From 2232642ec3fb4aad6ae4da1e109f55a0e7f2d204 Mon Sep 17 00:00:00 2001 From: Dust Li Date: Fri, 20 Aug 2021 13:37:52 +0800 Subject: ipvs: add sysctl_run_estimation to support disable estimation estimation_timer will iterate the est_list to do estimation for each ipvs stats. When there are lots of services, the list can be very large. We found that estimation_timer() run for more then 200ms on a machine with 104 CPU and 50K services. yunhong-cgl jiang report the same phenomenon before: https://www.spinics.net/lists/lvs-devel/msg05426.html In some cases(for example a large K8S cluster with many ipvs services), ipvs estimation may not be needed. So adding a sysctl blob to allow users to disable this completely. Default is: 1 (enable) Cc: yunhong-cgl jiang Signed-off-by: Dust Li Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++++++ net/netfilter/ipvs/ip_vs_est.c | 5 +++++ 2 files changed, 13 insertions(+) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c25097092a06..cbea5a68afb5 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2017,6 +2017,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "run_estimation", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -4090,6 +4096,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; + ipvs->sysctl_run_estimation = 1; + tbl[idx++].data = &ipvs->sysctl_run_estimation; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 05b8112ffb37..9a1a7af6a186 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -100,6 +100,9 @@ static void estimation_timer(struct timer_list *t) u64 rate; struct netns_ipvs *ipvs = from_timer(ipvs, t, est_timer); + if (!sysctl_run_estimation(ipvs)) + goto skip; + spin_lock(&ipvs->est_lock); list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); @@ -131,6 +134,8 @@ static void estimation_timer(struct timer_list *t) spin_unlock(&s->lock); } spin_unlock(&ipvs->est_lock); + +skip: mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } -- cgit v1.2.3-59-g8ed1b