (generation == GENERATION_NUMBER_INFINITY ||
-				    generation == GENERATION_NUMBER_ZERO) {
+				if (level == GENERATION_NUMBER_ZERO ||
+				    corrected_commit_date == GENERATION_NUMBER_ZERO) {
 					all_parents_computed = 0;
 					commit_list_insert(parent->item, &list);
 					break;
-				} else if (generation > max_generation) {
-					max_generation = generation;
 				}
+
+				if (level > max_level)
+					max_level = level;
+
+				if (corrected_commit_date > max_corrected_commit_date)
+					max_corrected_commit_date = corrected_commit_date;
 			}
 
 			if (all_parents_computed) {
-				struct commit_graph_data *data = commit_graph_data_at(current);
-
-				data->generation = max_generation + 1;
 				pop_commit(&list);
 
-				if (data->generation > GENERATION_NUMBER_MAX)
-					data->generation = GENERATION_NUMBER_MAX;
+				if (max_level > GENERATION_NUMBER_V1_MAX - 1)
+					max_level = GENERATION_NUMBER_V1_MAX - 1;
+				*topo_level_slab_at(ctx->topo_levels, current) = max_level + 1;
+
+				if (current->date && current->date > max_corrected_commit_date)
+					max_corrected_commit_date = current->date - 1;
+				commit_graph_data_at(current)->generation = max_corrected_commit_date + 1;
+
+				if (commit_graph_data_at(current)->generation - current->date > GENERATION_NUMBER_V2_OFFSET_MAX)
+					ctx->num_generation_data_overflows++;
 			}
 		}
 	}
@@ -1707,6 +1824,21 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 	chunks[2].id = GRAPH_CHUNKID_DATA;
 	chunks[2].size = (hashsz + 16) * ctx->commits.nr;
 	chunks[2].write_fn = write_graph_chunk_data;
+
+	if (git_env_bool(GIT_TEST_COMMIT_GRAPH_NO_GDAT, 0))
+		ctx->write_generation_data = 0;
+	if (ctx->write_generation_data) {
+		chunks[num_chunks].id = GRAPH_CHUNKID_GENERATION_DATA;
+		chunks[num_chunks].size = sizeof(uint32_t) * ctx->commits.nr;
+		chunks[num_chunks].write_fn = write_graph_chunk_generation_data;
+		num_chunks++;
+	}
+	if (ctx->num_generation_data_overflows) {
+		chunks[num_chunks].id = GRAPH_CHUNKID_GENERATION_DATA_OVERFLOW;
+		chunks[num_chunks].size = sizeof(timestamp_t) * ctx->num_generation_data_overflows;
+		chunks[num_chunks].write_fn = write_graph_chunk_generation_data_overflow;
+		num_chunks++;
+	}
 	if (ctx->num_extra_edges) {
 		chunks[num_chunks].id = GRAPH_CHUNKID_EXTRAEDGES;
 		chunks[num_chunks].size = 4 * ctx->num_extra_edges;
@@ -1918,6 +2050,13 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 		if (i < ctx->num_commit_graphs_after)
 			ctx->commit_graph_hash_after[i] = xstrdup(oid_to_hex(&g->oid));
 
+		/*
+		 * If the topmost remaining layer has generation data chunk, the
+		 * resultant layer also has generation data chunk.
+		 */
+		if (i == ctx->num_commit_graphs_after - 2)
+			ctx->write_generation_data = !!g->chunk_generation_data;
+
 		i--;
 		g = g->base_graph;
 	}
@@ -2109,6 +2248,7 @@ int write_commit_graph(struct object_directory *odb,
 	int res = 0;
 	int replace = 0;
 	struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
+	struct topo_level_slab topo_levels;
 
 	prepare_repo_settings(the_repository);
 	if (!the_repository->settings.core_commit_graph) {
@@ -2126,6 +2266,8 @@ int write_commit_graph(struct object_directory *odb,
 	ctx->split = flags & COMMIT_GRAPH_WRITE_SPLIT ? 1 : 0;
 	ctx->opts = opts;
 	ctx->total_bloom_filter_data_size = 0;
+	ctx->write_generation_data = 1;
+	ctx->num_generation_data_overflows = 0;
 
 	bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
 						      bloom_settings.bits_per_entry);
@@ -2135,6 +2277,18 @@ int write_commit_graph(struct object_directory *odb,
 							 bloom_settings.max_changed_paths);
 	ctx->bloom_settings = &bloom_settings;
 
+	init_topo_level_slab(&topo_levels);
+	ctx->topo_levels = &topo_levels;
+
+	if (ctx->r->objects->commit_graph) {
+		struct commit_graph *g = ctx->r->objects->commit_graph;
+
+		while (g) {
+			g->topo_levels = &topo_levels;
+			g = g->base_graph;
+		}
+	}
+
 	if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
 		ctx->changed_paths = 1;
 	if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
@@ -2227,6 +2381,8 @@ int write_commit_graph(struct object_directory *odb,
 	} else
 		ctx->num_commit_graphs_after = 1;
 
+	validate_mixed_generation_chain(ctx->r->objects->commit_graph);
+
 	compute_generation_numbers(ctx);
 
 	if (ctx->changed_paths)
@@ -2355,8 +2511,8 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 	for (i = 0; i < g->num_commits; i++) {
 		struct commit *graph_commit, *odb_commit;
 		struct commit_list *graph_parents, *odb_parents;
-		uint32_t max_generation = 0;
-		uint32_t generation;
+		timestamp_t max_generation = 0;
+		timestamp_t generation;
 
 		display_progress(progress, i + 1);
 		hashcpy(cur_oid.hash, g->chunk_oid_lookup + g->hash_len * i);
@@ -2420,16 +2576,17 @@ int verify_commit_graph(struct repository *r, struct commit_graph *g, int flags)
 			continue;
 
 		/*
-		 * If one of our parents has generation GENERATION_NUMBER_MAX, then
-		 * our generation is also GENERATION_NUMBER_MAX. Decrement to avoid
-		 * extra logic in the following condition.
+		 * If we are using topological level and one of our parents has
+		 * generation GENERATION_NUMBER_V1_MAX, then our generation is
+		 * also GENERATION_NUMBER_V1_MAX. Decrement to avoid extra logic
+		 * in the following condition.
 		 */
-		if (max_generation == GENERATION_NUMBER_MAX)
+		if (!g->read_generation_data && max_generation == GENERATION_NUMBER_V1_MAX)
 			max_generation--;
 
 		generation = commit_graph_generation(graph_commit);
-		if (generation != max_generation + 1)
-			graph_report(_("commit-graph generation for commit %s is %u != %u"),
+		if (generation < max_generation + 1)
+			graph_report(_("commit-graph generation for commit %s is %"PRItime" < %"PRItime),
 				     oid_to_hex(&cur_oid),
 				     generation,
 				     max_generation + 1);