Merge branch 'ps/reftable-reflog-iteration-perf'

The code to iterate over reflogs in the reftable has been optimized
to reduce memory allocation and deallocation.

Reviewed-by: Josh Steadmon <steadmon@google.com>
cf. <Ze9eX-aaWoVaqsPP@google.com>

* ps/reftable-reflog-iteration-perf:
  refs/reftable: track last log record name via strbuf
  reftable/record: use scratch buffer when decoding records
  reftable/record: reuse message when decoding log records
  reftable/record: reuse refnames when decoding log records
  reftable/record: avoid copying author info
  reftable/record: convert old and new object IDs to arrays
  refs/reftable: reload correct stack when creating reflog iter

9 files changed, 138 insertions, 175 deletions

diff --git a/reftable/block.c b/reftable/block.c
index c469a9b529..e2a2cee58d 100644
--- a/reftable/block.c
+++ b/reftable/block.c
@@ -332,7 +332,8 @@ int block_iter_next(struct block_iter *it, struct reftable_record *rec)
 		return REFTABLE_FORMAT_ERROR;
 
 	string_view_consume(&in, n);
-	n = reftable_record_decode(rec, it->last_key, extra, in, it->br->hash_size);
+	n = reftable_record_decode(rec, it->last_key, extra, in, it->br->hash_size,
+				   &it->scratch);
 	if (n < 0)
 		return -1;
 	string_view_consume(&in, n);
@@ -369,6 +370,7 @@ int block_iter_seek(struct block_iter *it, struct strbuf *want)
 void block_iter_close(struct block_iter *it)
 {
 	strbuf_release(&it->last_key);
+	strbuf_release(&it->scratch);
 }
 
 int block_reader_seek(struct block_reader *br, struct block_iter *it,
diff --git a/reftable/block.h b/reftable/block.h
index 51699af233..47acc62c0a 100644
--- a/reftable/block.h
+++ b/reftable/block.h
@@ -84,10 +84,12 @@ struct block_iter {
 
 	/* key for last entry we read. */
 	struct strbuf last_key;
+	struct strbuf scratch;
 };
 
 #define BLOCK_ITER_INIT { \
 	.last_key = STRBUF_INIT, \
+	.scratch = STRBUF_INIT, \
 }
 
 /* initializes a block reader. */
diff --git a/reftable/merged_test.c b/reftable/merged_test.c
index d0f77a3b8f..530fc82d1c 100644
--- a/reftable/merged_test.c
+++ b/reftable/merged_test.c
@@ -289,16 +289,13 @@ merged_table_from_log_records(struct reftable_log_record **logs,
 
 static void test_merged_logs(void)
 {
-	uint8_t hash1[GIT_SHA1_RAWSZ] = { 1 };
-	uint8_t hash2[GIT_SHA1_RAWSZ] = { 2 };
-	uint8_t hash3[GIT_SHA1_RAWSZ] = { 3 };
 	struct reftable_log_record r1[] = {
 		{
 			.refname = "a",
 			.update_index = 2,
 			.value_type = REFTABLE_LOG_UPDATE,
 			.value.update = {
-				.old_hash = hash2,
+				.old_hash = { 2 },
 				/* deletion */
 				.name = "jane doe",
 				.email = "jane@invalid",
@@ -310,8 +307,8 @@ static void test_merged_logs(void)
 			.update_index = 1,
 			.value_type = REFTABLE_LOG_UPDATE,
 			.value.update = {
-				.old_hash = hash1,
-				.new_hash = hash2,
+				.old_hash = { 1 },
+				.new_hash = { 2 },
 				.name = "jane doe",
 				.email = "jane@invalid",
 				.message = "message1",
@@ -324,7 +321,7 @@ static void test_merged_logs(void)
 			.update_index = 3,
 			.value_type = REFTABLE_LOG_UPDATE,
 			.value.update = {
-				.new_hash = hash3,
+				.new_hash = { 3 },
 				.name = "jane doe",
 				.email = "jane@invalid",
 				.message = "message3",
diff --git a/reftable/readwrite_test.c b/reftable/readwrite_test.c
index 363fe0f998..a6dbd214c5 100644
--- a/reftable/readwrite_test.c
+++ b/reftable/readwrite_test.c
@@ -77,18 +77,15 @@ static void write_table(char ***names, struct strbuf *buf, int N,
 	}
 
