From: Praveen Balasubramanian <pravb@microsoft.com>
To: Yuchung Cheng <ycheng@google.com>, Karen Elisabeth Egede Nielsen
 <karen.nielsen@tieto.com>
Thread-Topic: [tcpm] Fwd: I-D Action: draft-bagnulo-tcpm-tcp-low-rtt-00.txt
Thread-Index: AQHR9M4ywbpExZthr0er6u5O8CZMX6BFxyYA
Date: Fri, 12 Aug 2016 20:35:40 +0000
Message-ID: <BLUPR03MB0042AEE20FBD0F0F4DE638CB61F0@BLUPR03MB004.namprd03.prod.outlook.com>
References: <20160708211635.32095.77047.idtracker@ietfa.amsl.com>
 <2f56d1b8-7450-42de-4a24-53df9cf4c045@it.uc3m.es>
 <a1f456db6e656785da8e356b9f530717@mail.gmail.com>
 <CAK6E8=etaxFSgBvQt27s=rB03rRQxQ_u43qWRExTVXys9A82wg@mail.gmail.com>
In-Reply-To: <CAK6E8=etaxFSgBvQt27s=rB03rRQxQ_u43qWRExTVXys9A82wg@mail.gmail.com>
Accept-Language: en-US
Content-Language: en-US
received-spf: None (protection.outlook.com: microsoft.com does not designate
 permitted sender hosts)
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-originalarrivaltime: 12 Aug 2016 20:35:40.7032 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 72f988bf-86f1-41af-91ab-2d7cd011db47
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BLUPR03MB001
Archived-At: <https://mailarchive.ietf.org/arch/msg/tcpm/UNZ8kQtLWlLoSQe5dpndx7NV8a0>
Cc: tcpm IETF list <tcpm@ietf.org>, TCP Prague List <tcpPrague@ietf.org>
Subject: Re: [tcpm] Fwd: I-D Action: draft-bagnulo-tcpm-tcp-low-rtt-00.txt
X-BeenThere: tcpm@ietf.org
X-Mailman-Version: 2.1.17
Precedence: list
List-Id: TCP Maintenance and Minor Extensions Working Group <tcpm.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/tcpm>,
 <mailto:tcpm-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/tcpm/>
List-Post: <mailto:tcpm@ietf.org>
List-Help: <mailto:tcpm-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/tcpm>,
 <mailto:tcpm-request@ietf.org?subject=subscribe>
X-List-Received-Date: Fri, 12 Aug 2016 20:35:48 -0000

>>2. delayed acks:
as mentioned the actual time depends a lot on the DC implementation, which =
is really "vender/owner"-specific. instead of perhaps an option during setu=
p to inform the sender about the max delay in the ack works better.

Yeah this is a real problem in IaaS environment today since TCP sender pick=
s minrto and receiver picks delayed ACK timeout independently and can cause=
 spurious RTOs if the minrto is too aggressive. Windows server tries to use=
 the connection handshake RTT (< 10 msec) to auto pick the DC values but th=
is is a heuristic that can fail and doesn't really work in the Linux intero=
p cases.=20

-----Original Message-----
From: tcpm [mailto:tcpm-bounces@ietf.org] On Behalf Of Yuchung Cheng
Sent: Friday, August 12, 2016 12:17 PM
To: Karen Elisabeth Egede Nielsen <karen.nielsen@tieto.com>
Cc: tcpm IETF list <tcpm@ietf.org>; TCP Prague List <tcpPrague@ietf.org>
Subject: Re: [tcpm] Fwd: I-D Action: draft-bagnulo-tcpm-tcp-low-rtt-00.txt

