git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 11/19] packfile: introduce function to read object info from a store

From
Patrick Steinhardt <ps@pks.im>
Date
Nov 21, 2025, 07:40 UTC
Message-ID
<20251121-b4-pks-odb-read-stream-v2-11-ca8534963150@pks.im>
In-Reply-To
<20251121-b4-pks-odb-read-stream-v2-0-ca8534963150@pks.im>

Extract the logic to read object info for a packed object from `do_oid_object_into_extended()` into a standalone function that operates on the packfile store. This function will be used in a subsequent commit.

Note that this change allows us to make `find_pack_entry()` an internal implementation detail. As a consequence though we have to move around `packfile_store_freshen_object()` so that it is defined after that function.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 odb.c      | 29 ++++---------------------
 packfile.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++---------------
 packfile.h | 12 ++++++++++-
 3 files changed, 69 insertions(+), 43 deletions(-)
diff --git a/odb.c b/odb.c
index 3ec21ef24e..f4cbee4b04 100644
--- a/odb.c
+++ b/odb.c
@@ -666,8 +666,6 @@ static int do_oid_object_info_extended(struct object_database *odb,
 {
 	static struct object_info blank_oi = OBJECT_INFO_INIT;
 	const struct cached_object *co;
-	struct pack_entry e;
-	int rtype;
 	const struct object_id *real = oid;
 	int already_retried = 0;
 
@@ -702,8 +700,8 @@ static int do_oid_object_info_extended(struct object_database *odb,
 	while (1) {
 		struct odb_source *source;
 
-		if (find_pack_entry(odb->repo, real, &e))
-			break;
+		if (!packfile_store_read_object_info(odb->packfiles, real, oi, flags))
+			return 0;
 
 		/* Most likely it's a loose object. */
 		for (source = odb->sources; source; source = source->next)
@@ -713,8 +711,8 @@ static int do_oid_object_info_extended(struct object_database *odb,
 		/* Not a loose object; someone else may have just packed it. */
 		if (!(flags & OBJECT_INFO_QUICK)) {
 			odb_reprepare(odb->repo->objects);
-			if (find_pack_entry(odb->repo, real, &e))
-				break;
+			if (!packfile_store_read_object_info(odb->packfiles, real, oi, flags))
+				return 0;
 		}
 
 		/*
@@ -747,25 +745,6 @@ static int do_oid_object_info_extended(struct object_database *odb,
 		}
 		return -1;
 	}
-
-	if (oi == &blank_oi)
-		/*
-		 * We know that the caller doesn't actually need the
-		 * information below, so return early.
-		 */
-		return 0;
-	rtype = packed_object_info(odb->repo, e.p, e.offset, oi);
-	if (rtype < 0) {
-		mark_bad_packed_object(e.p, real);
-		return do_oid_object_info_extended(odb, real, oi, 0);
-	} else if (oi->whence == OI_PACKED) {
-		oi->u.packed.offset = e.offset;
-		oi->u.packed.pack = e.p;
-		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
-					 rtype == OBJ_OFS_DELTA);
-	}
-
-	return 0;
 }
 
 static int oid_object_info_convert(struct repository *r,
diff --git a/packfile.c b/packfile.c
index 40f733dd23..b4bc40d895 100644
--- a/packfile.c
+++ b/packfile.c
@@ -819,22 +819,6 @@ struct packed_git *packfile_store_load_pack(struct packfile_store *store,
 	return p;
 }
 
-int packfile_store_freshen_object(struct packfile_store *store,
-				  const struct object_id *oid)
-{
-	struct pack_entry e;
-	if (!find_pack_entry(store->odb->repo, oid, &e))
-		return 0;
-	if (e.p->is_cruft)
-		return 0;
-	if (e.p->freshened)
-		return 1;
-	if (utime(e.p->pack_name, NULL))
-		return 0;
-	e.p->freshened = 1;
-	return 1;
-}
-
 void (*report_garbage)(unsigned seen_bits, const char *path);
 
 static void report_helper(const struct string_list *list,
@@ -2064,7 +2048,9 @@ static int fill_pack_entry(const struct object_id *oid,
 	return 1;
 }
 
