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 X-Spam-Level: X-Spam-Status: No, score=-14.4 required=3.0 tests=DKIMWL_WL_MED,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH, MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,USER_IN_DEF_DKIM_WL autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 25B18C47257 for ; Fri, 8 May 2020 18:06:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 08FA3218AC for ; Fri, 8 May 2020 18:06:30 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="kq7vugtu" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727942AbgEHSG3 (ORCPT ); Fri, 8 May 2020 14:06:29 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53614 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1726746AbgEHSG2 (ORCPT ); Fri, 8 May 2020 14:06:28 -0400 Received: from mail-yb1-xb42.google.com (mail-yb1-xb42.google.com [IPv6:2607:f8b0:4864:20::b42]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A3953C061A0C for ; Fri, 8 May 2020 11:06:28 -0700 (PDT) Received: by mail-yb1-xb42.google.com with SMTP id b8so1389486ybn.0 for ; Fri, 08 May 2020 11:06:28 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=uAlBu8SMURqxDUbt8GgIpem8C7ql67Dv+Tr8gF2aESg=; b=kq7vugtujJ5vxoZBw3u9S9dSw5gIiw04tv0nSkdBlOt2xUFQWEQCZkDs1f8y6uVO3G yRT+rFegE2jqgsTH17YbiCmFkGotyagStIwU+RxsorkCw/RRL+KfWfOxrNRxhN7dZYk7 orw0sw+UdBSVzQ9MOPKI2NX/BAnqwensu6ndb2OpOMIhURSoNbh3sAqxmmE2zO4iyoaJ yzSX5VxkXJWa3wr7qEZurzaHLBE6o3XkkSctpQv9AcnKcH4DnSbvNheJWanCefglUekK sHPm7chftIbEM/jN0sUNNkcqLpLmqzIZAgYblycLPtM0RejjcehqdvH4NaNbbSK7v/Hr 92hw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=uAlBu8SMURqxDUbt8GgIpem8C7ql67Dv+Tr8gF2aESg=; b=jFEW+SmMNbQ1+6Cj4oJVrmYvrE+gecQxeJqSzavCG3ILS1tABN1tsFzQKALs3ozfEJ /FKL9a2akJtMiCAFYgPrjf1ONUXCwj6u+V2Pk/TRwuiDwNoZp7nVGcf2HdlERdrT4CiG e//+109Ub8fdH/iUpQ9unTFgmQKHpHzkWB4WkC6UVSE07J+X7fceYR0nQXfrssdXQH1f IZbASjIV1/SHesOHE2U6plwVw2Xwp19eu01aw/mNlmA/BPmQVXJ1Y8F6rkQzg5MTmjVJ I38o+ZA8VlFaXpjdsCWaq0ZD7ZsOLh3/WoD1OID1gKvrnSSWuF8zrZJt8NQiSOKMSE3D tynA== X-Gm-Message-State: AGi0Publ1UXbBdtmUYwpzLbFZxode7iCS1jvhMtZ3jB9UWZcjm1XWkdc C3GbqrgQ1iJFV3trAUSHpYJbyoLhBx+jdSP58eGSiA== X-Google-Smtp-Source: APiQypKMGBkKZWfx5NlblA5Dee7bC7/k9PXZNodfIPqzfCeyQtVZ3PG4/B54OXTYfRCl2KH+N8BX1MZiCFmBGkehwGw= X-Received: by 2002:a25:6f86:: with SMTP id k128mr6529346ybc.520.1588961187542; Fri, 08 May 2020 11:06:27 -0700 (PDT) MIME-Version: 1.0 References: <20200508015810.46023-1-edumazet@google.com> In-Reply-To: From: Eric Dumazet Date: Fri, 8 May 2020 11:06:16 -0700 Message-ID: Subject: Re: [PATCH net-next] net/dst: use a smaller percpu_counter batch for dst entries accounting To: Brian Vazquez Cc: "David S . Miller" , netdev , Eric Dumazet Content-Type: text/plain; charset="UTF-8" Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org On Fri, May 8, 2020 at 10:30 AM Brian Vazquez wrote: > > On Thu, May 7, 2020 at 7:00 PM Eric Dumazet wrote: > > > > percpu_counter_add() uses a default batch size which is quite big > > on platforms with 256 cpus. (2*256 -> 512) > > > > This means dst_entries_get_fast() can be off by +/- 2*(nr_cpus^2) > > (131072 on servers with 256 cpus) > > > > Reduce the batch size to something more reasonable, and > > add logic to ip6_dst_gc() to call dst_entries_get_slow() > > before calling the _very_ expensive fib6_run_gc() function. > > > > Signed-off-by: Eric Dumazet > > --- > > include/net/dst_ops.h | 4 +++- > > net/core/dst.c | 8 ++++---- > > net/ipv6/route.c | 3 +++ > > 3 files changed, 10 insertions(+), 5 deletions(-) > > > > diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h > > index 