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

[PATCH v5 6/7] builtin/repo: add disk size info to keyvalue stucture output

From
Justin Tobler <jltobler@gmail.com>
Date
Dec 17, 2025, 17:54 UTC
Message-ID
<20251217175404.37963-7-jltobler@gmail.com>
In-Reply-To
<20251217175404.37963-1-jltobler@gmail.com>

Similar to a prior commit, extend the keyvalue and nul output formats of the git-repo(1) structure command to additionally provide info regarding total object disk sizes by object type.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
---
 Documentation/git-repo.adoc |  1 +
 builtin/repo.c              | 18 ++++++++++++++++++
 t/t1901-repo-structure.sh   | 11 ++++++++++-
 3 files changed, 29 insertions(+), 1 deletion(-)
diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index 287eee4b93..861073f641 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -51,6 +51,7 @@ supported:
 * Reference counts categorized by type
 * Reachable object counts categorized by type
 * Total inflated size of reachable objects by type
+* Total disk size of reachable objects by type
 
 +
 The output format can be chosen through the flag `--format`. Three formats are
diff --git a/builtin/repo.c b/builtin/repo.c
index 67d7548b88..7ea051f3af 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -214,6 +214,7 @@ struct object_values {
 struct object_stats {
 	struct object_values type_counts;
 	struct object_values inflated_sizes;
+	struct object_values disk_sizes;
 };
 
 struct repo_structure {
@@ -462,6 +463,15 @@ static void structure_keyvalue_print(struct repo_structure *stats,
 	printf("objects.tags.inflated_size%c%" PRIuMAX "%c", key_delim,
 	       (uintmax_t)stats->objects.inflated_sizes.tags, value_delim);
 
+	printf("objects.commits.disk_size%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.commits, value_delim);
+	printf("objects.trees.disk_size%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.trees, value_delim);
+	printf("objects.blobs.disk_size%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.blobs, value_delim);
+	printf("objects.tags.disk_size%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.tags, value_delim);
+
 	fflush(stdout);
 }
 
@@ -536,13 +546,16 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
 	struct count_objects_data *data = cb_data;
 	struct object_stats *stats = data->stats;
 	size_t inflated_total = 0;
+	size_t disk_total = 0;
 	size_t object_count;
 
 	for (size_t i = 0; i < oids->nr; i++) {
 		struct object_info oi = OBJECT_INFO_INIT;
 		unsigned long inflated;
+		off_t disk;
 
 		oi.sizep = &inflated;
+		oi.disk_sizep = &disk;
 
 		if (odb_read_object_info_extended(data->odb, &oids->oid[i], &oi,
 						  OBJECT_INFO_SKIP_FETCH_OBJECT |
@@ -550,24 +563,29 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
 			continue;
 
 		inflated_total += inflated;
+		disk_total += disk;
 	}
 
 	switch (type) {
 	case OBJ_TAG:
 		stats->type_counts.tags += oids->nr;
 		stats->inflated_sizes.tags += inflated_total;
+		stats->disk_sizes.tags += disk_total;
 		break;
 	case OBJ_COMMIT:
 		stats->type_counts.commits += oids->nr;
 		stats->inflated_sizes.commits += inflated_total;
+		stats->disk_sizes.commits += disk_total;
 		break;
 	case OBJ_TREE:
 		stats->type_counts.trees += oids->nr;
 		stats->inflated_sizes.trees += inflated_total;
+		stats->disk_sizes.trees += disk_total;
 		break;
 	case OBJ_BLOB:
 		stats->type_counts.blobs += oids->nr;
 		stats->inflated_sizes.blobs += inflated_total;
+		stats->disk_sizes.blobs += disk_total;
 		break;
 	default:
 		BUG("invalid object type");
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
index b18213c660..dd17caad05 100755
--- a/t/t1901-repo-structure.sh
+++ b/t/t1901-repo-structure.sh
@@ -4,6 +4,11 @@ test_description='test git repo structure'
 
