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

[PATCH v3 15/19] streaming: move logic to read loose objects streams into backend

From
Patrick Steinhardt <ps@pks.im>
Date
Nov 23, 2025, 18:59 UTC
Message-ID
<20251123-b4-pks-odb-read-stream-v3-15-1a129182822b@pks.im>
In-Reply-To
<20251123-b4-pks-odb-read-stream-v3-0-1a129182822b@pks.im>

Move the logic to read loose object streams into the respective subsystem. This allows us to make a couple of function declarations private.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 object-file.c | 167 ++++++++++++++++++++++++++++++++++++++++++++++++++++++----
 object-file.h |  42 ++-------------
 streaming.c   | 133 +---------------------------------------------
 3 files changed, 164 insertions(+), 178 deletions(-)
diff --git a/object-file.c b/object-file.c
index b62b21a452..8c67847fea 100644
--- a/object-file.c
+++ b/object-file.c
@@ -234,9 +234,9 @@ static void *map_fd(int fd, const char *path, unsigned long *size)
 	return map;
 }
 
-void *odb_source_loose_map_object(struct odb_source *source,
-				  const struct object_id *oid,
-				  unsigned long *size)
+static void *odb_source_loose_map_object(struct odb_source *source,
+					 const struct object_id *oid,
+					 unsigned long *size)
 {
 	const char *p;
 	int fd = open_loose_object(source->loose, oid, &p);
@@ -246,11 +246,29 @@ void *odb_source_loose_map_object(struct odb_source *source,
 	return map_fd(fd, p, size);
 }
 
-enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
-						    unsigned char *map,
-						    unsigned long mapsize,
-						    void *buffer,
-						    unsigned long bufsiz)
+enum unpack_loose_header_result {
+	ULHR_OK,
+	ULHR_BAD,
+	ULHR_TOO_LONG,
+};
+
+/**
+ * unpack_loose_header() initializes the data stream needed to unpack
+ * a loose object header.
+ *
+ * Returns:
+ *
+ * - ULHR_OK on success
+ * - ULHR_BAD on error
+ * - ULHR_TOO_LONG if the header was too long
+ *
+ * It will only parse up to MAX_HEADER_LEN bytes.
+ */
+static enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
+							   unsigned char *map,
+							   unsigned long mapsize,
+							   void *buffer,
+							   unsigned long bufsiz)
 {
 	int status;
 
