[v4,08/15] commit-graph: examine commits by generation number
diff mbox series

Message ID 5ed16f35fed43018ce441adfff55b85967d3918c.1586192395.git.gitgitgadget@gmail.com
State New
Headers show
Series
  • Changed Paths Bloom Filters
Related show

Commit Message

Marco Trevisan via GitGitGadget April 6, 2020, 4:59 p.m. UTC
From: Garima Singh <garima.singh@microsoft.com>

When running 'git commit-graph write --changed-paths', we sort the
commits by pack-order to save time when computing the changed-paths
bloom filters. This does not help when finding the commits via the
'--reachable' flag.

If not using pack-order, then sort by generation number before
examining the diff. Commits with similar generation are more likely
to have many trees in common, making the diff faster.

On the Linux kernel repository, this change reduced the computation
time for 'git commit-graph write --reachable --changed-paths' from
3m00s to 1m37s.

Helped-by: Jeff King <peff@peff.net>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Garima Singh <garima.singh@microsoft.com>
---
 commit-graph.c | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

Patch
diff mbox series

diff --git a/commit-graph.c b/commit-graph.c
index 31b06f878ce..732c81fa1b2 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -70,6 +70,25 @@  static int commit_pos_cmp(const void *va, const void *vb)
 	       commit_pos_at(&commit_pos, b);
 }
 
+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;
+
+	/* lower generation commits first */
+	if (a->generation < b->generation)
+		return -1;
+	else if (a->generation > b->generation)
+		return 1;
+
+	/* use date as a heuristic when generations are equal */
+	if (a->date < b->date)
+		return -1;
+	else if (a->date > b->date)
+		return 1;
+	return 0;
+}
+
 char *get_commit_graph_filename(struct object_directory *obj_dir)
 {
 	return xstrfmt("%s/info/commit-graph", obj_dir->path);
@@ -815,7 +834,8 @@  struct write_commit_graph_context {
 		 report_progress:1,
 		 split:1,
 		 check_oids:1,
-		 changed_paths:1;
+		 changed_paths:1,
+		 order_by_pack:1;
 
 	const struct split_commit_graph_opts *split_opts;
 	size_t total_bloom_filter_data_size;
@@ -1178,7 +1198,11 @@  static void compute_bloom_filters(struct write_commit_graph_context *ctx)
 
 	ALLOC_ARRAY(sorted_commits, ctx->commits.nr);
 	COPY_ARRAY(sorted_commits, ctx->commits.list, ctx->commits.nr);
-	QSORT(sorted_commits, ctx->commits.nr, commit_pos_cmp);
+
+	if (ctx->order_by_pack)
+		QSORT(sorted_commits, ctx->commits.nr, commit_pos_cmp);
+	else
+		QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
 
 	for (i = 0; i < ctx->commits.nr; i++) {
 		struct commit *c = sorted_commits[i];
@@ -1884,6 +1908,7 @@  int write_commit_graph(struct object_directory *odb,
 	}
 
 	if (pack_indexes) {
+		ctx->order_by_pack = 1;
 		if ((res = fill_oids_from_packs(ctx, pack_indexes)))
 			goto cleanup;
 	}
@@ -1893,8 +1918,10 @@  int write_commit_graph(struct object_directory *odb,
 			goto cleanup;
 	}
 
-	if (!pack_indexes && !commit_hex)
+	if (!pack_indexes && !commit_hex) {
+		ctx->order_by_pack = 1;
 		fill_oids_from_all_packs(ctx);
+	}
 
 	close_reachable(ctx);