 	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);
 
 		log.refname = name;
 		log.update_index = update_index;
 		log.value_type = REFTABLE_LOG_UPDATE;
-		log.value.update.new_hash = hash;
+		set_test_hash(log.value.update.new_hash, i);
 		log.value.update.message = "message";
 
 		n = reftable_writer_add_log(w, &log);
@@ -137,13 +134,10 @@ static void test_log_buffer_size(void)
 	/* This tests buffer extension for log compression. Must use a random
 	   hash, to ensure that the compressed part is larger than the original.
 	*/
-	uint8_t hash1[GIT_SHA1_RAWSZ], hash2[GIT_SHA1_RAWSZ];
 	for (i = 0; i < GIT_SHA1_RAWSZ; i++) {
-		hash1[i] = (uint8_t)(git_rand() % 256);
-		hash2[i] = (uint8_t)(git_rand() % 256);
+		log.value.update.old_hash[i] = (uint8_t)(git_rand() % 256);
+		log.value.update.new_hash[i] = (uint8_t)(git_rand() % 256);
 	}
-	log.value.update.old_hash = hash1;
-	log.value.update.new_hash = hash2;
 	reftable_writer_set_limits(w, update_index, update_index);
 	err = reftable_writer_add_log(w, &log);
 	EXPECT_ERR(err);
@@ -161,25 +155,26 @@ static void test_log_overflow(void)
 		.block_size = ARRAY_SIZE(msg),
 	};
 	int err;
-	struct reftable_log_record
-		log = { .refname = "refs/heads/master",
-			.update_index = 0xa,
-			.value_type = REFTABLE_LOG_UPDATE,
-			.value = { .update = {
-					   .name = "Han-Wen Nienhuys",
-					   .email = "hanwen@google.com",
-					   .tz_offset = 100,
-					   .time = 0x5e430672,
-					   .message = msg,
-				   } } };
+	struct reftable_log_record log = {
+		.refname = "refs/heads/master",
+		.update_index = 0xa,
+		.value_type = REFTABLE_LOG_UPDATE,
+		.value = {
+			.update = {
+				.old_hash = { 1 },
+				.new_hash = { 2 },
+				.name = "Han-Wen Nienhuys",
+				.email = "hanwen@google.com",
+				.tz_offset = 100,
+				.time = 0x5e430672,
+				.message = msg,
+			},
+		},
+	};
 	struct reftable_writer *w =
 		reftable_new_writer(&strbuf_add_void, &noop_flush, &buf, &opts);
 
-	uint8_t hash1[GIT_SHA1_RAWSZ]  = {1}, hash2[GIT_SHA1_RAWSZ] = { 2 };
-
 	memset(msg, 'x', sizeof(msg) - 1);
-	log.value.update.old_hash = hash1;
-	log.value.update.new_hash = hash2;
 	reftable_writer_set_limits(w, update_index, update_index);
 	err = reftable_writer_add_log(w, &log);
 	EXPECT(err == REFTABLE_ENTRY_TOO_BIG_ERROR);
@@ -219,16 +214,13 @@ static void test_log_write_read(void)
 		EXPECT_ERR(err);
 	}
 	for (i = 0; i < N; i++) {
-		uint8_t hash1[GIT_SHA1_RAWSZ], hash2[GIT_SHA1_RAWSZ];
 		struct reftable_log_record log = { NULL };
-		set_test_hash(hash1, i);
-		set_test_hash(hash2, i + 1);
 
 		log.refname = names[i];
 		log.update_index = i;
 		log.value_type = REFTABLE_LOG_UPDATE;
-		log.value.update.old_hash = hash1;
-		log.value.update.new_hash = hash2;
+		set_test_hash(log.value.update.old_hash, i);
+		set_test_hash(log.value.update.new_hash, i + 1);
 
