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

[PATCH 4/7] reftable/record: store "val1" hashes as static arrays

From
Patrick Steinhardt <ps@pks.im>
Date
Dec 20, 2023, 09:17 UTC
Message-ID
<06c9eab67802ba933b44d32f5c8d11fddc216c26.1703063544.git.ps@pks.im>
In-Reply-To
<cover.1703063544.git.ps@pks.im>

When reading ref records of type "val1" we store its object ID in an allocated array. This results in an additional allocation for every single ref record we read, which is rather inefficient especially when iterating over refs.

Refactor the code to instead use a static array of `GIT_MAX_RAWSZ` bytes. While this means that `struct ref_record` is bigger now, we typically do not store all refs in an array anyway and instead only handle a limited number of records at the same point in time.

Using `git show-ref --quiet` in a repository with ~350k refs this leads to a significant drop in allocations. Before:

    HEAP SUMMARY:
        in use at exit: 21,098 bytes in 192 blocks
      total heap usage: 2,116,683 allocs, 2,116,491 frees, 76,098,060 bytes allocated
After:
    HEAP SUMMARY:
        in use at exit: 21,098 bytes in 192 blocks
      total heap usage: 1,419,031 allocs, 1,418,839 frees, 62,145,036 bytes allocated
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 reftable/block_test.c      |  4 +---
 reftable/merged_test.c     | 16 ++++++----------
 reftable/readwrite_test.c  | 11 +++--------
 reftable/record.c          |  3 ---
 reftable/record_test.c     |  1 -
 reftable/reftable-record.h |  2 +-
 reftable/stack_test.c      |  2 --
 7 files changed, 11 insertions(+), 28 deletions(-)
diff --git a/reftable/block_test.c b/reftable/block_test.c
index c00bbc8aed..dedb05c7d8 100644
--- a/reftable/block_test.c
+++ b/reftable/block_test.c
@@ -49,13 +49,11 @@ static void test_block_read_write(void)
 
 	for (i = 0; i < N; i++) {
 		char name[100];
-		uint8_t hash[GIT_SHA1_RAWSZ];
 		snprintf(name, sizeof(name), "branch%02d", i);
-		memset(hash, i, sizeof(hash));
 
 		rec.u.ref.refname = name;
 		rec.u.ref.value_type = REFTABLE_REF_VAL1;
-		rec.u.ref.value.val1 = hash;
+		memset(rec.u.ref.value.val1, i, GIT_SHA1_RAWSZ);
 
 		names[i] = xstrdup(name);
 		n = block_writer_add(&bw, &rec);
diff --git a/reftable/merged_test.c b/reftable/merged_test.c
index d08c16abef..b3927a5d73 100644
--- a/reftable/merged_test.c
+++ b/reftable/merged_test.c
@@ -123,13 +123,11 @@ static void readers_destroy(struct reftable_reader **readers, size_t n)
 
 static void test_merged_between(void)
 {
-	uint8_t hash1[GIT_SHA1_RAWSZ] = { 1, 2, 3, 0 };
-
 	struct reftable_ref_record r1[] = { {
 		.refname = "b",
 		.update_index = 1,
 		.value_type = REFTABLE_REF_VAL1,
-		.value.val1 = hash1,
+		.value.val1 = { 1, 2, 3, 0 },
 	} };
 	struct reftable_ref_record r2[] = { {
 		.refname = "a",
@@ -165,26 +163,24 @@ static void test_merged_between(void)
 
 static void test_merged(void)
 {
-	uint8_t hash1[GIT_SHA1_RAWSZ] = { 1 };
-	uint8_t hash2[GIT_SHA1_RAWSZ] = { 2 };
 	struct reftable_ref_record r1[] = {
 		{
 			.refname = "a",
 			.update_index = 1,
 			.value_type = REFTABLE_REF_VAL1,
-			.value.val1 = hash1,
+			.value.val1 = { 1 },
 		},
 		{
 			.refname = "b",
 			.update_index = 1,
 			.value_type = REFTABLE_REF_VAL1,
-			.value.val1 = hash1,
+			.value.val1 = { 1 },
 		},
 		{
 			.refname = "c",
 			.update_index = 1,
 			.value_type = REFTABLE_REF_VAL1,
-			.value.val1 = hash1,
+			.value.val1 = { 1 },
 		}
 	};
 	struct reftable_ref_record r2[] = { {
@@ -197,13 +193,13 @@ static void test_merged(void)
 			.refname = "c",
 			.update_index = 3,
 			.value_type = REFTABLE_REF_VAL1,
-			.value.val1 = hash2,
+			.value.val1 = { 2 },
 		},
 		{
 			.refname = "d",
 			.update_index = 3,
 			.value_type = REFTABLE_REF_VAL1,
-			.value.val1 = hash1,
+			.value.val1 = { 1 },
 		},
 	};
 
diff --git a/reftable/readwrite_test.c b/reftable/readwrite_test.c
index 9c16e0504e..56c0b4db5d 100644
--- a/reftable/readwrite_test.c
+++ b/reftable/readwrite_test.c
@@ -60,18 +60,15 @@ static void write_table(char ***names, struct strbuf *buf, int N,
 	*names = reftable_calloc(sizeof(char *) * (N + 1));
 	reftable_writer_set_limits(w, update_index, update_index);
 	for (i = 0; i < N; i++) {
-		uint8_t hash[GIT_SHA256_RAWSZ] = { 0 };
 		char name[100];
 		int n;
 
