Minutes IETF115: mops: Mon 09:30
minutes-115-mops-202211070930-00
Meeting Minutes | Media OPerationS (mops) WG | |
---|---|---|
Date and time | 2022-11-07 09:30 | |
Title | Minutes IETF115: mops: Mon 09:30 | |
State | Active | |
Other versions | markdown | |
Last updated | 2022-11-17 |
MOPS IETF 115 London Hybrid Agenda
09:30 GMT, Monday 2022-Nov-07
About / Intro:
- Admin [5 min]
- Note well
- Minute taker: Warren Kumari
- Agenda bash
Working Group Documents [20 min]
Media Operations Use Case for an Augmented Reality Application on Edge Computing Infrastructure: Where to go? [20 min]
-
Updates
- S 3.x: Elaborated techniquess to aquire model of real world
- S 5.1: ATR Traffic Workloads
-
Pretty chart with numbers
- BW for various contexts / usages -- 1Mbps -> 1000Mbps
-
Simlar, but in a table
- Latency for things like AR surgery - <750 us, >30Gbps
- Latence for things like Cloud based mobile AR - <50ms,
50/100Mbps
-
Questions:
- Renan Krishna: Is the WG Ok with us putting these in the draft?
- Q: Are these numbers RTT or 1-Way?
- A: 1-way (I think, I missed it because I was playing with
formatting!) - A:(Edited by Renan)These are RTT numbers
- Q: 30Gbps seems very high
- A: Well, this seems like it is for uncompressed.
- Q (Sam Hurst): Have you soncidered iframe only.
- A: We are trying to capture industry practice. Would welcome
comments on GH. - Q (Kyle Rose): If you are going to put in numbers, they are
"moment in time" - are these numbers all from the same rough
time? Should state in the draft. - A: Yes. We should specify in draft
- Q (Spencer): WG should think of rough orders of magnitude. Do
'somewhere between x and y, not 34.324385223226Mbps'. That's one
thing I wish we'd done differently, with the streaming media
operational considerations draft (now published as
rfc9317). - Q (Giles Heron): Latency figures below x (~1ms) are somewhat
pointless - C: Other issue is that we envision running this over other
transports (e.g WiFi) - want comments on how this affects
things.
-
Actions items for draft (notes from chairs):
- Numbers
- Are we done?!
- Pull all questions out, send them to the list, and try get
answers. Hope to WGLC by next meeting...
Industry News/Experiences [25min]
Updates from SVTA (Glenn Deen) [15 min]
- Original intent from MOPS was to bring professional video people and
IETF together. Update from Streaming Video Technology Alliance (SVTA
nee SVA) -
What is the SVTA?
- List of areas / groups
- Wheee! SVTA uses RFCs... Many RFCs...!
-
How SVTA Open Caching relates to CDNi
-
Updated Open Caching Config info...
- SVTA is doing a QUIC PoC (actually HTTP3). Developing test
environement for streaming with QUIC -
SVTA Contacts:
- Glenn Deen (Comcast-NBCUniversal) - glenn_deen@comcast.com
- Sanjay Mishra (Verizon) - Sanjay.Mishra@verizon.com
- Jason Thibeault (Streaming Video Technology Alliance Executive
Director) - JT@SVTA.ORG
-
MOPS was able to bring new people to the IETF
- Questions:
- (Sam Hurst): For clarification, is this over HTTP/3 or over QUIC
itself? - A: HTTP/3 for now, maybe deeper in the future
- (Sam Hurst): For clarification, is this over HTTP/3 or over QUIC
Update on ALTO at Telefonica (Luis M. Contreras) [10 min]
-
Why make TCDN be a transport aware network?
- Benefit from real time awareness
-
Network map & Cost Map
- Received over BGP-LS
-
Progress / update since IETF114
- Pilot run on Oct 27th
-
Known isuses / limits
- One vendor has issues disseminating BGP-LS
-
Good News!
