From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 85D7FC433F5 for ; Sun, 17 Oct 2021 22:15:45 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 678E960FED for ; Sun, 17 Oct 2021 22:15:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1344753AbhJQWRw (ORCPT ); Sun, 17 Oct 2021 18:17:52 -0400 Received: from mail.netfilter.org ([217.70.188.207]:53388 "EHLO mail.netfilter.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235725AbhJQWRv (ORCPT ); Sun, 17 Oct 2021 18:17:51 -0400 Received: from localhost.localdomain (unknown [78.30.32.163]) by mail.netfilter.org (Postfix) with ESMTPSA id 3E39563586; Mon, 18 Oct 2021 00:13:59 +0200 (CEST) From: Pablo Neira Ayuso To: netfilter-devel@vger.kernel.org Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org Subject: [PATCH nf-next 01/15] ipvs: add sysctl_run_estimation to support disable estimation Date: Mon, 18 Oct 2021 00:15:08 +0200 Message-Id: <20211017221522.853838-2-pablo@netfilter.org> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20211017221522.853838-1-pablo@netfilter.org> References: <20211017221522.853838-1-pablo@netfilter.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org From: Dust Li 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 --- Documentation/networking/ipvs-sysctl.rst | 11 +++++++++++ include/net/ip_vs.h | 11 +++++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++++++ net/netfilter/ipvs/ip_vs_est.c | 5 +++++ 4 files changed, 35 insertions(+) diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 2afccc63856e..95ef56d62077 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -300,3 +300,14 @@ sync_version - INTEGER Kernels with this sync_version entry are able to receive messages of both version 1 and version 2 of the synchronisation protocol. + +run_estimation - BOOLEAN + 0 - disabled + not 0 - enabled (default) + + If disabled, the estimation will be stop, and you can't see + any update on speed estimation data. + + You can always re-enable estimation by setting this value to 1. + But be careful, the first estimation after re-enable is not + accurate. diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 7cb5a1aace40..ff1804a0c469 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -931,6 +931,7 @@ struct netns_ipvs { int sysctl_conn_reuse_mode; int sysctl_schedule_icmp; int sysctl_ignore_tunneled; + int sysctl_run_estimation; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1071,6 +1072,11 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) return ipvs->sysctl_cache_bypass; } +static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_run_estimation; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1163,6 +1169,11 @@ static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) +{ + return 1; +} + #endif /* IPVS core functions 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); } -- 2.30.2