commit-graph: allow cross-alternate chains

In an environment like a fork network, it is helpful to have a
commit-graph chain that spans both the base repo and the fork repo. The
fork is usually a small set of data on top of the large repo, but
sometimes the fork is much larger. For example, git-for-windows/git has
almost double the number of commits as git/git because it rebases its
commits on every major version update.

To allow cross-alternate commit-graph chains, we need a few pieces:

1. When looking for a graph-{hash}.graph file, check all alternates.

2. When merging commit-graph chains, do not merge across alternates.

3. When writing a new commit-graph chain based on a commit-graph file
   in another object directory, do not allow success if the base file
   has of the name "commit-graph" instead of
   "commit-graphs/graoh-{hash}.graph".

Signed-off-by: Derrick Stolee <[email protected]>

Author: derrickstolee

Documentation/technical/commit-graph.txt

@@ -266,6 +266,42 @@ The merge strategy values (2 for the size multiple, 64,000 for the maximum
 number of commits) could be extracted into config settings for full
 flexibility.
 
+## Chains across multiple object directories
+
+In a repo with alternates, we look for the `commit-graph-chain` file starting
+in the local object directory and then in each alternate. The first file that
+exists defines our chain. As we look for the `graph-{hash}` files for
+each `{hash}` in the chain file, we follow the same pattern for the host
+directories.
+
+This allows commit-graphs to be split across multiple forks in a fork network.
+The typical case is a large "base" repo with many smaller forks.
+
+As the base repo advances, it will likely update and merge its commit-graph
+chain more frequently than the forks. If a fork updates their commit-graph after
+the base repo, then it should "reparent" the commit-graph chain onto the new
+chain in the base repo. When reading each `graph-{hash}` file, we track
+the object directory containing it. During a write of a new commit-graph file,
+we check for any changes in the source object directory and read the
+`commit-graph-chain` file for that source and create a new file based on those
+files. During this "reparent" operation, we necessarily need to collapse all
+levels in the fork, as all of the files are invalid against the new base file.
+
+It is crucial to be careful when cleaning up "unreferenced" `graph-{hash}.graph`
+files in this scenario. It falls to the user to define the proper settings for
+their custom environment:
+
+ 1. When merging levels in the base repo, the unreferenced files may still be
+    referenced by chains from fork repos.
+
+ 2. The expiry time should be set to a length of time such that every fork has
+    time to recompute their commit-graph chain to "reparent" onto the new base
+    file(s).
+
+ 3. If the commit-graph chain is updated in the base, the fork will not have
+    access to the new chain until its chain is updated to reference those files.
+    (This may change in the future [5].)
+
 Related Links
 -------------
 [0] https://bugs.chromium.org/p/git/issues/detail?id=8
@@ -292,3 +328,7 @@ Related Links
 
 [4] https://public-inbox.org/git/[email protected]/T/#u
     A patch to remove the ahead-behind calculation from 'status'.
+
+[5] https://public-inbox.org/git/[email protected]/
+    A discussion of a "two-dimensional graph position" that can allow reading
+    multiple commit-graph chains at the same time.

commit-graph.c

@@ -320,6 +320,9 @@ static struct commit_graph *load_commit_graph_v1(struct repository *r, const cha
 	struct commit_graph *g = load_commit_graph_one(graph_name);
 	free(graph_name);
 
+	if (g)
+		g->obj_dir = obj_dir;
+
 	return g;
 }
 
@@ -385,8 +388,7 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, const
 	oids = xcalloc(st.st_size / (the_hash_algo->hexsz + 1), sizeof(struct object_id));
 
 	while (strbuf_getline_lf(&line, fp) != EOF && valid) {
-		char *graph_name;
-		struct commit_graph *g;
+		struct object_directory *odb;
 
 		if (get_oid_hex(line.buf, &oids[i])) {
 			warning(_("invalid commit-graph chain: line '%s' not a hash"),
@@ -395,14 +397,23 @@ static struct commit_graph *load_commit_graph_chain(struct repository *r, const
 			break;
 		}
 
-		graph_name = get_split_graph_filename(obj_dir, line.buf);
-		g = load_commit_graph_one(graph_name);
-		free(graph_name);
+		for (odb = r->objects->odb; odb; odb = odb->next) {
+			char *graph_name = get_split_graph_filename(odb->path, line.buf);
+			struct commit_graph *g = load_commit_graph_one(graph_name);
 
