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=-9.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED autolearn=unavailable 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 C0AA2C2BD0C for ; Tue, 13 Oct 2020 15:29:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 73A9F251BE for ; Tue, 13 Oct 2020 15:29:27 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com header.i=@bytedance-com.20150623.gappssmtp.com header.b="lyyUl7Z9" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2389480AbgJMP3V (ORCPT ); Tue, 13 Oct 2020 11:29:21 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:45406 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2389467AbgJMP3U (ORCPT ); Tue, 13 Oct 2020 11:29:20 -0400 Received: from mail-pj1-x1042.google.com (mail-pj1-x1042.google.com [IPv6:2607:f8b0:4864:20::1042]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E6632C0613D0 for ; Tue, 13 Oct 2020 08:29:19 -0700 (PDT) Received: by mail-pj1-x1042.google.com with SMTP id a1so50818pjd.1 for ; Tue, 13 Oct 2020 08:29:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20150623.gappssmtp.com; s=20150623; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc:content-transfer-encoding; bh=xmr9b2Ggp8vOLTZ40kBRiYw2atMdRLPI8Ee7OiUDyHc=; b=lyyUl7Z9ThTPlq9D2rp4fQb4kHeOa2+gyk1WzoDlJ81EPW4a1S7cHQBclhadcWkuts +pTnQ3BZKMze2oN803izG6UhpDN8TPayQltN5p0sSHSa3Q7nCT+5KEjjlqOjqputq3cc 4ogahHM0g0MZkQrVz8qlPbLicoR/9tbhsyClHF7hnEIXQcCq7uSJUv6sqHyRTrUSFtQv BQmWSD9+Sr2Tj/3BgV3HG+/mxrzsOUcpmJyZhsAwfAMUHuCWlTKpgYgQNlx6jCKoLHTC GgKJH5amJfyNqn+3LnJT3B77eLhaVCn3vQhI6w1MfbWQSBHHuO6zwVOyO2t8ZT6AwxZ8 Pizg== 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:content-transfer-encoding; bh=xmr9b2Ggp8vOLTZ40kBRiYw2atMdRLPI8Ee7OiUDyHc=; b=cdx7wAo0PqKYO/EgeoAkl7w+LiJxVP7RHfi15Q7gw6v0KDVa2ZxRVxSMTuxxs/aBkZ 2hA7nMti22XQoSnfvCiYXrrQYx8TZIeu9UR97lwfTm6exCk8tfYqrtPBFixGN/U/i9fi RdUpXo8ikSM611IJENStHzW00ERPXwkMKPVAraRrGtKbSym4XUUUtBBzgUdhDc5ebgn8 iVCr3nMuTLasmJTjt5sY8vh0iAHCl4VhRncqCr3MU30og6Q3Yj3YWf2ymh7qYy8ccsqS OjHf+IgSvE20ScBzJyQvzaUFcqmvTyAJrJxCjw458+TImTuu8hwngPRYXwDZ1IxIBVtW hc3w== X-Gm-Message-State: AOAM532GobkwND9WjI6N7KhQohfc9FOi7W3hXzPPiwkkzbswEtBXXTAw rORzPI6qF80IeYSlnhkor0dvK/0co22cAMSWrk6dmA== X-Google-Smtp-Source: ABdhPJza1dCd7KiemxFvOO8CGqWiAW2qXHNbFR3rDPenQOK0HTo9HZRimzAjnS7d53o9A0B4BtDP+1rwCnL2rU9nptk= X-Received: by 2002:a17:902:7681:b029:d2:88b1:b130 with SMTP id m1-20020a1709027681b02900d288b1b130mr393135pll.20.1602602959313; Tue, 13 Oct 2020 08:29:19 -0700 (PDT) MIME-Version: 1.0 References: <20201010103854.66746-1-songmuchun@bytedance.com> <9262ea44-fc3a-0b30-54dd-526e16df85d1@gmail.com> <20201013080906.GD4251@kernel.org> In-Reply-To: <20201013080906.GD4251@kernel.org> From: Muchun Song Date: Tue, 13 Oct 2020 23:28:41 +0800 Message-ID: Subject: Re: [External] Re: [PATCH] mm: proc: add Sock to /proc/meminfo To: Mike Rapoport Cc: Eric Dumazet , Eric Dumazet , Cong Wang , Greg KH , rafael@kernel.org, "Michael S. Tsirkin" , Jason Wang , David Miller , Jakub Kicinski , Alexey Dobriyan , Andrew Morton , Alexey Kuznetsov , Hideaki YOSHIFUJI , Steffen Klassert , Herbert Xu , Shakeel Butt , Will Deacon , Michal Hocko , Roman Gushchin , Neil Brown , Sami Tolvanen , "Kirill A. Shutemov" , Feng Tang , Paolo Abeni , Willem de Bruijn , Randy Dunlap , Florian Westphal , gustavoars@kernel.org, Pablo Neira Ayuso , Dexuan Cui , Jakub Sitnicki , Peter Zijlstra , Christian Brauner , "Eric W. Biederman" , Thomas Gleixner , dave@stgolabs.net, Michel Lespinasse , Jann Horn , chenqiwu@xiaomi.com, christophe.leroy@c-s.fr, Minchan Kim , Martin KaFai Lau , Alexei Starovoitov , Daniel