- Retrieved ~16k summarized IP ranges, spaning differnt types of
nodes (fixed, mobile, enterprise, etc) - IP ranges currently internal only
- Cost map correctly reflect IGP metric
- Server load is not really significant
- Retrieved ~16k summarized IP ranges, spaning differnt types of
-
Less good news
- Missing some IP ranges
- Still looking to see why... Perhaps missing some BGP-LS
sessions... - A few duplicates
- Still looking to see why... Perhaps missing some BGP-LS
- Missing some IP ranges
-
Next steps:
- How often to consume?
- Debug issues
- Wait till vendor fixes their stuff...
- For ALTO / MOPS:
- Document pilot (does MOPS want to see this?!)
- Identify gaps / issues, etc.
- Hope to update at IETF116
-
Q:
- Frédéric Fieau@Orange: Do you plan to work with other telcos and
share maps? - A: No plans at the moment
- Frédéric Fieau@Orange: Do you plan to work with other telcos and
Related IETF work [15 min]
TreeDN: draft-giuliano-treedn (Lenny Giuliano) [15 min]
Presenter: Lenny Giuliano lenny@juniper.net
-
Why (Problem Statement)?!
- With large live audences and moar bitrates, are we at inflection
point? -
Live streaming != On-Demand Streaming
- Expectations for low latency. If you hear the bar downstairs
cheering before you see the person with the ball do, um,
whatever people do with balls in sprts things..... Clearly
the minute taker doesn't sport...
- Expectations for low latency. If you hear the bar downstairs
-
Join rates are vastly differnt; smooth for on-demand, step
function for live
- With large live audences and moar bitrates, are we at inflection
-
Multicast has been successful in some places.
- Not so wonderful on the Internets...
- "All or Nothing" -- all L3 hops need to do this.
- "Too Complex" -- perceived benefit not worth the cost.
(WK/scribe comment: And often the benefit is negative..) - "Chicken and Egg" -- no-one does this, because no-one does this.
-
TreeDN...
- Native and overlay concepts to deliver serive to users who don't
have multicast. -
Native On-Net SSM
- SSM is less complex
-
Overlay - AMT (RFC7450)
- Dynamically built tunnels hop unicast-only bits of the
network. - Solves "All or Nothing" and "Chicken & Egg"
- Dynamically built tunnels hop unicast-only bits of the
-
Incremental deployment
- Native and overlay concepts to deliver serive to users who don't
-
Diagrams (with and without Multicast and TreeDN)
- If deployed on existing infrastructure, it is basically
CDN-on-a-Chip - $0 capex, ~$0 opex- Just some config
- If deployed on existing infrastructure, it is basically
-
Benefits
- More efficent network
- Allows SP to offer Replication As A Service
- Democratizes and decentralizes content sourcing
-
Applicability
- Any multi-destination content
- Live treaming is the sexy example
- But large files (e.g sw updates) also work well...
- Any multi-destination content
-
Next Steps / Action Items:
- Q (Kyle): Read draft, interesting... Still had issues, like
democratizing content - this is just for the fanout though, not
the rights issues, etc. Creating novel attack surface with
replication as a service. This hand-waves away things like key
mgmt - they are still there, just not in the replication.
Exposes what content is being consumed. Willing to help, but
still unresolved (non-technical) issues. - A: 1: Yes, content rights are an issues, but thats orthogonal -
e.g nature cams, drones, etc. 2: Attacks: Multicast is a
differnt attack surface. Not more or less, just differnt. 3: Key
Mgmt - What was meant was the key mgmt is that it goes on
between user and provider; intervening providers don't have to
participate. Not unique to mulicast... - Q (Eric Vynke): Looks like this is best current practices for
using MBONE best current practices "just" stitching existing
bits together, not new work. Seems like it belongs in MOPS. Is
there a deployed PoC? - A: Yes. Come to MBONED...
- Q (Hang Shi): What transport does this use? Can be used with
TCP? - A: Nope. Multicast doesn't really do TCP, works with UDP - can
carry any multicast compatiable transport. - Q - Chairs: WG Adoption? If so, MOPS or MBONED? Show of hands...
- Chairs: Looks like there is good support for adopting
(approx 23 hands raised, 3 not raised in Meetecho queue)
- Chairs: Looks like there is good support for adopting
- Q (Kyle): Read draft, interesting... Still had issues, like
AoB [5min]
- None!