[PATCH 3/6] object-file: extract logic to approximate object count

From

Patrick Steinhardt <ps@pks.im>

Date

Mar 10, 2026, 15:18 UTC

Message-ID

<20260310-b4-pks-odb-source-count-objects-v1-3-109e07d425f4@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  | 37 +++++++++----------------------------
 object-file.c | 41 +++++++++++++++++++++++++++++++++++++++++
 object-file.h | 13 +++++++++++++
 3 files changed, 63 insertions(+), 28 deletions(-)

diff --git a/builtin/gc.c b/builtin/gc.c
index fb329c2cff..a08c7554cb 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -467,37 +467,18 @@ static int rerere_gc_condition(struct gc_config *cfg UNUSED)
 static int too_many_loose_objects(int limit)
 {
 	/*
-	 * Quickly check if a "gc" is needed, by estimating how
-	 * many loose objects there are.  Because SHA-1 is evenly
-	 * distributed, we can check only one and get a reasonable
-	 * estimate.
+	 * This is weird, but stems from legacy behaviour: the GC auto
+	 * threshold was always essentially interpreted as if it was rounded up
+	 * to the next multiple 256 of, so we retain this behaviour for now.
 	 */
-	DIR *dir;
-	struct dirent *ent;
-	int auto_threshold;
-	int num_loose = 0;
-	int needed = 0;
-	const unsigned hexsz_loose = the_hash_algo->hexsz - 2;
-	char *path;
-
-	path = repo_git_path(the_repository, "objects/17");
-	dir = opendir(path);
-	free(path);
-	if (!dir)
+	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)
 		return 0;
 
-	auto_threshold = DIV_ROUND_UP(limit, 256);
-	while ((ent = readdir(dir)) != NULL) {
-		if (strspn(ent->d_name, "0123456789abcdef") != hexsz_loose ||
-		    ent->d_name[hexsz_loose] != '\0')
-			continue;
-		if (++num_loose > auto_threshold) {
-			needed = 1;
-			break;
-		}
-	}
-	closedir(dir);
-	return needed;
+	return loose_count > auto_threshold;
 }
 
 static struct packed_git *find_base_packs(struct string_list *packs,
diff --git a/object-file.c b/object-file.c
index a3ff7f586c..da67e3c9ff 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1868,6 +1868,47 @@ 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)
+{
+	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);
+
+	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;
+	}
+
+	while ((ent = readdir(dir)) != NULL) {
+		if (strspn(ent->d_name, "0123456789abcdef") != hexsz ||
+		    ent->d_name[hexsz] != '\0')
+			continue;
+		count++;
+	}
+
+	*out = count * 256;
+	ret = 0;
+
+out:
+	if (dir)
+		closedir(dir);
+	free(path);
+	return ret;
+}
+
 static int append_loose_object(const struct object_id *oid,
 			       const char *path UNUSED,
 			       void *data)
diff --git a/object-file.h b/object-file.h
index ff6da65296..b870ea9fa8 100644
--- a/object-file.h
+++ b/object-file.h
@@ -139,6 +139,19 @@ int odb_source_loose_for_each_object(struct odb_source *source,
 				     void *cb_data,
 				     unsigned flags);
 
+/*
+ * Count the number of loose objects in this source.
+ *
+ * The object count is approximated by opening a single sharding directory for
+ * loose objects and scanning its contents. The result is then extrapolated by
+ * 256. This should generally work as a reasonable estimate given that the
+ * object hash is supposed to be indistinguishable from random.
+ *
+ * Returns 0 on success, a negative error code otherwise.
+ */
+int odb_source_loose_approximate_object_count(struct odb_source *source,
+					      unsigned long *out);
+
 /**
  * format_object_header() is a thin wrapper around s xsnprintf() that
  * writes the initial "<type> <obj-len>" part of the loose object

-- 
2.53.0.880.g73c4285caa.dirty