-		set_test_hash(hash, i);
-
 		snprintf(name, sizeof(name), "refs/heads/branch%02d", i);
 
 		ref.refname = name;
 		ref.update_index = update_index;
 		ref.value_type = REFTABLE_REF_VAL1;
-		ref.value.val1 = hash;
+		set_test_hash(ref.value.val1, i);
 		(*names)[i] = xstrdup(name);
 
 		n = reftable_writer_add_ref(w, &ref);
@@ -675,11 +672,10 @@ static void test_write_object_id_min_length(void)
 	struct strbuf buf = STRBUF_INIT;
 	struct reftable_writer *w =
 		reftable_new_writer(&strbuf_add_void, &buf, &opts);
-	uint8_t hash[GIT_SHA1_RAWSZ] = {42};
 	struct reftable_ref_record ref = {
 		.update_index = 1,
 		.value_type = REFTABLE_REF_VAL1,
-		.value.val1 = hash,
+		.value.val1 = {42},
 	};
 	int err;
 	int i;
@@ -711,11 +707,10 @@ static void test_write_object_id_length(void)
 	struct strbuf buf = STRBUF_INIT;
 	struct reftable_writer *w =
 		reftable_new_writer(&strbuf_add_void, &buf, &opts);
-	uint8_t hash[GIT_SHA1_RAWSZ] = {42};
 	struct reftable_ref_record ref = {
 		.update_index = 1,
 		.value_type = REFTABLE_REF_VAL1,
-		.value.val1 = hash,
+		.value.val1 = {42},
 	};
 	int err;
 	int i;
diff --git a/reftable/record.c b/reftable/record.c
index 5e258c734b..a67a6b4d8a 100644
--- a/reftable/record.c
+++ b/reftable/record.c
@@ -219,7 +219,6 @@ static void reftable_ref_record_copy_from(void *rec, const void *src_rec,
 	case REFTABLE_REF_DELETION:
 		break;
 	case REFTABLE_REF_VAL1:
-		ref->value.val1 = reftable_malloc(hash_size);
 		memcpy(ref->value.val1, src->value.val1, hash_size);
 		break;
 	case REFTABLE_REF_VAL2:
@@ -303,7 +302,6 @@ void reftable_ref_record_release(struct reftable_ref_record *ref)
 		reftable_free(ref->value.val2.value);
 		break;
 	case REFTABLE_REF_VAL1:
-		reftable_free(ref->value.val1);
 		break;
 	case REFTABLE_REF_DELETION:
 		break;
@@ -394,7 +392,6 @@ static int reftable_ref_record_decode(void *rec, struct strbuf key,
 			return -1;
 		}
 
-		r->value.val1 = reftable_malloc(hash_size);
 		memcpy(r->value.val1, in.buf, hash_size);
 		string_view_consume(&in, hash_size);
 		break;
diff --git a/reftable/record_test.c b/reftable/record_test.c
index 70ae78feca..5c94d26e35 100644
--- a/reftable/record_test.c
+++ b/reftable/record_test.c
@@ -119,7 +119,6 @@ static void test_reftable_ref_record_roundtrip(void)
 		case REFTABLE_REF_DELETION:
 			break;
 		case REFTABLE_REF_VAL1:
-			in.u.ref.value.val1 = reftable_malloc(GIT_SHA1_RAWSZ);
 			set_hash(in.u.ref.value.val1, 1);
 			break;
 		case REFTABLE_REF_VAL2:
diff --git a/reftable/reftable-record.h b/reftable/reftable-record.h
index f7eb2d6015..44b5125445 100644
--- a/reftable/reftable-record.h
+++ b/reftable/reftable-record.h
@@ -38,7 +38,7 @@ struct reftable_ref_record {
 #define REFTABLE_NR_REF_VALUETYPES 4
 	} value_type;
 	union {
-		uint8_t *val1; /* malloced hash. */
+		unsigned char val1[GIT_MAX_RAWSZ];
 		struct {
 			uint8_t *value; /* first value, malloced hash  */
 			uint8_t *target_value; /* second value, malloced hash */
diff --git a/reftable/stack_test.c b/reftable/stack_test.c
index 14a3fc11ee..feab49d7f7 100644
--- a/reftable/stack_test.c
+++ b/reftable/stack_test.c
@@ -463,7 +463,6 @@ static void test_reftable_stack_add(void)
 		refs[i].refname = xstrdup(buf);
 		refs[i].update_index = i + 1;
 		refs[i].value_type = REFTABLE_REF_VAL1;
-		refs[i].value.val1 = reftable_malloc(GIT_SHA1_RAWSZ);
 		set_test_hash(refs[i].value.val1, i);
 
