reftable/record: use scratch buffer when decoding records

When decoding log records we need a temporary buffer to decode the
reflog entry's name, mail address and message. As this buffer is local
to the function we thus have to reallocate it for every single log
record which we're about to decode, which is inefficient.

Refactor the code such that callers need to pass in a scratch buffer,
which allows us to reuse it for multiple decodes. This reduces the
number of allocations when iterating through reflogs. Before:

    HEAP SUMMARY:
        in use at exit: 13,473 bytes in 122 blocks
      total heap usage: 2,068,487 allocs, 2,068,365 frees, 305,122,946 bytes allocated

After:

    HEAP SUMMARY:
        in use at exit: 13,473 bytes in 122 blocks
      total heap usage: 1,068,485 allocs, 1,068,363 frees, 281,122,886 bytes allocated

Note that this commit also drop some redundant calls to `strbuf_reset()`
right before calling `decode_string()`. The latter already knows to
reset the buffer, so there is no need for these.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 24 insertions, 28 deletions

diff --git a/reftable/record.c b/reftable/record.c
index 7c86877586..060244337f 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;
@@ -849,13 +848,12 @@ 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)
@@ -892,7 +890,7 @@ static int reftable_log_record_decode(void *rec, struct strbuf key,
 
 	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);
@@ -904,26 +902,25 @@ static int reftable_log_record_decode(void *rec, struct strbuf key,
 	 * skip copying over the name in case it's accurate already.
 	 */
 	if (!r->value.update.name ||
-	    strcmp(r->value.update.name, dest.buf)) {
+	    strcmp(r->value.update.name, scratch->buf)) {
 		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;
+			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);
 
 	/* Same as above, but for the reflog email. */
 	if (!r->value.update.email ||
-	    strcmp(r->value.update.email, dest.buf)) {
+	    strcmp(r->value.update.email, scratch->buf)) {
 		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;
+			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;
@@ -938,22 +935,19 @@ 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);
 
-	REFTABLE_ALLOC_GROW(r->value.update.message, dest.len + 1,
+	REFTABLE_ALLOC_GROW(r->value.update.message, scratch->len + 1,
 			    r->value.update.message_cap);
-	memcpy(r->value.update.message, dest.buf, dest.len);
-	r->value.update.message[dest.len] = 0;
+	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;
 }
 
@@ -1093,7 +1087,7 @@ 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;
@@ -1174,10 +1168,12 @@ 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)