diff options
| author | Eric Dumazet | 2018-02-19 11:56:47 -0800 |
|---|---|---|
| committer | David S. Miller | 2018-02-21 14:24:13 -0500 |
| commit | 0a6b2a1dc2a2105f178255fe495eb914b09cb37a (patch) | |
| tree | 532480b47dccd07039b68b0fc813fedd313905f5 | |
| parent | 960103ff8dd176511d3735d22c14fb0a5ce3183e (diff) | |
tcp: switch to GSO being always on
Oleksandr Natalenko reported performance issues with BBR without FQ
packet scheduler that were root caused to lack of SG and GSO/TSO on
his configuration.
In this mode, TCP internal pacing has to setup a high resolution timer
for each MSS sent.
We could implement in TCP a strategy similar to the one adopted
in commit fefa569a9d4b ("net_sched: sch_fq: account for schedule/timers drifts")
or decide to finally switch TCP stack to a GSO only mode.
This has many benefits :
1) Most TCP developments are done with TSO in mind.
2) Less high-resolution timers needs to be armed for TCP-pacing
3) GSO can benefit of xmit_more hint
4) Receiver GRO is more effective (as if TSO was used for real on sender)
-> Lower ACK traffic
5) Write queues have less overhead (one skb holds about 64KB of payload)
6) SACK coalescing just works.
7) rtx rb-tree contains less packets, SACK is cheaper.
This patch implements the minimum patch, but we can remove some legacy
code as follow ups.
Tested:
On 40Gbit link, one netperf -t TCP_STREAM
BBR+fq:
sg on: 26 Gbits/sec
sg off: 15.7 Gbits/sec (was 2.3 Gbit before patch)
BBR+pfifo_fast:
sg on: 24.2 Gbits/sec
sg off: 14.9 Gbits/sec (was 0.66 Gbit before patch !!! )
BBR+fq_codel:
sg on: 24.4 Gbits/sec
sg off: 15 Gbits/sec (was 0.66 Gbit before patch !!! )
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: David S. Miller <davem@davemloft.net>
| -rw-r--r-- | include/net/sock.h | 1 | ||||
| -rw-r--r-- | net/core/sock.c | 2 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 1 |
3 files changed, 3 insertions, 1 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 3aa7b7d6e6c7..f0f576ff5603 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -417,6 +417,7 @@ struct sock { struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; + netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; diff --git a/net/core/sock.c b/net/core/sock.c index a1fa4a548f1b..507d8c6c4319 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1777,7 +1777,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) u32 max_segs = 1; sk_dst_set(sk, dst); - sk->sk_route_caps = dst->dev->features; + sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; sk->sk_route_caps &= ~sk->sk_route_nocaps; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 48636aee23c3..4b46a2ae46e3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -453,6 +453,7 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk_sockets_allocated_inc(sk); + sk->sk_route_forced_caps = NETIF_F_GSO; } EXPORT_SYMBOL(tcp_init_sock); |