Repository files (latest commit first)

Filename	Latest commit message	Latest commit date
Eric Dumazet 50c8339e92 tcp: tso: restore IW10 after TSO autosizing ... With sysctl_tcp_min_tso_segs being 4, it is very possible that tcp_tso_should_defer() decides not sending last 2 MSS of initial window of 10 packets. This also applies if autosizing decides to send X MSS per GSO packet, and cwnd is not a multiple of X. This patch implements an heuristic based on age of first skb in write queue : If it was sent very recently (less than half srtt), we can predict that no ACK packet will come in less than half rtt, so deferring might cause an under utilization of our window. This is visible on initial send (IW10) on web servers, but more generally on some RPC, as the last part of the message might need an extra RTT to get delivered. Tested: Ran following packetdrill test // A simple server-side test that sends exactly an initial window (IW10) // worth of packets. `sysctl -e -q net.ipv4.tcp_min_tso_segs=4` 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +.1 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6> +.1 < . 1:1(0) ack 1 win 257 +0 accept(3, ..., ...) = 4 +0 write(4, ..., 14600) = 14600 +0 > . 1:5841(5840) ack 1 win 457 +0 > . 5841:11681(5840) ack 1 win 457 // Following packet should be sent right now. +0 > P. 11681:14601(2920) ack 1 win 457 +.1 < . 1:1(0) ack 14601 win 257 +0 close(4) = 0 +0 > F. 14601:14601(0) ack 1 +.1 < F. 1:1(0) ack 14602 win 257 +0 > . 14602:14602(0) ack 2 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>		2015-02-28 15:10:39 -05:00
..
netfilter	netfilter: nf_tables: fix port natting in little endian archs	2014-12-23 15:34:28 +01:00
af_inet.c	net: rfs: add hash collision detection	2015-02-08 16:53:57 -08:00
ah4.c	ipsec: Remove obsolete MAX_AH_AUTH_LEN	2014-09-18 10:54:36 +02:00
arp.c	neigh: remove dynamic neigh table registration support	2014-11-11 15:23:54 -05:00
cipso_ipv4.c	cipso: don't use IPCB() to locate the CIPSO IP option	2015-02-11 14:46:37 -05:00
datagram.c
devinet.c	multicast: Extend ip address command to enable multicast group join/leave on	2015-02-27 16:25:25 -05:00
esp4.c	net: esp: Convert NETDEBUG to pr_info	2014-11-06 15:11:10 -05:00
fib_frontend.c	fib_trie: Push rcu_read_lock/unlock to callers	2014-12-31 18:25:54 -05:00
fib_lookup.h	fib_trie: Add slen to fib alias	2015-02-27 16:37:07 -05:00
fib_rules.c	fib_trie: Push rcu_read_lock/unlock to callers	2014-12-31 18:25:54 -05:00
fib_semantics.c	fib_trie: Convert fib_alias to hlist from list	2015-02-27 16:37:06 -05:00
fib_trie.c	fib_trie: Remove leaf_info	2015-02-27 16:37:07 -05:00
fou.c	gue: Use checksum partial with remote checksum offload	2015-02-11 15:12:13 -08:00
geneve.c	openvswitch: Add support for checksums on UDP tunnels.	2015-01-28 23:04:15 -08:00
gre_demux.c	net: Fix GRE RX to use skb_transport_header for GRE header offset	2014-09-08 15:23:05 -07:00
gre_offload.c	gre: Set inner mac header in gro complete	2014-12-05 21:18:34 -08:00
icmp.c	ipv4: icmp: use percpu allocation	2015-01-31 17:48:18 -08:00
igmp.c	multicast: Extend ip address command to enable multicast group join/leave on	2015-02-27 16:25:25 -05:00
inet_connection_sock.c
inet_diag.c	netlink: make nlmsg_end() and genlmsg_end() void	2015-01-18 01:03:45 -05:00
inet_fragment.c	net: Convert LIMIT_NETDEBUG to net_dbg_ratelimited	2014-11-11 14:10:31 -05:00
inet_hashtables.c	net: use reciprocal_scale() helper	2014-08-23 12:21:21 -07:00
inet_lro.c
inet_timewait_sock.c
inetpeer.c	inet: remove dead inetpeer sequence code	2014-09-08 16:42:42 -07:00
ip_forward.c	ipv4: try to cache dst_entries which would cause a redirect	2015-01-26 17:28:27 -08:00
ip_fragment.c	net: Convert LIMIT_NETDEBUG to net_dbg_ratelimited	2014-11-11 14:10:31 -05:00
ip_gre.c	gre/ipip: use be16 variants of netlink functions	2015-02-08 16:28:06 -08:00
ip_input.c
ip_options.c	ipv4: rename ip_options_echo to __ip_options_echo()	2014-09-28 16:35:42 -04:00
