Hi Linda,
The first concern the draft is formulated to address is minimize the
detrimental impacts against the ongoing routing mechanism with the status
propagation by routing network layer of computing resources as well as
associated services. This is why the computing and service status are to be
categoried into two class one of which is actually an aggregation of the
general computing and service status of the cloud sites (rather than specific
server and container etc.) which is maintained at the remote edge nodes,
another one is the service instances which is maintained at the local edge
nodes.
when it comes to Kubernetes, it's an application-level solution without
routing network involved, and more importantly, what it manages and maintains
is application-specific rather than the enabled routing network which is open
to and serve any third parties.
Thanks again for your questions and comments.
Daniel Huang
黄光平 huangguangping
架构团队/有线规划部 Wireline architecture team./Wireline Product R&D Institute
南京市雨花区软件大道50号中兴通讯2号楼
R&D Building, ZTE
Corporation Software Road No.50,
Yuhua District, Nanjing, P..R.China, 210012
M: +86 13770311052
E: [email protected]
www.zte.com.cn
原始邮件
发件人：LindaDunbar
收件人：黄光平10039714;[email protected];
抄送人：[email protected];
日 期 ：2021年07月20日 06:08
主 题 ：RE: Fw:New Version Notification for
draft-huang-computing-delivery-in-routing-network-00.txt
Daniel,
Is it draft describing a way for each Compute node to propagate its computing
resources?
How is it different from computer resource management system collecting Server
load status periodically? , e.g. Kubernetes, one of its function is collecting
VM or Containers running status (in addition to many other functions).
Thanks,
Linda Dunbar
From: rtgwg <[email protected]> On Behalf Of [email protected]
Sent: Sunday, July 11, 2021 9:58 PM
To: [email protected]
Cc: [email protected]
Subject: Fw:New Version Notification for
draft-huang-computing-delivery-in-routing-network-00.txt
Hi all, a new draft of computing delivery in routing network has been posted in
RTGWG.
The draft is proposed upon pretty much the same use cases about sensing and
routing of computing services from the clouds (MECs) which has been raised and
discussed in the community with impressive contributions.
Nevertheless, the authors bear in mind the challenges, problems as well as
concerns raised in the community discussions when formulating the solutions in
this proposal. As underlay network of the purported computing delivery, the
detrimental impacts upon the routing network have been designed to be minimized
to a reasonable degree while the benefits of computing delivery in routing
network is achieved..
Any comments, suggestions and contributions would be very much appreciated.
Best regard,
Daniel Huang
黄光平 huangguangping
架构团队/有线规划部 Wireline architecture team./Wireline Product R&D Institute
南京市雨花区软件大道50号中兴通讯2号楼
R&D Building, ZTE Corporation Software Road No.50,
Yuhua District, Nanjing, P..R.China, 210012
M: +86 13770311052
E: [email protected]
www.zte.com.cn
原始邮件
发件人：[email protected]
收件人：谭斌10006579;黄光平10039714;Peng Liu;
日 期 ：2021年07月11日 16:55
主 题 ：New Version Notification for
draft-huang-computing-delivery-in-routing-network-00.txt
A new version of I-D, draft-huang-computing-delivery-in-routing-network-00.txt
has been successfully submitted by Daniel Huang and posted to the
IETF repository.
Name: draft-huang-computing-delivery-in-routing-network
Revision: 00
Title: Computing Delivery in Routing Network
Document date: 2021-07-10
Group: Individual Submission
Pages: 11
URL:
https://www.ietf.org/archive/id/draft-huang-computing-delivery-in-routing-network-00.txt
Status:
https://datatracker.ietf.org/doc/draft-huang-computing-delivery-in-routing-network/
Html:
https://www.ietf.org/archive/id/draft-huang-computing-delivery-in-routing-network-00.html
Htmlized:
https://datatracker.ietf.org/doc/html/draft-huang-computing-delivery-in-routing-network
Abstract:
This document drafts a proposal of Computing Delivery in Routing
Network which incorporates both computing and networking metrics into
the routing polices and enables the network sensing and scheduling
computing services based upon traditional networking services. A
mechanism of two-class computing power granularity and two segment
forwarding is illustrated for end-to-end networking and computing
service in the cloud sites, while major networking and computing
actors is defined in terms of functionality. An example work flow is
demonstrated, and both control plane and data plane solution
consideration is proposed.
The IETF Secretariat_______________________________________________
rtgwg mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/rtgwg
