From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from nm3-vm0.bullet.mail.ne1.yahoo.com (nm3-vm0.bullet.mail.ne1.yahoo.com [98.138.91.55]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id D5370208AA0 for ; Tue, 4 Dec 2012 01:23:49 -0800 (PST) Received: from [98.138.90.53] by nm3.bullet.mail.ne1.yahoo.com with NNFMP; 04 Dec 2012 09:23:46 -0000 Received: from [98.138.87.9] by tm6.bullet.mail.ne1.yahoo.com with NNFMP; 04 Dec 2012 09:23:46 -0000 Received: from [127.0.0.1] by omp1009.mail.ne1.yahoo.com with NNFMP; 04 Dec 2012 09:23:46 -0000 X-Yahoo-Newman-Property: ymail-3 X-Yahoo-Newman-Id: 737911.12783.bm@omp1009.mail.ne1.yahoo.com Received: (qmail 77583 invoked by uid 60001); 4 Dec 2012 09:23:46 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1354613026; bh=ZHtK+I62kqzjKeFUOlN5pue341uKNxveNRtcspdc2JE=; h=X-YMail-OSG:Received:X-Rocket-MIMEInfo:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=OwVF4PRxGEfPXXEQW3A/rCqgfG4ssT0afcITBovR98b5uD3xb7Mv4GtACtdsbdelB8smd2ufWj8BnsTSqhdbK0rajVvoPI8y6nF9d1/of98FCuTCvhJO+bM/a/ZdcOg2a/4QuLlsEiHJXrCjTtl7LiTuM3G/VmBRyk4BLdJorRI= DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:X-Rocket-MIMEInfo:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=vB9Awn/dIIh8+HFnFtWoq6ScNRSOTkdQbXwmDmKChe8JWR9q7CgSHfzKTxxumcZ0sRoZkcfzNYcM6riG9hE0657snLZV/UO5V6svQSMTDsFwsKpbLNkVkkxS1aCnSkzTMcJRZV8RJjOyAugje+oyIGThLD74DNDvvE8Uiod53J8=; X-YMail-OSG: DCEdEyYVM1kVBq2jEWXlKtQ7MXNsoaS6RHQsCJVat0WTM7Q K1xbq01HOVb9.fg86dJQzmfkO7XTMDUvZS.zUbUuBiVNFszk4DRgEZnkdg3A MgELPTqf8uZnXqW7sEO9pLUBdLqbaljXsTiv6WwWIKTTnhYoGCrVh8zgvAau JYQ4yc.EAQjj3cjCZyrm.UHd2.IxwC1eS5yKV8a2NmWzIXiYM7Ts57Z3OG.W 0ld4BSerCxQ1XQmXZOdwj00_BiqDSv7dO87YxTdJd2YQ5Oy..5KxJELoUfP7 DDSuDlgzg0O0m7W7nbXymd0RdIgW8VlucJh0331AcB_667cIKICAF7scxvR1 qntkbxStSBWfyrcNL2Ueh9qWeEm8X_MdLChNiMozaBKuXFfrTGLHEABu.hP7 8I1Kp9s.wdlROqxzD6TofAf_Gt1i2FhknBgI2TAbrCdkdVgY4gVtQo.Uq6Mv YxiF8hQ18LrnnpPxbblmCOIjD.T6UEr9rfRSgHGnwXM6yJhVam05iclXDU2a .5CoX8siexgxC19czIZHNtX5kC5Q434f_1YGbAzuMNvuXCPXX9tXet4kexMQ sLgTPlZ9lHm_WGr3Jkna46ftCg9CdH4ywMQsbkzOcnethcMt3MA4oOmoXKI6 jYbjjtJI8CVHOzdzLSDLmWqK70edMikAs6WBU737Qm3otnjvRFqjjQJiHIjt JGPz7HDN9xen0NASutHJxsRFdsEGYXBlbG14uSIG2DHOOEDUVleynjdlYCHb aXjDO_N2gBR0J8iEAJA_Pn1bcBuUIPsvr4kUiyQfTvJ_RJPpEWG949SPyThR uQ13JFZQtrCnNBCcKUC9xgl0EUZayUtkcKHvDQoGBhDK8_VdzFb1Mkvj1Aqg qghY9_9CnM.Xrlfxazro7_mhBbU5R0vqrA5mhllfVnHA- Received: from [79.68.67.23] by web126202.mail.ne1.yahoo.com via HTTP; Tue, 04 Dec 2012 01:23:46 PST X-Rocket-MIMEInfo: 001.001, W09vcHMsIGludGVuZGVkIHRvIENDIHRoZSBsaXN0Ll0KCkFuIGV4dHJhIDE1LTIwbXMgb2YgbGF0ZW5jeSwgd2hpY2ggaXMgd2hhdCB5b3UncmUgc2VlaW5nIHRoZXJlLCAKc2hvdWxkbid0IGJlIGNhdXNlZCBieSBwYWNrZXQgb3ZlcmhlYWQgaW4gdGhlIGFjdHVhbCBWRFNMIG1vZGVtIHBhcnQgb2YgCnRoZSBkZXZpY2UuIFdvcnN0IGNhc2UgdGhlIGltcGxlbWVudGF0aW9uIG9mIHRoZSBQVE0tVEMgbGF5ZXIgKHRoZSAKZXF1aXZhbGVudCBvZiBBVE0pIG1pZ2h0IHJvdW5kIHRoZSBwYWNrZXQgdXAgdG8gYSABMAEBAQE- X-Mailer: YahooMailWebService/0.8.128.478 References: <20121123221842.GD2829@linux.vnet.ibm.com> <20121128172058.GB2474@linux.vnet.ibm.com> <20121202230635.GA16359@linux.vnet.ibm.com> <87obib5qf8.fsf@toke.dk> <1354550303.24281.103.camel@shinybook.infradead.org> <1354590837.29387.9.camel@ganymede.home> Message-ID: <1354613026.72238.YahooMailNeo@web126202.mail.ne1.yahoo.com> Date: