Re: [mpls] agenda for the design team meeting tonight

[Loa Andersson <[e-mail]>]

Sasha,

Thanks for answering, the answer is close to what I suspected, would 
that mean that

- if you have info at a depth where you can't reach it in normal 
operation would that mean that as long as executing on it is "optimal" 
it is no big deal

- but if execution is mandatory it is ill-advised to rely on scanning 
the entire stack?

A very different question is how we document these questions and answers.

/Loa


but there are some

On 08/04/2021 21:04, Alexander Vainshtein wrote:
> Loa and all,
> 
> Regarding one of the example questions in the agenda, namely "- does 
> scanning the entire stack have performance impacts".
> 
> AFAIK most (if not all) off-the-shelf-available NPUs have limits on the 
> depth of the label stack in which they, say, can see the <ELI, EL> pair 
> - see also RFC 8662 <https://tools.ietf.org/html/rfc8662> that has 
> introduced the notion of Entropy Readable Label Depth (ERLD).
> 
> To me this means that in most cases scanning the entire label stack 
> requires pushing the packet for slow path handling with the associated 
> performance impact.
> 
> Regards,
> 
> Sasha
> 
> Office: [phone]
> 
> Cell:      [phone]
> 
> Email:   [e-mail]
> 
> -----Original Message-----
> From: mpls <[e-mail]> On Behalf Of Loa Andersson
> Sent: Thursday, April 8, 2021 3:37 PM
> To: [e-mail]
> Cc: [e-mail]
> Subject: [mpls] agenda for the design team meeting tonite
> 
> NOTICE: This email was received from an EXTERNAL sender.
> 
> Tentative agenda for the MPLS WG Open DT on carrying info in an MPLS 
> packet 2021-04-08 
> ===========================================================================
> 
> Calling the meeting
> 
> -------------------
> 
> - Apologies
> 
>     -- Yes, we had problem, and the Webex did go out late
> 
> - The times in the agenda is one hour off from what we said, at the
> 
>     wg chair meeting.
> 
> - Unfortunate collision with the IESG Teleconference
> 
>     Time: 07:00 US/Canada Pacific
> 
>           09:00 US/Canada Central
> 
>           10:00 US/Canada Eastern
> 
>           14:00 UTC
> 
>           15:00 United Kingdom
> 
>           16:00 Germany, France, Belgium
> 
>           17:00 Finland
> 
>     No ADs can participate today.
> 
> Tentative DT Structure
> 
> -------------------
> 
> Coordination: Loa Andersson
> 
> - meeting week 1 (e.g. this week)
> 
> Track 1: J Doe
> 
> - meeting Week 2 and 4
> 
> Track 2: K Doe
> 
> - meeting Week 2 and 5
> 
> DT output / Track output
> 
> ------------------------
> 
> - Document(s) that address general architecture, at BoS architecture and
> 
>     in the SPL architecture
> 
> - Could be a single document or three documents, possibly a BCP with
> 
>     3 RFC
> 
> - DT charter (?) anyone that want to work on it
> 
>     -- The design team will not takc over the solutions documents, but
> 
>        create architectural guidelines that should support the development
> 
>        of the solutions documents
> 
> DT input
> 
> --------
> 
> draft-bryant-mpls-dev-primer (walk through)
> 
> Questions
> 
> ---------
> 
> - What questions do we want answered
> 
>     -- example 1 - would it be beneficial to know already from the
> 
>        top label what to look for
> 
>     -- example 2 - does scanning the entire stack have performance impacts
> 
> - Decisions?
> 
>     -- how to keep track
> 
> - How do we document this
> 
>     -- should we use the wiki?
> 
> /Loa
> 
> --
> 
> Loa Andersson                        email: [e-mail] <mailto:[e-mail]>
> 
> Senior MPLS Expert [e-mail] <mailto:[e-mail]>
> 
> Bronze Dragon Consulting             phone: [phone]
> 
> _______________________________________________
> 
> mpls mailing list
> 
> [e-mail] <mailto:[e-mail]>
> 
> https://clicktime.symantec.com/3EHDLWkmGWWE4481kNXVLt36H2?u=https%3A%2F%2Fwww.ietf.org%2Fmailman%2Flistinfo%2Fmpls 
> <https://clicktime.symantec.com/3EHDLWkmGWWE4481kNXVLt36H2?u=https%3A%2F%2Fwww.ietf.org%2Fmailman%2Flistinfo%2Fmpls>
> 
> Notice: This e-mail together with any attachments may contain 
> information of Ribbon Communications Inc. and its Affiliates that is 
> confidential and/or proprietary for the sole use of the intended 
> recipient. Any review, disclosure, reliance or distribution by others or 
> forwarding without express permission is strictly prohibited. If you are 
> not the intended recipient, please notify the sender immediately and 
> then delete all copies, including any attachments.
> 
> 
> Notice: This e-mail together with any attachments may contain 
> information of Ribbon Communications Inc. and its Affiliates that is 
> confidential and/or proprietary for the sole use of the intended 
> recipient. Any review, disclosure, reliance or distribution by others or 
> forwarding without express permission is strictly prohibited. If you are 
> not the intended recipient, please notify the sender immediately and 
> then delete all copies, including any attachments.

-- 

Loa Andersson                        email: [e-mail]
Senior MPLS Expert                          [e-mail]
Bronze Dragon Consulting             phone: [phone]