 . ./test-lib.sh
 
+object_type_disk_usage() {
+	git rev-list --all --objects --disk-usage --filter=object:type=$1 \
+		--filter-provided-objects
+}
+
 test_expect_success 'empty repository' '
 	test_when_finished "rm -rf repo" &&
 	git init repo &&
@@ -91,7 +96,7 @@ test_expect_success SHA1 'keyvalue and nul format' '
 		test_commit_bulk 42 &&
 		git tag -a foo -m bar &&
 
-		cat >expect <<-\EOF &&
+		cat >expect <<-EOF &&
 		references.branches.count=1
 		references.tags.count=1
 		references.remotes.count=0
@@ -104,6 +109,10 @@ test_expect_success SHA1 'keyvalue and nul format' '
 		objects.trees.inflated_size=28554
 		objects.blobs.inflated_size=453
 		objects.tags.inflated_size=132
+		objects.commits.disk_size=$(object_type_disk_usage commit)
+		objects.trees.disk_size=$(object_type_disk_usage tree)
+		objects.blobs.disk_size=$(object_type_disk_usage blob)
+		objects.tags.disk_size=$(object_type_disk_usage tag)
 		EOF
 
 		git repo structure --format=keyvalue >out 2>err &&
-- 
2.52.0.209.ge85ae279b0
Previous: Justin ToblerNext: Justin Tobler
Message 78 of 80 in “builtin/repo: add object size info to structure output”
  1. 0/6 builtin/repo: add object size info to structure outputJustin Tobler, Dec 9, 2025
  2. 1/6 builtin/repo: group per-type object values into structJustin Tobler, Dec 9, 2025
  3. 2/6 builtin/repo: humanise count values in structure outputJustin Tobler, Dec 9, 2025
  4. Patrick SteinhardtDec 10, 2025
  5. Justin ToblerDec 10, 2025
  6. Junio C HamanoDec 11, 2025
  7. Justin ToblerDec 12, 2025
  8. 3/6 builtin/repo: add inflated object info to keyvalue structure outputJustin Tobler, Dec 9, 2025
  9. 4/6 builtin/repo: add inflated object info to structure tableJustin Tobler, Dec 9, 2025
  10. Patrick SteinhardtDec 10, 2025
  11. Justin ToblerDec 10, 2025
  12. 5/6 builtin/repo: add disk size info to keyvalue stucture outputJustin Tobler, Dec 9, 2025
  13. Patrick SteinhardtDec 10, 2025
  14. Justin ToblerDec 10, 2025
  15. Justin ToblerDec 12, 2025
  16. Patrick SteinhardtDec 15, 2025
  17. Justin ToblerDec 15, 2025
  18. Junio C HamanoDec 10, 2025
  19. Lucas Seiki OshiroDec 10, 2025
  20. Justin ToblerDec 12, 2025
  21. Junio C HamanoDec 12, 2025
  22. 6/6 builtin/repo: add object disk size info to structure tableJustin Tobler, Dec 9, 2025
  23. Patrick SteinhardtDec 10, 2025
  24. Justin ToblerDec 10, 2025
  25. 0/7 builtin/repo: add object size info to structure outputJustin Tobler, Dec 12, 2025
  26. 1/7 builtin/repo: group per-type object values into structJustin Tobler, Dec 12, 2025
  27. 2/7 strbuf: split out logic to humanise byte valuesJustin Tobler, Dec 12, 2025
  28. Patrick SteinhardtDec 15, 2025
  29. Justin ToblerDec 15, 2025
  30. Junio C HamanoDec 15, 2025
  31. Justin ToblerDec 15, 2025
  32. Jiang XinDec 16, 2025
  33. Junio C HamanoDec 16, 2025
  34. Jiang XinDec 16, 2025
  35. Justin ToblerDec 16, 2025
  36. 3/7 builtin/repo: humanise count values in structure outputJustin Tobler, Dec 12, 2025
  37. Patrick SteinhardtDec 15, 2025
  38. 4/7 builtin/repo: add inflated object info to keyvalue structure outputJustin Tobler, Dec 12, 2025
