From: Colin Dearborn <Colin.Dearborn@sjrb.ca>
To: Sebastian Moeller <moeller0@gmx.de>,
Neal Cardwell <ncardwell@google.com>
Cc: bloat <bloat@lists.bufferbloat.net>
Subject: Re: [Bloat] DOCSIS cable modems that support PIE?
Date: Mon, 13 May 2019 15:48:57 +0000 [thread overview]
Message-ID: <CY4PR04MB0393A49C5122CE49B6212358950F0@CY4PR04MB0393.namprd04.prod.outlook.com> (raw)
In-Reply-To: <435DE302-6F36-47A2-9338-CADED90CB66B@gmx.de>
CM AQM was added as an optional feature in DOCSIS 3.0. I don't know of any 3.0 modems where this was actually implemented though.
This feature requires no support from the CMTS/CCAP chassis, so as long as the modem supports it, it will work, regardless of the supported DOCSIS version of the CMTS.
I have verified AQM working with the Arris CM8200A, the Technicolor TC4400, the Hitron CODA-46 and the Hitron CODA-4582. AQM is on by default on these modems, so unless the ISP is intentionally turning it off, it'll be there.
-----Original Message-----
From: Bloat <bloat-bounces@lists.bufferbloat.net> On Behalf Of Sebastian Moeller
Sent: Monday, May 13, 2019 9:28 AM
To: Neal Cardwell <ncardwell@google.com>
Cc: bloat <bloat@lists.bufferbloat.net>
Subject: Re: [Bloat] DOCSIS cable modems that support PIE?
CAUTION: This email is from an external source. Do not click links or open attachments unless you recognize the sender and know the content is safe.
Hi Neal,
> On May 13, 2019, at 17:13, Neal Cardwell <ncardwell@google.com> wrote:
>
> Thanks for the details!
>
> Given that DOCSIS 3.1 (released initially in 2013) has many revisions - https://specification-search.cablelabs.com/CM-SP-MULPIv3.1?v=03 - and low-latency DOCSIS and L4S was added in 2019 (CM-SP-MULPIv3.1-I17-190121), I had been under the impression that the PIE AQM for upstream traffic was also added in some later revision. But I do see now that the PIE AQM for upstream traffic was in Annex M of the initial 3.1 spec (CM-SP-MULPIv3.1-I01-131029).
Yes, that was actually pretty col to see this as a requirement from day 1. It is a bit of a downer how long the ISPs take/took to actually roll-out docsis 3.1.
>
> Does anyone happen to know if (and if so, how widely) the major cable ISPs world-wide enable the upstream PIE AQM functionality?
I have no clue, but I believe Greg White (CC'd) might have more insight in this.
Best Regards
Sebastian
>
> neal
>
>
> From: Sebastian Moeller <moeller0@gmx.de>
> Date: Mon, May 13, 2019 at 5:16 AM
> To: bloat, Neal Cardwell
>
> Hi Neal,
>
> As far as I can tell the PIE aqm is mandatory in all DOCSIS 3.1 CPEs, do Al you need is a modem certified for 3.1 and probably also an DOCSIS ISP supplying 3.1 services (I assume the AQM will only be engaged in a docsis 3.1 environment), as in DOCSIS the ISP basically has control over the CPE, so you would need their cooperation. Not every DOCSIS ISP will provision any customer modem, but I assume you have enough leverage to make this happen.
>
> Anyway according to the spec sheets:
> AVM Fritzbox 6591
> Netgear CM1000-1AZNAS
> Arris SB8200
> Motorola MB8600
> should give you what you want.
>
> Best Reards
> Sebastian
>
> P.S.: I would love to hear your results, as information about the effects of docsis pie in the wild is quite limited...
>
>
> On May 12, 2019 11:24:50 PM GMT+02:00, Neal Cardwell <ncardwell@google.com> wrote:
> Anyone have a pointer to a cable modem model that is available for purchase and implements the DOCSIS 3.1 PIE mechanism? (So far, my searches for this have only found other people asking this question, rather than the answer. Apologies if I missed something that should be easy to find.)
>
> I'm curious to have one for testing with BBR v2. I'm aware of the Linux PIE implementation, but it would be nice to have the actual cable modem version to play with as well.
>
> Thanks!
> neal
>
_______________________________________________
Bloat mailing list
Bloat@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/bloat
next prev parent reply other threads:[~2019-05-13 15:49 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-12 21:24 Neal Cardwell
2019-05-13 9:16 ` Sebastian Moeller
2019-05-13 15:13 ` Neal Cardwell
2019-05-13 15:27 ` Sebastian Moeller
2019-05-13 15:48 ` Colin Dearborn [this message]
2019-05-15 13:53 ` Neal Cardwell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://lists.bufferbloat.net/postorius/lists/bloat.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CY4PR04MB0393A49C5122CE49B6212358950F0@CY4PR04MB0393.namprd04.prod.outlook.com \
--to=colin.dearborn@sjrb.ca \
--cc=bloat@lists.bufferbloat.net \
--cc=moeller0@gmx.de \
--cc=ncardwell@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox