@@ -1592,7 +1592,6 @@ static int write_partial_message_data(struct ceph_connection *con)
struct page *page;
size_t page_offset;
size_t length;
- bool last_piece;
int ret;
if (!cursor->resid) {
@@ -1600,10 +1599,9 @@ static int write_partial_message_data(struct ceph_connection *con)
continue;
}
- page = ceph_msg_data_next(cursor, &page_offset, &length,
- &last_piece);
- ret = ceph_tcp_sendpage(con->sock, page, page_offset,
- length, !last_piece);
+ page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
+ ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
+ true);
if (ret <= 0) {
if (do_datacrc)
msg->footer.data_crc = cpu_to_le32(crc);
last_piece is for the last piece in the current data item, not in the entire data payload of the message. This is harmful for messages with multiple data items. On top of that, we don't need to signal the end of a data payload either because it is always followed by a footer. We used to signal "more" unconditionally, until commit fe38a2b67bc6 ("libceph: start defining message data cursor"). Part of a large series, it introduced cursor->last_piece and also mistakenly inverted the hint by passing last_piece for "more". This was corrected with commit c2cfa1940097 ("libceph: Fix ceph_tcp_sendpage()'s more boolean usage"). As it is, last_piece is not helping at all: because Nagle algorithm is disabled, for a simple message with two 512-byte data items we end up emitting three packets: front + first data item, second data item and footer. Go back to the original pre-fe38a2b67bc6 behavior -- a single packet in most cases. Signed-off-by: Ilya Dryomov <idryomov@gmail.com> --- net/ceph/messenger.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)