From 5d134f1c1f36166e8a738de92c4d2f4c262ff91b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 5 Jan 2013 16:10:48 +0000 Subject: tcp: make sysctl_tcp_ecn namespace aware As per suggestion from Eric Dumazet this patch makes tcp_ecn sysctl namespace aware. The reason behind this patch is to ease the testing of ecn problems on the internet and allows applications to tune their own use of ecn. Cc: Eric Dumazet Cc: David Miller Cc: Stephen Hemminger Signed-off-by: Hannes Frederic Sowa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index aed42c785153..614af8b7758e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -266,7 +266,6 @@ extern int sysctl_tcp_abort_on_overflow; extern int sysctl_tcp_max_orphans; extern int sysctl_tcp_fack; extern int sysctl_tcp_reordering; -extern int sysctl_tcp_ecn; extern int sysctl_tcp_dsack; extern int sysctl_tcp_wmem[3]; extern int sysctl_tcp_rmem[3]; @@ -504,7 +503,8 @@ static inline __u32 cookie_v4_init_sequence(struct sock *sk, #endif extern __u32 cookie_init_timestamp(struct request_sock *req); -extern bool cookie_check_timestamp(struct tcp_options_received *opt, bool *); +extern bool cookie_check_timestamp(struct tcp_options_received *opt, + struct net *net, bool *ecn_ok); /* From net/ipv6/syncookies.c */ extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); @@ -728,11 +728,12 @@ struct tcp_skb_cb { * notifications, we disable TCP ECN negociation. */ static inline void -TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb) +TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb, + struct net *net) { const struct tcphdr *th = tcp_hdr(skb); - if (sysctl_tcp_ecn && th->ece && th->cwr && + if (net->ipv4.sysctl_tcp_ecn && th->ece && th->cwr && INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield)) inet_rsk(req)->ecn_ok = 1; } -- cgit v1.2.3 From ca2eb5679f8ddffff60156af42595df44a315ef0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 5 Feb 2013 07:25:17 +0000 Subject: tcp: remove Appropriate Byte Count support TCP Appropriate Byte Count was added by me, but later disabled. There is no point in maintaining it since it is a potential source of bugs and Linux already implements other better window protection heuristics. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 614af8b7758e..23f2e98d4b65 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -279,7 +279,6 @@ extern int sysctl_tcp_dma_copybreak; extern int sysctl_tcp_nometrics_save; extern int sysctl_tcp_moderate_rcvbuf; extern int sysctl_tcp_tso_win_divisor; -extern int sysctl_tcp_abc; extern int sysctl_tcp_mtu_probing; extern int sysctl_tcp_base_mss; extern int sysctl_tcp_workaround_signed_windows; -- cgit v1.2.3 From 79ffef1fe213851f44bfccf037170a140e929f85 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 27 Feb 2013 07:05:03 +0000 Subject: tcp: avoid wakeups for pure ACK TCP prequeue mechanism purpose is to let incoming packets being processed by the thread currently blocked in tcp_recvmsg(), instead of behalf of the softirq handler, to better adapt flow control on receiver host capacity to schedule the consumer. But in typical request/answer workloads, we send request, then block to receive the answer. And before the actual answer, TCP stack receives the ACK packets acknowledging the request. Processing pure ACK on behalf of the thread blocked in tcp_recvmsg() is a waste of resources, as thread has to immediately sleep again because it got no payload. This patch avoids the extra context switches and scheduler overhead. Before patch : a:~# echo 0 >/proc/sys/net/ipv4/tcp_low_latency a:~# perf stat ./super_netperf 300 -t TCP_RR -l 10 -H 7.7.7.84 -- -r 8k,8k 231676 Performance counter stats for './super_netperf 300 -t TCP_RR -l 10 -H 7.7.7.84 -- -r 8k,8k': 116251.501765 task-clock # 11.369 CPUs utilized 5,025,463 context-switches # 0.043 M/sec 1,074,511 CPU-migrations # 0.009 M/sec 216,923 page-faults # 0.002 M/sec 311,636,972,396 cycles # 2.681 GHz 260,507,138,069 stalled-cycles-frontend # 83.59% frontend cycles idle 155,590,092,840 stalled-cycles-backend # 49.93% backend cycles idle 100,101,255,411 instructions # 0.32 insns per cycle # 2.60 stalled cycles per insn 16,535,930,999 branches # 142.243 M/sec 646,483,591 branch-misses # 3.91% of all branches 10.225482774 seconds time elapsed After patch : a:~# echo 0 >/proc/sys/net/ipv4/tcp_low_latency a:~# perf stat ./super_netperf 300 -t TCP_RR -l 10 -H 7.7.7.84 -- -r 8k,8k 233297 Performance counter stats for './super_netperf 300 -t TCP_RR -l 10 -H 7.7.7.84 -- -r 8k,8k': 91084.870855 task-clock # 8.887 CPUs utilized 2,485,916 context-switches # 0.027 M/sec 815,520 CPU-migrations # 0.009 M/sec 216,932 page-faults # 0.002 M/sec 245,195,022,629 cycles # 2.692 GHz 202,635,777,041 stalled-cycles-frontend # 82.64% frontend cycles idle 124,280,372,407 stalled-cycles-backend # 50.69% backend cycles idle 83,457,289,618 instructions # 0.34 insns per cycle # 2.43 stalled cycles per insn 13,431,472,361 branches # 147.461 M/sec 504,470,665 branch-misses # 3.76% of all branches 10.249594448 seconds time elapsed Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Tom Herbert Cc: Yuchung Cheng Cc: Andi Kleen 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 23f2e98d4b65..cf0694d4ad60 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1045,6 +1045,10 @@ static inline bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (sysctl_tcp_low_latency || !tp->ucopy.task) return false; + if (skb->len <= tcp_hdrlen(skb) && + skb_queue_len(&tp->ucopy.prequeue) == 0) + return false; + __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; if (tp->ucopy.memory > sk->sk_rcvbuf) { -- cgit v1.2.3