diff options
| author | Eric Dumazet <edumazet@google.com> | 2015-10-02 14:43:35 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-10-03 07:32:43 -0400 |
| commit | ca6fb06518836ef9b65dc0aac02ff97704d52a05 (patch) | |
| tree | 3fbe433aac9dcf1cae49e6715ced18bd3505d811 /net/ipv6 | |
| parent | 1b33bc3e9e903f7293f7dfe80a875b2a5d0305aa (diff) | |
tcp: attach SYNACK messages to request sockets instead of listener
If a listen backlog is very big (to avoid syncookies), then
the listener sk->sk_wmem_alloc is the main source of false
sharing, as we need to touch it twice per SYNACK re-transmit
and TX completion.
(One SYN packet takes listener lock once, but up to 6 SYNACK
are generated)
By attaching the skb to the request socket, we remove this
source of contention.
Tested:
listen(fd, 10485760); // single listener (no SO_REUSEPORT)
16 RX/TX queue NIC
Sustain a SYNFLOOD attack of ~320,000 SYN per second,
Sending ~1,400,000 SYNACK per second.
Perf profiles now show listener spinlock being next bottleneck.
20.29% [kernel] [k] queued_spin_lock_slowpath
10.06% [kernel] [k] __inet_lookup_established
5.12% [kernel] [k] reqsk_timer_handler
3.22% [kernel] [k] get_next_timer_interrupt
3.00% [kernel] [k] tcp_make_synack
2.77% [kernel] [k] ipt_do_table
2.70% [kernel] [k] run_timer_softirq
2.50% [kernel] [k] ip_finish_output
2.04% [kernel] [k] cascade
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6')
| -rw-r--r-- | net/ipv6/tcp_ipv6.c | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a215614cfb2b..3d18571811c5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c | |||
| @@ -438,7 +438,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, | |||
| 438 | struct flowi *fl, | 438 | struct flowi *fl, |
| 439 | struct request_sock *req, | 439 | struct request_sock *req, |
| 440 | u16 queue_mapping, | 440 | u16 queue_mapping, |
| 441 | struct tcp_fastopen_cookie *foc) | 441 | struct tcp_fastopen_cookie *foc, |
| 442 | bool attach_req) | ||
| 442 | { | 443 | { |
| 443 | struct inet_request_sock *ireq = inet_rsk(req); | 444 | struct inet_request_sock *ireq = inet_rsk(req); |
| 444 | struct ipv6_pinfo *np = inet6_sk(sk); | 445 | struct ipv6_pinfo *np = inet6_sk(sk); |
| @@ -451,7 +452,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, | |||
| 451 | IPPROTO_TCP)) == NULL) | 452 | IPPROTO_TCP)) == NULL) |
| 452 | goto done; | 453 | goto done; |
| 453 | 454 | ||
| 454 | skb = tcp_make_synack(sk, dst, req, foc); | 455 | skb = tcp_make_synack(sk, dst, req, foc, attach_req); |
| 455 | 456 | ||
| 456 | if (skb) { | 457 | if (skb) { |
| 457 | __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, | 458 | __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, |