[PATCH v2 11/14] odb: introduce mtime fields for object info requests

From: Patrick Steinhardt <ps@pks.im>
Date: Jan 20, 2026, 15:26 UTC
Message-ID: <20260120-pks-odb-for-each-object-v2-11-d05cbfd3d6f8@pks.im>
In-Reply-To: <20260120-pks-odb-for-each-object-v2-0-d05cbfd3d6f8@pks.im>

There are some use cases where we need to figure out the mtime for objects. Most importantly, this is the case when we want to prune unreachable objects. But getting at that data requires users to manually derive the info either via the loose object's mtime, the packfiles' mtime or via the ".mtimes" file.

Introduce a new `struct object_info::mtimep` pointer that allows callers to request an object's mtime. This new field will be used in a subsequent commit.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 object-file.c | 29 +++++++++++++++++++++++++----
 odb.c         |  2 ++
 odb.h         |  1 +
 packfile.c    | 40 +++++++++++++++++++++++++++++++++-------
 4 files changed, 61 insertions(+), 11 deletions(-)

diff --git a/object-file.c b/object-file.c
index 65e730684b..c0f896673b 100644
--- a/object-file.c
+++ b/object-file.c
@@ -409,6 +409,7 @@ static int read_object_info_from_path(struct odb_source *source,
 	char hdr[MAX_HEADER_LEN];
 	unsigned long size_scratch;
 	enum object_type type_scratch;
+	struct stat st;
 
 	/*
 	 * If we don't care about type or size, then we don't
@@ -421,7 +422,7 @@ static int read_object_info_from_path(struct odb_source *source,
 	if (!oi || (!oi->typep && !oi->sizep && !oi->contentp)) {
 		struct stat st;
 
-		if ((!oi || !oi->disk_sizep) && (flags & OBJECT_INFO_QUICK)) {
+		if ((!oi || (!oi->disk_sizep && !oi->mtimep)) && (flags & OBJECT_INFO_QUICK)) {
 			ret = quick_has_loose(source->loose, oid) ? 0 : -1;
 			goto out;
 		}
@@ -431,8 +432,12 @@ static int read_object_info_from_path(struct odb_source *source,
 			goto out;
 		}
 
-		if (oi && oi->disk_sizep)
-			*oi->disk_sizep = st.st_size;
+		if (oi) {
+			if (oi->disk_sizep)
+				*oi->disk_sizep = st.st_size;
+			if (oi->mtimep)
+				*oi->mtimep = st.st_mtime;
+		}
 
 		ret = 0;
 		goto out;
@@ -446,7 +451,21 @@ static int read_object_info_from_path(struct odb_source *source,
 		goto out;
 	}
 
-	map = map_fd(fd, path, &mapsize);
+	if (fstat(fd, &st)) {
+		close(fd);
+		ret = -1;
+		goto out;
+	}
+
+	mapsize = xsize_t(st.st_size);
+	if (!mapsize) {
+		close(fd);
+		ret = error(_("object file %s is empty"), path);
+		goto out;
+	}
+
+	map = xmmap(NULL, mapsize, PROT_READ, MAP_PRIVATE, fd, 0);
+	close(fd);
 	if (!map) {
 		ret = -1;
 		goto out;
@@ -454,6 +473,8 @@ static int read_object_info_from_path(struct odb_source *source,
 
 	if (oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
+	if (oi->mtimep)
+		*oi->mtimep = st.st_mtime;
 
 	stream_to_end = &stream;
 
diff --git a/odb.c b/odb.c
index 65f0447aa5..67decd3908 100644
--- a/odb.c
+++ b/odb.c
@@ -702,6 +702,8 @@ static int do_oid_object_info_extended(struct object_database *odb,
 				oidclr(oi->delta_base_oid, odb->repo->hash_algo);
 			if (oi->contentp)
 				*oi->contentp = xmemdupz(co->buf, co->size);
+			if (oi->mtimep)
+				*oi->mtimep = 0;
 			oi->whence = OI_CACHED;
 		}
 		return 0;
diff --git a/odb.h b/odb.h
index 8a37fe08e0..68336d2730 100644
--- a/odb.h
+++ b/odb.h
@@ -317,6 +317,7 @@ struct object_info {
 	off_t *disk_sizep;
 	struct object_id *delta_base_oid;
 	void **contentp;
+	time_t *mtimep;
 
 	/* Response */
 	enum {
diff --git a/packfile.c b/packfile.c
index 4f84bc19d9..c96ec21f86 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1578,13 +1578,14 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
 	hashmap_add(&delta_base_cache, &ent->ent);
 }
 
-int packed_object_info(struct packed_git *p,
-		       off_t obj_offset, struct object_info *oi)
+static int packed_object_info_with_index_pos(struct packed_git *p, off_t obj_offset,
+					     uint32_t *maybe_index_pos, struct object_info *oi)
 {
 	struct pack_window *w_curs = NULL;
 	unsigned long size;
 	off_t curpos = obj_offset;
 	enum object_type type = OBJ_NONE;
+	uint32_t pack_pos;
 	int ret;
 
 	/*
@@ -1619,16 +1620,34 @@ int packed_object_info(struct packed_git *p,
 		}
 	}
 
-	if (oi->disk_sizep) {
-		uint32_t pos;
-		if (offset_to_pack_pos(p, obj_offset, &pos) < 0) {
+	if (oi->disk_sizep || (oi->mtimep && p->is_cruft)) {
+		if (offset_to_pack_pos(p, obj_offset, &pack_pos) < 0) {
 			error("could not find object at offset %"PRIuMAX" "
 			      "in pack %s", (uintmax_t)obj_offset, p->pack_name);
 			ret = -1;
 			goto out;
 		}
+	}
+
+	if (oi->disk_sizep)
+		*oi->disk_sizep = pack_pos_to_offset(p, pack_pos + 1) - obj_offset;
+
+	if (oi->mtimep) {
+		if (p->is_cruft) {
+			uint32_t index_pos;
+
+			if (load_pack_mtimes(p) < 0)
+				die(_("could not load cruft pack .mtimes"));
+
+			if (maybe_index_pos)
+				index_pos = *maybe_index_pos;
+			else
+				index_pos = pack_pos_to_index(p, pack_pos);
 
-		*oi->disk_sizep = pack_pos_to_offset(p, pos + 1) - obj_offset;
+			*oi->mtimep = nth_packed_mtime(p, index_pos);
+		} else {
+			*oi->mtimep = p->mtime;
+		}
 	}
 
 	if (oi->typep) {
@@ -1681,6 +1700,12 @@ int packed_object_info(struct packed_git *p,
 	return ret;
 }
 
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+		       struct object_info *oi)
+{
+	return packed_object_info_with_index_pos(p, obj_offset, NULL, oi);
+}
+
 static void *unpack_compressed_entry(struct packed_git *p,
 				    struct pack_window **w_curs,
 				    off_t curpos,
@@ -2377,7 +2402,8 @@ static int packfile_store_for_each_object_wrapper(const struct object_id *oid,
 	if (data->oi) {
 		off_t offset = nth_packed_object_offset(pack, index_pos);
 
-		if (packed_object_info(pack, offset, data->oi) < 0) {
+		if (packed_object_info_with_index_pos(pack, offset,
+						      &index_pos, data->oi) < 0) {
 			mark_bad_packed_object(pack, oid);
 			return -1;
 		}

-- 
2.53.0.rc0.250.g0ac79233d6.dirty