linux_dsm_epyc7002/net/ipv4
Yuchung Cheng 0f7cc9a3c2 tcp: increase throughput when reordering is high
The stack currently detects reordering and avoid spurious
retransmission very well. However the throughput is sub-optimal under
high reordering because cwnd is increased only if the data is deliverd
in order. I.e., FLAG_DATA_ACKED check in tcp_ack().  The more packet
are reordered the worse the throughput is.

Therefore when reordering is proven high, cwnd should advance whenever
the data is delivered regardless of its ordering. If reordering is low,
conservatively advance cwnd only on ordered deliveries in Open state,
and retain cwnd in Disordered state (RFC5681).

Using netperf on a qdisc setup of 20Mbps BW and random RTT from 45ms
to 55ms (for reordering effect). This change increases TCP throughput
by 20 - 25% to near bottleneck BW.

A special case is the stretched ACK with new SACK and/or ECE mark.
For example, a receiver may receive an out of order or ECN packet with
unacked data buffered because of LRO or delayed ACK. The principle on
such an ACK is to advance cwnd on the cummulative acked part first,
then reduce cwnd in tcp_fastretrans_alert().

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-22 14:39:46 -07:00
..
netfilter netfilter: nf_conntrack: don't send destroy events from iterator 2013-08-09 12:03:33 +02:00
af_inet.c gro: remove a sparse error 2013-06-12 15:03:24 -07:00
ah4.c ipv4: properly refresh rtable entries on pmtu/redirect events 2013-06-03 00:07:42 -07:00
arp.c arp: flush arp cache on IFF_NOARP change 2013-05-28 13:11:02 -07:00
cipso_ipv4.c cipso: don't follow a NULL pointer when setsockopt() is called 2012-07-18 09:01:12 -07:00
datagram.c ipv4: Add a socket release callback for datagram sockets 2013-01-21 14:17:05 -05:00
devinet.c net: igmp: Allow user-space configuration of igmp unsolicited report interval 2013-08-09 11:27:46 -07:00
esp4.c net: esp{4,6}: fix potential MTU calculation overflows 2013-08-05 12:26:50 -07:00
fib_frontend.c netlink: fix splat in skb_clone with large messages 2013-06-27 22:44:16 -07:00
fib_lookup.h ipv4: Fix nexthop caching wrt. scoping. 2011-03-24 18:06:47 -07:00
fib_rules.c fib_rules: fix suppressor names and default values 2013-08-03 10:40:23 -07:00
fib_semantics.c ipv4: use next hop exceptions also for input routes 2013-06-28 21:27:47 -07:00
fib_trie.c fib_trie: remove potential out of bound access 2013-08-05 15:26:11 -07:00
gre_demux.c net: gre: move GSO functions to gre_offload 2013-07-03 14:37:39 -07:00
gre_offload.c gso: Update tunnel segmentation to support Tx checksum offload 2013-07-11 12:18:49 -07:00
icmp.c icmp: avoid allocating large struct on stack 2013-06-03 00:28:44 -07:00
igmp.c net: igmp: Allow user-space configuration of igmp unsolicited report interval 2013-08-09 11:27:46 -07:00
inet_connection_sock.c tcp: Remove TCPCT 2013-03-17 14:35:13 -04:00
inet_diag.c netlink: rename ssk to sk in struct netlink_skb_params 2013-04-19 14:57:56 -04:00
inet_fragment.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next 2013-07-09 18:24:39 -07:00
inet_hashtables.c inet: fix spacing in assignment 2013-07-11 12:02:39 -07:00
inet_lro.c ipv4: replace ip_fast_csum with csum_replace2 2013-03-15 09:12:25 -04:00
inet_timewait_sock.c hlist: drop the node parameter from iterators 2013-02-27 19:10:24 -08:00
inetpeer.c Merge branch 'for-3.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq 2012-10-02 09:54:49 -07:00
ip_forward.c ipv4: introduce rt_uses_gateway 2012-10-08 17:42:36 -04:00
ip_fragment.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2013-04-22 20:32:51 -04:00
ip_gre.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2013-08-16 15:37:26 -07:00
ip_input.c net: add SNMP counters tracking incoming ECN bits 2013-08-08 22:24:59 -07:00
ip_options.c net/ipv4: Ensure that location of timestamp option is stored 2013-03-12 05:35:39 -04:00
ip_output.c ipv4: ip_output: remove inline marking of EXPORT_SYMBOL functions 2013-05-11 16:12:44 -07:00
ip_sockglue.c net: prevent setting ttl=0 via IP_TTL 2013-01-08 17:57:10 -08:00
ip_tunnel_core.c ip_tunnel: Do not use inner ip-header-id for tunnel ip-header-id. 2013-08-13 16:52:50 -07:00
ip_tunnel.c ipip: dereferencing an ERR_PTR in ip_tunnel_init_net() 2013-08-20 15:12:15 -07:00
ip_vti.c ipip: add x-netns support 2013-08-15 01:00:20 -07:00