 		logs[i].refname = xstrdup(buf);
@@ -600,7 +599,6 @@ static void test_reftable_stack_tombstone(void)
 		refs[i].update_index = i + 1;
 		if (i % 2 == 0) {
 			refs[i].value_type = REFTABLE_REF_VAL1;
-			refs[i].value.val1 = reftable_malloc(GIT_SHA1_RAWSZ);
 			set_test_hash(refs[i].value.val1, i);
 		}
 
-- 
2.43.GIT
Previous: Patrick SteinhardtNext: Patrick Steinhardt
Message 5 of 36 in “reftable: fixes and optimizations (pt.2)”
  1. 0/7 reftable: fixes and optimizations (pt.2)Patrick Steinhardt, Dec 20, 2023
  2. 1/7 reftable/stack: do not overwrite errors when compactingPatrick Steinhardt, Dec 20, 2023
  3. 2/7 reftable/writer: fix index corruption when writing multiple indicesPatrick Steinhardt, Dec 20, 2023
  4. 3/7 reftable/record: constify some parts of the interfacePatrick Steinhardt, Dec 20, 2023
  5. 4/7 reftable/record: store "val1" hashes as static arraysPatrick Steinhardt, Dec 20, 2023
  6. Patrick SteinhardtDec 20, 2023
  7. 5/7 reftable/record: store "val2" hashes as static arraysPatrick Steinhardt, Dec 20, 2023
  8. 6/7 reftable/merged: really reuse buffers to compute record keysPatrick Steinhardt, Dec 20, 2023
  9. 7/7 reftable/merged: transfer ownership of records when iteratingPatrick Steinhardt, Dec 20, 2023
  10. Junio C HamanoDec 20, 2023
  11. 0/8 reftable: fixes and optimizations (pt.2)Patrick Steinhardt, Dec 28, 2023
  12. 1/8 reftable/stack: do not overwrite errors when compactingPatrick Steinhardt, Dec 28, 2023
  13. 2/8 reftable/stack: do not auto-compact twice in `reftable_stack_add()`Patrick Steinhardt, Dec 28, 2023
  14. 3/8 reftable/writer: fix index corruption when writing multiple indicesPatrick Steinhardt, Dec 28, 2023
  15. 4/8 reftable/record: constify some parts of the interfacePatrick Steinhardt, Dec 28, 2023
  16. 5/8 reftable/record: store "val1" hashes as static arraysPatrick Steinhardt, Dec 28, 2023
  17. Junio C HamanoDec 28, 2023
  18. 6/8 reftable/record: store "val2" hashes as static arraysPatrick Steinhardt, Dec 28, 2023
  19. 7/8 reftable/merged: really reuse buffers to compute record keysPatrick Steinhardt, Dec 28, 2023
  20. Junio C HamanoDec 28, 2023
  21. 8/8 reftable/merged: transfer ownership of records when iteratingPatrick Steinhardt, Dec 28, 2023
  22. Junio C HamanoDec 28, 2023
  23. 0/8 reftable: fixes and optimizations (pt.2)Patrick Steinhardt, Jan 3, 2024
  24. 1/8 reftable/stack: do not overwrite errors when compactingPatrick Steinhardt, Jan 3, 2024
  25. Han-Wen NienhuysFeb 14, 2024
  26. Patrick SteinhardtFeb 15, 2024
  27. 2/8 reftable/stack: do not auto-compact twice in `reftable_stack_add()`Patrick Steinhardt, Jan 3, 2024
  28. 3/8 reftable/writer: fix index corruption when writing multiple indicesPatrick Steinhardt, Jan 3, 2024
  29. 4/8 reftable/record: constify some parts of the interfacePatrick Steinhardt, Jan 3, 2024
  30. 5/8 reftable/record: store "val1" hashes as static arraysPatrick Steinhardt, Jan 3, 2024
  31. Karthik NayakFeb 5, 2024
  32. Patrick SteinhardtFeb 6, 2024
  33. 6/8 reftable/record: store "val2" hashes as static arraysPatrick Steinhardt, Jan 3, 2024
  34. 7/8 reftable/merged: really reuse buffers to compute record keysPatrick Steinhardt, Jan 3, 2024
  35. 8/8 reftable/merged: transfer ownership of records when iteratingPatrick Steinhardt, Jan 3, 2024
  36. Karthik NayakFeb 5, 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.