On 07/09/2014 04:29 AM, David Laight wrote:
> If MSG_MORE is set then buffer sends as if Nagle were enabled.
> The first data chunk is still sent on its own, but subsequent chunks
> will be bundled and full packets sent.
> Full MSG_MORE support would require a timout (preferably configurable
> per-socket) to send the last chunk(s), instead of sending them
> when there is nothing outstanding.
>
> Signed-off-by: David Laight <david.laight@xxxxxxxxxx>
> ---
> include/net/sctp/structs.h | 6 +++++-
> net/sctp/output.c | 12 ++++++++++--
> net/sctp/socket.c | 18 +++++++++++++++---
> 3 files changed, 30 insertions(+), 6 deletions(-)
>
> diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
> index 0dfcc92..629346f 100644
> --- a/include/net/sctp/structs.h
> +++ b/include/net/sctp/structs.h
> @@ -209,7 +209,11 @@ struct sctp_sock {
> struct sctp_assocparams assocparams;
> int user_frag;
> __u32 autoclose;
> - __u8 nodelay;
> +
> +#define SCTP_F_TX_NODELAY 0
> +#define SCTP_F_TX_NAGLE 1 /* SCTP_NODELAY not set */
> +#define SCTP_F_TX_MSG_MORE 2 /* MSG_MORE set on last send */
> + __u8 tx_delay;
> __u8 disable_fragments;
> __u8 v4mapped;
> __u8 frag_interleave;
> diff --git a/net/sctp/output.c b/net/sctp/output.c
> index 7f28a8e..df7889c 100644
> --- a/net/sctp/output.c
> +++ b/net/sctp/output.c
> @@ -679,14 +679,22 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
> flight_size >= transport->cwnd)
> return SCTP_XMIT_RWND_FULL;
>
> + /* If MSG_MORE is set we probably shouldn't create a new message.
> + * However unless we also implement a timeout (preferable settable
> + * as a socket option) then data could easily be left unsent.
> + * Instead we ignore MSG_MORE on the first data chunk.
> + * This makes the implementation of MSG_MORE the same as the
> + * implementation of Nagle.
> + */
> +
> /* Nagle's algorithm to solve small-packet problem:
> * Inhibit the sending of new chunks when new outgoing data arrives
> * if any previously transmitted data on the connection remains
> * unacknowledged.
> */
>
> - if (sctp_sk(asoc->base.sk)->nodelay)
> - /* Nagle disabled */
> + if (sctp_sk(asoc->base.sk)->tx_delay == SCTP_F_TX_NODELAY)
> + /* Nagle disabled and MSG_MORE unset */
> return SCTP_XMIT_OK;
>
> if (!sctp_packet_empty(packet))
> diff --git a/net/sctp/socket.c b/net/sctp/socket.c
> index fee06b9..4a9f760 100644
> --- a/net/sctp/socket.c
> +++ b/net/sctp/socket.c
> @@ -1927,6 +1927,18 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk,
> pr_debug("%s: we associated primitively\n", __func__);
> }
>
> + /* Setting MSG_MORE currently has the same effect as enabling Nagle.
> + * This means that the user can't force bundling of the first two data
> + * chunks. It does mean that all the data chunks will be sent
> + * without an extra timer.
> + * It is enough to save the last value since any data sent with
> + * MSG_MORE clear will already have been sent (subject to flow control).
> + */
> + if (msg->msg_flags & MSG_MORE)
> + sp->tx_delay |= SCTP_F_TX_MSG_MORE;
> + else
> + sp->tx_delay &= ~SCTP_F_TX_MSG_MORE;
> +
This is ok for 1-1 sockets, but it doesn't really work for 1-many sockets. If one of
the associations uses MSG_MORE while another does not, we'll see some interesting
side-effects on the wire.
-vlad
> /* Break the message into multiple chunks of maximum size. */
> datamsg = sctp_datamsg_from_user(asoc, sinfo, msg, msg_len);
> if (IS_ERR(datamsg)) {
> @@ -2821,7 +2833,7 @@ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval,
> if (get_user(val, (int __user *)optval))
> return -EFAULT;
>
> - sctp_sk(sk)->nodelay = (val == 0) ? 0 : 1;
> + sctp_sk(sk)->tx_delay = val == 0 ? SCTP_F_TX_NAGLE : SCTP_F_TX_NODELAY;
> return 0;
> }
>
> @@ -3968,7 +3980,7 @@ static int sctp_init_sock(struct sock *sk)
> sp->disable_fragments = 0;
>
> /* Enable Nagle algorithm by default. */
> - sp->nodelay = 0;
> + sp->tx_delay = SCTP_F_TX_NAGLE;
>
> /* Enable by default. */
> sp->v4mapped = 1;
> @@ -5020,7 +5032,7 @@ static int sctp_getsockopt_nodelay(struct sock *sk, int len,
> return -EINVAL;
>
> len = sizeof(int);
> - val = (sctp_sk(sk)->nodelay == 1);
> + val = sctp_sk(sk)->tx_delay & SCTP_F_TX_NAGLE ? 0 : 1;
> if (put_user(len, optlen))
> return -EFAULT;
> if (copy_to_user(optval, &val, len))
>
--
To unsubscribe from this list: send the line "unsubscribe linux-sctp" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
