commit-graph: Use the commit-graph in revwalks

This change makes revwalks a bit faster by using the `commit-graph` file
(if present). This is thanks to the `commit-graph` allow much faster
parsing of the commit information by requiring near-zero I/O (aside from
reading a few dozen bytes off of a `mmap(2)`-ed file) for each commit,
instead of having to read the ODB, inflate the commit, and parse it.

This is done by modifying `git_commit_list_parse()` and letting it use
the ODB-owned commit-graph file.

Part of: #5757

1 files changed, 74 insertions, 0 deletions

diff --git a/src/odb.c b/src/odb.c
index b2988c429..02f97915d 100644
--- a/src/odb.c
+++ b/src/odb.c
@@ -465,6 +465,13 @@ int git_odb_new(git_odb **out)
 		git__free(db);
 		return -1;
 	}
+	if (git_buf_init(&db->objects_dir, 0) < 0) {
+		git_vector_free(&db->backends);
+		git_cache_dispose(&db->own_cache);
+		git_mutex_free(&db->lock);
+		git__free(db);
+		return -1;
+	}
 
 	*out = db;
 	GIT_REFCOUNT_INC(db);
@@ -612,6 +619,17 @@ int git_odb__add_default_backends(
 	git_mutex_unlock(&db->lock);
 #endif
 
+	if (git_mutex_lock(&db->lock) < 0) {
+		git_error_set(GIT_ERROR_ODB, "failed to acquire the odb lock");
+		return -1;
+	}
+	if (git_buf_len(&db->objects_dir) == 0 && git_buf_sets(&db->objects_dir, objects_dir) < 0) {
+		git_mutex_unlock(&db->lock);
+		git_odb_free(db);
+		return -1;
+	}
+	git_mutex_unlock(&db->lock);
+
 	/* add the loose object backend */
 	if (git_odb_backend_loose(&loose, objects_dir, -1, db->do_fsync, 0, 0) < 0 ||
 		add_backend_internal(db, loose, GIT_LOOSE_PRIORITY, as_alternates, inode) < 0)
@@ -742,6 +760,8 @@ static void odb_free(git_odb *db)
 	if (locked)
 		git_mutex_unlock(&db->lock);
 
+	git_buf_dispose(&db->objects_dir);
+	git_commit_graph_free(db->cgraph);
 	git_vector_free(&db->backends);
 	git_cache_dispose(&db->own_cache);
 	git_mutex_free(&db->lock);
@@ -786,6 +806,53 @@ static int odb_exists_1(
 	return (int)found;
 }
 
+int git_odb__get_commit_graph(git_commit_graph_file **out, git_odb *db)
+{
+	int error = 0;
+
+	if ((error = git_mutex_lock(&db->lock)) < 0) {
+		git_error_set(GIT_ERROR_ODB, "failed to acquire the db lock");
+		return error;
+	}
+	if (!db->cgraph_checked) {
+		git_buf commit_graph_path = GIT_BUF_INIT;
+		git_commit_graph_file *cgraph = NULL;
+
+		/* We only check once, no matter the result. */
+		db->cgraph_checked = 1;
+
+		if (git_buf_len(&db->objects_dir) == 0) {
+			/*
+			 * This odb was not opened with an objects directory
+			 * associated. Skip opening the commit graph.
+			 */
+			goto done;
+		}
+
+		if ((error = git_buf_joinpath(
+				     &commit_graph_path,
+				     git_buf_cstr(&db->objects_dir),
+				     "info/commit-graph"))
+		    < 0) {
+			git_buf_dispose(&commit_graph_path);
+			goto done;
+		}
+		/* Best effort */
+		error = git_commit_graph_open(&cgraph, git_buf_cstr(&commit_graph_path));
+		git_buf_dispose(&commit_graph_path);
+
+		if (error < 0)
+			goto done;
+
+		db->cgraph = cgraph;
+	}
+
+done:
+	*out = db->cgraph;
+	git_mutex_unlock(&db->lock);
+	return 0;
+}
+
 static int odb_freshen_1(
 	git_odb *db,
 	const git_oid *id,
@@ -1695,6 +1762,13 @@ int git_odb_refresh(struct git_odb *db)
 			}
 		}
 	}
+	if (db->cgraph && git_commit_graph_needs_refresh(db->cgraph, NULL)) {
+		/* We just free the commit graph. The next time it is requested, it will be re-loaded. */
+		git_commit_graph_free(db->cgraph);
+		db->cgraph = NULL;
+	}
+	/* Force a lazy re-check next time it is needed. */
+	db->cgraph_checked = 0;
 	git_mutex_unlock(&db->lock);
 
 	return 0;