Huamin Chen comments

Results 225 comments of


                                            Huamin Chen

[RFE] Correlate Pod and Intel ACC100 FEC power consumption

The next iteration will plan a plugin model so that new HW metrics collector can be developed independently. Let's use AC100 FEC as our first plugin for the exercise.

cpu time becomes zero after long run

cpu time is calculated [here](https://github.com/sustainable-computing-io/kepler/blob/main/pkg/collector/reader.go#L284-L290) cc @marceloamaral

since dropping Fatalf to Infof if BPF not installed on host, make the bcc fileNotFound log/error message friendlier

On VMs, the perf counters are not available, so the warning are a result of this environment. It would help if we add that info to the log.

Make kepler metrics conform to the Prometheus metrics guideline

@sustainable-computing-io/reviewer

Make kepler metrics conform to the Prometheus metrics guideline

The metric change will also impact dashboard @williamcaban @Feelas @sallyom

Make kepler metrics conform to the Prometheus metrics guideline

let's prioritize merge this one. @marceloamaral would you like to follow up with an option to turn on/off/enable metrics? That'll give us flexibility to meet multiple goals.

Make kepler metrics conform to the Prometheus metrics guideline

@sustainable-computing-io/reviewer any more feedback?

Make kepler metrics conform to the Prometheus metrics guideline

I did some rough tests and want to have some idea the cpu load and scrape latency if the metrics go into the conformance direction. I use node_exporter as a...

Create ephemeral cluster with k3d/k3s

@akyriako thank you for the contribution! Can you break the PR into two? One for the k3d cluster, that is independent and can get merged quickly. The second is to...

Make `pod_total_*` metrics persistent/survive a Kepler restart

I would think this requires at three changes: - A CLI flag to load and persist metrics - Functions that allow Kepler to load the last metrics upon start and...