-int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e)
+static int find_pack_entry(struct repository *r,
+			   const struct object_id *oid,
+			   struct pack_entry *e)
 {
 	struct list_head *pos;
 
@@ -2087,6 +2073,57 @@ int find_pack_entry(struct repository *r, const struct object_id *oid, struct pa
 	return 0;
 }
 
+int packfile_store_freshen_object(struct packfile_store *store,
+				  const struct object_id *oid)
+{
+	struct pack_entry e;
+	if (!find_pack_entry(store->odb->repo, oid, &e))
+		return 0;
+	if (e.p->is_cruft)
+		return 0;
+	if (e.p->freshened)
+		return 1;
+	if (utime(e.p->pack_name, NULL))
+		return 0;
+	e.p->freshened = 1;
+	return 1;
+}
+
+int packfile_store_read_object_info(struct packfile_store *store,
+				    const struct object_id *oid,
+				    struct object_info *oi,
+				    unsigned flags UNUSED)
+{
+	static struct object_info blank_oi = OBJECT_INFO_INIT;
+	struct pack_entry e;
+	int rtype;
+
+	if (!find_pack_entry(store->odb->repo, oid, &e))
+		return 1;
+
+	/*
+	 * We know that the caller doesn't actually need the
+	 * information below, so return early.
+	 */
+	if (oi == &blank_oi)
+		return 0;
+
+	rtype = packed_object_info(store->odb->repo, e.p, e.offset, oi);
+	if (rtype < 0) {
+		mark_bad_packed_object(e.p, oid);
+		return -1;
+	}
+
+	if (oi->whence == OI_PACKED) {
+		oi->u.packed.offset = e.offset;
+		oi->u.packed.pack = e.p;
+		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+					 rtype == OBJ_OFS_DELTA);
+	}
+
+	return 0;
+}
+
 static void maybe_invalidate_kept_pack_cache(struct repository *r,
 					     unsigned flags)
 {
diff --git a/packfile.h b/packfile.h
index 58fcc88e20..0a98bddd81 100644
--- a/packfile.h
+++ b/packfile.h
@@ -144,6 +144,17 @@ void packfile_store_add_pack(struct packfile_store *store,
 #define repo_for_each_pack(repo, p) \
 	for (p = packfile_store_get_packs(repo->objects->packfiles); p; p = p->next)
 
+/*
+ * Try to read the object identified by its ID from the object store and
+ * populate the object info with its data. Returns 1 in case the object was
+ * not found, 0 if it was and read successfully, and a negative error code in
+ * case the object was corrupted.
+ */
+int packfile_store_read_object_info(struct packfile_store *store,
+				    const struct object_id *oid,
+				    struct object_info *oi,
+				    unsigned flags);
+
 /*
  * Get all packs managed by the given store, including packfiles that are
  * referenced by multi-pack indices.
@@ -357,7 +368,6 @@ const struct packed_git *has_packed_and_bad(struct repository *, const struct ob
  * Iff a pack file in the given repository contains the object named by sha1,
  * return true and store its location to e.
  */
-int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e);
 int find_kept_pack_entry(struct repository *r, const struct object_id *oid, unsigned flags, struct pack_entry *e);
 