443863c7b8da362476c15fd290ac2a32a8aa86e3..88ff7bb2bb9bd950cc54fd5e0ae4573d4c66873d 100644 > > --- a/include/net/dst_ops.h > > +++ b/include/net/dst_ops.h > > @@ -53,9 +53,11 @@ static inline int dst_entries_get_slow(struct dst_ops *dst) > > return percpu_counter_sum_positive(&dst->pcpuc_entries); > > } > > > > +#define DST_PERCPU_COUNTER_BATCH 32 > > static inline void dst_entries_add(struct dst_ops *dst, int val) > > { > > - percpu_counter_add(&dst->pcpuc_entries, val); > > + percpu_counter_add_batch(&dst->pcpuc_entries, val, > > + DST_PERCPU_COUNTER_BATCH); > > } > > > > static inline int dst_entries_init(struct dst_ops *dst) > > diff --git a/net/core/dst.c b/net/core/dst.c > > index 193af526e908afa4b868cf128470f0fbc3850698..d6b6ced0d451a39c0ccb88ae39dba225ea9f5705 100644 > > --- a/net/core/dst.c > > +++ b/net/core/dst.c > > @@ -81,11 +81,11 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, > > { > > struct dst_entry *dst; > > > > - if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { > > + if (ops->gc && > > + !(flags & DST_NOCOUNT) && > > + dst_entries_get_fast(ops) > ops->gc_thresh) { > > if (ops->gc(ops)) { > > - printk_ratelimited(KERN_NOTICE "Route cache is full: " > > - "consider increasing sysctl " > > - "net.ipv[4|6].route.max_size.\n"); > > + pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); > > return NULL; > > } > > } > > diff --git a/net/ipv6/route.c b/net/ipv6/route.c > > index 1ff142393c768f85c495474a1d05e1ae1642301c..a9072dba00f4fb0b61bce1fc0f44a3a81ba702fa 100644 > > --- a/net/ipv6/route.c > > +++ b/net/ipv6/route.c > > @@ -3195,6 +3195,9 @@ static int ip6_dst_gc(struct dst_ops *ops) > > int entries; > > > > entries = dst_entries_get_fast(ops); > > + if (entries > rt_max_size) > > + entries = dst_entries_get_slow(ops); > > + > > if (time_after(rt_last_gc + rt_min_interval, jiffies) && > if this part of the condition is not satisfied, you are going to call > fib6_run_gc anyways and after that you will update the entries. So I > was wondering if code here could be something like: > --- a/net/ipv6/route.c > +++ b/net/ipv6/route.c > @@ -3197,11 +3197,16 @@ static int ip6_dst_gc(struct dst_ops *ops) > unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; > int entries; > > + if (time_before(rt_last_gc + rt_min_interval, jiffies) > + goto run_gc; > + > entries = dst_entries_get_fast(ops); > - if (time_after(rt_last_gc + rt_min_interval, jiffies) && > - entries <= rt_max_size) > + if (entries > rt_max_size) > + entries = dst_entries_get_slow(ops); > + if (entries <= rt_max_size) > goto out; > > +run_gc: > net->ipv6.ip6_rt_gc_expire++; > fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); > entries = dst_entries_get_slow(ops); > > That way you could potentially avoid an extra call to > dst_entries_get_slow when you know for sure that fib6_run_gc will be > run. WDYT? The problem is that you might still return a wrong status in the final : return entries > rt_max_size; If we are in ip6_dst_gc(), we know for sure entries might be wrong, if it holds dst_entries_get_fast(ops) If you prefer, the patch is really (since the caller calls us only if dst_entries_get_fast(ops) was suspect) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ff847a324220bc4cac8b103640f7e1a5db374a87..78e7f3c14e8a9c937866361aaf641cecfe1fed43 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3196,7 +3196,7 @@ static int ip6_dst_gc(struct dst_ops *ops) unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; int entries; - entries = dst_entries_get_fast(ops); + entries = dst_entries_get_slow(ops); if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out;