Borkmann , Miaohe Lin , Kees Cook , LKML , virtualization@lists.linux-foundation.org, Linux Kernel Network Developers , linux-fsdevel , linux-mm , Michael Kerrisk Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org On Tue, Oct 13, 2020 at 4:09 PM Mike Rapoport wrote: > > On Mon, Oct 12, 2020 at 05:53:01PM +0800, Muchun Song wrote: > > On Mon, Oct 12, 2020 at 5:24 PM Eric Dumazet w= rote: > > > > > > On 10/12/20 10:39 AM, Muchun Song wrote: > > > > On Mon, Oct 12, 2020 at 3:42 PM Eric Dumazet = wrote: > > > >> > > > >> On Mon, Oct 12, 2020 at 6:22 AM Muchun Song wrote: > > > >>> > > > >>> On Mon, Oct 12, 2020 at 2:39 AM Cong Wang wrote: > > > >>>> > > > >>>> On Sat, Oct 10, 2020 at 3:39 AM Muchun Song wrote: > > > >>>>> > > > >>>>> The amount of memory allocated to sockets buffer can become sig= nificant. > > > >>>>> However, we do not display the amount of memory consumed by soc= kets > > > >>>>> buffer. In this case, knowing where the memory is consumed by t= he kernel > > > >>>> > > > >>>> We do it via `ss -m`. Is it not sufficient? And if not, why not = adding it there > > > >>>> rather than /proc/meminfo? > > > >>> > > > >>> If the system has little free memory, we can know where the memor= y is via > > > >>> /proc/meminfo. If a lot of memory is consumed by socket buffer, w= e cannot > > > >>> know it when the Sock is not shown in the /proc/meminfo. If the u= naware user > > > >>> can't think of the socket buffer, naturally they will not `ss -m`= . The > > > >>> end result > > > >>> is that we still don=E2=80=99t know where the memory is consumed.= And we add the > > > >>> Sock to the /proc/meminfo just like the memcg does('sock' item in= the cgroup > > > >>> v2 memory.stat). So I think that adding to /proc/meminfo is suffi= cient. > > > >>> > > > >>>> > > > >>>>> static inline void __skb_frag_unref(skb_frag_t *frag) > > > >>>>> { > > > >>>>> - put_page(skb_frag_page(frag)); > > > >>>>> + struct page *page =3D skb_frag_page(frag); > > > >>>>> + > > > >>>>> + if (put_page_testzero(page)) { > > > >>>>> + dec_sock_node_page_state(page); > > > >>>>> + __put_page(page); > > > >>>>> + } > > > >>>>> } > > > >>>> > > > >>>> You mix socket page frag with skb frag at least, not sure this i= s exactly > > > >>>> what you want, because clearly skb page frags are frequently use= d > > > >>>> by network drivers rather than sockets. > > > >>>> > > > >>>> Also, which one matches this dec_sock_node_page_state()? Clearly > > > >>>> not skb_fill_page_desc() or __skb_frag_ref(). > > > >>> > > > >>> Yeah, we call inc_sock_node_page_state() in the skb_page_frag_ref= ill(). > > > >>> So if someone gets the page returned by skb_page_frag_refill(), i= t must > > > >>> put the page via __skb_frag_unref()/skb_frag_unref(). We use PG_p= rivate > > > >>> to indicate that we need to dec the node page state when the refc= ount of > > > >>> page reaches zero. > > > >>> > > > >> > > > >> Pages can be transferred from pipe to socket, socket to pipe (spli= ce() > > > >> and zerocopy friends...) > > > >> > > > >> If you want to track TCP memory allocations, you always can look = at > > > >> /proc/net/sockstat, > > > >> without adding yet another expensive memory accounting. > > > > > > > > The 'mem' item in the /proc/net/sockstat does not represent real > > > > memory usage. This is just the total amount of charged memory. > > > > > > > > For example, if a task sends a 10-byte message, it only charges one > > > > page to memcg. But the system may allocate 8 pages. Therefore, it > > > > does not truly reflect the memory allocated by the above memory > > > > allocation