From 72659ecce68588b74f6c46862c2b4cec137d7a5a Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Sun, 17 Jan 2010 19:09:39 -0800 Subject: tcp: account SYN-ACK timeouts & retransmissions Currently we don't increment SYN-ACK timeouts & retransmissions although we do increment the same stats for SYN. We seem to have lost the SYN-ACK accounting with the introduction of tcp_syn_recv_timer (commit 2248761e in the netdev-vger-cvs tree). This patch fixes this issue. In the process we also rename the v4/v6 syn/ack retransmit functions for clarity. We also add a new request_socket operations (syn_ack_timeout) so we can keep code in inet_connection_sock.c protocol agnostic. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8816a20c2597..de7d1bf9114f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -474,6 +474,12 @@ static void tcp_synack_timer(struct sock *sk) TCP_TIMEOUT_INIT, TCP_RTO_MAX); } +void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +{ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); +} +EXPORT_SYMBOL(tcp_syn_ack_timeout); + void tcp_set_keepalive(struct sock *sk, int val) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) -- cgit v1.2.3 From 3ad2f3fbb961429d2aa627465ae4829758bc7e07 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 3 Feb 2010 08:01:28 +0800 Subject: tree-wide: Assorted spelling fixes In particular, several occurances of funny versions of 'success', 'unknown', 'therefore', 'acknowledge', 'argument', 'achieve', 'address', 'beginning', 'desirable', 'separate' and 'necessary' are fixed. Signed-off-by: Daniel Mack Cc: Joe Perches Cc: Junio C Hamano Signed-off-by: Jiri Kosina --- net/ipv4/tcp_timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8816a20c2597..aff48d657181 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -133,7 +133,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } /* This function calculates a "timeout" which is equivalent to the timeout of a - * TCP connection after "boundary" unsucessful, exponentially backed-off + * TCP connection after "boundary" unsuccessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, -- cgit v1.2.3 From 36e31b0af58728071e8023cf8e20c5166b700717 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Thu, 18 Feb 2010 02:47:01 +0000 Subject: net: TCP thin linear timeouts This patch will make TCP use only linear timeouts if the stream is thin. This will help to avoid the very high latencies that thin stream suffer because of exponential backoff. This mechanism is only active if enabled by iocontrol or syscontrol and the stream is identified as thin. A maximum of 6 linear timeouts is tried before exponential backoff is resumed. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index de7d1bf9114f..a17629b8912e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -29,6 +29,7 @@ int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; int sysctl_tcp_orphan_retries __read_mostly; +int sysctl_tcp_thin_linear_timeouts __read_mostly; static void tcp_write_timer(unsigned long); static void tcp_delack_timer(unsigned long); @@ -415,7 +416,25 @@ void tcp_retransmit_timer(struct sock *sk) icsk->icsk_retransmits++; out_reset_timer: - icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); + /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is + * used to reset timer, set to 0. Recalculate 'icsk_rto' as this + * might be increased if the stream oscillates between thin and thick, + * thus the old value might already be too high compared to the value + * set by 'tcp_set_rto' in tcp_input.c which resets the rto without + * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating + * exponential backoff behaviour to avoid continue hammering + * linear-timeout retransmissions into a black hole + */ + if (sk->sk_state == TCP_ESTABLISHED && + (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) && + tcp_stream_is_thin(tp) && + icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { + icsk->icsk_backoff = 0; + icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); + } else { + /* Use normal (exponential) backoff */ + icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); + } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1)) __sk_dst_reset(sk); -- cgit v1.2.3