[v6+,7/7] scalar: teach `diagnose` to gather loose objects information

Commit Message

Junio C Hamano May 28, 2022, 11:11 p.m. UTC

From: Matthew John Cheetham <[e-mail]>

When operating at the scale that Scalar wants to support, certain data
shapes are more likely to cause undesirable performance issues, such as
large numbers of loose objects.

By including statistics about this, `scalar diagnose` now makes it
easier to identify such scenarios.

Signed-off-by: Matthew John Cheetham <[e-mail]>
Signed-off-by: Johannes Schindelin <[e-mail]>
Signed-off-by: Junio C Hamano <[e-mail]>
---
 contrib/scalar/scalar.c          | 59 ++++++++++++++++++++++++++++++++
 contrib/scalar/t/t9099-scalar.sh |  5 ++-
 2 files changed, 63 insertions(+), 1 deletion(-)

Patch

diff --git a/contrib/scalar/scalar.c b/contrib/scalar/scalar.c
index f745519038..28176914e5 100644
--- a/contrib/scalar/scalar.c
+++ b/contrib/scalar/scalar.c
@@ -618,6 +618,60 @@  static int dir_file_stats(struct object_directory *object_dir, void *data)
 	return 0;
 }
 
+static int count_files(char *path)
+{
+	DIR *dir = opendir(path);
+	struct dirent *e;
+	int count = 0;
+
+	if (!dir)
+		return 0;
+
+	while ((e = readdir(dir)) != NULL)
+		if (!is_dot_or_dotdot(e->d_name) && e->d_type == DT_REG)
+			count++;
+
+	closedir(dir);
+	return count;
+}
+
+static void loose_objs_stats(struct strbuf *buf, const char *path)
+{
+	DIR *dir = opendir(path);
+	struct dirent *e;
+	int count;
+	int total = 0;
+	unsigned char c;
+	struct strbuf count_path = STRBUF_INIT;
+	size_t base_path_len;
+
+	if (!dir)
+		return;
+
+	strbuf_addstr(buf, "Object directory stats for ");
+	strbuf_add_absolute_path(buf, path);
+	strbuf_addstr(buf, ":\n");
+
+	strbuf_add_absolute_path(&count_path, path);
+	strbuf_addch(&count_path, '/');
+	base_path_len = count_path.len;
+
+	while ((e = readdir(dir)) != NULL)
+		if (!is_dot_or_dotdot(e->d_name) &&
+		    e->d_type == DT_DIR && strlen(e->d_name) == 2 &&
+		    !hex_to_bytes(&c, e->d_name, 1)) {
+			strbuf_setlen(&count_path, base_path_len);
+			strbuf_addstr(&count_path, e->d_name);
+			total += (count = count_files(count_path.buf));
+			strbuf_addf(buf, "%s : %7d files\n", e->d_name, count);
+		}
+
+	strbuf_addf(buf, "Total: %d loose objects", total);
+
+	strbuf_release(&count_path);
+	closedir(dir);
+}
+
 static int cmd_diagnose(int argc, const char **argv)
 {
 	struct option options[] = {
@@ -686,6 +740,11 @@  static int cmd_diagnose(int argc, const char **argv)
 	foreach_alt_odb(dir_file_stats, &buf);
 	strvec_push(&archiver_args, buf.buf);
 
+	strbuf_reset(&buf);
+	strbuf_addstr(&buf, "--add-virtual-file=objects-local.txt:");
+	loose_objs_stats(&buf, ".git/objects");
+	strvec_push(&archiver_args, buf.buf);
+
 	if ((res = add_directory_to_archiver(&archiver_args, ".git", 0)) ||
 	    (res = add_directory_to_archiver(&archiver_args, ".git/hooks", 0)) ||
 	    (res = add_directory_to_archiver(&archiver_args, ".git/info", 0)) ||
diff --git a/contrib/scalar/t/t9099-scalar.sh b/contrib/scalar/t/t9099-scalar.sh
index 2603e2278f..10b1172a8a 100755
--- a/contrib/scalar/t/t9099-scalar.sh
+++ b/contrib/scalar/t/t9099-scalar.sh
@@ -103,6 +103,7 @@  test_expect_success UNZIP 'scalar diagnose' '
 	scalar clone "file://$(pwd)" cloned --single-branch &&
 	git repack &&
 	echo "$(pwd)/.git/objects/" >>cloned/src/.git/objects/info/alternates &&
+	test_commit -C cloned/src loose &&
 	scalar diagnose cloned >out 2>err &&
 	grep "Available space" out &&
 	sed -n "s/.*$SQ\\(.*\\.zip\\)$SQ.*/\\1/p" <err >zip_path &&
@@ -114,7 +115,9 @@  test_expect_success UNZIP 'scalar diagnose' '
 	unzip -p "$zip_path" diagnostics.log >out &&
 	test_file_not_empty out &&
 	unzip -p "$zip_path" packs-local.txt >out &&
-	grep "$(pwd)/.git/objects" out
+	grep "$(pwd)/.git/objects" out &&
+	unzip -p "$zip_path" objects-local.txt >out &&
+	grep "^Total: [1-9]" out
 '
 
 test_done