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

[PATCH v1 07/10] object_info: content_limit only applies to blobs

From
EWEric Wong <e@80x24.org>
Date
Jul 15, 2024, 00:35 UTC
Message-ID
<20240715003519.2671385-8-e@80x24.org>
In-Reply-To
<20240715003519.2671385-1-e@80x24.org>

Streaming is only supported for blobs, so we'd end up having to slurp all the other object types into memory regardless. So slurp all the non-blob types up front when requesting content since we always handle them in-core, anyways.

Signed-off-by: Eric Wong <e@80x24.org>
---
 builtin/cat-file.c | 51 +++++++++++++++++++++-------------------------
 object-file.c      |  3 ++-
 packfile.c         |  8 +++++---
 3 files changed, 30 insertions(+), 32 deletions(-)
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 769c8b48d2..0752ff7a74 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -386,20 +386,39 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 	assert(data->info.typep);
 
 	if (data->content) {
-		batch_write(opt, data->content, data->size);
+		void *content = data->content;
+		unsigned long size = data->size;
+
+		data->content = NULL;
+		if (use_mailmap && (data->type == OBJ_COMMIT ||
+					data->type == OBJ_TAG)) {
+			size_t s = size;
+
+			if (USE_DIRECT_CACHE &&
+					data->info.whence == OI_DBCACHED) {
+				content = xmemdupz(content, s);
+				data->info.whence = OI_PACKED;
+			}
+
+			content = replace_idents_using_mailmap(content, &s);
+			size = cast_size_t_to_ulong(s);
+		}
+
+		batch_write(opt, content, size);
 		switch (data->info.whence) {
 		case OI_CACHED: BUG("FIXME OI_CACHED support not done");
 		case OI_LOOSE:
 		case OI_PACKED:
-			FREE_AND_NULL(data->content);
+			free(content);
 			break;
 		case OI_DBCACHED:
 			if (USE_DIRECT_CACHE)
 				unlock_delta_base_cache();
 			else
-				FREE_AND_NULL(data->content);
+				free(content);
 		}
-	} else if (data->type == OBJ_BLOB) {
+	} else {
+		assert(data->type == OBJ_BLOB);
 		if (opt->buffer_output)
 			fflush(stdout);
 		if (opt->transform_mode) {
@@ -434,30 +453,6 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 			stream_blob(oid);
 		}
 	}
-	else {
-		enum object_type type;
-		unsigned long size;
-		void *contents;
-
-		contents = repo_read_object_file(the_repository, oid, &type,
-						 &size);
-		if (!contents)
-			die("object %s disappeared", oid_to_hex(oid));
-
-		if (use_mailmap) {
-			size_t s = size;
-			contents = replace_idents_using_mailmap(contents, &s);
-			size = cast_size_t_to_ulong(s);
-		}
-
-		if (type != data->type)
-			die("object %s changed type!?", oid_to_hex(oid));
-		if (data->info.sizep && size != data->size && !use_mailmap)
-			die("object %s changed size!?", oid_to_hex(oid));
-
-		batch_write(opt, contents, size);
-		free(contents);
-	}
 }
 
 static void print_default_format(struct strbuf *scratch, struct expand_data *data,
diff --git a/object-file.c b/object-file.c
index 19100e823d..59842cfe1b 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1492,7 +1492,8 @@ static int loose_object_info(struct repository *r,
 
 		if (!oi->contentp)
 			break;
-		if (oi->content_limit && *oi->sizep > oi->content_limit) {
+		if (oi->content_limit && *oi->typep == OBJ_BLOB &&
+				*oi->sizep > oi->content_limit) {
 			git_inflate_end(&stream);
 			oi->contentp = NULL;
 			goto cleanup;
diff --git a/packfile.c b/packfile.c
index c2ba6ab203..01ce3a49db 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1542,7 +1542,7 @@ int packed_object_info(struct repository *r, struct packed_git *p,
 			if (oi->direct_cache) {
 				lock_delta_base_cache();
 				*oi->contentp = ent->data;
-			} else if (!oi->content_limit ||
+			} else if (type != OBJ_BLOB || !oi->content_limit ||
 					ent->size <= oi->content_limit) {
 				*oi->contentp = xmemdupz(ent->data, ent->size);
 			} else {
@@ -1579,10 +1579,12 @@ int packed_object_info(struct repository *r, struct packed_git *p,
 		}
 
