[PATCH 4/6] object-file: generalize counting objects

From

Patrick Steinhardt <ps@pks.im>

Date

Mar 10, 2026, 15:18 UTC

Message-ID

<20260310-b4-pks-odb-source-count-objects-v1-4-109e07d425f4@pks.im>

In-Reply-To

<20260310-b4-pks-odb-source-count-objects-v1-0-109e07d425f4@pks.im>

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 builtin/gc.c  |  5 +++--
 object-file.c | 58 +++++++++++++++++++++++++++++++++++++---------------------
 object-file.h |  5 +++--
 odb.h         |  9 +++++++++
 4 files changed, 52 insertions(+), 25 deletions(-)

diff --git a/builtin/gc.c b/builtin/gc.c
index a08c7554cb..3a64d28da8 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -474,8 +474,9 @@ static int too_many_loose_objects(int limit)
 	int auto_threshold = DIV_ROUND_UP(limit, 256) * 256;
 	unsigned long loose_count;
 
-	if (odb_source_loose_approximate_object_count(the_repository->objects->sources,
-						      &loose_count) < 0)
+	if (odb_source_loose_count_objects(the_repository->objects->sources,
+					   ODB_COUNT_OBJECTS_APPROXIMATE,
+					   &loose_count) < 0)
 		return 0;
 
 	return loose_count > auto_threshold;
diff --git a/object-file.c b/object-file.c
index da67e3c9ff..d35cec201f 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1868,40 +1868,56 @@ int odb_source_loose_for_each_object(struct odb_source *source,
 					     NULL, NULL, &data);
 }
 
-int odb_source_loose_approximate_object_count(struct odb_source *source,
-					      unsigned long *out)
+static int count_loose_object(const struct object_id *oid UNUSED,
+			      struct object_info *oi UNUSED,
+			      void *payload)
+{
+	unsigned long *count = payload;
+	(*count)++;
+	return 0;
+}
+
+int odb_source_loose_count_objects(struct odb_source *source,
+				   enum odb_count_objects_flags flags,
+				   unsigned long *out)
 {
 	const unsigned hexsz = source->odb->repo->hash_algo->hexsz - 2;
-	unsigned long count = 0;
-	struct dirent *ent;
 	char *path = NULL;
 	DIR *dir = NULL;
 	int ret;
 
-	path = xstrfmt("%s/17", source->path);
+	if (flags & ODB_COUNT_OBJECTS_APPROXIMATE) {
+		unsigned long count = 0;
+		struct dirent *ent;
 
-	dir = opendir(path);
-	if (!dir) {
-		if (errno == ENOENT) {
-			*out = 0;
-			ret = 0;
+		path = xstrfmt("%s/17", source->path);
+
+		dir = opendir(path);
+		if (!dir) {
+			if (errno == ENOENT) {
+				*out = 0;
+				ret = 0;
+				goto out;
+			}
+
+			ret = error_errno("cannot open object shard '%s'", path);
 			goto out;
 		}
 
-		ret = error_errno("cannot open object shard '%s'", path);
-		goto out;
-	}
+		while ((ent = readdir(dir)) != NULL) {
+			if (strspn(ent->d_name, "0123456789abcdef") != hexsz ||
+			    ent->d_name[hexsz] != '\0')
+				continue;
+			count++;
+		}
 
-	while ((ent = readdir(dir)) != NULL) {
-		if (strspn(ent->d_name, "0123456789abcdef") != hexsz ||
-		    ent->d_name[hexsz] != '\0')
-			continue;
-		count++;
+		*out = count * 256;
+		ret = 0;
+	} else {
+		ret = odb_source_loose_for_each_object(source, NULL, count_loose_object,
+						       out, 0);
 	}
 
-	*out = count * 256;
-	ret = 0;
-
 out:
 	if (dir)
 		closedir(dir);
diff --git a/object-file.h b/object-file.h
index b870ea9fa8..f8d8805a18 100644
--- a/object-file.h
+++ b/object-file.h
@@ -149,8 +149,9 @@ int odb_source_loose_for_each_object(struct odb_source *source,
  *
  * Returns 0 on success, a negative error code otherwise.
  */
-int odb_source_loose_approximate_object_count(struct odb_source *source,
-					      unsigned long *out);
+int odb_source_loose_count_objects(struct odb_source *source,
+				   enum odb_count_objects_flags flags,
+				   unsigned long *out);
 
 /**
  * format_object_header() is a thin wrapper around s xsnprintf() that
diff --git a/odb.h b/odb.h
index 7a583e3873..e6057477f6 100644
--- a/odb.h
+++ b/odb.h
@@ -500,6 +500,15 @@ int odb_for_each_object(struct object_database *odb,
 			void *cb_data,
 			unsigned flags);
 
+enum odb_count_objects_flags {
+	/*
+	 * Instead of providing an accurate count, allow the number of objects
+	 * to be approximated. Details of how this approximation works are
+	 * subject to the specific source's implementation.
+	 */
+	ODB_COUNT_OBJECTS_APPROXIMATE = (1 << 0),
+};
+
 enum {
 	/*
 	 * By default, `odb_write_object()` does not actually write anything

-- 
2.53.0.880.g73c4285caa.dirty