Hi Robert,
Inline........
Ron
________________________________
From: Robert Raszuk <[email protected]>
Sent: Tuesday, July 21, 2026 11:00 PM
To: Bonica, Ron <[email protected]>
Cc: lsr <[email protected]>; Zafar Ali (zali) <[email protected]>
Subject: Re: [Lsr] IS-IS Support for PCPPS
Hi Ron,
I am not sure what types of platforms Zafar had in mind but I would be
interested in your response how do you apply concept of power groups to
single-chip/systems-on-chip (SoCs) 1RU pizza ODM boxes.
Would you say put each QSFP into a separate group and the only saving you could
claim is to turn off laser on the selective sender interfaces after drying the
entire traffic on it ?
[RB] For any piece of hardware, power grouping is determined by the location of
power switches.
[RB] In the system that you describe, I assume that the system has a single,
manual power switch. In order to change the system's power state, human fingers
must touch a power switch. When that switch is toggled, the entire system
changes power state.
[RB] I also assume that the system has N lasers, each of which supports an
interface. Each of these lasers can be powered on or off independently of one
another through a software command.
[RB] Finally, I assume that the system has no other power switches, manual or
command-driven.
[RB] In this case, each interface can be power save capable, but no power
groups are configured. Only the lasers can be powered on or off.
[RB] Power Groups are applicable in more complex devices. See
draft-many-teas-power-steering for an example.
- - - A side two question - - -
1)
To what % number of link utilization do you consider acceptable to consolidate
traffic for the purpose of power saving on some other links ?
This is configurable, but beyond the scope of this document.
2)
If the network is built in a bit complex way ... say there is Algo 0 but also
16 other Flex_Algo topologies I have a question how do you account for that
such that before the optimization and after optimization traffic suddenly is
not forwarded in a "foreign" topology ? Or is the current proposal simply not
interested in addressing such networks ?
[RB] Again, see draft-many-teas-power-steering. The TLVs described in this
document are used to calculate a PCPPS metric. Flex-algo doesn't use the PCPPS
metric. So, these metrics don't impact flex algo.
Thx,
R.
On Mon, Jul 20, 2026 at 9:55 AM Bonica, Ron
<[email protected]<mailto:[email protected]>> wrote:
Zafar,
If I understood your comment during the IETF 126 session correctly, you said
that the Power Group model may not support some existing hardware
architectures. Can you describe such an architecture?
Ron
_______________________________________________
Lsr mailing list -- [email protected]<mailto:[email protected]>
To unsubscribe send an email to [email protected]<mailto:[email protected]>
_______________________________________________
Lsr mailing list -- [email protected]
To unsubscribe send an email to [email protected]