  39. Patrick SteinhardtDec 15, 2025
  40. Justin ToblerDec 15, 2025
  41. 5/7 builtin/repo: add inflated object info to structure tableJustin Tobler, Dec 12, 2025
  42. 6/7 builtin/repo: add disk size info to keyvalue stucture outputJustin Tobler, Dec 12, 2025
  43. Patrick SteinhardtDec 15, 2025
  44. 7/7 builtin/repo: add object disk size info to structure tableJustin Tobler, Dec 12, 2025
  45. 0/7 builtin/repo: add object size info to structure outputJustin Tobler, Dec 15, 2025
  46. 1/7 builtin/repo: group per-type object values into structJustin Tobler, Dec 15, 2025
  47. 2/7 strbuf: split out logic to humanise byte valuesJustin Tobler, Dec 15, 2025
  48. Junio C HamanoDec 16, 2025
  49. Justin ToblerDec 16, 2025
  50. 3/7 builtin/repo: humanise count values in structure outputJustin Tobler, Dec 15, 2025
  51. Patrick SteinhardtDec 16, 2025
  52. 4/7 builtin/repo: add inflated object info to keyvalue structure outputJustin Tobler, Dec 15, 2025
  53. 5/7 builtin/repo: add inflated object info to structure tableJustin Tobler, Dec 15, 2025
  54. 6/7 builtin/repo: add disk size info to keyvalue stucture outputJustin Tobler, Dec 15, 2025
  55. 7/7 builtin/repo: add object disk size info to structure tableJustin Tobler, Dec 15, 2025
  56. Patrick SteinhardtDec 16, 2025
  57. Justin ToblerDec 16, 2025
  58. 0/7 builtin/repo: add object size info to structure outputJustin Tobler, Dec 16, 2025
  59. 1/7 builtin/repo: group per-type object values into structJustin Tobler, Dec 16, 2025
  60. 2/7 strbuf: split out logic to humanise byte valuesJustin Tobler, Dec 16, 2025
  61. Junio C HamanoDec 16, 2025
  62. Justin ToblerDec 16, 2025
  63. 4/7 builtin/repo: add inflated object info to keyvalue structure outputJustin Tobler, Dec 16, 2025
  64. Patrick SteinhardtDec 17, 2025
  65. Justin ToblerDec 17, 2025
  66. 3/7 builtin/repo: humanise count values in structure outputJustin Tobler, Dec 16, 2025
  67. 5/7 builtin/repo: add inflated object info to structure tableJustin Tobler, Dec 16, 2025
  68. 6/7 builtin/repo: add disk size info to keyvalue stucture outputJustin Tobler, Dec 16, 2025
  69. 7/7 builtin/repo: add object disk size info to structure tableJustin Tobler, Dec 16, 2025
  70. Patrick SteinhardtDec 17, 2025
  71. Justin ToblerDec 17, 2025
  72. 0/7 builtin/repo: add object size info to structure outputJustin Tobler, Dec 17, 2025
  73. 1/7 builtin/repo: group per-type object values into structJustin Tobler, Dec 17, 2025
  74. 2/7 strbuf: split out logic to humanise byte valuesJustin Tobler, Dec 17, 2025
  75. 4/7 builtin/repo: add inflated object info to keyvalue structure outputJustin Tobler, Dec 17, 2025
  76. 3/7 builtin/repo: humanise count values in structure outputJustin Tobler, Dec 17, 2025
  77. 5/7 builtin/repo: add inflated object info to structure tableJustin Tobler, Dec 17, 2025
  78. 6/7 builtin/repo: add disk size info to keyvalue stucture outputJustin Tobler, Dec 17, 2025
  79. 7/7 builtin/repo: add object disk size info to structure tableJustin Tobler, Dec 17, 2025
  80. Patrick SteinhardtDec 18, 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.