commit-graph: expire commit-graph files

As we merge commit-graph files in a commit-graph chain, we should clean
up the files that are no longer used.

This change introduces an 'expiry_window' value to the context, which is
always zero (for now). We then check the modified time of each
graph-{hash}.graph file in the $OBJDIR/info/commit-graphs folder and
unlink the files that are older than the expiry_window.

Since this is always zero, this immediately clears all unused graph
files. We will update the value to match a config setting in a future
change.

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

Author: derrickstolee

Documentation/technical/commit-graph.txt

@@ -267,6 +267,21 @@ 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.
 
+## Deleting graph-{hash} files
+
+After a new tip file is written, some `graph-{hash}` files may no longer
+be part of a chain. It is important to remove these files from disk, eventually.
+The main reason to delay removal is that another process could read the
+`commit-graph-chain` file before it is rewritten, but then look for the
+`graph-{hash}` files after they are deleted.
+
+To allow holding old split commit-graphs for a while after they are unreferenced,
+we update the modified times of the files when they become unreferenced. Then,
+we scan the `$OBJDIR/info/commit-graphs/` directory for `graph-{hash}`
+files whose modified times are older than a given expiry window. This window
+defaults to zero, but can be changed using command-line arguments or a config
+setting.
+
 ## Chains across multiple object directories
 
 In a repo with alternates, we look for the `commit-graph-chain` file starting

commit-graph.c

@@ -739,6 +739,8 @@ struct write_commit_graph_context {
 	unsigned append:1,
 		 report_progress:1,
 		 split:1;
+
+	time_t expire_window;
 };
 
 static void write_graph_chunk_fanout(struct hashfile *f,
@@ -1629,6 +1631,70 @@ static void merge_commit_graphs(struct write_commit_graph_context *ctx)
 	deduplicate_commits(ctx);
 }
 
+static void mark_commit_graphs(struct write_commit_graph_context *ctx)
+{
+	uint32_t i;
+	time_t now = time(NULL);
+
+	for (i = ctx->num_commit_graphs_after - 1; i < ctx->num_commit_graphs_before; i++) {
+		struct stat st;
+		struct utimbuf updated_time;
+
+		stat(ctx->commit_graph_filenames_before[i], &st);
+
+		updated_time.actime = st.st_atime;
+		updated_time.modtime = now;
+		utime(ctx->commit_graph_filenames_before[i], &updated_time);
+	}
+}
+
+static void expire_commit_graphs(struct write_commit_graph_context *ctx)
+{
+	struct strbuf path = STRBUF_INIT;
+	DIR *dir;
+	struct dirent *de;
+	size_t dirnamelen;
+	time_t expire_time = time(NULL) - ctx->expire_window;
+
+	strbuf_addstr(&path, ctx->obj_dir);
+	strbuf_addstr(&path, "/info/commit-graphs");
+	dir = opendir(path.buf);
+
+	if (!dir) {
+		strbuf_release(&path);
+		return;
+	}
+
+	strbuf_addch(&path, '/');
+	dirnamelen = path.len;
+	while ((de = readdir(dir)) != NULL) {
+		struct stat st;
+		uint32_t i, found = 0;
+
+		strbuf_setlen(&path, dirnamelen);
+		strbuf_addstr(&path, de->d_name);
+
+		stat(path.buf, &st);
+
+		if (st.st_mtime > expire_time)
+			continue;
+		if (path.len < 6 || strcmp(path.buf + path.len - 6, ".graph"))
+			continue;
+
+		for (i = 0; i < ctx->num_commit_graphs_after; i++) {
+			if (!strcmp(ctx->commit_graph_filenames_after[i],
+				    path.buf)) {
+				found = 1;
+				break;
+			}
+		}
+
+		if (!found)
+			unlink(path.buf);
+
+	}
+}
+
 int write_commit_graph(const char *obj_dir,
 		       struct string_list *pack_indexes,
 		       struct string_list *commit_hex,
@@ -1741,6 +1807,11 @@ int write_commit_graph(const char *obj_dir,
 
 	res = write_commit_graph_file(ctx);
 
+	if (ctx->split) {
+		mark_commit_graphs(ctx);
+		expire_commit_graphs(ctx);
+	}
+
 cleanup:
 	free(ctx->graph_name);
 	free(ctx->commits.list);

t/t5323-split-commit-graph.sh

@@ -141,7 +141,7 @@ test_expect_success 'add one commit, write a merged graph' '
 	test_path_is_file $graphdir/commit-graph-chain &&
 	test_line_count = 2 $graphdir/commit-graph-chain &&
 	ls $graphdir/graph-*.graph >graph-files &&
-	test_line_count = 4 graph-files &&
+	test_line_count = 2 graph-files &&
 	verify_chain_files_exist $graphdir
 '