path. We can see the difference via the following messag= e. > > > > > > > > cat /proc/net/sockstat > > > > sockets: used 698 > > > > TCP: inuse 70 orphan 0 tw 617 alloc 134 mem 13 > > > > UDP: inuse 90 mem 4 > > > > UDPLITE: inuse 0 > > > > RAW: inuse 1 > > > > FRAG: inuse 0 memory 0 > > > > > > > > cat /proc/meminfo | grep Sock > > > > Sock: 13664 kB > > > > > > > > The /proc/net/sockstat only shows us that there are 17*4 kB TCP > > > > memory allocations. But apply this patch, we can see that we truly > > > > allocate 13664 kB(May be greater than this value because of per-cpu > > > > stat cache). Of course the load of the example here is not high. In > > > > some high load cases, I believe the difference here will be even > > > > greater. > > > > > > > > > > This is great, but you have not addressed my feedback. > > > > > > TCP memory allocations are bounded by /proc/sys/net/ipv4/tcp_mem > > > > > > Fact that the memory is forward allocated or not is a detail. > > > > > > If you think we must pre-allocate memory, instead of forward allocati= ons, > > > your patch does not address this. Adding one line per consumer in /pr= oc/meminfo looks > > > wrong to me. > > > > I think that the consumer which consumes a lot of memory should be adde= d > > to the /proc/meminfo. This can help us know the user of large memory. > > > > > > > > If you do not want 9.37 % of physical memory being possibly used by T= CP, > > > just change /proc/sys/net/ipv4/tcp_mem accordingly ? > > > > We are not complaining about TCP using too much memory, but how do > > we know that TCP uses a lot of memory. When I firstly face this problem= , > > I do not know who uses the 25GB memory and it is not shown in the /proc= /meminfo. > > If we can know the amount memory of the socket buffer via /proc/meminfo= , we > > may not need to spend a lot of time troubleshooting this problem. Not e= veryone > > knows that a lot of memory may be used here. But I believe many people > > should know /proc/meminfo to confirm memory users. > > If I undestand correctly, the problem you are trying to solve is to > simplify troubleshooting of memory usage for people who may not be aware > that networking stack can be a large memory consumer. Yeah, you are right. Although the information provided by /proc/net/socksta= t is not accurate, it can also provide some valuable information. I think tha= t it might be better if we can add a total amount socket buffer to /proc/meminfo= . The amount socket buffer statistics can be from /proc/net/sockstat directly= . Thanks. > > For that a paragraph in 'man 5 proc' maybe a good start: > > From ddbcf38576d1a2b0e36fe25a27350d566759b664 Mon Sep 17 00:00:00 2001 > From: Mike Rapoport > Date: Tue, 13 Oct 2020 11:07:35 +0300 > Subject: [PATCH] proc.5: meminfo: add not anout network stack memory > consumption > > Signed-off-by: Mike Rapoport > --- > man5/proc.5 | 8 ++++++++ > 1 file changed, 8 insertions(+) > > diff --git a/man5/proc.5 b/man5/proc.5 > index ed309380b..8414676f1 100644 > --- a/man5/proc.5 > +++ b/man5/proc.5 > @@ -3478,6 +3478,14 @@ Except as noted below, > all of the fields have been present since at least Linux 2.6.0. > Some fields are displayed only if the kernel was configured > with various options; those dependencies are noted in the list. > +.IP > +Note that significant part of memory allocated by the network stack > +is not accounted in the file. > +The memory consumption of the network stack can be queried > +using > +.IR /proc/net/sockstat > +or > +.BR ss (8) > .RS > .TP > .IR MemTotal " %lu" > -- > 2.25.4 > > --=20 Yours, Muchun