From f54b311142a92ea2e42598e347b84e1655caf8e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Dec 2013 22:36:05 -0800 Subject: tcp: auto corking With the introduction of TCP Small Queues, TSO auto sizing, and TCP pacing, we can implement Automatic Corking in the kernel, to help applications doing small write()/sendmsg() to TCP sockets. Idea is to change tcp_push() to check if the current skb payload is under skb optimal size (a multiple of MSS bytes) If under 'size_goal', and at least one packet is still in Qdisc or NIC TX queues, set the TCP Small Queue Throttled bit, so that the push will be delayed up to TX completion time. This delay might allow the application to coalesce more bytes in the skb in following write()/sendmsg()/sendfile() system calls. The exact duration of the delay is depending on the dynamics of the system, and might be zero if no packet for this flow is actually held in Qdisc or NIC TX ring. Using FQ/pacing is a way to increase the probability of autocorking being triggered. Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control this feature and default it to 1 (enabled) Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking This counter is incremented every time we detected skb was under used and its flush was deferred. Tested: Interesting effects when using line buffered commands under ssh. Excellent performance results in term of cpu usage and total throughput. lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128 9410.39 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128': 35209.439626 task-clock # 2.901 CPUs utilized 2,294 context-switches # 0.065 K/sec 101 CPU-migrations # 0.003 K/sec 4,079 page-faults # 0.116 K/sec 97,923,241,298 cycles # 2.781 GHz [83.31%] 51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%] 25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%] 102,225,978,536 instructions # 1.04 insns per cycle # 0.51 stalled cycles per insn [83.38%] 18,657,696,819 branches # 529.906 M/sec [83.29%] 91,679,646 branch-misses # 0.49% of all branches [83.40%] 12.136204899 seconds time elapsed lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128 6624.89 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128': 40045.864494 task-clock # 3.301 CPUs utilized 171 context-switches # 0.004 K/sec 53 CPU-migrations # 0.001 K/sec 4,080 page-faults # 0.102 K/sec 111,340,458,645 cycles # 2.780 GHz [83.34%] 61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%] 29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%] 108,654,349,355 instructions # 0.98 insns per cycle # 0.57 stalled cycles per insn [83.34%] 19,552,170,748 branches # 488.244 M/sec [83.34%] 157,875,417 branch-misses # 0.81% of all branches [83.34%] 12.130267788 seconds time elapsed Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/sysctl_net_ipv4.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3d69ec8dac57..38c8ec90ff68 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -732,6 +732,15 @@ static struct ctl_table ipv4_table[] = { .extra1 = &zero, .extra2 = &gso_max_segs, }, + { + .procname = "tcp_autocorking", + .data = &sysctl_tcp_autocorking, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, { .procname = "udp_mem", .data = &sysctl_udp_mem, -- cgit v1.2.3 From 974eda11c54290a1be8f8b155edae7d791e5ce57 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 14 Dec 2013 05:13:38 +0100 Subject: inet: make no_pmtu_disc per namespace and kill ipv4_config The other field in ipv4_config, log_martians, was converted to a per-interface setting, so we can just remove the whole structure. Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 38c8ec90ff68..d7b63a614454 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -285,13 +285,6 @@ static struct ctl_table ipv4_table[] = { .extra1 = &ip_ttl_min, .extra2 = &ip_ttl_max, }, - { - .procname = "ip_no_pmtu_disc", - .data = &ipv4_config.no_pmtu_disc, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "ip_nonlocal_bind", .data = &sysctl_ip_nonlocal_bind, @@ -831,6 +824,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = ipv4_local_port_range, }, + { + .procname = "ip_no_pmtu_disc", + .data = &init_net.ipv4.sysctl_ip_no_pmtu_disc, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; -- cgit v1.2.3 From 5797deb657b9bec41214b50eaa3e2c4feb4b7d8d Mon Sep 17 00:00:00 2001 From: Weilong Chen Date: Mon, 23 Dec 2013 14:37:31 +0800 Subject: ipv4: ERROR: code indent should use tabs where possible Signed-off-by: Weilong Chen Signed-off-by: David S. Miller --- net/ipv4/sysctl_net_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d7b63a614454..1d2480ac2bb6 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -700,7 +700,7 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { + { .procname = "tcp_thin_dupack", .data = &sysctl_tcp_thin_dupack, .maxlen = sizeof(int), -- cgit v1.2.3 From f87c10a8aa1e82498c42d0335524d6ae7cf5a52b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Thu, 9 Jan 2014 10:01:15 +0100 Subject: ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing While forwarding we should not use the protocol path mtu to calculate the mtu for a forwarded packet but instead use the interface mtu. We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was introduced for multicast forwarding. But as it does not conflict with our usage in unicast code path it is perfect for reuse. I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular dependencies because of IPSKB_FORWARDED. Because someone might have written a software which does probe destinations manually and expects the kernel to honour those path mtus I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone can disable this new behaviour. We also still use mtus which are locked on a route for forwarding. The reason for this change is, that path mtus information can be injected into the kernel via e.g. icmp_err protocol handler without verification of local sockets. As such, this could cause the IPv4 forwarding path to wrongfully emit fragmentation needed notifications or start to fragment packets along a path. Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED won't be set and further fragmentation logic will use the path mtu to determine the fragmentation size. They also recheck packet size with help of path mtu discovery and report appropriate errors. Cc: Eric Dumazet Cc: David Miller Cc: John Heffner Cc: Steffen Klassert Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/sysctl_net_ipv4.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1d2480ac2bb6..44eba052b43d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -831,6 +831,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_forward_use_pmtu", + .data = &init_net.ipv4.sysctl_ip_fwd_use_pmtu, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { } }; -- cgit v1.2.3