summaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
authorJulian Anastasov <ja@ssi.bg>2020-07-01 18:17:19 +0300
committerPablo Neira Ayuso <pablo@netfilter.org>2020-07-04 01:18:37 +0200
commitf0a5e4d7a594e0fe237d3dfafb069bb82f80f42f (patch)
treed26a576289061522fe123838e08999f26d87d55e /net/netfilter
parentf9200a52eedfe96ae8d9cbf68a363f5409a46117 (diff)
ipvs: allow connection reuse for unconfirmed conntrack
YangYuxi is reporting that connection reuse is causing one-second delay when SYN hits existing connection in TIME_WAIT state. Such delay was added to give time to expire both the IPVS connection and the corresponding conntrack. This was considered a rare case at that time but it is causing problem for some environments such as Kubernetes. As nf_conntrack_tcp_packet() can decide to release the conntrack in TIME_WAIT state and to replace it with a fresh NEW conntrack, we can use this to allow rescheduling just by tuning our check: if the conntrack is confirmed we can not schedule it to different real server and the one-second delay still applies but if new conntrack was created, we are free to select new real server without any delays. YangYuxi lists some of the problem reports: - One second connection delay in masquerading mode: https://marc.info/?t=151683118100004&r=1&w=2 - IPVS low throughput #70747 https://github.com/kubernetes/kubernetes/issues/70747 - Apache Bench can fill up ipvs service proxy in seconds #544 https://github.com/cloudnativelabs/kube-router/issues/544 - Additional 1s latency in `host -> service IP -> pod` https://github.com/kubernetes/kubernetes/issues/90854 Fixes: f719e3754ee2 ("ipvs: drop first packet to redirect conntrack") Co-developed-by: YangYuxi <yx.atom1@gmail.com> Signed-off-by: YangYuxi <yx.atom1@gmail.com> Signed-off-by: Julian Anastasov <ja@ssi.bg> Reviewed-by: Simon Horman <horms@verge.net.au> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c12
1 files changed, 7 insertions, 5 deletions
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index ca3670152565..b4a6b7662f3f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2066,14 +2066,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
- bool uses_ct = false, resched = false;
+ bool old_ct = false, resched = false;
if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
unlikely(!atomic_read(&cp->dest->weight))) {
resched = true;
- uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+ old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
- uses_ct = ip_vs_conn_uses_conntrack(cp, skb);
+ old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
if (!atomic_read(&cp->n_control)) {
resched = true;
} else {
@@ -2081,15 +2081,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
* that uses conntrack while it is still
* referenced by controlled connection(s).
*/
- resched = !uses_ct;
+ resched = !old_ct;
}
}
if (resched) {
+ if (!old_ct)
+ cp->flags &= ~IP_VS_CONN_F_NFCT;
if (!atomic_read(&cp->n_control))
ip_vs_conn_expire_now(cp);
__ip_vs_conn_put(cp);
- if (uses_ct)
+ if (old_ct)
return NF_DROP;
cp = NULL;
}