...
| Item | Desc | who | Notes/minutes |
| UNH transition | All | Sridhar working on a bug with the deployment of eBPF-based solutions, intending to benchmark the OVS and VPP, North Bound userspace CNI. May need special network connectivity to restore our Node back2back capability (from Intel lab) Sridhar will contact Fulvio Risso in Italy for possible chat and maybe some collaboration - just want to learn from his experiences. Have began to move IXIA generator to UNH, for connection there to the pod we are using. Notes of Sridhar has started setup in the new testbed. Seems stable and going well. VPN is good stability. Need a few more days to get going (all the basic stuff needs to be setup.) Completing install of PROX and Trex. eBPF support varies from OS to OS: Different form Ubuntu 20.04 to 20.04 - strange - trying to create superset of library of eBPF support and deployment. Needed kernel rebuild in one system, but not in another - so need to re-build to to be safe or check in the kernel. All the details must be known so that the automation works. Sawyer Bergeron says that the booking has been extended to late May, 2023. | |
| CN Perf Verification | Trevor and Luc | Market in Edge-cloud Infra..structure. For smallish Companies who need to make decisions on their deployments, but don't have the people or expertise to do the work in a timely way. Sridhar - Are you in an SI – What is this? has established suppliers and a complete framework. Sridhar - HW gives SW compatibility only, visa-versa, but do not guarantee specific performance. They begin and end with their Compatibility Lists, but in reality this is not enough! They may never get the performance they are promised, then finger-pointing between CNF and HW vendors. There is an enormous amount of stuff to configure. acm - TCO is the most important aspect of this proposal - modeling is hard, cores/resources can be stranded. Networking costs can be really high - swamping the rest of costs! Sridhar - work-out what the follow-up would be, every time the HW or SW changes (frequent event). Training can be a part of the solution - but only if the customer will build or have access to a lab. Sridhar - Artifacts should include the golden configurations. Sridhar - Also provide Root-Cause Analysis - benchmarking with bottlenecks identified. acm - power benchmarking - see https://datatracker.ietf.org/doc/html/draft-manral-bmwg-power-usage-04 Sridhar - apart from solving today's problems, additional HW adds complexity and performance improvements - can ID ability to solve the next generation of problems (DPUs and beyond). Sridhar - How are Tier 1 Operators doing this? A Major question = Obsession with Tier 2 and lower. | |
| Student Volunteers | Federica | Notes from No news on Student Candidates. (from student forum) It would be to know the school deadline. - It is the entire Semester. ViNePerf will not do an LFN internship this year. | |
| Deepdive on eBPF XDP AF_XDP | Sridhar | Note from First step is to verify that a single L2 forwarder will work (Cillium's ability to use DPDK is in question) | |
| Discussion: Contribution on Containerized network benchmarking in BMWG session IETF-115 | All | ||
| UNH transition | All | Given that our Pod terminated (time-out) is there any way to recover? Or better to start from scratch? Can automate the IP addrs assignments for all the traffic links - How? Can Config.YAML really work? or is Ansible better? | |
| Testbed - IXIA support | Sridhar/Al | Tim Gresham asks for resolution on this. If we can get it, do we want it? No good without license! So, is a license still valid or available for update? THEN - need to ship and install in UNH, get working there - IXIA help to do this.
Trevor Cooper says connected and powered on, but we still might have a license issue. Need Pierre's help. this activity seems to have stalled ... Pod 19 also not accessible - Dan Xu. |
...