 		err = reftable_writer_add_log(w, &log);
 		EXPECT_ERR(err);
@@ -298,18 +290,15 @@ static void test_log_zlib_corruption(void)
 	struct reftable_writer *w =
 		reftable_new_writer(&strbuf_add_void, &noop_flush, &buf, &opts);
 	const struct reftable_stats *stats = NULL;
-	uint8_t hash1[GIT_SHA1_RAWSZ] = { 1 };
-	uint8_t hash2[GIT_SHA1_RAWSZ] = { 2 };
 	char message[100] = { 0 };
 	int err, i, n;
-
 	struct reftable_log_record log = {
 		.refname = "refname",
 		.value_type = REFTABLE_LOG_UPDATE,
 		.value = {
 			.update = {
-				.new_hash = hash1,
-				.old_hash = hash2,
+				.new_hash = { 1 },
+				.old_hash = { 2 },
 				.name = "My Name",
 				.email = "myname@invalid",
 				.message = message,
@@ -821,13 +810,12 @@ static void test_write_multiple_indices(void)
 	}
 
 	for (i = 0; i < 100; i++) {
-		unsigned char hash[GIT_SHA1_RAWSZ] = {i};
 		struct reftable_log_record log = {
 			.update_index = 1,
 			.value_type = REFTABLE_LOG_UPDATE,
 			.value.update = {
-				.old_hash = hash,
-				.new_hash = hash,
+				.old_hash = { i },
+				.new_hash = { i },
 			},
 		};
 
diff --git a/reftable/record.c b/reftable/record.c
index 2e2061d082..23b497adab 100644
--- a/reftable/record.c
+++ b/reftable/record.c
@@ -374,7 +374,7 @@ static int reftable_ref_record_encode(const void *rec, struct string_view s,
 
 static int reftable_ref_record_decode(void *rec, struct strbuf key,
 				      uint8_t val_type, struct string_view in,
-				      int hash_size)
+				      int hash_size, struct strbuf *scratch)
 {
 	struct reftable_ref_record *r = rec;
 	struct string_view start = in;
@@ -425,13 +425,12 @@ static int reftable_ref_record_decode(void *rec, struct strbuf key,
 		break;
 
 	case REFTABLE_REF_SYMREF: {
-		struct strbuf dest = STRBUF_INIT;
-		int n = decode_string(&dest, in);
+		int n = decode_string(scratch, in);
 		if (n < 0) {
 			return -1;
 		}
 		string_view_consume(&in, n);
-		r->value.symref = dest.buf;
+		r->value.symref = strbuf_detach(scratch, NULL);
 	} break;
 
 	case REFTABLE_REF_DELETION:
@@ -579,7 +578,7 @@ static int reftable_obj_record_encode(const void *rec, struct string_view s,
 
 static int reftable_obj_record_decode(void *rec, struct strbuf key,
 				      uint8_t val_type, struct string_view in,
-				      int hash_size)
+				      int hash_size, struct strbuf *scratch UNUSED)
 {
 	struct string_view start = in;
 	struct reftable_obj_record *r = rec;
@@ -765,16 +764,10 @@ static void reftable_log_record_copy_from(void *rec, const void *src_rec,
 				xstrdup(dst->value.update.message);
 		}
 
-		if (dst->value.update.new_hash) {
-			REFTABLE_ALLOC_ARRAY(dst->value.update.new_hash, hash_size);
-			memcpy(dst->value.update.new_hash,
-			       src->value.update.new_hash, hash_size);
-		}
-		if (dst->value.update.old_hash) {
-			REFTABLE_ALLOC_ARRAY(dst->value.update.old_hash, hash_size);
-			memcpy(dst->value.update.old_hash,
-			       src->value.update.old_hash, hash_size);
-		}
+		memcpy(dst->value.update.new_hash,
+		       src->value.update.new_hash, hash_size);
+		memcpy(dst->value.update.old_hash,
+		       src->value.update.old_hash, hash_size);
 		break;
 	}
 }
@@ -792,8 +785,6 @@ void reftable_log_record_release(struct reftable_log_record *r)
 	case REFTABLE_LOG_DELETION:
 		break;
 	case REFTABLE_LOG_UPDATE:
-		reftable_free(r->value.update.new_hash);
-		reftable_free(r->value.update.old_hash);
 		reftable_free(r->value.update.name);
 		reftable_free(r->value.update.email);
 		reftable_free(r->value.update.message);
@@ -810,33 +801,20 @@ static uint8_t reftable_log_record_val_type(const void *rec)
 	return reftable_log_record_is_deletion(log) ? 0 : 1;
 }
 
