Francesco Romani
Francesco Romani
Reviewing the isolation level concept of the resources, we need more details about how we expose the pod-level exclusive resources in the pod resources API, which was overlooked in the...
@drewhagen This is an important enhancement, and the process so far has been very productive. We've identified that the implementation needs some structural changes, requiring careful thought and refactoring to...
> > Let's make sure we have unit tests to cover the migration path back and forth cpumanager v2v3 and memorymanager v1v2. The changes done here should be very easy...
@KevinTMtz I agree the current priorities are 1. make sure the new flows are guarded by the FG to avoid regressions if the FG is disabled 2. add and verify...
> @KevinTMtz I agree the current priorities are > > 1. make sure the new flows are guarded by the FG to avoid regressions if the FG is disabled >...
> [@esotsal](https://github.com/esotsal) , [@kad](https://github.com/kad) , [@ffromani](https://github.com/ffromani) , [@dchen1107](https://github.com/dchen1107) , [@mrunalp](https://github.com/mrunalp) , [@swatisehgal](https://github.com/swatisehgal) . Hello everyone, I create an issue and two PRs for delay-sensitive service request. This request is described...
> > I think a bug is fine, which should be solved in the context of the current in-place-VPA KEP > > Thank you for your reply, is the in-place-VPA...
I see the usecase for the devices or non-core resources. I'm thinking especially about exclusive CPUs, but memory/hugepages can have the same problem. IIUC core resources (cpu, memory) are out...