From 12d50c46dc0f7fd2e625c4befaa5fa5740a7a594 Mon Sep 17 00:00:00 2001 From: Krishna Kumar Date: Tue, 8 Dec 2009 22:26:13 +0000 Subject: tcp: Remove check in __tcp_push_pending_frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tcp_push checks tcp_send_head and calls __tcp_push_pending_frames, which again checks tcp_send_head, and this unnecessary check is done for every other caller of __tcp_push_pending_frames. Remove tcp_send_head check in __tcp_push_pending_frames and add the check to tcp_push_pending_frames. Other functions call __tcp_push_pending_frames only when tcp_send_head would evaluate to true. Signed-off-by: Krishna Kumar Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 34f5cc24d903..185e22baecb1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -856,13 +856,6 @@ static inline void tcp_check_probe_timer(struct sock *sk) icsk->icsk_rto, TCP_RTO_MAX); } -static inline void tcp_push_pending_frames(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); -} - static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; @@ -1342,6 +1335,15 @@ static inline int tcp_write_queue_empty(struct sock *sk) return skb_queue_empty(&sk->sk_write_queue); } +static inline void tcp_push_pending_frames(struct sock *sk) +{ + if (tcp_send_head(sk)) { + struct tcp_sock *tp = tcp_sk(sk); + + __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); + } +} + /* Start sequence of the highest skb with SACKed bit, valid only if * sacked > 0 or when the caller has ensured validity by itself. */ -- cgit v1.2.3 From 31d12926e37291970dd4f6e9940df3897766a81d Mon Sep 17 00:00:00 2001 From: laurent chavey Date: Tue, 15 Dec 2009 11:15:28 +0000 Subject: net: Add rtnetlink init_rcvwnd to set the TCP initial receive window Add rtnetlink init_rcvwnd to set the TCP initial receive window size advertised by passive and active TCP connections. The current Linux TCP implementation limits the advertised TCP initial receive window to the one prescribed by slow start. For short lived TCP connections used for transaction type of traffic (i.e. http requests), bounding the advertised TCP initial receive window results in increased latency to complete the transaction. Support for setting initial congestion window is already supported using rtnetlink init_cwnd, but the feature is useless without the ability to set a larger TCP initial receive window. The rtnetlink init_rcvwnd allows increasing the TCP initial receive window, allowing TCP connection to advertise larger TCP receive window than the ones bounded by slow start. Signed-off-by: Laurent Chavey Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 185e22baecb1..788c99f98597 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -965,7 +965,8 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) /* Determine a window scaling and initial window to offer. */ extern void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, - int wscale_ok, __u8 *rcv_wscale); + int wscale_ok, __u8 *rcv_wscale, + __u32 init_rcv_wnd); static inline int tcp_win_from_space(int space) { -- cgit v1.2.3 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 --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 788c99f98597..87d164b9bd8f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -400,6 +400,8 @@ extern int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); extern void tcp_set_keepalive(struct sock *sk, int val); +extern void tcp_syn_ack_timeout(struct sock *sk, + struct request_sock *req); extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int nonblock, -- cgit v1.2.3 From 7d720c3e4f0c4fc152a6bf17e24244a3c85412d2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Feb 2010 15:20:26 +0000 Subject: percpu: add __percpu sparse annotations to net Add __percpu sparse annotations to net. These annotations are to make sparse consider percpu variables to be in a different address space and warn if accessed without going through percpu accessors. This patch doesn't affect normal builds. The macro and type tricks around snmp stats make things a bit interesting. DEFINE/DECLARE_SNMP_STAT() macros mark the target field as __percpu and SNMP_UPD_PO_STATS() macro is updated accordingly. All snmp_mib_*() users which used to cast the argument to (void **) are updated to cast it to (void __percpu **). Signed-off-by: Tejun Heo Acked-by: David S. Miller Cc: Patrick McHardy Cc: Arnaldo Carvalho de Melo Cc: Vlad Yasevich Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 87d164b9bd8f..75a00c80bdda 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1189,7 +1189,7 @@ extern int tcp_v4_md5_do_del(struct sock *sk, #define tcp_twsk_md5_key(twsk) NULL #endif -extern struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(struct sock *); +extern struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *); extern void tcp_free_md5sig_pool(void); extern struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu); -- cgit v1.2.3 From 5aa4b32fc86408705337e941ed716880c63d1590 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Thu, 18 Feb 2010 02:45:45 +0000 Subject: net: TCP thin-stream detection Inline function to dynamically detect thin streams based on the number of packets in flight. Used to dynamically trigger thin-stream mechanisms if enabled by ioctl or sysctl. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 75a00c80bdda..0bdc3f640247 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1386,6 +1386,14 @@ static inline void tcp_highest_sack_combine(struct sock *sk, tcp_sk(sk)->highest_sack = new; } +/* Determines whether this is a thin stream (which may suffer from + * increased latency). Used to trigger latency-reducing mechanisms. + */ +static inline unsigned int tcp_stream_is_thin(struct tcp_sock *tp) +{ + return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); +} + /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, -- 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 --- include/net/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 0bdc3f640247..6278fc734abd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ +/* TCP thin-stream limits */ +#define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -241,6 +244,7 @@ extern int sysctl_tcp_workaround_signed_windows; extern int sysctl_tcp_slow_start_after_idle; extern int sysctl_tcp_max_ssthresh; extern int sysctl_tcp_cookie_size; +extern int sysctl_tcp_thin_linear_timeouts; extern atomic_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; -- cgit v1.2.3 From 7e38017557bc0b87434d184f8804cadb102bb903 Mon Sep 17 00:00:00 2001 From: Andreas Petlund Date: Thu, 18 Feb 2010 04:48:19 +0000 Subject: net: TCP thin dupack This patch enables fast retransmissions after one dupACK for TCP if the stream is identified as thin. This will reduce latencies for thin streams that are not able to trigger fast retransmissions due to high packet interarrival time. This mechanism is only active if enabled by iocontrol or syscontrol and the stream is identified as thin. Signed-off-by: Andreas Petlund Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6278fc734abd..56f0aec40ed6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -245,6 +245,7 @@ extern int sysctl_tcp_slow_start_after_idle; 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 atomic_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; -- cgit v1.2.3