-static uint8_t zero[GIT_SHA256_RAWSZ] = { 0 };
-
 static int reftable_log_record_encode(const void *rec, struct string_view s,
 				      int hash_size)
 {
 	const struct reftable_log_record *r = rec;
 	struct string_view start = s;
 	int n = 0;
-	uint8_t *oldh = NULL;
-	uint8_t *newh = NULL;
 	if (reftable_log_record_is_deletion(r))
 		return 0;
 
-	oldh = r->value.update.old_hash;
-	newh = r->value.update.new_hash;
-	if (!oldh) {
-		oldh = zero;
-	}
-	if (!newh) {
-		newh = zero;
-	}
-
 	if (s.len < 2 * hash_size)
 		return -1;
 
-	memcpy(s.buf, oldh, hash_size);
-	memcpy(s.buf + hash_size, newh, hash_size);
+	memcpy(s.buf, r->value.update.old_hash, hash_size);
+	memcpy(s.buf + hash_size, r->value.update.new_hash, hash_size);
 	string_view_consume(&s, 2 * hash_size);
 
 	n = encode_string(r->value.update.name ? r->value.update.name : "", s);
@@ -872,19 +850,18 @@ static int reftable_log_record_encode(const void *rec, struct string_view s,
 
 static int reftable_log_record_decode(void *rec, struct strbuf key,
 				      uint8_t val_type, struct string_view in,
-				      int hash_size)
+				      int hash_size, struct strbuf *scratch)
 {
 	struct string_view start = in;
 	struct reftable_log_record *r = rec;
 	uint64_t max = 0;
 	uint64_t ts = 0;
-	struct strbuf dest = STRBUF_INIT;
 	int n;
 
 	if (key.len <= 9 || key.buf[key.len - 9] != 0)
 		return REFTABLE_FORMAT_ERROR;
 
-	r->refname = reftable_realloc(r->refname, key.len - 8);
+	REFTABLE_ALLOC_GROW(r->refname, key.len - 8, r->refname_cap);
 	memcpy(r->refname, key.buf, key.len - 8);
 	ts = get_be64(key.buf + key.len - 8);
 
@@ -893,9 +870,8 @@ static int reftable_log_record_decode(void *rec, struct strbuf key,
 	if (val_type != r->value_type) {
 		switch (r->value_type) {
 		case REFTABLE_LOG_UPDATE:
-			FREE_AND_NULL(r->value.update.old_hash);
-			FREE_AND_NULL(r->value.update.new_hash);
 			FREE_AND_NULL(r->value.update.message);
+			r->value.update.message_cap = 0;
 			FREE_AND_NULL(r->value.update.email);
 			FREE_AND_NULL(r->value.update.name);
 			break;
@@ -911,36 +887,43 @@ static int reftable_log_record_decode(void *rec, struct strbuf key,
 	if (in.len < 2 * hash_size)
 		return REFTABLE_FORMAT_ERROR;
 
-	r->value.update.old_hash =
-		reftable_realloc(r->value.update.old_hash, hash_size);
-	r->value.update.new_hash =
-		reftable_realloc(r->value.update.new_hash, hash_size);
-
 	memcpy(r->value.update.old_hash, in.buf, hash_size);
 	memcpy(r->value.update.new_hash, in.buf + hash_size, hash_size);
 
 	string_view_consume(&in, 2 * hash_size);
 
-	n = decode_string(&dest, in);
+	n = decode_string(scratch, in);
 	if (n < 0)
 		goto done;
 	string_view_consume(&in, n);
 
-	r->value.update.name =
-		reftable_realloc(r->value.update.name, dest.len + 1);
-	memcpy(r->value.update.name, dest.buf, dest.len);
-	r->value.update.name[dest.len] = 0;
+	/*
+	 * In almost all cases we can expect the reflog name to not change for
+	 * reflog entries as they are tied to the local identity, not to the
+	 * target commits. As an optimization for this common case we can thus
+	 * skip copying over the name in case it's accurate already.
+	 */
+	if (!r->value.update.name ||
+	    strcmp(r->value.update.name, scratch->buf)) {
+		r->value.update.name =
+			reftable_realloc(r->value.update.name, scratch->len + 1);
+		memcpy(r->value.update.name, scratch->buf, scratch->len);
+		r->value.update.name[scratch->len] = 0;
+	}
 