ip_output.c	Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net	2015-02-05 14:33:28 -08:00
ip_sockglue.c	net-timestamp: no-payload option	2015-02-02 18:46:51 -08:00
ip_tunnel.c	tunnels: advertise link netns via netlink	2015-01-19 14:32:03 -05:00
ip_tunnel_core.c	ipv4: fix a potential use after free in ip_tunnel_core.c	2014-10-17 23:45:26 -04:00
ip_vti.c	tunnels: advertise link netns via netlink	2015-01-19 14:32:03 -05:00
ipcomp.c
ipconfig.c	net: ipv4: handle DSA enabled master network devices	2015-01-19 15:45:10 -05:00
ipip.c	gre/ipip: use be16 variants of netlink functions	2015-02-08 16:28:06 -08:00
ipmr.c	netlink: make nlmsg_end() and genlmsg_end() void	2015-01-18 01:03:45 -05:00
Kconfig	net: Move fou_build_header into fou.c and refactor	2014-11-05 16:30:02 -05:00
Makefile	net: Add Geneve tunneling protocol driver	2014-10-06 00:32:20 -04:00
netfilter.c
ping.c	net: switch memcpy_fromiovec()/memcpy_fromiovecend() users to copy_from_iter()	2015-02-04 01:34:15 -05:00
proc.c	tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks	2015-02-08 01:03:12 -08:00
protocol.c	net: Export inet_offloads and inet6_offloads	2014-09-19 17:15:31 -04:00
raw.c	net: switch memcpy_fromiovec()/memcpy_fromiovecend() users to copy_from_iter()	2015-02-04 01:34:15 -05:00
route.c	Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net	2015-02-05 14:33:28 -08:00
syncookies.c	net: allow setting ecn via routing table	2014-11-04 16:06:09 -05:00
sysctl_net_ipv4.c	ipv4: Namespecify TCP PMTU mechanism	2015-02-09 18:45:00 -08:00
tcp.c	ip: convert tcp_sendmsg() to iov_iter primitives	2015-02-04 01:34:14 -05:00
tcp_bic.c	tcp: stretch ACK fixes prep	2015-01-28 22:18:37 -08:00
tcp_cong.c	tcp: silence registration message	2015-02-20 15:04:03 -05:00
tcp_cubic.c	tcp: fix timing issue in CUBIC slope calculation	2015-01-28 22:18:38 -08:00
tcp_dctcp.c	net: tcp: add DCTCP congestion control algorithm	2014-09-29 00:13:10 -04:00
tcp_diag.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_fastopen.c	tcp: make sure skb is not shared before using skb_get()	2015-02-13 07:11:40 -08:00
tcp_highspeed.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_htcp.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_hybla.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_illinois.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_input.c	tcp: mitigate ACK loops for connections as tcp_sock	2015-02-08 01:03:12 -08:00
tcp_ipv4.c	ipv4: Namespecify TCP PMTU mechanism	2015-02-09 18:45:00 -08:00
tcp_lp.c
tcp_memcontrol.c	memcg: cleanup static keys decrement	2015-02-12 18:54:10 -08:00
tcp_metrics.c	netlink: make nlmsg_end() and genlmsg_end() void	2015-01-18 01:03:45 -05:00
tcp_minisocks.c	tcp: mitigate ACK loops for connections as tcp_timewait_sock	2015-02-08 01:03:13 -08:00
tcp_offload.c	net: Remove MPLS GSO feature.	2014-11-05 23:52:33 -08:00
tcp_output.c	tcp: tso: restore IW10 after TSO autosizing	2015-02-28 15:10:39 -05:00
tcp_probe.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_scalable.c	tcp: stretch ACK fixes prep	2015-01-28 22:18:37 -08:00
tcp_timer.c	ipv4: Namespecify TCP PMTU mechanism	2015-02-09 18:45:00 -08:00
tcp_vegas.c	tcp: whitespace fixes	2014-09-01 18:12:45 -07:00
tcp_vegas.h
tcp_veno.c	tcp: stretch ACK fixes prep	2015-01-28 22:18:37 -08:00
tcp_westwood.c	net: tcp: split ack slow/fast events from cwnd_event	2014-09-29 00:13:10 -04:00
tcp_yeah.c	tcp: stretch ACK fixes prep	2015-01-28 22:18:37 -08:00
tunnel4.c
udp.c	udp: In udp_flow_src_port use random hash value if skb_get_hash fails	2015-02-27 16:00:01 -05:00
udp_diag.c	udp_diag: Fix socket skipping within chain	2015-01-27 00:02:41 -08:00
udp_impl.h
udp_offload.c	udp: Set SKB_GSO_UDP_TUNNEL* in UDP GRO path	2015-02-11 15:12:10 -08:00
udp_tunnel.c	udp: Do not require sock in udp_tunnel_xmit_skb	2015-01-24 23:15:40 -08:00
udplite.c
xfrm4_input.c
xfrm4_mode_beet.c
xfrm4_mode_transport.c
xfrm4_mode_tunnel.c
xfrm4_output.c
xfrm4_policy.c
xfrm4_protocol.c
xfrm4_state.c
xfrm4_tunnel.c