summaryrefslogtreecommitdiffstats
path: root/net/sctp
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2010-04-27 15:13:20 -0700
committerDavid S. Miller <davem@davemloft.net>2010-04-27 15:13:20 -0700
commitc377411f2494a931ff7facdbb3a6839b1266bcf6 (patch)
tree6846cdcec913f50839e3916856f78f7e059ff5fb /net/sctp
parent6e7676c1a76aed6e957611d8d7a9e5592e23aeba (diff)
downloadop-kernel-dev-c377411f2494a931ff7facdbb3a6839b1266bcf6.zip
op-kernel-dev-c377411f2494a931ff7facdbb3a6839b1266bcf6.tar.gz
net: sk_add_backlog() take rmem_alloc into account
Current socket backlog limit is not enough to really stop DDOS attacks, because user thread spend many time to process a full backlog each round, and user might crazy spin on socket lock. We should add backlog size and receive_queue size (aka rmem_alloc) to pace writers, and let user run without being slow down too much. Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in stress situations. Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp receiver can now process ~200.000 pps (instead of ~100 pps before the patch) on a 8 core machine. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sctp')
-rw-r--r--net/sctp/socket.c3
1 files changed, 0 insertions, 3 deletions
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f34adcc..13d8229 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3721,9 +3721,6 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
SCTP_DBG_OBJCNT_INC(sock);
percpu_counter_inc(&sctp_sockets_allocated);
- /* Set socket backlog limit. */
- sk->sk_backlog.limit = sysctl_sctp_rmem[1];
-
local_bh_disable();
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
local_bh_enable();
OpenPOWER on IntegriCloud