From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.15.19]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 2B2A83B2A0 for ; Sun, 16 Oct 2016 13:59:09 -0400 (EDT) Received: from android-e61e9610024ea52f.lan ([80.135.113.61]) by mail.gmx.com (mrgmx003) with ESMTPSA (Nemesis) id 0M1W5x-1coTX02Tcn-00tTAR; Sun, 16 Oct 2016 19:59:07 +0200 User-Agent: K-9 Mail for Android In-Reply-To: References: <1312D3AE-75A2-44F1-8F34-74AE81A5455B@yahoo.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----L9T6KPW7RVSNJ68M20ALILH9C53TUK" Content-Transfer-Encoding: 7bit From: Sebastian Moeller Date: Sun, 16 Oct 2016 19:59:08 +0200 To: "G. Amanakis" ,cake@lists.bufferbloat.net Message-ID: X-Provags-ID: V03:K0:RaVW3xqZUdHbshvxhExM0jseiSH0cmIK1I08tDFCpsnp8SKs9LM xmx5BYCrx4SoZbh02eIhBRlFeBc7apyZwwmFJYJ9LM0U3VHbnBAm0ILpto+r580KY5SoeUu MndrldqyK6JG8lwCHMofeWXPnPb78MDmsxbT9C2JK5IFyXPEjnoRRWbo/p0EVXpxV4kFAcT wWFLpdbKhk5sJezvxNZSg== X-UI-Out-Filterresults: notjunk:1;V01:K0:GtwvSxHB0fE=:xp52DAy1qu1VETmVMwY1Em fMDErdG3XliGLB26fvx9YIoahvjS3hjhMFsvv/VyiQLqKt8lqejBt+19I5MG8tGQu+CrCHCec mkM910E7ZMQHjWollCRm24F3CCNbhgnx2Kt4bwUk0jDu5MPxe8GBUf9FdqxbQUaFKxL7vkrlk xNqo/LLpfP/9ycWoESmZhVAZ5PU3lggcAt/TFsDySCGQHqfY5OzF7tX/sUfgH+RvA/uWZdPhv rULyjWNr34NoQ8SdbICZB42OSrtxblYmuT58MfaClLdsMwPlE5mP8ATWHM+g6W6wOQfzQD1+c mFwIOFDpHpirjpJFMZO7DKCC4zS0uXCbfAn61KhSh+f85EGJsZIviqTRJnehYuaWNY29tqw9a rp8+0oetDqtoMnsbIBF4rEsWhfOy9QFeIynDwr3KihDm2Zcx+NhIf7k3dznfBHa2Jrd2SJlfL ize49EfaZA6KBu7niqvKLuWP4/Es23EAN33uaympsiirKihfYqay3PrgW3RH8e83NMWSXJWZw wZ4Xr8wRxJhIN/gtNvWIfNT9DSjhP1WwI8+xbekAprha52NNMJ3vyltjRrwFk8jz0Vd0UDwza XTa0t9jkoGT2FwLrQ6bv3+nEHZ1CUg9zNVE2yul3Gau3pWdlSUoO0/StIixzZ4w2JB1z0dxuc hszfFKUrRwkMHdRfPQHclfCDQIvGiUkVqEqjsNzCjzMfuGeFLNq+4P+BkKb41OK8KvryjfbKh xc6gUeaWo5aTtKFA5ZSwJ39Czm0tYa6f8iJ9YAiBxbrpx0KFaqEOHLqM1YroLQUAjbe8arM/9 gO6KMUA Subject: Re: [Cake] Per-host fairness 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: Sun, 16 Oct 2016 17:59:09 -0000 ------L9T6KPW7RVSNJ68M20ALILH9C53TUK Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Hi, Could you also try dual-srchost on egress and dual-srchost on ingress, ple= ase=2E These promise per-IP fairness at the first level and per-flow fairne= ss "inside" each IP=2E So if you think through it you can setup the ingress= and egress shapers to aim for per-internal-IP address which I believe is w= hat you are after=2E Triple-isolate is much harder to argue with, partly be= cause it is lacking a clear description what it does short of the source co= de, so it is somewhat opaque what to expect in a given set of bidirectional= flows=2E In short you might have found a flaw in triple-isolate or it is w= orking as intended, which only JM will be able to answer=2E Cursory experim= ents in the past indicated that a properly configured dual-srchost/dsthost = pair on ingress and egress work closer to a layman's expectations=2E=2E=2E = Oh, with the new and shiny deNAT features the dual-isolation options should= now also work on a wan interface for IPv4, thanks to Kevin's persistence= =2E Best Regards Sebastian On October 16, 2016 7:30:04 PM GMT+02:00, "G=2E Amanakis" wrote: >I meant B gets always 1/3 of the bandwidth=2E It also gets worse if A is >using bittorrent=2E The setup with cake doesn't involve tc-flow or >marking packets with iptables=2E > >On October 16, 2016 11:57:03 AM EDT, "G=2E Amanakis" > wrote: >>I am trying the cobalt branch along with the 950-add-cake-to-tc=2Epatch >>from lede-git on Archlinux=2E However, I cannot get per-host fairness as >>expected, neither with IPv4 behind NAT, nor with IPv6=2E Having host A >>downloading from 2 sites and host B from 1, A gets always 1/3 of >>available bandwidth=2E I am using "bestefforts triple-isolate nat" on >>egress and ingress ifb of the WAN interface=2E Kernel 4=2E4=2E24 and 4= =2E7=2E6=2E >> >>The same setup with the same bandwidth limiting (3300kbit/900kbit) >>works as expected with fq_codel, tc-flow using mark for hashing, and >>iptables with HMARK using source egress ip for hashing and CONNMARK on >>WAN=2E > > >------------------------------------------------------------------------ > >_______________________________________________ >Cake mailing list >Cake@lists=2Ebufferbloat=2Enet >https://lists=2Ebufferbloat=2Enet/listinfo/cake ------L9T6KPW7RVSNJ68M20ALILH9C53TUK Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable Hi,

Could you also try dual-srchost on egress and dual-srchost on ingress, ple= ase=2E These promise per-IP fairness at the first level and per-flow fairne= ss "inside" each IP=2E So if you think through it you can setup t= he ingress and egress shapers to aim for per-internal-IP address which I be= lieve is what you are after=2E Triple-isolate is much harder to argue with,= partly because it is lacking a clear description what it does short of the= source code, so it is somewhat opaque what to expect in a given set of bid= irectional flows=2E In short you might have found a flaw in triple-isolate = or it is working as intended, which only JM will be able to answer=2E Curso= ry experiments in the past indicated that a properly configured dual-srchos= t/dsthost pair on ingress and egress work closer to a layman's expectat= ions=2E=2E=2E Oh, with the new and shiny deNAT features the dual-isolation = options should now also work on a wan interface for IPv4, thanks to Kevin&#= 39;s persistence=2E

Best Regards
Sebastian



On October 16, 2016 7:30:04 PM GMT+02:0= 0, "G=2E Amanakis" <g_amanakis@yahoo=2Ecom> wrote: I meant B gets always 1/3 of the bandwidth=2E It also gets worse if A is u= sing bittorrent=2E The setup with cake doesn't involve tc-flow or marki= ng packets with iptables=2E

On Octobe= r 16, 2016 11:57:03 AM EDT, "G=2E Amanakis" <g_amanakis@yahoo= =2Ecom> wrote:


Cake mailing listCake@lists=2Ebufferbloat=2Enet
https://lists=2Ebufferbloat=2Enet/listinfo/cake=
------L9T6KPW7RVSNJ68M20ALILH9C53TUK--