From b6e32ffc2266e33c6d2bbc4cc8f56794d1605dba Mon Sep 17 00:00:00 2001 From: YangYuxi Date: Thu, 11 Jun 2020 17:28:49 +0800 Subject: [PATCH] ipvs: avoid drop first packet to reuse conntrack MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit f719e3754ee ("ipvs: drop first packet to redirect conntrack"), when a new TCP connection meet the conditions that need reschedule, the first syn packet is dropped, this cause one second latency for the new connection, more discussion about this problem can easy seach from google, such as: 1)One second connection delay in masque https://marc.info/?t=151683118100004&r=1&w=2 2)IPVS low throughput #70747 https://github.com/kubernetes/kubernetes/issues/70747 3)Apache Bench can fill up ipvs service proxy in seconds #544 https://github.com/cloudnativelabs/kube-router/issues/544 4)Additional 1s latency in `host -> service IP -> pod` https://github.com/kubernetes/kubernetes/issues/90854 The root cause is when the old session is expired, the conntrack related to the session is dropped by ip_vs_conn_drop_conntrack. The code is as follows: ``` static void ip_vs_conn_expire(struct timer_list *t) { ... if ((cp->flags & IP_VS_CONN_F_NFCT) && !(cp->flags & IP_VS_CONN_F_ONE_PACKET)) { /* Do not access conntracks during subsys cleanup * because nf_conntrack_find_get can not be used after * conntrack cleanup for the net. */ smp_rmb(); if (ipvs->enable) ip_vs_conn_drop_conntrack(cp); } ... } ``` As the code show, only if the condition (cp->flags & IP_VS_CONN_F_NFCT) is true, ip_vs_conn_drop_conntrack will be called. So we solve this bug by following steps: 1) erase the IP_VS_CONN_F_NFCT flag (it is safely because no packets will use the old session) 2) call ip_vs_conn_expire_now to release the old session, then the related conntrack will not be dropped 3) then ipvs unnecessary to drop the first syn packet, it just continue to pass the syn packet to the next process, create a new ipvs session, and the new session will related to the old conntrack(which is reopened by conntrack as a new one), the next whole things is just as normal as that the old session isn't used to exist. This patch has been verified on our thousands of kubernets node servers on Tencent Inc. Signed-off-by: YangYuxi --- net/netfilter/ipvs/ip_vs_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index aa6a603a2425be..2f750145172fdc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2086,11 +2086,11 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int } if (resched) { + if (uses_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) - return NF_DROP; cp = NULL; } }