@@ -329,11 +347,18 @@ static void *unpack_loose_rest(git_zstream *stream,
 }
 
 /*
+ * parse_loose_header() parses the starting "<type> <len>\0" of an
+ * object. If it doesn't follow that format -1 is returned. To check
+ * the validity of the <type> populate the "typep" in the "struct
+ * object_info". It will be OBJ_BAD if the object type is unknown. The
+ * parsed <len> can be retrieved via "oi->sizep", and from there
+ * passed to unpack_loose_rest().
+ *
  * We used to just use "sscanf()", but that's actually way
  * too permissive for what we want to check. So do an anal
  * object header parse by hand.
  */
-int parse_loose_header(const char *hdr, struct object_info *oi)
+static int parse_loose_header(const char *hdr, struct object_info *oi)
 {
 	const char *type_buf = hdr;
 	size_t size;
@@ -1976,3 +2001,127 @@ void odb_source_loose_free(struct odb_source_loose *loose)
 	loose_object_map_clear(&loose->map);
 	free(loose);
 }
+
+struct odb_loose_read_stream {
+	struct odb_read_stream base;
+	git_zstream z;
+	enum {
+		ODB_LOOSE_READ_STREAM_INUSE,
+		ODB_LOOSE_READ_STREAM_DONE,
+		ODB_LOOSE_READ_STREAM_ERROR,
+	} z_state;
+	void *mapped;
+	unsigned long mapsize;
+	char hdr[32];
+	int hdr_avail;
+	int hdr_used;
+};
+
+static ssize_t read_istream_loose(struct odb_read_stream *_st, char *buf, size_t sz)
+{
+	struct odb_loose_read_stream *st = (struct odb_loose_read_stream *)_st;
+	size_t total_read = 0;
+
+	switch (st->z_state) {
+	case ODB_LOOSE_READ_STREAM_DONE:
+		return 0;
+	case ODB_LOOSE_READ_STREAM_ERROR:
+		return -1;
+	default:
+		break;
+	}
+
+	if (st->hdr_used < st->hdr_avail) {
+		size_t to_copy = st->hdr_avail - st->hdr_used;
+		if (sz < to_copy)
+			to_copy = sz;
+		memcpy(buf, st->hdr + st->hdr_used, to_copy);
+		st->hdr_used += to_copy;
+		total_read += to_copy;
+	}
+
+	while (total_read < sz) {
+		int status;
+
+		st->z.next_out = (unsigned char *)buf + total_read;
+		st->z.avail_out = sz - total_read;
+		status = git_inflate(&st->z, Z_FINISH);
+
+		total_read = st->z.next_out - (unsigned char *)buf;
+
+		if (status == Z_STREAM_END) {
+			git_inflate_end(&st->z);
+			st->z_state = ODB_LOOSE_READ_STREAM_DONE;
+			break;
+		}
+		if (status != Z_OK && (status != Z_BUF_ERROR || total_read < sz)) {
+			git_inflate_end(&st->z);
+			st->z_state = ODB_LOOSE_READ_STREAM_ERROR;
+			return -1;
+		}
+	}
+	return total_read;
+}
+
+static int close_istream_loose(struct odb_read_stream *_st)
+{
+	struct odb_loose_read_stream *st = (struct odb_loose_read_stream *)_st;
+	if (st->z_state == ODB_LOOSE_READ_STREAM_INUSE)
+		git_inflate_end(&st->z);
+	munmap(st->mapped, st->mapsize);
+	return 0;
+}
+
+int odb_source_loose_read_object_stream(struct odb_read_stream **out,
+					struct odb_source *source,
+					const struct object_id *oid)
+{
+	struct object_info oi = OBJECT_INFO_INIT;
+	struct odb_loose_read_stream *st;
+	unsigned long mapsize;
+	void *mapped;
+
+	mapped = odb_source_loose_map_object(source, oid, &mapsize);
+	if (!mapped)
+		return -1;
+
+	/*
+	 * Note: we must allocate this structure early even though we may still
+	 * fail. This is because we need to initialize the zlib stream, and it
+	 * is not possible to copy the stream around after the fact because it
+	 * has self-referencing pointers.
+	 */
+	CALLOC_ARRAY(st, 1);
+
+	switch (unpack_loose_header(&st->z, mapped, mapsize, st->hdr,
+				    sizeof(st->hdr))) {
+	case ULHR_OK:
+		break;
+	case ULHR_BAD:
+	case ULHR_TOO_LONG:
+		goto error;
+	}
+
+	oi.sizep = &st->base.size;
+	oi.typep = &st->base.type;
+
+	if (parse_loose_header(st->hdr, &oi) < 0 || st->base.type < 0)
+		goto error;
+
+	st->mapped = mapped;
+	st->mapsize = mapsize;
+	st->hdr_used = strlen(st->hdr) + 1;
+	st->hdr_avail = st->z.total_out;
+	st->z_state = ODB_LOOSE_READ_STREAM_INUSE;
+	st->base.close = close_istream_loose;
+	st->base.read = read_istream_loose;
+
+	*out = &st->base;
+
+	return 0;
+error:
+	git_inflate_end(&st->z);
+	munmap(st->mapped, st->mapsize);
+	free(st);
+	return -1;
+}
diff --git a/object-file.h b/object-file.h
index eeffa67bbd..1229d5f675 100644
--- a/object-file.h
+++ b/object-file.h
@@ -16,6 +16,8 @@ enum {
 int index_fd(struct index_state *istate, struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags);
 int index_path(struct index_state *istate, struct object_id *oid, const char *path, struct stat *st, unsigned flags);
 
+struct object_info;
+struct odb_read_stream;
 struct odb_source;
 
 struct odb_source_loose {
@@ -47,9 +49,9 @@ int odb_source_loose_read_object_info(struct odb_source *source,
 				      const struct object_id *oid,
 				      struct object_info *oi, int flags);
 
-void *odb_source_loose_map_object(struct odb_source *source,
-				  const struct object_id *oid,
-				  unsigned long *size);
+int odb_source_loose_read_object_stream(struct odb_read_stream **out,
+					struct odb_source *source,
+					const struct object_id *oid);
 
 /*
  * Return true iff an object database source has a loose object
@@ -143,40 +145,6 @@ int for_each_loose_object(struct object_database *odb,
 int format_object_header(char *str, size_t size, enum object_type type,
 			 size_t objsize);
 
-/**
- * unpack_loose_header() initializes the data stream needed to unpack
- * a loose object header.
- *
- * Returns:
- *
- * - ULHR_OK on success
- * - ULHR_BAD on error
- * - ULHR_TOO_LONG if the header was too long
- *
- * It will only parse up to MAX_HEADER_LEN bytes.
- */
-enum unpack_loose_header_result {
-	ULHR_OK,
-	ULHR_BAD,
-	ULHR_TOO_LONG,
-};
-enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
-						    unsigned char *map,
-						    unsigned long mapsize,
-						    void *buffer,
-						    unsigned long bufsiz);
-
-/**
- * parse_loose_header() parses the starting "<type> <len>\0" of an
- * object. If it doesn't follow that format -1 is returned. To check
- * the validity of the <type> populate the "typep" in the "struct
- * object_info". It will be OBJ_BAD if the object type is unknown. The
- * parsed <len> can be retrieved via "oi->sizep", and from there
- * passed to unpack_loose_rest().
- */
-struct object_info;
-int parse_loose_header(const char *hdr, struct object_info *oi);
-
 int force_object_loose(struct odb_source *source,
 		       const struct object_id *oid, time_t mtime);
 
diff --git a/streaming.c b/streaming.c
index 0635b7c12e..d5acc1c396 100644
--- a/streaming.c
+++ b/streaming.c
@@ -114,137 +114,6 @@ static struct odb_read_stream *attach_stream_filter(struct odb_read_stream *st,
 	return &fs->base;
 }
 
