From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-io0-x22f.google.com (mail-io0-x22f.google.com [IPv6:2607:f8b0:4001:c06::22f]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 7CEA63CB3C for ; Mon, 23 Apr 2018 07:23:13 -0400 (EDT) Received: by mail-io0-x22f.google.com with SMTP id o7-v6so16161316iob.8 for ; Mon, 23 Apr 2018 04:23:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc; bh=4SXps5RPZazaXk2MilCUC5TLvruDC/40hIdVHytmf5c=; b=Plt2VFW7TVB2aX1PSoR/hB/Wr1dKaxyee4M0xWK5n9x2YIxKicL68Tq5HovdsUOauF NmJD77uNkS8dFGa8StFYUZs34SWfGFs8QCcnA85uJJJlKOenO7Ic3QVB332icBz8qITV VksHZygWhf0gn8fdqLam6PQSD1lk667SdWR2jvGDILJNFiGRY+qzmRmPBRuk68uPhYDf ptfl8L8dhnvzgqX1ToBbItN8bam6PChTnNesJvijfqip3HtxhtCAFo5T3twp3tLXK3bY eLEynynMm9P3EtIZXnZTwSjxfrrmDnN7kh3WAZbWsgjVpvyDdSEF2LwT2lCl/ZavJVkm Z5OQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:in-reply-to:references:from:date :message-id:subject:to:cc; bh=4SXps5RPZazaXk2MilCUC5TLvruDC/40hIdVHytmf5c=; b=eo5pLNhHspT2l/1V8ZUXBcsMi6oGZ9GdCLDIMMae/tJ9tRu70gV+tM8pKGmi89zIkG DVnLV/TN2rsmsz8Ie84+qrKDQK8QwytJlTcJIcXTaJt96htjAo0cdlLUAeMsKgzAi4jq 4CoiQGVUMFvkqOZjhyRtZ+oy26Y7BBm7YBvbEO2aELd88l593tgcNIjPnBR2ssn8o0/p UG3wtceGmaZWXfnW/VRXHQtLDcQEtKbtW+qOHa3VXedk5Yi1xMv2cy0CUWStrLrIcmUs LExCFkG4NPcic2aZtOGGyON20/k76Bdf+Rrb7dJ3SrhdRWfhSwrVU9UWHrcTNzniZB8q j08g== X-Gm-Message-State: ALQs6tDjot+4k4VzsyrfrpgKdrSHxSH03TGBs5kgYfvLTeWMcDKBqb1Q DOLtHg9yKlp9IqFm7smr3XDcrvpDgTZMMvpbCU4= X-Google-Smtp-Source: AB8JxZrmcA4R0Yd3ohU3g22IuZUA3QM7XP0FTybZA6z5PpO+nD9MtMsfjuKHBs/UJQN4n5bYox+e3kd0g+hUxGSBrUg= X-Received: by 2002:a6b:a867:: with SMTP id r100-v6mr20691022ioe.143.1524482592930; Mon, 23 Apr 2018 04:23:12 -0700 (PDT) MIME-Version: 1.0 Received: by 2002:a02:52c8:0:0:0:0:0 with HTTP; Mon, 23 Apr 2018 04:23:12 -0700 (PDT) In-Reply-To: References: <87a7tv3r5z.fsf@toke.dk> From: =?UTF-8?Q?Jonas_M=C3=A5rtensson?= Date: Mon, 23 Apr 2018 13:23:12 +0200 Message-ID: To: Jonathan Morton Cc: =?UTF-8?B?VG9rZSBIw7hpbGFuZC1Kw7hyZ2Vuc2Vu?= , Cake List Content-Type: multipart/alternative; boundary="0000000000006b0132056a824378" Subject: Re: [Cake] Testing variants of the MTU latency scaling X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Apr 2018 11:23:13 -0000 --0000000000006b0132056a824378 Content-Type: text/plain; charset="UTF-8" One thing that is still not clear to me from these results: if I run cake on an IFB without ingress mode (i.e. the default?), does the MTU scaling have any impact on TCP download throughput? /Jonas On Sun, Apr 22, 2018 at 11:09 PM, Jonathan Morton wrote: > > Takeaways (see attached plots): > > > > - The MTU scaling does indeed give a nice benefit in egress mode > > "tcp-download-totals" plot. From just over 6 Mbps to just over 8 Mbps > > of goodput on the 10 Mbit link. There is not a large difference > > between 2MTU and 4MTU, except that 4MTU hurts inter-flow latency > > somewhat. > > > > - The effect for upload flows (where Cake is before the bottleneck; > > 10mbit-upload.png) is negligible. > > > > - The MTU scaling really hurts TCP RTT (intra-flow latency; > > tcp-upload-tcprtt-10mbit.png and rrul-tcprtt.png). > > > > - For bidirectional traffic the combined effect is also negligible. > > > > > > Based on all this, I propose we change the scaling mechanism so that it > > is only active in egress mode, and change it from 4 MTUs to 2. I'll > > merge Kevin's patch to do this unless someone complains loudly :) > > > > If you want me to run other tests, let me know. > > I'm not actually sure what you've measured here - unless you've somehow > managed to swap "ingress" with "egress" mode in a strange manner. I don't > see any systematic measurement of the different MTU scales in ingress mode > in your results, which makes your assertion that it should only be active > in egress mode rather odd. > > - Jonathan Morton > > _______________________________________________ > Cake mailing list > Cake@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/cake > --0000000000006b0132056a824378 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
One thing that is still not clear to me from these results= : if I run cake on an IFB without ingress mode (i.e. the default?), does th= e MTU scaling have any impact on TCP download throughput?

/Jonas

On Sun, Apr 22, 2018 at 11:09 PM, Jonathan Morton <= chromatix99@gmai= l.com> wrote:
> Takeaways (see attached plots):
>
> - The MTU scaling does indeed give a nice benefit in egress mode
>=C2=A0 "tcp-download-totals" plot. From just over 6 Mbps to j= ust over 8 Mbps
>=C2=A0 of goodput on the 10 Mbit link. There is not a large difference<= br> >=C2=A0 between 2MTU and 4MTU, except that 4MTU hurts inter-flow latency=
>=C2=A0 somewhat.
>
> - The effect for upload flows (where Cake is before the bottleneck; >=C2=A0 10mbit-upload.png) is negligible.
>
> - The MTU scaling really hurts TCP RTT (intra-flow latency;
>=C2=A0 tcp-upload-tcprtt-10mbit.png and rrul-tcprtt.png).
>
> - For bidirectional traffic the combined effect is also negligible. >
>
> Based on all this, I propose we change the scaling mechanism so that i= t
> is only active in egress mode, and change it from 4 MTUs to 2. I'l= l
> merge Kevin's patch to do this unless someone complains loudly :)<= br> >
> If you want me to run other tests, let me know.

I'm not actually sure what you've measured here - unless you= 've somehow managed to swap "ingress" with "egress"= mode in a strange manner.=C2=A0 I don't see any systematic measurement= of the different MTU scales in ingress mode in your results, which makes y= our assertion that it should only be active in egress mode rather odd.

=C2=A0- Jonathan Morton

_______________________________________________
Cake mailing list
Cake@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/cake

--0000000000006b0132056a824378--