Received-SPF: pass (google.com: best guess record for domain of linux-wireless-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Content-Type: text/plain;
        charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 11.5 \(3445.9.1\))
Subject: Re: [Make-wifi-fast] debugging TCP stalls on high-speed wifi
From:   Simon Barber <simon@superduper.net>
In-Reply-To: <34a05f62-8dd0-9ea0-2192-1da5bfe6d843@gmail.com>
Date:   Thu, 12 Dec 2019 17:57:13 -0800
Cc:     Dave Taht <dave.taht@gmail.com>,
        Make-Wifi-fast <make-wifi-fast@lists.bufferbloat.net>,
        Johannes Berg <johannes@sipsolutions.net>,
        linux-wireless <linux-wireless@vger.kernel.org>,
        Neal Cardwell <ncardwell@google.com>,
        Netdev <netdev@vger.kernel.org>
Content-Transfer-Encoding: 8BIT
Message-Id: <5DBB113A-E61A-4032-B877-18BE3ABBC616@superduper.net>
References: <14cedbb9300f887fecc399ebcdb70c153955f876.camel@sipsolutions.net>
 <CADVnQym_CNktZ917q0-9dVY9dhtiJVRRotGTrPNdZUpkjd3vyw@mail.gmail.com>
 <f4670ce0f4399fe82e7168fb9c491d8eb718e8d8.camel@sipsolutions.net>
 <99748db5-7898-534b-d407-ed819f07f939@gmail.com>
 <ff6b35ad589d7cf0710cb9fca4c799538da2e653.camel@sipsolutions.net>
 <CAA93jw6b6n0jm_BC6DbccEU3uN9zXcfjqnZMNm=vFjLVqYKyNA@mail.gmail.com>
 <22B5F072-630A-44BE-A0E5-BF814A6CB9B0@superduper.net>
 <34a05f62-8dd0-9ea0-2192-1da5bfe6d843@gmail.com>
To:     Eric Dumazet <eric.dumazet@gmail.com>
Sender: linux-wireless-owner@vger.kernel.org
Precedence: bulk

In my application this is a bridge or router (not TCP endpoint), and the driver is doing GRO and NAPI polling. Also looking at using the skb->fraglist to make the GRO code more effective and more transparent by passing flags, short segments, etc through for perfect reconstruction by TSO.

Simon

> On Dec 12, 2019, at 5:46 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> 
> 
> 
> On 12/12/19 4:59 PM, Simon Barber wrote:
>> I’m currently adding ACK thinning to Linux’s GRO code. Quite a simple addition given the way that code works.
>> 
>> Simon
>> 
>> 
> 
> Please don't.
> 
> 1) It will not help since many NIC  do not use GRO.
> 
> 2) This does not help if you receive one ACK per NIC interrupt, which is quite common.
> 
> 3) This breaks GRO transparency.
> 
> 4) TCP can implement this in a more effective/controlled way,
>   since the peer know a lot more flow characteristics.
> 
> Middle-box should not try to make TCP better, they usually break things.