Re: [tcpm] TCP Tail Loss Probe

Martin Winbjörk <martin.winbjork@ericsson.com> Mon, 03 March 2014 07:36 UTC

From: Martin Winbjörk <martin.winbjork@ericsson.com>
To: "Scheffenegger, Richard" <rs@netapp.com>, "tcpm@ietf.org" <tcpm@ietf.org>, "nanditad@google.com" <nanditad@google.com>, "ncardwell@google.com" <ncardwell@google.com>, "ycheng@google.com" <ycheng@google.com>, "mattmathis@google.com" <mattmathis@google.com>
Thread-Topic: TCP Tail Loss Probe
Thread-Index: Ac80kCQu6lpocKtXSlyq1O7Kw8QrmAAHXD5gAIFq/4A=
Date: Mon, 03 Mar 2014 07:36:26 +0000
Message-ID: <7FD625EF1E1B1D4586EEAB7471ECDC0A200519@ESESSMB109.ericsson.se>
References: <7FD625EF1E1B1D4586EEAB7471ECDC0A200469@ESESSMB109.ericsson.se> <012C3117EDDB3C4781FD802A8C27DD4F260A5E48@SACEXCMBX02-PRD.hq.netapp.com>
In-Reply-To: <012C3117EDDB3C4781FD802A8C27DD4F260A5E48@SACEXCMBX02-PRD.hq.netapp.com>
Accept-Language: en-US
Content-Language: en-US
Content-Type: multipart/alternative; boundary="_000_7FD625EF1E1B1D4586EEAB7471ECDC0A200519ESESSMB109ericsso_"
MIME-Version: 1.0
Archived-At: http://mailarchive.ietf.org/arch/msg/tcpm/_tpgFjuBoS8EW1ilhSGyH9SPxts
Cc: Ingemar Johansson S <ingemar.s.johansson@ericsson.com>
Subject: Re: [tcpm] TCP Tail Loss Probe
Precedence: list

Hi



Thank you for the answer



Regards

Martin Winbjörk


From: Scheffenegger, Richard [mailto:rs@netapp.com]
Sent: den 28 februari 2014 19:05
To: Martin Winbjörk; tcpm@ietf.org; nanditad@google.com; ncardwell@google.com; ycheng@google.com; mattmathis@google.com
Cc: Ingemar Johansson S
Subject: RE: TCP Tail Loss Probe

Hi Martin,

I hope that work hasn't been abandoned.

For one, I would like this work being formally adopted as a TCPM item and discussed, as this mechanism would address some of the problems that I wanted addressed, which can be summarized as TCP HOL blocking latency.

Now that 1323bis is asymptotically nearing publication, I also want to revive some work that got me started with Timestamps. That work was also related to loss-related latency in TCP, but dealing with lost retransmissions (and the non-ambiguous detection that a retransmission was lost).

If time permits, I want to give a short overview of that work, even though the current (expired) drafts don't include things learned during the discussions of 1323bis:

http://tools.ietf.org/html/draft-scheffenegger-tcpm-timestamp-negotiation-05
http://tools.ietf.org/html/draft-trammell-tcpm-timestamp-interval-01

And ideally also the way Linux currently recovers from lost retransmissions (even though the scheme making use of a modified TS sematic does not incur unnecessary latency, or fails at the end-of-stream).

Best regards,

Richard Scheffenegger

From: tcpm [mailto:tcpm-bounces@ietf.org] On Behalf Of Martin Winbjörk
Sent: Freitag, 28. Februar 2014 15:26
To: tcpm@ietf.org<mailto:tcpm@ietf.org>; nanditad@google.com<mailto:nanditad@google.com>; ncardwell@google.com<mailto:ncardwell@google.com>; ycheng@google.com<mailto:ycheng@google.com>; mattmathis@google.com<mailto:mattmathis@google.com>
Cc: Ingemar Johansson S
Subject: [tcpm] TCP Tail Loss Probe

Hi

I have a question regarding the draft for Tail Loss Probe found on the following link
http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01

What is the status of the draft? It has expired on August 29 2013. Is it still relevant and updated or has it been abandoned or continued elsewhere?

Regards
Martin Winbjörk

[tcpm] TCP Tail Loss Probe Martin Winbjörk
Re: [tcpm] TCP Tail Loss Probe Scheffenegger, Richard
Re: [tcpm] TCP Tail Loss Probe Yuchung Cheng
Re: [tcpm] TCP Tail Loss Probe Martin Winbjörk
Re: [tcpm] TCP Tail Loss Probe Martin Winbjörk
Re: [tcpm] TCP Tail Loss Probe Ingemar Johansson S
Re: [tcpm] TCP Tail Loss Probe Nandita Dukkipati