-	strbuf_reset(&dest);
-	n = decode_string(&dest, in);
+	n = decode_string(scratch, in);
 	if (n < 0)
 		goto done;
 	string_view_consume(&in, n);
 
-	r->value.update.email =
-		reftable_realloc(r->value.update.email, dest.len + 1);
-	memcpy(r->value.update.email, dest.buf, dest.len);
-	r->value.update.email[dest.len] = 0;
+	/* Same as above, but for the reflog email. */
+	if (!r->value.update.email ||
+	    strcmp(r->value.update.email, scratch->buf)) {
+		r->value.update.email =
+			reftable_realloc(r->value.update.email, scratch->len + 1);
+		memcpy(r->value.update.email, scratch->buf, scratch->len);
+		r->value.update.email[scratch->len] = 0;
+	}
 
 	ts = 0;
 	n = get_var_int(&ts, &in);
@@ -954,22 +937,19 @@ static int reftable_log_record_decode(void *rec, struct strbuf key,
 	r->value.update.tz_offset = get_be16(in.buf);
 	string_view_consume(&in, 2);
 
-	strbuf_reset(&dest);
-	n = decode_string(&dest, in);
+	n = decode_string(scratch, in);
 	if (n < 0)
 		goto done;
 	string_view_consume(&in, n);
 
-	r->value.update.message =
-		reftable_realloc(r->value.update.message, dest.len + 1);
-	memcpy(r->value.update.message, dest.buf, dest.len);
-	r->value.update.message[dest.len] = 0;
+	REFTABLE_ALLOC_GROW(r->value.update.message, scratch->len + 1,
+			    r->value.update.message_cap);
+	memcpy(r->value.update.message, scratch->buf, scratch->len);
+	r->value.update.message[scratch->len] = 0;
 
-	strbuf_release(&dest);
 	return start.len - in.len;
 
 done:
-	strbuf_release(&dest);
 	return REFTABLE_FORMAT_ERROR;
 }
 
@@ -985,17 +965,6 @@ static int null_streq(char *a, char *b)
 	return 0 == strcmp(a, b);
 }
 
-static int zero_hash_eq(uint8_t *a, uint8_t *b, int sz)
-{
-	if (!a)
-		a = zero;
-
-	if (!b)
-		b = zero;
-
-	return !memcmp(a, b, sz);
-}
-
 static int reftable_log_record_equal_void(const void *a,
 					  const void *b, int hash_size)
 {
@@ -1039,10 +1008,10 @@ int reftable_log_record_equal(const struct reftable_log_record *a,
 				  b->value.update.email) &&
 		       null_streq(a->value.update.message,
 				  b->value.update.message) &&
-		       zero_hash_eq(a->value.update.old_hash,
-				    b->value.update.old_hash, hash_size) &&
-		       zero_hash_eq(a->value.update.new_hash,
-				    b->value.update.new_hash, hash_size);
+		       !memcmp(a->value.update.old_hash,
+			       b->value.update.old_hash, hash_size) &&
+		       !memcmp(a->value.update.new_hash,
+			       b->value.update.new_hash, hash_size);
 	}
 
 	abort();
@@ -1120,7 +1089,7 @@ static int reftable_index_record_encode(const void *rec, struct string_view out,
 
 static int reftable_index_record_decode(void *rec, struct strbuf key,
 					uint8_t val_type, struct string_view in,
-					int hash_size)
+					int hash_size, struct strbuf *scratch UNUSED)
 {
 	struct string_view start = in;
 	struct reftable_index_record *r = rec;
@@ -1201,10 +1170,12 @@ uint8_t reftable_record_val_type(struct reftable_record *rec)
 }
 
 int reftable_record_decode(struct reftable_record *rec, struct strbuf key,
-			   uint8_t extra, struct string_view src, int hash_size)
+			   uint8_t extra, struct string_view src, int hash_size,
+			   struct strbuf *scratch)
 {
 	return reftable_record_vtable(rec)->decode(reftable_record_data(rec),
-						   key, extra, src, hash_size);
+						   key, extra, src, hash_size,
+						   scratch);
 }
 
 void reftable_record_release(struct reftable_record *rec)
diff --git a/reftable/record.h b/reftable/record.h
index 5e8304e052..826ee1c55c 100644
--- a/reftable/record.h
+++ b/reftable/record.h
@@ -55,7 +55,8 @@ struct reftable_record_vtable {
 
