Huamin Chen comments

Results 222 comments of


                                            Huamin Chen

idle power calculations for container metrics don't look right

> This is a question for @rootfs : is the image using the code that was refactored? yes, this image has fix in #1185

idle power calculations for container metrics don't look right

Regarding the dashboard, the green one is the efficient node while the red one is the power hungry node. The node metrics looks right (green one is ~29% more efficient...

idle power calculations for container metrics don't look right

@marceloamaral this needs some thinking, the idle power formula uses the cpu time that we know has some problem https://github.com/sustainable-computing-io/kepler/blob/main/pkg/collector/stats/node_stats.go#L64-L68 ```go func (ne *NodeStats) UpdateIdleEnergyWithMinValue(isComponentsSystemCollectionSupported bool) { // gpu metric...

idle power calculations for container metrics don't look right

For reference, the image used in last June had [this](https://github.com/sustainable-computing-io/kepler/pull/665/commits/0152a3ba053d976976a30eb1ab3380f04041a904) commit that disabled idle power

Native integration with KEDA for LLM inference autoscaling

@yuzisun Thank you for starting this thread. Serverless LLM inference has many use cases. When it comes to power efficiency and power capping, autoscaling capabilities from KEDA and power consumption...

Kepler metrics reporting higher values

@marceloamaral can you take a look? I think the delta between 0.7.1 and latest is the new build process and the refactoring

Kepler metrics reporting higher values

@vprashar2929 can you add 0.7.2 in the same cluster too? thanks

Bump up to golang 1.21

contributions are always welcome

chore(bpfassets): Refactor to reduce the API exposed by bpfassets

@dave-tucker this is great, can we have this soon so we can include it in the next release on Thu? Thanks

Cannot get pod energy information

> Using `quay.io/sustainable_computing_io/kepler:release-0.5` on Fedora Core 33 with cGroup v1 (`systemd.unified_cgroup_hierarchy=0` in grub) does not work as expected: > > See bellow an extract of the logs (verbose=5) where every...