 int has_object_pack(struct repository *r, const struct object_id *oid);
-- 
2.52.0.rc2.482.gaa765fefd0.dirty
Previous: Patrick SteinhardtNext: Patrick Steinhardt
Message 50 of 85 in “Refactor object read streams to work via object sources”
  1. 00/18 Refactor object read streams to work via object sourcesPatrick Steinhardt, Nov 19, 2025
  2. 01/18 streaming: rename `git_istream` into `odb_read_stream`Patrick Steinhardt, Nov 19, 2025
  3. Justin ToblerNov 19, 2025
  4. Junio C HamanoNov 19, 2025
  5. Patrick SteinhardtNov 21, 2025
  6. 02/18 streaming: drop the `open()` callback functionPatrick Steinhardt, Nov 19, 2025
  7. Karthik NayakNov 19, 2025
  8. Justin ToblerNov 19, 2025
  9. Patrick SteinhardtNov 21, 2025
  10. 03/18 streaming: propagate final object type via the streamPatrick Steinhardt, Nov 19, 2025
  11. Justin ToblerNov 19, 2025
  12. Patrick SteinhardtNov 21, 2025
  13. 04/18 streaming: explicitly pass packfile info when streaming a packed objectPatrick Steinhardt, Nov 19, 2025
  14. 05/18 streaming: allocate stream inside the backend-specific logicPatrick Steinhardt, Nov 19, 2025
  15. Karthik NayakNov 19, 2025
  16. Patrick SteinhardtNov 21, 2025
  17. 06/18 streaming: create structure for in-core object streamsPatrick Steinhardt, Nov 19, 2025
  18. Karthik NayakNov 19, 2025
  19. Patrick SteinhardtNov 21, 2025
  20. 07/18 streaming: create structure for loose object streamsPatrick Steinhardt, Nov 19, 2025
  21. 08/18 streaming: create structure for packed object streamsPatrick Steinhardt, Nov 19, 2025
  22. 09/18 streaming: create structure for filtered object streamsPatrick Steinhardt, Nov 19, 2025
  23. 10/18 streaming: move zlib stream into backendsPatrick Steinhardt, Nov 19, 2025
  24. 11/18 packfile: introduce function to read object info from a storePatrick Steinhardt, Nov 19, 2025
  25. Karthik NayakNov 19, 2025
  26. Patrick SteinhardtNov 21, 2025
  27. 12/18 streaming: rely on object sources to create object streamPatrick Steinhardt, Nov 19, 2025
  28. Karthik NayakNov 19, 2025
  29. 13/18 streaming: get rid of `the_repository`Patrick Steinhardt, Nov 19, 2025
  30. 14/18 streaming: make the `odb_read_stream` definition publicPatrick Steinhardt, Nov 19, 2025
  31. Karthik NayakNov 19, 2025
  32. Patrick SteinhardtNov 21, 2025
  33. 15/18 streaming: move logic to read loose objects streams into backendPatrick Steinhardt, Nov 19, 2025
  34. 16/18 streaming: move logic to read packed objects streams into backendPatrick Steinhardt, Nov 19, 2025
  35. 17/18 streaming: refactor interface to be object-database-centricPatrick Steinhardt, Nov 19, 2025
  36. 18/18 streaming: move into object database subsystemPatrick Steinhardt, Nov 19, 2025
  37. 00/19 Refactor object read streams to work via object sourcesPatrick Steinhardt, Nov 21, 2025
  38. 01/19 streaming: rename `git_istream` into `odb_read_stream`Patrick Steinhardt, Nov 21, 2025
  39. 02/19 streaming: drop the `open()` callback functionPatrick Steinhardt, Nov 21, 2025
  40. Junio C HamanoNov 21, 2025
  41. Patrick SteinhardtNov 23, 2025
  42. 03/19 streaming: propagate final object type via the streamPatrick Steinhardt, Nov 21, 2025
  43. 04/19 streaming: explicitly pass packfile info when streaming a packed objectPatrick Steinhardt, Nov 21, 2025
  44. 05/19 streaming: allocate stream inside the backend-specific logicPatrick Steinhardt, Nov 21, 2025
  45. 06/19 streaming: create structure for in-core object streamsPatrick Steinhardt, Nov 21, 2025