 	/* decode data from `src` into the record. */
 	int (*decode)(void *rec, struct strbuf key, uint8_t extra,
-		      struct string_view src, int hash_size);
+		      struct string_view src, int hash_size,
+		      struct strbuf *scratch);
 
 	/* deallocate and null the record. */
 	void (*release)(void *rec);
@@ -138,7 +139,7 @@ int reftable_record_encode(struct reftable_record *rec, struct string_view dest,
 			   int hash_size);
 int reftable_record_decode(struct reftable_record *rec, struct strbuf key,
 			   uint8_t extra, struct string_view src,
-			   int hash_size);
+			   int hash_size, struct strbuf *scratch);
 int reftable_record_is_deletion(struct reftable_record *rec);
 
 static inline uint8_t reftable_record_type(struct reftable_record *rec)
diff --git a/reftable/record_test.c b/reftable/record_test.c
index 89209894d8..c158ee79ff 100644
--- a/reftable/record_test.c
+++ b/reftable/record_test.c
@@ -99,6 +99,7 @@ static void set_hash(uint8_t *h, int j)
 
 static void test_reftable_ref_record_roundtrip(void)
 {
+	struct strbuf scratch = STRBUF_INIT;
 	int i = 0;
 
 	for (i = REFTABLE_REF_DELETION; i < REFTABLE_NR_REF_VALUETYPES; i++) {
@@ -140,7 +141,7 @@ static void test_reftable_ref_record_roundtrip(void)
 		EXPECT(n > 0);
 
 		/* decode into a non-zero reftable_record to test for leaks. */
-		m = reftable_record_decode(&out, key, i, dest, GIT_SHA1_RAWSZ);
+		m = reftable_record_decode(&out, key, i, dest, GIT_SHA1_RAWSZ, &scratch);
 		EXPECT(n == m);
 
 		EXPECT(reftable_ref_record_equal(&in.u.ref, &out.u.ref,
@@ -150,6 +151,8 @@ static void test_reftable_ref_record_roundtrip(void)
 		strbuf_release(&key);
 		reftable_record_release(&out);
 	}
+
+	strbuf_release(&scratch);
 }
 
 static void test_reftable_log_record_equal(void)
@@ -175,7 +178,6 @@ static void test_reftable_log_record_equal(void)
 static void test_reftable_log_record_roundtrip(void)
 {
 	int i;
-
 	struct reftable_log_record in[] = {
 		{
 			.refname = xstrdup("refs/heads/master"),
@@ -183,8 +185,6 @@ static void test_reftable_log_record_roundtrip(void)
 			.value_type = REFTABLE_LOG_UPDATE,
 			.value = {
 				.update = {
-					.old_hash = reftable_malloc(GIT_SHA1_RAWSZ),
-					.new_hash = reftable_malloc(GIT_SHA1_RAWSZ),
 					.name = xstrdup("han-wen"),
 					.email = xstrdup("hanwen@google.com"),
 					.message = xstrdup("test"),
@@ -202,15 +202,10 @@ static void test_reftable_log_record_roundtrip(void)
 			.refname = xstrdup("branch"),
 			.update_index = 33,
 			.value_type = REFTABLE_LOG_UPDATE,
-			.value = {
-				.update = {
-					.old_hash = reftable_malloc(GIT_SHA1_RAWSZ),
-					.new_hash = reftable_malloc(GIT_SHA1_RAWSZ),
-					/* rest of fields left empty. */
-				},
-			},
 		}
 	};
+	struct strbuf scratch = STRBUF_INIT;
+
 	set_test_hash(in[0].value.update.new_hash, 1);
 	set_test_hash(in[0].value.update.old_hash, 2);
 	set_test_hash(in[2].value.update.new_hash, 3);
@@ -231,8 +226,6 @@ static void test_reftable_log_record_roundtrip(void)
 				.value_type = REFTABLE_LOG_UPDATE,
 				.value = {
 					.update = {
-						.new_hash = reftable_calloc(GIT_SHA1_RAWSZ, 1),
-						.old_hash = reftable_calloc(GIT_SHA1_RAWSZ, 1),
 						.name = xstrdup("old name"),
 						.email = xstrdup("old@email"),
 						.message = xstrdup("old message"),
@@ -252,7 +245,7 @@ static void test_reftable_log_record_roundtrip(void)
 		EXPECT(n >= 0);
 		valtype = reftable_record_val_type(&rec);
 		m = reftable_record_decode(&out, key, valtype, dest,
-					   GIT_SHA1_RAWSZ);
+					   GIT_SHA1_RAWSZ, &scratch);
 		EXPECT(n == m);
 