-		if (g && add_graph_to_chain(g, graph_chain, oids, i))
-			graph_chain = g;
-		else
-			valid = 0;
+			free(graph_name);
+
+			if (g) {
+				g->obj_dir = odb->path;
+
+				if (add_graph_to_chain(g, graph_chain, oids, i))
+					graph_chain = g;
+				else
+					valid = 0;
+
+				break;
+			}
+		}
 	}
 
 	free(oids);
@@ -1411,7 +1422,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
 
 	if (ctx->split && ctx->base_graph_name && ctx->num_commit_graphs_after > 1) {
 		char *new_base_hash = xstrdup(oid_to_hex(&ctx->new_base_graph->oid));
-		char *new_base_name = get_split_graph_filename(ctx->obj_dir, new_base_hash);
+		char *new_base_name = get_split_graph_filename(ctx->new_base_graph->obj_dir, new_base_hash);
 
 		free(ctx->commit_graph_filenames_after[ctx->num_commit_graphs_after - 2]);
 		free(ctx->commit_graph_hash_after[ctx->num_commit_graphs_after - 2]);
@@ -1482,6 +1493,9 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 
 	while (g && (g->num_commits <= split_strategy_size_mult * num_commits ||
 		     num_commits > split_strategy_max_commits)) {
+		if (strcmp(g->obj_dir, ctx->obj_dir))
+			break;
+
 		num_commits += g->num_commits;
 		g = g->base_graph;
 
@@ -1490,6 +1504,18 @@ static void split_graph_merge_strategy(struct write_commit_graph_context *ctx)
 
 	ctx->new_base_graph = g;
 
+	if (ctx->num_commit_graphs_after == 2) {
+		char *old_graph_name = get_commit_graph_filename(g->obj_dir);
+
+		if (!strcmp(g->filename, old_graph_name) &&
+		    strcmp(g->obj_dir, ctx->obj_dir)) {
+			ctx->num_commit_graphs_after = 1;
+			ctx->new_base_graph = NULL;
+		}
+
+		free(old_graph_name);
+	}
+
 	ALLOC_ARRAY(ctx->commit_graph_filenames_after, ctx->num_commit_graphs_after);
 	ALLOC_ARRAY(ctx->commit_graph_hash_after, ctx->num_commit_graphs_after);
 

commit-graph.h

@@ -48,6 +48,7 @@ struct commit_graph {
 	uint32_t num_commits;
 	struct object_id oid;
 	char *filename;
+	const char *obj_dir;
 
 	uint32_t num_commits_in_base;
 	struct commit_graph *base_graph;

t/t5323-split-commit-graph.sh

@@ -90,6 +90,21 @@ test_expect_success 'add more commits, and write a new base graph' '
 	graph_read_expect 12
 '
 
+test_expect_success 'fork and fail to base a chain on a commit-graph file' '
+	test_when_finished rm -rf fork &&
+	git clone . fork &&
+	(
+		cd fork &&
+		rm .git/objects/info/commit-graph &&
+		echo "$TRASH_DIRECTORY/.git/objects" >.git/objects/info/alternates &&
+		test_commit new-commit &&
+		git commit-graph write --reachable --split &&
+		test_path_is_file $graphdir/commit-graph-chain &&
+		test_line_count = 1 $graphdir/commit-graph-chain &&
+		verify_chain_files_exist $graphdir
+	)
+'
+
 test_expect_success 'add three more commits, write a tip graph' '
 	git reset --hard commits/3 &&
 	git merge merge/1 &&
@@ -132,4 +147,26 @@ test_expect_success 'add one commit, write a merged graph' '
 
 graph_git_behavior 'merged commit-graph: commit 12 vs 6' commits/12 commits/6
 
+test_expect_success 'create fork and chain across alternate' '
+	git clone . fork &&
+	(
+		cd fork &&
+		git config core.commitGraph true &&
+		rm -rf $graphdir &&
+		echo "$TRASH_DIRECTORY/.git/objects" >.git/objects/info/alternates &&
+		test_commit 13 &&
+		git branch commits/13 &&
+		git commit-graph write --reachable --split &&
+		test_path_is_file $graphdir/commit-graph-chain &&
+		test_line_count = 3 $graphdir/commit-graph-chain &&
+		ls $graphdir/graph-*.graph >graph-files &&
+		test_line_count = 1 graph-files &&
+		git -c core.commitGraph=true  rev-list HEAD >expect &&
+		git -c core.commitGraph=false rev-list HEAD >actual &&
+		test_cmp expect actual
+	)
+'
+
+graph_git_behavior 'alternate: commit 13 vs 6' commits/13 commits/6
+
 test_done