  46. 07/19 streaming: create structure for loose object streamsPatrick Steinhardt, Nov 21, 2025
  47. 08/19 streaming: create structure for packed object streamsPatrick Steinhardt, Nov 21, 2025
  48. 09/19 streaming: create structure for filtered object streamsPatrick Steinhardt, Nov 21, 2025
  49. 10/19 streaming: move zlib stream into backendsPatrick Steinhardt, Nov 21, 2025
  50. 11/19 packfile: introduce function to read object info from a storePatrick Steinhardt, Nov 21, 2025
  51. 12/19 streaming: rely on object sources to create object streamPatrick Steinhardt, Nov 21, 2025
  52. Junio C HamanoNov 21, 2025
  53. Patrick SteinhardtNov 23, 2025
  54. 13/19 streaming: get rid of `the_repository`Patrick Steinhardt, Nov 21, 2025
  55. Junio C HamanoNov 21, 2025
  56. Patrick SteinhardtNov 23, 2025
  57. 14/19 streaming: make the `odb_read_stream` definition publicPatrick Steinhardt, Nov 21, 2025
  58. 15/19 streaming: move logic to read loose objects streams into backendPatrick Steinhardt, Nov 21, 2025
  59. 16/19 streaming: move logic to read packed objects streams into backendPatrick Steinhardt, Nov 21, 2025
  60. 17/19 streaming: refactor interface to be object-database-centricPatrick Steinhardt, Nov 21, 2025
  61. Junio C HamanoNov 22, 2025
  62. Patrick SteinhardtNov 23, 2025
  63. 18/19 streaming: move into object database subsystemPatrick Steinhardt, Nov 21, 2025
  64. Junio C HamanoNov 23, 2025
  65. 19/19 streaming: drop redundant type and size pointersPatrick Steinhardt, Nov 21, 2025
  66. 00/19 Refactor object read streams to work via object sourcesPatrick Steinhardt, Nov 23, 2025
  67. 01/19 streaming: rename `git_istream` into `odb_read_stream`Patrick Steinhardt, Nov 23, 2025
  68. 02/19 streaming: drop the `open()` callback functionPatrick Steinhardt, Nov 23, 2025
  69. 03/19 streaming: propagate final object type via the streamPatrick Steinhardt, Nov 23, 2025
  70. 04/19 streaming: explicitly pass packfile info when streaming a packed objectPatrick Steinhardt, Nov 23, 2025
  71. 05/19 streaming: allocate stream inside the backend-specific logicPatrick Steinhardt, Nov 23, 2025
  72. 06/19 streaming: create structure for in-core object streamsPatrick Steinhardt, Nov 23, 2025
  73. 07/19 streaming: create structure for loose object streamsPatrick Steinhardt, Nov 23, 2025
  74. 08/19 streaming: create structure for packed object streamsPatrick Steinhardt, Nov 23, 2025
  75. 09/19 streaming: create structure for filtered object streamsPatrick Steinhardt, Nov 23, 2025
  76. 10/19 streaming: move zlib stream into backendsPatrick Steinhardt, Nov 23, 2025
  77. 11/19 packfile: introduce function to read object info from a storePatrick Steinhardt, Nov 23, 2025
  78. 12/19 streaming: rely on object sources to create object streamPatrick Steinhardt, Nov 23, 2025
  79. 13/19 streaming: get rid of `the_repository`Patrick Steinhardt, Nov 23, 2025
  80. 14/19 streaming: make the `odb_read_stream` definition publicPatrick Steinhardt, Nov 23, 2025
  81. 15/19 streaming: move logic to read loose objects streams into backendPatrick Steinhardt, Nov 23, 2025
  82. 16/19 streaming: move logic to read packed objects streams into backendPatrick Steinhardt, Nov 23, 2025
  83. 17/19 streaming: refactor interface to be object-database-centricPatrick Steinhardt, Nov 23, 2025
  84. 18/19 streaming: move into object database subsystemPatrick Steinhardt, Nov 23, 2025
  85. 19/19 streaming: drop redundant type and size pointersPatrick Steinhardt, Nov 23, 2025

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.