From eed530b6c67624db3f2cf477bac7c4d005d8f7ba Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 2 May 2012 13:30:03 +0000 Subject: tcp: early retransmit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch implements RFC 5827 early retransmit (ER) for TCP. It reduces DUPACK threshold (dupthresh) if outstanding packets are less than 4 to recover losses by fast recovery instead of timeout. While the algorithm is simple, small but frequent network reordering makes this feature dangerous: the connection repeatedly enter false recovery and degrade performance. Therefore we implement a mitigation suggested in the appendix of the RFC that delays entering fast recovery by a small interval, i.e., RTT/4. Currently ER is conservative and is disabled for the rest of the connection after the first reordering event. A large scale web server experiment on the performance impact of ER is summarized in section 6 of the paper "Proportional Rate Reduction for TCP”, IMC 2011. http://conferences.sigcomm.org/imc/2011/docs/p155.pdf Note that Linux has a similar feature called THIN_DUPACK. The differences are THIN_DUPACK do not mitigate reorderings and is only used after slow start. Currently ER is disabled if THIN_DUPACK is enabled. I would be happy to merge THIN_DUPACK feature with ER if people think it's a good idea. ER is enabled by sysctl_tcp_early_retrans: 0: Disables ER 1: Reduce dupthresh to packets_out - 1 when outstanding packets < 4. 2: (Default) reduce dupthresh like mode 1. In addition, delay entering fast recovery by RTT/4. Note: mode 2 is implemented in the third part of this patch series. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 0fb84de6da3..685437a16c9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -252,6 +252,7 @@ extern int sysctl_tcp_max_ssthresh; extern int sysctl_tcp_cookie_size; extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; +extern int sysctl_tcp_early_retrans; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -797,6 +798,20 @@ static inline void tcp_enable_fack(struct tcp_sock *tp) tp->rx_opt.sack_ok |= TCP_FACK_ENABLED; } +/* TCP early-retransmit (ER) is similar to but more conservative than + * the thin-dupack feature. Enable ER only if thin-dupack is disabled. + */ +static inline void tcp_enable_early_retrans(struct tcp_sock *tp) +{ + tp->do_early_retrans = sysctl_tcp_early_retrans && + !sysctl_tcp_thin_dupack && sysctl_tcp_reordering == 3; +} + +static inline void tcp_disable_early_retrans(struct tcp_sock *tp) +{ + tp->do_early_retrans = 0; +} + static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; -- cgit v1.2.2