[PATCH v5 5/5] revision: avoid hitting packfiles when commits are in commit-graph

[Patrick Steinhardt <ps@pks.im>]

[-- Attachment #1: Type: text/plain, Size: 4772 bytes --]

When queueing references in git-rev-list(1), we try to optimize parsing
of commits via the commit-graph. To do so, we first look up the object's
type, and if it is a commit we call `repo_parse_commit()` instead of
`parse_object()`. This is quite inefficient though given that we're
always uncompressing the object header in order to determine the type.
Instead, we can opportunistically search the commit-graph for the object
ID: in case it's found, we know it's a commit and can directly fill in
the commit object without having to uncompress the object header.

Expose a new function `lookup_commit_in_graph()`, which tries to find a
commit in the commit-graph by ID, and convert `get_reference()` to use
this function. This provides a big performance win in cases where we
load references in a repository with lots of references pointing to
commits. The following has been executed in a real-world repository with
about 2.2 million refs:

    Benchmark #1: HEAD~: rev-list --unsorted-input --objects --quiet --not --all --not $newrev
      Time (mean ± σ):      4.458 s ±  0.044 s    [User: 4.115 s, System: 0.342 s]
      Range (min … max):    4.409 s …  4.534 s    10 runs

    Benchmark #2: HEAD: rev-list --unsorted-input --objects --quiet --not --all --not $newrev
      Time (mean ± σ):      3.089 s ±  0.015 s    [User: 2.768 s, System: 0.321 s]
      Range (min … max):    3.061 s …  3.105 s    10 runs

    Summary
      'HEAD: rev-list --unsorted-input --objects --quiet --not --all --not $newrev' ran
        1.44 ± 0.02 times faster than 'HEAD~: rev-list --unsorted-input --objects --quiet --not --all --not $newrev'

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 commit-graph.c | 24 ++++++++++++++++++++++++
 commit-graph.h |  8 ++++++++
 revision.c     | 18 ++++++++----------
 3 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index 8c4c7262c8..00614acd65 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -891,6 +891,30 @@ static int find_commit_pos_in_graph(struct commit *item, struct commit_graph *g,
 	}
 }
 
+struct commit *lookup_commit_in_graph(struct repository *repo, const struct object_id *id)
+{
+	struct commit *commit;
+	uint32_t pos;
+
+	if (!repo->objects->commit_graph)
+		return NULL;
+	if (!search_commit_pos_in_graph(id, repo->objects->commit_graph, &pos))
+		return NULL;
+	if (!repo_has_object_file(repo, id))
+		return NULL;
+
+	commit = lookup_commit(repo, id);
+	if (!commit)
+		return NULL;
+	if (commit->object.parsed)
+		return commit;
+
+	if (!fill_commit_in_graph(repo, commit, repo->objects->commit_graph, pos))
+		return NULL;
+
+	return commit;
+}
+
 static int parse_commit_in_graph_one(struct repository *r,
 				     struct commit_graph *g,
 				     struct commit *item)
diff --git a/commit-graph.h b/commit-graph.h
index 96c24fb577..04a94e1830 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -40,6 +40,14 @@ int open_commit_graph(const char *graph_file, int *fd, struct stat *st);
  */
 int parse_commit_in_graph(struct repository *r, struct commit *item);
 
+/*
+ * Look up the given commit ID in the commit-graph. This will only return a
+ * commit if the ID exists both in the graph and in the object database such
+ * that we don't return commits whose object has been pruned. Otherwise, this
+ * function returns `NULL`.
+ */
+struct commit *lookup_commit_in_graph(struct repository *repo, const struct object_id *id);
+
 /*
  * It is possible that we loaded commit contents from the commit buffer,
  * but we also want to ensure the commit-graph content is correctly
diff --git a/revision.c b/revision.c
index 80a59896b9..0dabb5a0bc 100644
--- a/revision.c
+++ b/revision.c
@@ -360,20 +360,18 @@ static struct object *get_reference(struct rev_info *revs, const char *name,
 				    unsigned int flags)
 {
 	struct object *object;
+	struct commit *commit;
 
 	/*
-	 * If the repository has commit graphs, repo_parse_commit() avoids
-	 * reading the object buffer, so use it whenever possible.
+	 * If the repository has commit graphs, we try to opportunistically
+	 * look up the object ID in those graphs. Like this, we can avoid
+	 * parsing commit data from disk.
 	 */
-	if (oid_object_info(revs->repo, oid, NULL) == OBJ_COMMIT) {
-		struct commit *c = lookup_commit(revs->repo, oid);
-		if (!repo_parse_commit(revs->repo, c))
-			object = (struct object *) c;
-		else
-			object = NULL;
-	} else {
+	commit = lookup_commit_in_graph(revs->repo, oid);
+	if (commit)
+		object = &commit->object;
+	else
 		object = parse_object(revs->repo, oid);
-	}
 
 	if (!object) {
 		if (revs->ignore_missing)
-- 
2.32.0


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]