On Fri, Aug 12, 2016 at 4:30 AM, Karen Elisabeth Egede Nielsen <karen.niels=
en@tieto.com> wrote:
>
> Hi Marcello,
>
> I very much appreciate your draft.
>
> Even more so as it addresses one of the things I find to be a bit=20
> "disturbing"  in the l4s drafts - Namely the claim that the finer saw=20
> tooth functionality of l4s/DCTCP alone solves the latency problems=20
> (while DCTCP indeed also is tuning the RTO timeout aggressively).
> E.g., the formulation in  section 1.1 of=20
> https://datatracker.ietf.org/doc/draft-briscoe-tsvwg-ecn-l4s-id/?inclu
> de_t
> ext=3D1
>
> It turns out that a TCP algorithm like DCTCP that solves TCP's
>    scalability problem also solves the latency problem, because the
>    finer sawteeth cause very little queuing delay.  A supporting paper
>    [DCttH15] gives the full explanation of why the design solves both
>    the latency and the scaling problems, both in plain English and in
>    more precise mathematical form.  The explanation is summarised
>    without the maths in [I-D.briscoe-aqm-dualq-coupled].
>
> could benefit from a reference to your draft or the issue that you=20
> addresses here (at least for comprehensiveness).
>
> An additional comment is  that new approaches to retransmissions -=20
> like TCP TLP and TCP RACK (also SCTP TLR which however is not=20
> progressing at the moment) might fundamentally alter the picture.=20
> I.e., if retransmissions are sent pro-actively in tail loss situations=20
> then more conservative RTOs may be kept for situations where it is=20
> prudent to wait longer. Don't know if TCP TLP is so widely deployed=20
> that it is something that you should relate to even if it may be=20
> superseded by RACK. Just a thought.
TLP and RACK help reduce timeout cases in DC environment for sure. But stil=
l it can not completely avoid timeouts. So I agree we should keep timeouts =
conservative, but the current RFCs are way too conservative:
min RTO of 1 second is 4-5 orders of magnitude of DC RTTs.

The issue is, the "right" min-RTO depends on the actual DC and stacks:
they all have different RTTs and timer granularity. The draft cites Glenn's=
 paper, but Morgan Stanley's DC could be different than others.


Other comments on the draft:

1. min ssthresh or cwnd: with very large incast ((tens of) thousands of sen=
ders into one receiver), cwnd of 0.1 pkt can still be too big. the only way=
 is to pace the packets over N*RTT intervals.


2. delayed acks:
as mentioned the actual time depends a lot on the DC implementation, which =
is really "vender/owner"-specific. instead of perhaps an option during setu=
p to inform the sender about the max delay in the ack works better.



>
> BR, Karen
>
> > -----Original Message-----
> > From: tcpm [mailto:tcpm-bounces@ietf.org] On Behalf Of marcelo=20
> > bagnulo braun
> > Sent: 8. juli 2016 23:19
> > To: tcpm IETF list <tcpm@ietf.org>
> > Subject: [tcpm] Fwd: I-D Action:=20
> > draft-bagnulo-tcpm-tcp-low-rtt-00.txt
> >
> > Hi,
> >
> > We just submitted this draft for consideration of the WG. Comments=20
> > are appreciated.
> >
> > Regards, marcelo
> >
> >
> >
> >
> > -------- Mensaje reenviado --------
> > Asunto:       I-D Action: draft-bagnulo-tcpm-tcp-low-rtt-00.txt
> > Fecha:        Fri, 08 Jul 2016 14:16:35 -0700
> > De:   internet-drafts@ietf.org
> > Responder a:  internet-drafts@ietf.org
> > Para:         i-d-announce@ietf.org
> >
> >
> >
> > A New Internet-Draft is available from the on-line Internet-Drafts
> directories.
> >
> >
> >          Title           : Recommendations for increasing TCP
> performance in low RTT
> > networks.
> >          Authors         : Marcelo Bagnulo
> >                            Koen De Schepper
> >                            Glenn Judd
> >       Filename        : draft-bagnulo-tcpm-tcp-low-rtt-00.txt
> >       Pages           : 7
> >       Date            : 2016-07-08
> >
> > Abstract:
> >     This documents compiles a set of issues that negatively affect TCP
> >     performance in low RTT networks as well as the recommendations to
> >     overcome them.
> >
> >
> > The IETF datatracker status page for this draft is:
> > https://datatracker.ietf.org/doc/draft-bagnulo-tcpm-tcp-low-rtt/
> >
> > There's also a htmlized version available at:
> > https://tools.ietf.org/html/draft-bagnulo-tcpm-tcp-low-rtt-00
> >
> >
> > Please note that it may take a couple of minutes from the time of
> submission
> > until the htmlized version and diff are available at tools.ietf.org.
> >
> > Internet-Drafts are also available by anonymous FTP at:
> > ftp://ftp.ietf.org/internet-drafts/
> >
> > _______________________________________________
> > I-D-Announce mailing list
> > I-D-Announce@ietf.org
> > https://www.ietf.org/mailman/listinfo/i-d-announce
> > Internet-Draft directories: http://www.ietf.org/shadow.html or=20
> > ftp://ftp.ietf.org/ietf/1shadow-sites.txt
> >
> >
> > _______________________________________________
> > tcpm mailing list
> > tcpm@ietf.org
> > https://www.ietf.org/mailman/listinfo/tcpm

_______________________________________________
tcpm mailing list
tcpm@ietf.org
https://www.ietf.org/mailman/listinfo/tcpm