 		if (oi->contentp) {
-			if (oi->sizep && *oi->sizep <= oi->content_limit) {
+			final_type = packed_to_object_type(r, p, obj_offset,
+						     type, &w_curs, curpos);
+			if (final_type != OBJ_BLOB || (oi->sizep &&
+					*oi->sizep <= oi->content_limit)) {
 				*oi->contentp = unpack_entry(r, p, obj_offset,
 							&type, oi->sizep);
-				final_type = type;
 				if (!*oi->contentp)
 					type = OBJ_BAD;
 			} else {
Previous: Eric WongNext: Eric Wong
Message 19 of 51 in “cat-file speedups”
  1. 00/10 cat-file speedupsEric Wong, Jul 15, 2024
  2. 01/10 packfile: move sizep computationEric Wong, Jul 15, 2024
  3. Patrick SteinhardtJul 24, 2024
  4. 02/10 packfile: allow content-limit for cat-fileEric Wong, Jul 15, 2024
  5. Patrick SteinhardtJul 24, 2024
  6. Eric WongJul 26, 2024
  7. 03/10 packfile: fix off-by-one in content_limit comparisonEric Wong, Jul 15, 2024
  8. Patrick SteinhardtJul 24, 2024
  9. Eric WongJul 26, 2024
  10. 04/10 packfile: inline cache_or_unpack_entryEric Wong, Jul 15, 2024
  11. 05/10 cat-file: use delta_base_cache entries directlyEric Wong, Jul 15, 2024
  12. Patrick SteinhardtJul 24, 2024
  13. Eric WongJul 26, 2024
  14. assert vs BUG [was: [PATCH v1 05/10] cat-file: use delta_base_cache entries directly]Eric Wong, Aug 18, 2024
  15. Junio C HamanoAug 19, 2024
  16. 06/10 packfile: packed_object_info avoids packed_to_object_typeEric Wong, Jul 15, 2024
  17. Patrick SteinhardtJul 24, 2024
  18. Eric WongJul 26, 2024
  19. 07/10 object_info: content_limit only applies to blobsEric Wong, Jul 15, 2024
  20. 08/10 cat-file: batch-command uses content_limitEric Wong, Jul 15, 2024
  21. 09/10 cat-file: batch_write: use size_t for lengthEric Wong, Jul 15, 2024
  22. 10/10 cat-file: use writev(2) if availableEric Wong, Jul 15, 2024
  23. Patrick SteinhardtJul 24, 2024
  24. 00/10 cat-file speedupsEric Wong, Aug 23, 2024
  25. 01/10 packfile: move sizep computationEric Wong, Aug 23, 2024
  26. Taylor BlauSep 17, 2024
  27. 02/10 packfile: allow content-limit for cat-fileEric Wong, Aug 23, 2024
  28. Junio C HamanoAug 26, 2024
  29. Eric WongAug 27, 2024
  30. Taylor BlauSep 17, 2024
  31. Junio C HamanoSep 17, 2024
  32. 03/10 packfile: fix off-by-one in content_limit comparisonEric Wong, Aug 23, 2024
  33. Junio C HamanoAug 26, 2024
  34. Taylor BlauSep 17, 2024
  35. 04/10 packfile: inline cache_or_unpack_entryEric Wong, Aug 23, 2024
  36. Junio C HamanoAug 26, 2024
  37. Eric WongOct 6, 2024
  38. 05/10 cat-file: use delta_base_cache entries directlyEric Wong, Aug 23, 2024
  39. Junio C HamanoAug 26, 2024
  40. Junio C HamanoAug 26, 2024
  41. 06/10 packfile: packed_object_info avoids packed_to_object_typeEric Wong, Aug 23, 2024
  42. Junio C HamanoAug 26, 2024
  43. 07/10 object_info: content_limit only applies to blobsEric Wong, Aug 23, 2024
  44. Junio C HamanoAug 26, 2024
  45. 08/10 cat-file: batch-command uses content_limitEric Wong, Aug 23, 2024
  46. Junio C HamanoAug 26, 2024
  47. 09/10 cat-file: batch_write: use size_t for lengthEric Wong, Aug 23, 2024
  48. Junio C HamanoAug 27, 2024
  49. 10/10 cat-file: use writev(2) if availableEric Wong, Aug 23, 2024
  50. Junio C HamanoAug 27, 2024
  51. Junio C HamanoAug 27, 2024

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.