[v2,4/6] commit-graph: compute generations separately

Commit Message

Derrick Stolee Feb. 2, 2021, 3:01 a.m. UTC

From: Derrick Stolee <[e-mail]>

The compute_generation_numbers() method was introduced by 3258c663
(commit-graph: compute generation numbers, 2018-05-01) to compute what
is now known as "topological levels". These are still stored in the
commit-graph file for compatibility sake while c1a09119 (commit-graph:
implement corrected commit date, 2021-01-16) updated the method to also
compute the new version of generation numbers: corrected commit date.

It makes sense why these are grouped. They perform very similar walks of
the necessary commits and compute similar maximums over each parent.
However, having these two together conflates them in subtle ways that is
hard to separate.

In particular, the topo_level slab is used to store the topological
levels in all cases, but the commit_graph_data_at(c)->generation member
stores different values depending on the state of the existing
commit-graph file.

* If the existing commit-graph file has a "GDAT" chunk, then these
  values represent corrected commit dates.

* If the existing commit-graph file doesn't have a "GDAT" chunk, then
  these values are actually the topological levels.

This issue only occurs only when upgrading an existing commit-graph file
into one that has the "GDAT" chunk. The current change does not resolve
this upgrade problem, but splitting the implementation into two pieces
here helps with that process, which will follow in the next change.

The important thing this helps with is the case where the
num_generation_data_overflows was being incremented incorrectly,
triggering a write of the overflow chunk.

Signed-off-by: Derrick Stolee <[e-mail]>
---
 commit-graph.c | 70 ++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 56 insertions(+), 14 deletions(-)

Patch

diff --git a/commit-graph.c b/commit-graph.c
index b3f7c3bbcb3..2790f70d113 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1446,27 +1446,24 @@  static void close_reachable(struct write_commit_graph_context *ctx)
 	stop_progress(&ctx->progress);
 }
 
-static void compute_generation_numbers(struct write_commit_graph_context *ctx)
+static void compute_topological_levels(struct write_commit_graph_context *ctx)
 {
 	int i;
 	struct commit_list *list = NULL;
 
 	if (ctx->report_progress)
 		ctx->progress = start_delayed_progress(
-					_("Computing commit graph generation numbers"),
+					_("Computing commit graph topological levels"),
 					ctx->commits.nr);
 	for (i = 0; i < ctx->commits.nr; i++) {
 		struct commit *c = ctx->commits.list[i];
 		uint32_t level;
-		timestamp_t corrected_commit_date;
 
 		repo_parse_commit(ctx->r, c);
 		level = *topo_level_slab_at(ctx->topo_levels, c);
-		corrected_commit_date = commit_graph_data_at(c)->generation;
 
 		display_progress(ctx->progress, i + 1);
-		if (level != GENERATION_NUMBER_ZERO &&
-		    corrected_commit_date != GENERATION_NUMBER_ZERO)
+		if (level != GENERATION_NUMBER_ZERO)
 			continue;
 
 		commit_list_insert(c, &list);
@@ -1475,15 +1472,12 @@  static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 			struct commit_list *parent;
 			int all_parents_computed = 1;
 			uint32_t max_level = 0;
-			timestamp_t max_corrected_commit_date = 0;
 
 			for (parent = current->parents; parent; parent = parent->next) {
 				repo_parse_commit(ctx->r, parent->item);
 				level = *topo_level_slab_at(ctx->topo_levels, parent->item);
-				corrected_commit_date = commit_graph_data_at(parent->item)->generation;
 
-				if (level == GENERATION_NUMBER_ZERO ||
-				    corrected_commit_date == GENERATION_NUMBER_ZERO) {
+				if (level == GENERATION_NUMBER_ZERO) {
 					all_parents_computed = 0;
 					commit_list_insert(parent->item, &list);
 					break;
@@ -1491,9 +1485,6 @@  static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 
 				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) {
@@ -1502,6 +1493,55 @@  static void compute_generation_numbers(struct write_commit_graph_context *ctx)
 				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;
+			}
+		}
+	}
+	stop_progress(&ctx->progress);
+}
+
+static void compute_generation_numbers(struct write_commit_graph_context *ctx)
+{
+	int i;
+	struct commit_list *list = NULL;
+
+	if (ctx->report_progress)
+		ctx->progress = start_delayed_progress(
+					_("Computing commit graph generation numbers"),
+					ctx->commits.nr);
+	for (i = 0; i < ctx->commits.nr; i++) {
+		struct commit *c = ctx->commits.list[i];
+		timestamp_t corrected_commit_date;
+
+		repo_parse_commit(ctx->r, c);
+		corrected_commit_date = commit_graph_data_at(c)->generation;
+
+		display_progress(ctx->progress, i + 1);
+		if (corrected_commit_date != GENERATION_NUMBER_ZERO)
+			continue;
+
+		commit_list_insert(c, &list);
+		while (list) {
+			struct commit *current = list->item;
+			struct commit_list *parent;
+			int all_parents_computed = 1;
+			timestamp_t max_corrected_commit_date = 0;
+
+			for (parent = current->parents; parent; parent = parent->next) {
+				repo_parse_commit(ctx->r, parent->item);
+				corrected_commit_date = commit_graph_data_at(parent->item)->generation;
+
+				if (corrected_commit_date == GENERATION_NUMBER_ZERO) {
+					all_parents_computed = 0;
+					commit_list_insert(parent->item, &list);
+					break;
+				}
+
+				if (corrected_commit_date > max_corrected_commit_date)
+					max_corrected_commit_date = corrected_commit_date;
+			}
+
+			if (all_parents_computed) {
+				pop_commit(&list);
 
 				if (current->date && current->date > max_corrected_commit_date)
 					max_corrected_commit_date = current->date - 1;
@@ -2401,7 +2441,9 @@  int write_commit_graph(struct object_directory *odb,
 
 	validate_mixed_generation_chain(ctx->r->objects->commit_graph);
 
-	compute_generation_numbers(ctx);
+	compute_topological_levels(ctx);
+	if (ctx->write_generation_data)
+		compute_generation_numbers(ctx);
 
 	if (ctx->changed_paths)
 		compute_bloom_filters(ctx);