mirror of https://github.com/torvalds/linux.git
93bb0ceb75
nf_conntrack_lock is a monolithic lock and suffers from huge contention
on current generation servers (8 or more core/threads).
Perf locking congestion is clear on base kernel:
- 72.56% ksoftirqd/6 [kernel.kallsyms] [k] _raw_spin_lock_bh
- _raw_spin_lock_bh
+ 25.33% init_conntrack
+ 24.86% nf_ct_delete_from_lists
+ 24.62% __nf_conntrack_confirm
+ 24.38% destroy_conntrack
+ 0.70% tcp_packet
+ 2.21% ksoftirqd/6 [kernel.kallsyms] [k] fib_table_lookup
+ 1.15% ksoftirqd/6 [kernel.kallsyms] [k] __slab_free
+ 0.77% ksoftirqd/6 [kernel.kallsyms] [k] inet_getpeer
+ 0.70% ksoftirqd/6 [nf_conntrack] [k] nf_ct_delete
+ 0.55% ksoftirqd/6 [ip_tables] [k] ipt_do_table
This patch change conntrack locking and provides a huge performance
improvement. SYN-flood attack tested on a 24-core E5-2695v2(ES) with
10Gbit/s ixgbe (with tool trafgen):
Base kernel: 810.405 new conntrack/sec
After patch: 2.233.876 new conntrack/sec
Notice other floods attack (SYN+ACK or ACK) can easily be deflected using:
# iptables -A INPUT -m state --state INVALID -j DROP
# sysctl -w net/netfilter/nf_conntrack_tcp_loose=0
Use an array of hashed spinlocks to protect insertions/deletions of
conntracks into the hash table. 1024 spinlocks seem to give good
results, at minimal cost (4KB memory). Due to lockdep max depth,
1024 becomes 8 if CONFIG_LOCKDEP=y
The hash resize is a bit tricky, because we need to take all locks in
the array. A seqcount_t is used to synchronize the hash table users
with the resizing process.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
||
|---|---|---|
| .. | ||
| 9p | ||
| bluetooth | ||
| caif | ||
| irda | ||
| iucv | ||
| netfilter | ||
| netns | ||
| nfc | ||
| phonet | ||
| sctp | ||
| tc_act | ||
| Space.h | ||
| act_api.h | ||
| addrconf.h | ||
| af_ieee802154.h | ||
| af_rxrpc.h | ||
| af_unix.h | ||
| af_vsock.h | ||
| ah.h | ||
| arp.h | ||
| atmclip.h | ||
| ax25.h | ||
| ax88796.h | ||
| busy_poll.h | ||
| cfg80211-wext.h | ||
| cfg80211.h | ||
| checksum.h | ||
| cipso_ipv4.h | ||
| cls_cgroup.h | ||
| codel.h | ||
| compat.h | ||
| datalink.h | ||
| dcbevent.h | ||
| dcbnl.h | ||
| dn.h | ||
| dn_dev.h | ||
| dn_fib.h | ||
| dn_neigh.h | ||
| dn_nsp.h | ||
| dn_route.h | ||
| dsa.h | ||
| dsfield.h | ||
| dst.h | ||
| dst_ops.h | ||
| esp.h | ||
| ethoc.h | ||
| fib_rules.h | ||
| firewire.h | ||
| flow.h | ||
| flow_keys.h | ||
| garp.h | ||
| gen_stats.h | ||
| genetlink.h | ||
| gre.h | ||
| gro_cells.h | ||
| icmp.h | ||
| ieee80211_radiotap.h | ||
| ieee802154.h | ||
| ieee802154_netdev.h | ||
| if_inet6.h | ||
| inet6_connection_sock.h | ||
| inet6_hashtables.h | ||
| inet_common.h | ||
| inet_connection_sock.h | ||
| inet_ecn.h | ||
| inet_frag.h | ||
| inet_hashtables.h | ||
| inet_sock.h | ||
| inet_timewait_sock.h | ||
| inetpeer.h | ||
| ip.h | ||
| ip6_checksum.h | ||
| ip6_fib.h | ||
| ip6_route.h | ||
| ip6_tunnel.h | ||
| ip_fib.h | ||
| ip_tunnels.h | ||
| ip_vs.h | ||
| ipcomp.h | ||
| ipconfig.h | ||
| ipv6.h | ||
| ipx.h | ||
| iw_handler.h | ||
| lapb.h | ||
| lib80211.h | ||
| llc.h | ||
| llc_c_ac.h | ||
| llc_c_ev.h | ||
| llc_c_st.h | ||
| llc_conn.h | ||
| llc_if.h | ||
| llc_pdu.h | ||
| llc_s_ac.h | ||
| llc_s_ev.h | ||
| llc_s_st.h | ||
| llc_sap.h | ||
| mac80211.h | ||
| mac802154.h | ||
| mip6.h | ||
| mld.h | ||
| mrp.h | ||
| ndisc.h | ||
| neighbour.h | ||
| net_namespace.h | ||
| net_ratelimit.h | ||
| netdma.h | ||
| netevent.h | ||
| netlabel.h | ||
| netlink.h | ||
| netprio_cgroup.h | ||
| netrom.h | ||
| nexthop.h | ||
| nl802154.h | ||
| p8022.h | ||
| ping.h | ||
| pkt_cls.h | ||
| pkt_sched.h | ||
| protocol.h | ||
| psnap.h | ||
| raw.h | ||
| rawv6.h | ||
| red.h | ||
| regulatory.h | ||
| request_sock.h | ||
| rose.h | ||
| route.h | ||
| rtnetlink.h | ||
| sch_generic.h | ||
| scm.h | ||
| secure_seq.h | ||
| slhc_vj.h | ||
| snmp.h | ||
| sock.h | ||
| stp.h | ||
| tcp.h | ||
| tcp_memcontrol.h | ||
| tcp_states.h | ||
| timewait_sock.h | ||
| transp_v6.h | ||
| udp.h | ||
| udplite.h | ||
| vsock_addr.h | ||
| vxlan.h | ||
| wext.h | ||
| wimax.h | ||
| wpan-phy.h | ||
| x25.h | ||
| x25device.h | ||
| xfrm.h | ||