reftable/record: store "val1" hashes as static arrays

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 an embedded 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 <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

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);

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 },
 		},
 	};
 

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;
@@ -814,11 +809,10 @@ static void test_write_multiple_indices(void)
 	writer = reftable_new_writer(&strbuf_add_void, &writer_buf, &opts);
 	reftable_writer_set_limits(writer, 1, 1);
 	for (i = 0; i < 100; i++) {
-		unsigned char hash[GIT_SHA1_RAWSZ] = {i};
 		struct reftable_ref_record ref = {
 			.update_index = 1,
 			.value_type = REFTABLE_REF_VAL1,
-			.value.val1 = hash,
+			.value.val1 = {i},
 		};
 
 		strbuf_reset(&buf);

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;

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:

reftable/reftable-record.h

@@ -9,6 +9,7 @@ license that can be found in the LICENSE file or at
 #ifndef REFTABLE_RECORD_H
 #define REFTABLE_RECORD_H
 
+#include "hash-ll.h"
 #include <stdint.h>
 
 /*
@@ -38,7 +39,7 @@ 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 */

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);
 		}