f4805eded7
TCP peformance with TSO over networks with delay is awful. On a 100Mbit link with 150ms delay, we get 4Mbits/sec with TSO and 50Mbits/sec without TSO. The problem is with TSO, we intentionally do not keep the maximum number of packets in flight to fill the window, we hold out to until we can send a MSS chunk. But, we also don't update the congestion window unless we have filled, as per RFC2861. This patch replaces the check for the congestion window being full with something smarter that accounts for TSO. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net> |
||
|---|---|---|
| .. | ||
| ipvs | ||
| netfilter | ||
| af_inet.c | ||
| ah4.c | ||
| arp.c | ||
| datagram.c | ||
| devinet.c | ||
| esp4.c | ||
| fib_frontend.c | ||
| fib_hash.c | ||
| fib_lookup.h | ||
| fib_rules.c | ||
| fib_semantics.c | ||
| fib_trie.c | ||
| icmp.c | ||
| igmp.c | ||
| inet_connection_sock.c | ||
| inet_diag.c | ||
| inet_hashtables.c | ||
| inet_timewait_sock.c | ||
| inetpeer.c | ||
| ip_forward.c | ||
| ip_fragment.c | ||
| ip_gre.c | ||
| ip_input.c | ||
| ip_options.c | ||
| ip_output.c | ||
| ip_sockglue.c | ||
| ipcomp.c | ||
| ipconfig.c | ||
| ipip.c | ||
| ipmr.c | ||
| Kconfig | ||
| Makefile | ||
| multipath_drr.c | ||
| multipath_random.c | ||
| multipath_rr.c | ||
| multipath_wrandom.c | ||
| multipath.c | ||
| netfilter.c | ||
| proc.c | ||
| protocol.c | ||
| raw.c | ||
| route.c | ||
| syncookies.c | ||
| sysctl_net_ipv4.c | ||
| tcp_bic.c | ||
| tcp_cong.c | ||
| tcp_diag.c | ||
| tcp_highspeed.c | ||
| tcp_htcp.c | ||
| tcp_hybla.c | ||
| tcp_input.c | ||
| tcp_ipv4.c | ||
| tcp_minisocks.c | ||
| tcp_output.c | ||
| tcp_scalable.c | ||
| tcp_timer.c | ||
| tcp_vegas.c | ||
| tcp_westwood.c | ||
| tcp.c | ||
| udp.c | ||
| xfrm4_input.c | ||
| xfrm4_output.c | ||
| xfrm4_policy.c | ||
| xfrm4_state.c | ||
| xfrm4_tunnel.c | ||