 		EXPECT(reftable_log_record_equal(&in[i], &out.u.log,
@@ -261,6 +254,8 @@ static void test_reftable_log_record_roundtrip(void)
 		strbuf_release(&key);
 		reftable_record_release(&out);
 	}
+
+	strbuf_release(&scratch);
 }
 
 static void test_u24_roundtrip(void)
@@ -310,23 +305,27 @@ static void test_reftable_obj_record_roundtrip(void)
 {
 	uint8_t testHash1[GIT_SHA1_RAWSZ] = { 1, 2, 3, 4, 0 };
 	uint64_t till9[] = { 1, 2, 3, 4, 500, 600, 700, 800, 9000 };
-	struct reftable_obj_record recs[3] = { {
-						       .hash_prefix = testHash1,
-						       .hash_prefix_len = 5,
-						       .offsets = till9,
-						       .offset_len = 3,
-					       },
-					       {
-						       .hash_prefix = testHash1,
-						       .hash_prefix_len = 5,
-						       .offsets = till9,
-						       .offset_len = 9,
-					       },
-					       {
-						       .hash_prefix = testHash1,
-						       .hash_prefix_len = 5,
-					       } };
+	struct reftable_obj_record recs[3] = {
+		{
+			.hash_prefix = testHash1,
+			.hash_prefix_len = 5,
+			.offsets = till9,
+			.offset_len = 3,
+		},
+		{
+			.hash_prefix = testHash1,
+			.hash_prefix_len = 5,
+			.offsets = till9,
+			.offset_len = 9,
+		},
+		{
+			.hash_prefix = testHash1,
+			.hash_prefix_len = 5,
+		},
+	};
+	struct strbuf scratch = STRBUF_INIT;
 	int i = 0;
+
 	for (i = 0; i < ARRAY_SIZE(recs); i++) {
 		uint8_t buffer[1024] = { 0 };
 		struct string_view dest = {
@@ -350,13 +349,15 @@ static void test_reftable_obj_record_roundtrip(void)
 		EXPECT(n > 0);
 		extra = reftable_record_val_type(&in);
 		m = reftable_record_decode(&out, key, extra, dest,
-					   GIT_SHA1_RAWSZ);
+					   GIT_SHA1_RAWSZ, &scratch);
 		EXPECT(n == m);
 
 		EXPECT(reftable_record_equal(&in, &out, GIT_SHA1_RAWSZ));
 		strbuf_release(&key);
 		reftable_record_release(&out);
 	}
+
+	strbuf_release(&scratch);
 }
 
 static void test_reftable_index_record_roundtrip(void)
@@ -373,6 +374,7 @@ static void test_reftable_index_record_roundtrip(void)
 		.buf = buffer,
 		.len = sizeof(buffer),
 	};
+	struct strbuf scratch = STRBUF_INIT;
 	struct strbuf key = STRBUF_INIT;
 	struct reftable_record out = {
 		.type = BLOCK_TYPE_INDEX,
@@ -390,13 +392,15 @@ static void test_reftable_index_record_roundtrip(void)
 	EXPECT(n > 0);
 
 	extra = reftable_record_val_type(&in);
-	m = reftable_record_decode(&out, key, extra, dest, GIT_SHA1_RAWSZ);
+	m = reftable_record_decode(&out, key, extra, dest, GIT_SHA1_RAWSZ,
+				   &scratch);
 	EXPECT(m == n);
 