-/*****************************************************************
- *
- * Loose object stream
- *
- *****************************************************************/
-
-struct odb_loose_read_stream {
-	struct odb_read_stream base;
-	git_zstream z;
-	enum {
-		ODB_LOOSE_READ_STREAM_INUSE,
-		ODB_LOOSE_READ_STREAM_DONE,
-		ODB_LOOSE_READ_STREAM_ERROR,
-	} z_state;
-	void *mapped;
-	unsigned long mapsize;
-	char hdr[32];
-	int hdr_avail;
-	int hdr_used;
-};
-
-static ssize_t read_istream_loose(struct odb_read_stream *_st, char *buf, size_t sz)
-{
-	struct odb_loose_read_stream *st = (struct odb_loose_read_stream *)_st;
-	size_t total_read = 0;
-
-	switch (st->z_state) {
-	case ODB_LOOSE_READ_STREAM_DONE:
-		return 0;
-	case ODB_LOOSE_READ_STREAM_ERROR:
-		return -1;
-	default:
-		break;
-	}
-
-	if (st->hdr_used < st->hdr_avail) {
-		size_t to_copy = st->hdr_avail - st->hdr_used;
-		if (sz < to_copy)
-			to_copy = sz;
-		memcpy(buf, st->hdr + st->hdr_used, to_copy);
-		st->hdr_used += to_copy;
-		total_read += to_copy;
-	}
-
-	while (total_read < sz) {
-		int status;
-
-		st->z.next_out = (unsigned char *)buf + total_read;
-		st->z.avail_out = sz - total_read;
-		status = git_inflate(&st->z, Z_FINISH);
-
-		total_read = st->z.next_out - (unsigned char *)buf;
-
-		if (status == Z_STREAM_END) {
-			git_inflate_end(&st->z);
-			st->z_state = ODB_LOOSE_READ_STREAM_DONE;
-			break;
-		}
-		if (status != Z_OK && (status != Z_BUF_ERROR || total_read < sz)) {
-			git_inflate_end(&st->z);
-			st->z_state = ODB_LOOSE_READ_STREAM_ERROR;
-			return -1;
-		}
-	}
-	return total_read;
-}
-
-static int close_istream_loose(struct odb_read_stream *_st)
-{
-	struct odb_loose_read_stream *st = (struct odb_loose_read_stream *)_st;
-	if (st->z_state == ODB_LOOSE_READ_STREAM_INUSE)
-		git_inflate_end(&st->z);
-	munmap(st->mapped, st->mapsize);
-	return 0;
-}
-
-static int open_istream_loose(struct odb_read_stream **out,
-			      struct odb_source *source,
-			      const struct object_id *oid)
-{
-	struct object_info oi = OBJECT_INFO_INIT;
-	struct odb_loose_read_stream *st;
-	unsigned long mapsize;
-	void *mapped;
-
-	mapped = odb_source_loose_map_object(source, oid, &mapsize);
-	if (!mapped)
-		return -1;
-
-	/*
-	 * Note: we must allocate this structure early even though we may still
-	 * fail. This is because we need to initialize the zlib stream, and it
-	 * is not possible to copy the stream around after the fact because it
-	 * has self-referencing pointers.
-	 */
-	CALLOC_ARRAY(st, 1);
-
-	switch (unpack_loose_header(&st->z, mapped, mapsize, st->hdr,
-				    sizeof(st->hdr))) {
-	case ULHR_OK:
-		break;
-	case ULHR_BAD:
-	case ULHR_TOO_LONG:
-		goto error;
-	}
-
-	oi.sizep = &st->base.size;
-	oi.typep = &st->base.type;
-
-	if (parse_loose_header(st->hdr, &oi) < 0 || st->base.type < 0)
-		goto error;
-
-	st->mapped = mapped;
-	st->mapsize = mapsize;
-	st->hdr_used = strlen(st->hdr) + 1;
-	st->hdr_avail = st->z.total_out;
-	st->z_state = ODB_LOOSE_READ_STREAM_INUSE;
-	st->base.close = close_istream_loose;
-	st->base.read = read_istream_loose;
-
-	*out = &st->base;
-
-	return 0;
-error:
-	git_inflate_end(&st->z);
-	munmap(st->mapped, st->mapsize);
-	free(st);
-	return -1;
-}
-
-
 /*****************************************************************
  *
  * Non-delta packed object stream
@@ -455,7 +324,7 @@ static int istream_source(struct odb_read_stream **out,
 
 	odb_prepare_alternates(r->objects);
 	for (source = r->objects->sources; source; source = source->next)
-		if (!open_istream_loose(out, source, oid))
+		if (!odb_source_loose_read_object_stream(out, source, oid))
 			return 0;
 
 	return open_istream_incore(out, r, oid);
-- 
2.52.0.rc2.482.gaa765fefd0.dirty
Previous: Patrick SteinhardtNext: Patrick Steinhardt
Message 81 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.