ipcomp.c ipv4: properly refresh rtable entries on pmtu/redirect events 2013-06-03 00:07:42 -07:00
ipconfig.c ipconfig: add informative timeout messages while waiting for carrier 2013-04-02 14:35:33 -04:00
ipip.c ipip: add x-netns support 2013-08-15 01:00:20 -07:00
ipmr.c ipmr: change the prototype of ip_mr_forward(). 2013-07-23 17:01:05 -07:00
Kconfig Kconfig: remove dangling references to the deleted file 2013-06-04 15:17:39 -07:00
Makefile net: gre: move GSO functions to gre_offload 2013-07-03 14:37:39 -07:00
netfilter.c netfilter: add my copyright statements 2013-04-18 20:27:55 +02:00
ping.c net: proc_fs: trivial: print UIDs as unsigned int 2013-08-15 14:37:46 -07:00
proc.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2013-08-16 15:37:26 -07:00
protocol.c ipv4: Disallow non-namespace aware protocols to register. 2013-02-05 14:42:23 -05:00
raw.c net: proc_fs: trivial: print UIDs as unsigned int 2013-08-15 14:37:46 -07:00
route.c ipv4: raise IP_MAX_MTU to theoretical limit 2013-08-20 15:05:04 -07:00
syncookies.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2013-04-22 20:32:51 -04:00
sysctl_net_ipv4.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2013-08-03 21:36:46 -07:00
tcp_bic.c tcp: fix undo after RTO for BIC 2012-01-20 14:17:26 -05:00
tcp_cong.c tcp: remove Appropriate Byte Count support 2013-02-05 14:51:16 -05:00
tcp_cubic.c tcp: cubic: fix bug in bictcp_acked() 2013-08-07 10:35:08 -07:00
tcp_diag.c inet_diag: Rename inet_diag_req into inet_diag_req_v2 2012-01-11 12:56:06 -08:00
tcp_fastopen.c tcp: add server ip to encrypt cookie in fast open 2013-08-10 00:35:33 -07:00
tcp_highspeed.c tcp: mark tcp_congestion_ops read_mostly 2011-03-10 00:40:17 -08:00
tcp_htcp.c tcp: mark tcp_congestion_ops read_mostly 2011-03-10 00:40:17 -08:00
tcp_hybla.c tcp: bool conversions 2012-05-17 14:59:59 -04:00
tcp_illinois.c net: fix divide by zero in tcp algorithm illinois 2012-11-01 11:55:59 -04:00
tcp_input.c tcp: increase throughput when reordering is high 2013-08-22 14:39:46 -07:00
tcp_ipv4.c tcp: trivial: Remove nocache argument from tcp_v4_send_synack 2013-08-20 15:05:04 -07:00
tcp_lp.c Fix common misspellings 2011-03-31 11:26:23 -03:00
tcp_memcontrol.c net: tcp_memcontrol: minor: remove unused variable 2013-04-14 15:41:49 -04:00
tcp_metrics.c tcp: do not expire TCP fastopen cookies 2013-05-05 16:58:02 -04:00
tcp_minisocks.c tcp: consolidate SYNACK RTT sampling 2013-07-22 17:53:42 -07:00
tcp_offload.c net: tcp: move GRO/GSO functions to tcp_offload 2013-06-07 14:39:05 -07:00
tcp_output.c tcp: TCP_NOTSENT_LOWAT socket option 2013-07-24 17:54:48 -07:00
tcp_probe.c net: proc: change proc_net_remove to remove_proc_entry 2013-02-18 14:53:08 -05:00
tcp_scalable.c tcp: mark tcp_congestion_ops read_mostly 2011-03-10 00:40:17 -08:00
tcp_timer.c tcp: refactor F-RTO 2013-03-21 11:47:50 -04:00
tcp_vegas.c tcp: mark tcp_congestion_ops read_mostly 2011-03-10 00:40:17 -08:00
tcp_vegas.h
tcp_veno.c tcp: mark tcp_congestion_ops read_mostly 2011-03-10 00:40:17 -08:00
tcp_westwood.c tcp: refactor F-RTO 2013-03-21 11:47:50 -04:00
tcp_yeah.c Fix common misspellings 2011-03-31 11:26:23 -03:00
tcp.c tcp: Remove unused tcpct declarations and comments 2013-07-31 12:16:45 -07:00
tunnel4.c net: Convert printks to pr_<level> 2012-03-11 23:42:51 -07:00
udp_diag.c netlink: rename ssk to sk in struct netlink_skb_params 2013-04-19 14:57:56 -04:00
udp_impl.h ipv4: fix checkpatch errors 2012-04-15 12:37:19 -04:00
udp_offload.c net: udp4: move GSO functions to udp_offload 2013-06-12 00:47:25 -07:00
udp.c net: proc_fs: trivial: print UIDs as unsigned int 2013-08-15 14:37:46 -07:00
udplite.c net: ipv4: Standardize prefixes for message logging 2012-03-12 17:05:21 -07:00
xfrm4_input.c net: Add skb_unclone() helper function. 2013-02-15 15:10:37 -05:00
xfrm4_mode_beet.c ipsec: be careful of non existing mac headers 2012-02-23 16:50:45 -05:00
xfrm4_mode_transport.c
xfrm4_mode_tunnel.c xfrm: allow to avoid copying DSCP during encapsulation 2013-03-06 07:02:45 +01:00
xfrm4_output.c xfrm4: Don't call icmp_send on local error 2011-07-01 17:33:19 -07:00
xfrm4_policy.c xfrm: make gc_thresh configurable in all namespaces 2013-02-06 11:36:29 +01:00
xfrm4_state.c net: Add export.h for EXPORT_SYMBOL/THIS_MODULE to non-modules 2011-10-31 19:30:30 -04:00
xfrm4_tunnel.c sit: add IPv4 over IPv4 support 2013-05-31 17:19:05 -07:00