Re: [PATCH 1/1] net: tcp: RTO restart

[Bill Fink <billfink@mindspring.com>]

On Tue, 18 Feb 2014, Per Hurtig wrote:

> This patch implements the RTO restart modification described in
> http://tools.ietf.org/html/draft-ietf-tcpm-rtorestart-02
> 
> RTO Restart's goal is to provide quicker loss recovery for segments lost in the
> end of a burst/connection. To accomplish this the algorithm adjusts the RTO
> value on each rearm of the retransmission timer to be exactly RTO ms after the
> earliest outstanding segment was sent. The offsetting against the earliest
> outstanding segment is not done by the regular rearm algorithm, which causes
> RTOs to occur, on average, after RTO+RTT ms.
> 
> As a faster timeout is only beneficial in scenarios where fast retransmit/early
> retransmit cannot be triggered the algorithm will only kick in when there is a
> small amount of outstanding segments.
> 
> The RTO Restart proposal is accepted as a working group item in the IETF TCP
> Maintenance and Minor Extensions (tcpm) TCP wg and is intended for experimental
> RFC status.
> 
> Signed-off-by: Per Hurtig <per.hurtig@kau.se>
> ---
>  include/net/tcp.h          |    1 +
>  net/ipv4/sysctl_net_ipv4.c |    7 +++++++
>  net/ipv4/tcp_input.c       |   11 +++++++++++
>  3 files changed, 19 insertions(+)

This should also have a documentation update to ip-sysctl.txt.
A separate patch for the TCP(7) man page would also be useful
if the kernel patch is approved.

					-Bill



> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 56fc366..575e82a 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -278,6 +278,7 @@ extern int sysctl_tcp_slow_start_after_idle;
>  extern int sysctl_tcp_thin_linear_timeouts;
>  extern int sysctl_tcp_thin_dupack;
>  extern int sysctl_tcp_early_retrans;
> +extern int sysctl_tcp_rto_restart;
>  extern int sysctl_tcp_limit_output_bytes;
>  extern int sysctl_tcp_challenge_ack_limit;
>  extern unsigned int sysctl_tcp_notsent_lowat;
> diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
> index 44eba05..c605f4f 100644
> --- a/net/ipv4/sysctl_net_ipv4.c
> +++ b/net/ipv4/sysctl_net_ipv4.c
> @@ -717,6 +717,13 @@ static struct ctl_table ipv4_table[] = {
>  		.extra2		= &four,
>  	},
>  	{
> +		.procname	= "tcp_rto_restart",
> +		.data		= &sysctl_tcp_rto_restart,
> +		.maxlen		= sizeof(int),
> +		.mode		= 0644,
> +		.proc_handler	= proc_dointvec,
> +	},
> +	{
>  		.procname	= "tcp_min_tso_segs",
>  		.data		= &sysctl_tcp_min_tso_segs,
>  		.maxlen		= sizeof(int),
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index 227cba7..450ee30 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -98,6 +98,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
>  
>  int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
>  int sysctl_tcp_early_retrans __read_mostly = 3;
> +int sysctl_tcp_rto_restart __read_mostly = 1;
>  
>  #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
>  #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
> @@ -2972,6 +2973,16 @@ void tcp_rearm_rto(struct sock *sk)
>  			 */
>  			if (delta > 0)
>  				rto = delta;
> +		} else if (icsk->icsk_pending == ICSK_TIME_RETRANS &&
> +			   sysctl_tcp_rto_restart &&
> +			   sk->sk_send_head == NULL &&
> +			   tp->packets_out < 4) {
> +			struct sk_buff *skb = tcp_write_queue_head(sk);
> +			const u32 rto_time_stamp = TCP_SKB_CB(skb)->when;
> +			s32 delta = (s32)(tcp_time_stamp - rto_time_stamp);
> +
> +			if (delta > 0)
> +				rto -= delta;
>  		}
>  		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
>  					  TCP_RTO_MAX);
> -- 
> 1.7.9.5