Tue, 4 Dec 2012 01:23:46 -0800 (PST) From: Alex Burr To: Dan Siemon , bloat , "codel@lists.bufferbloat.net" , "cerowrt-devel@lists.bufferbloat.net" In-Reply-To: <1354590837.29387.9.camel@ganymede.home> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Subject: Re: [Bloat] [Codel] [Cerowrt-devel] FQ_Codel lwn draft article review X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list Reply-To: Alex Burr List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 04 Dec 2012 09:23:50 -0000 [Oops, intended to CC the list.]=0A=0AAn extra 15-20ms of latency, which is= what you're seeing there, =0Ashouldn't be caused by packet overhead in the= actual VDSL modem part of =0Athe device. Worst case the implementation of = the PTM-TC layer (the =0Aequivalent of ATM) might round the packet up to a = multiple of 64 bytes =0A(although it's not supposed to), but unless your li= ne rate is 25kbps, =0Athat should not cause 20ms of latency. =0A=0AVDSL2 op= erates at 4Khz or=0A 8Khz symbol rate, and while it contains and interleavi= ng or =0Aretransmission layer which can add up to 64ms in its most high-lat= ency =0Aconfiguration, those layers do not operate at the level of packets = and =0AI'm pretty sure that that latency cannot be affected by packet size = in a=0A conformant implementation.=0AThis latency is being caused by someth= ing else. =0A=0AThe=0A best way to figure out the per-packet overhead in yo= ur VDSL2 modem is =0Aprobably=A0 to count the number of packets that get th= rough, not measure =0Alatency. =0A=0AAlex=0A=0A=0A=0A----- Original Message= -----=0A> From: Dan Siemon =0A> To: bloat ; codel@lists.bufferbloat.net; cerowrt-devel@lists.bufferbl= oat.net=0A> Cc: =0A> Sent: Tuesday, December 4, 2012 3:13 AM=0A> Subject: R= e: [Bloat] [Codel] [Cerowrt-devel] FQ_Codel lwn draft article review=0A> = =0A> On Mon, 2012-12-03 at 15:58 +0000, David Woodhouse wrote:=0A>> ADSL i= s basically just ATM with a strange PHY. You have a bunch of=0A>> options = for how you use this ATM link. Mostly it's RFC2364 PPP-over-ATM=0A>> or it= 's PPPoE on top of RFC2684 Ethernet-over-ATM.=0A> =0A> Speaking of xDSL, do= es anyone on the list happen to have a good=0A> understanding of how much p= er-packet overhead there is on VDSL2? I've=0A> been tweaking the buffering = and shaping on my upstream link and noticed=0A> unexpected behavior with sm= all packets.=0A> =0A> The link below (use wayback machine version) has a go= od description of=0A> per-packet overhead for various forms of ADSL but I h= aven't found=0A> something similar for more modern DSL variants.=0A> http:/= /www.adsl-optimizer.dk/thesis/=0A> http://web.archive.org/web/2009042213154= 7/http://www.adsl-optimizer.dk/thesis/=0A> =0A> I started a discussion on D= SLReports=0A> http://www.dslreports.com/forum/r27565251-Internet-Per-packet= -overhead-on-Bell-s-VDSL-ATM-based-=0A> but experimentally the overhead dis= cussed there doesn't appear to be=0A> correct=0A> http://www.coverfire.com/= archives/2012/11/29/per-packet-overhead-on-vdsl2/=0A> =0A> =0A> =0A> ______= _________________________________________=0A> Bloat mailing list=0A> Bloat@= lists.bufferbloat.net=0A> https://lists.bufferbloat.net/listinfo/bloat=0A>