search

lensapp / lens

Lens - The way the world runs Kubernetes
https://k8slens.dev/
MIT License
22.58k stars 1.47k forks source link

Feature Request: Do not see any GPU Details #546

Open lalithvaka opened 4 years ago

lalithvaka commented 4 years ago

What would you like to be added:

  1. GPU Metrics in addition to the CPU, Memory and Pods would be great.
  2. GPU resource quota is not showing under namespace resource quota or pod resource quota

Why is this needed: To support GPU Clusters

Environment you are Lens application on:

eliaskoromilas commented 4 years ago

Support for inspecting extended resources (GPUs, FPGAs, ...) available on a node or assigned to a container would be very useful for us too.

https://kubernetes.io/docs/tasks/administer-cluster/extended-resource-node/#discussion

https://kubernetes.io/docs/tasks/configure-pod-container/extended-resource

elephantum commented 3 years ago

+1 for GPU monitoring

louis030195 commented 3 years ago

Interested too!

sigurdkb commented 2 years ago

+1

skandix commented 2 years ago

+1

tapter-mwm commented 2 years ago

+1

adylevy commented 2 years ago

+1

Nokel81 commented 1 year ago

Notes on implementation:

  1. Discover what the standard prometheus datapoints are produced for GPU metrics
  2. Create the correct set of GPU related prometheus queries
  3. Setup requesting that information for the cluster overview route
  4. Gracefully handle when the data is not present and not show a GPU button at all (or have it greyed out)
emchristiansen commented 1 year ago

+1

ysusuk commented 1 year ago

+1

Juhong-Namgung commented 1 year ago

+1

c3-ali commented 2 months ago

+1

jclarkk commented 2 months ago

+1