 	EXPECT(reftable_record_equal(&in, &out, GIT_SHA1_RAWSZ));
 
 	reftable_record_release(&out);
 	strbuf_release(&key);
+	strbuf_release(&scratch);
 	strbuf_release(&in.u.idx.last_key);
 }
 
diff --git a/reftable/reftable-record.h b/reftable/reftable-record.h
index e657001d42..2a2943cd13 100644
--- a/reftable/reftable-record.h
+++ b/reftable/reftable-record.h
@@ -74,6 +74,7 @@ int reftable_ref_record_equal(const struct reftable_ref_record *a,
 /* reftable_log_record holds a reflog entry */
 struct reftable_log_record {
 	char *refname;
+	size_t refname_cap;
 	uint64_t update_index; /* logical timestamp of a transactional update.
 				*/
 
@@ -88,13 +89,14 @@ struct reftable_log_record {
 
 	union {
 		struct {
-			uint8_t *new_hash;
-			uint8_t *old_hash;
+			unsigned char new_hash[GIT_MAX_RAWSZ];
+			unsigned char old_hash[GIT_MAX_RAWSZ];
 			char *name;
 			char *email;
 			uint64_t time;
 			int16_t tz_offset;
 			char *message;
+			size_t message_cap;
 		} update;
 	} value;
 };
diff --git a/reftable/stack_test.c b/reftable/stack_test.c
index 509f486623..7336757cf5 100644
--- a/reftable/stack_test.c
+++ b/reftable/stack_test.c
@@ -468,8 +468,6 @@ static void test_reftable_stack_add(void)
 		logs[i].refname = xstrdup(buf);
 		logs[i].update_index = N + i + 1;
 		logs[i].value_type = REFTABLE_LOG_UPDATE;
-
-		logs[i].value.update.new_hash = reftable_malloc(GIT_SHA1_RAWSZ);
 		logs[i].value.update.email = xstrdup("identity@invalid");
 		set_test_hash(logs[i].value.update.new_hash, i);
 	}
@@ -547,16 +545,17 @@ static void test_reftable_stack_log_normalize(void)
 	};
 	struct reftable_stack *st = NULL;
 	char *dir = get_tmp_dir(__LINE__);
-
-	uint8_t h1[GIT_SHA1_RAWSZ] = { 0x01 }, h2[GIT_SHA1_RAWSZ] = { 0x02 };
-
-	struct reftable_log_record input = { .refname = "branch",
-					     .update_index = 1,
-					     .value_type = REFTABLE_LOG_UPDATE,
-					     .value = { .update = {
-								.new_hash = h1,
-								.old_hash = h2,
-							} } };
+	struct reftable_log_record input = {
+		.refname = "branch",
+		.update_index = 1,
+		.value_type = REFTABLE_LOG_UPDATE,
+		.value = {
+			.update = {
+				.new_hash = { 1 },
+				.old_hash = { 2 },
+			},
+		},
+	};
 	struct reftable_log_record dest = {
 		.update_index = 0,
 	};
@@ -627,8 +626,6 @@ static void test_reftable_stack_tombstone(void)
 		logs[i].update_index = 42;
 		if (i % 2 == 0) {
 			logs[i].value_type = REFTABLE_LOG_UPDATE;
-			logs[i].value.update.new_hash =
-				reftable_malloc(GIT_SHA1_RAWSZ);
 			set_test_hash(logs[i].value.update.new_hash, i);
 			logs[i].value.update.email =
 				xstrdup("identity@invalid");
@@ -810,7 +807,6 @@ static void test_reflog_expire(void)
 		logs[i].update_index = i;
 		logs[i].value_type = REFTABLE_LOG_UPDATE;
 		logs[i].value.update.time = i;
-		logs[i].value.update.new_hash = reftable_malloc(GIT_SHA1_RAWSZ);
 		logs[i].value.update.email = xstrdup("identity@invalid");
 		set_test_hash(logs[i].value.update.new_hash, i);
 	}