From mboxrd@z Thu Jan  1 00:00:00 1970
From: Cong Wang <xiyou.wangcong@gmail.com>
Subject: Re: [PATCH net-next] net: preserve sock reference when scrubbing the skb.
Date: Tue, 26 Jun 2018 18:28:27 -0700
Message-ID: <CAM_iQpWxHb8VrHUQAEgOQ0YsSVt5MMZvGvAQVuA-JGcfjc=ubg@mail.gmail.com>
References: <20180625155610.30802-1-fbl@redhat.com> <CAM_iQpX_X4hhSSrhMZavLibobp6tgMEa_26T6j4QvACKg-HPvw@mail.gmail.com>
 <48e15faf-f935-0166-e1db-18f7286e7264@gmail.com> <CAM_iQpU0jp=wvutGbSLzVYX5qQeW0W8ARvR=-gp4MYJqWeee_A@mail.gmail.com>
 <20180626220300.GT19565@plex.lan> <CAM_iQpU8E5OuXx87Dm+jbqwbkkwETNF_RZh-VnUkF5seFPvv_A@mail.gmail.com>
 <20180626233302.GU19565@plex.lan> <CAM_iQpVmbuVK+pfhad7HrQtaSxFbe7K=59_34f0BwxoP_=W0VQ@mail.gmail.com>
 <20180627003925.GV19565@plex.lan>
Mime-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
        Linux Kernel Network Developers <netdev@vger.kernel.org>,
        Paolo Abeni <pabeni@redhat.com>,
        David Miller <davem@davemloft.net>,
        Florian Westphal <fw@strlen.de>,
        NetFilter <netfilter-devel@vger.kernel.org>
To: Flavio Leitner <fbl@redhat.com>
Return-path: <netdev-owner@vger.kernel.org>
Received: from mail-pl0-f66.google.com ([209.85.160.66]:43237 "EHLO
        mail-pl0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751984AbeF0B2l (ORCPT
        <rfc822;netdev@vger.kernel.org>); Tue, 26 Jun 2018 21:28:41 -0400
In-Reply-To: <20180627003925.GV19565@plex.lan>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

On Tue, Jun 26, 2018 at 5:39 PM Flavio Leitner <fbl@redhat.com> wrote:
>
> On Tue, Jun 26, 2018 at 05:29:51PM -0700, Cong Wang wrote:
> > On Tue, Jun 26, 2018 at 4:33 PM Flavio Leitner <fbl@redhat.com> wrote:
> > >
> > > It is still isolated, the sk carries the netns info and it is
> > > orphaned when it re-enters the stack.
> >
> > Then what difference does your patch make?
>
> Don't forget it is fixing two issues.

Sure. I am only talking about TSQ from the very beginning.
Let me rephrase my above question:
What difference does your patch make to TSQ?


>
> > Before your patch:
> > veth orphans skb in its xmit
> >
> > After your patch:
> > RX orphans it when re-entering stack (as you claimed, I don't know)
>
> ip_rcv, and equivalents.


ip_rcv() is L3, we enter a stack from L1. So your above claim is incorrect. :)

>
> > And for veth pair:
> > xmit from one side is RX for the other side
> > So, where is the queueing? Where is the buffer bloat? GRO list??
>
> CPU backlog.

Yeah, but this is never targeted by TSQ:

        tcp_limit_output_bytes limits the number of bytes on qdisc
        or device to reduce artificial RTT/cwnd and reduce bufferbloat.

which means you have to update Documentation/networking/ip-sysctl.txt
too.