Simplified the metrics#3182
Conversation
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
| print("- **Other**: Miscellaneous Kubeflow components including:") | ||
| print(" - PVC Viewer Controller") | ||
| print(" - Tensorboard Controller and Web App") | ||
| print(" - Multi-tenancy and RBAC components") | ||
| print(" - Network policies") | ||
| print(" - Custom resources and CRDs") | ||
| print(" - User namespace resources") | ||
| print(" - Additional Kubeflow utilities and tools") |
There was a problem hiding this comment.
We have the components here https://github.com/kubeflow/manifests#kubeflow-components-versions . It should be covered in the same detail and not under other. i would even just extend and merge the two tables with more columns and remove https://github.com/kubeflow/manifests#resource-usage-by-components
networkpolicies and other things without CPU/MEMORY/STORAGE you can ignore anyway.
There was a problem hiding this comment.
Please update the table in the main readme after fixing the other open issues
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
| 'keywords': ['pvcviewer'] | ||
| }, | ||
| 'Storage & Experimental': { | ||
| 'keywords': ['seaweedfs', 'ray', 'minio-tenant'] |
There was a problem hiding this comment.
What do you mean by minio-tenant? I think you can just ignore the experimental folder for now entirely.
There was a problem hiding this comment.
Seaweedfs can also be counted to kfp if needed.
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
| # Storage fallback values when YAML parsing is unavailable | ||
| STORAGE_FALLBACK = { | ||
| 'Katib': 3, | ||
| 'Metadata': 40, |
There was a problem hiding this comment.
Metadata also belongs to KFP. And please check the storage numbers manually. I remember less than 30 GB in total or so. Since it is either minio XOR seawedfs please do not count them twice.
There was a problem hiding this comment.
I checked it manually it is 25
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
| | Istio | 850m | 2464Mi | 0GB | | ||
| | Katib | 4m | 107Mi | 3GB | | ||
| | Kubeflow Core | 17m | 828Mi | 0GB | | ||
| | Training Operator | 2m | 27Mi | 0GB | |
There was a problem hiding this comment.
As discussed please remove this table and merge the columns with the existing table at the beginning of the document.
There was a problem hiding this comment.
Delete this section https://github.com/kubeflow/manifests#resource-usage-by-components and add it instead here in this table https://github.com/kubeflow/manifests#kubeflow-version-master
There was a problem hiding this comment.
I think kserve and a few other components are missing numbers in the table and let's merge istio, Knative etc. Into the same table.
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
Signed-off-by: Julius von Kohout <45896133+juliusvonkohout@users.noreply.github.com>
There was a problem hiding this comment.
please separate out Dex and oauth2-proxy in a follow up PR. I already separated it in the table in the readme
Signed-off-by: Julius von Kohout <45896133+juliusvonkohout@users.noreply.github.com>
|
ah and the numbers for Tensorboards Web Application are missing in the table |
Signed-off-by: kunal-511 <yoyokvunal@gmail.com>
| | Profiles + KFAM | applications/profiles/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/profile-controller/config) | 7m | 129Mi | 0GB | | ||
| | PodDefaults Webhook | applications/admission-webhook/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/admission-webhook/manifests) | 1m | 14Mi | 0GB | | ||
| | Jupyter Web Application | applications/jupyter/jupyter-web-app/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/crud-web-apps/jupyter/manifests) | 4m | 231Mi | 0GB | | ||
| | Tensorboards Web Application | applications/tensorboard/tensorboards-web-app/upstream | [v1.10.0](https://github.com/kubeflow/kubeflow/tree/v1.10.0/components/crud-web-apps/tensorboards/manifests) | | | | |
There was a problem hiding this comment.
where are the values for tensorboards?
| | Katib | applications/katib/upstream | [v0.18.0](https://github.com/kubeflow/katib/tree/v0.18.0/manifests/v1beta1) | 13m | 476Mi | 13GB | | ||
| | KServe | applications/kserve/kserve | [v0.15.0](https://github.com/kserve/kserve/releases/tag/v0.15.0/install/v0.15.0) | 600m | 1200Mi | 0GB | | ||
| | KServe Models Web Application | applications/kserve/models-web-app | [v0.14.0](https://github.com/kserve/models-web-app/tree/v0.14.0/config) | 6m | 259Mi | 0GB | | ||
| | Kubeflow Pipelines | applications/pipeline/upstream | [2.5.0](https://github.com/kubeflow/pipelines/tree/2.5.0/manifests/kustomize) | 970m | 3552Mi | 100GB | |
There was a problem hiding this comment.
100 GB for pipelines does not seem correct
| | KServe | applications/kserve/kserve | [v0.15.0](https://github.com/kserve/kserve/releases/tag/v0.15.0/install/v0.15.0) | 600m | 1200Mi | 0GB | | ||
| | KServe Models Web Application | applications/kserve/models-web-app | [v0.14.0](https://github.com/kserve/models-web-app/tree/v0.14.0/config) | 6m | 259Mi | 0GB | | ||
| | Kubeflow Pipelines | applications/pipeline/upstream | [2.5.0](https://github.com/kubeflow/pipelines/tree/2.5.0/manifests/kustomize) | 970m | 3552Mi | 100GB | | ||
| | Kubeflow Model Registry | applications/model-registry/upstream | [v0.2.19](https://github.com/kubeflow/model-registry/tree/v0.2.19/manifests/kustomize) | 510m | 2112Mi | 20GB | |
There was a problem hiding this comment.
is 20 GB for model registry correct ?
| if kind == 'PersistentVolumeClaim': | ||
| storage_str = doc.get('spec', {}).get('resources', {}).get('requests', {}).get('storage', '0') | ||
| storage_gb = parse_resource_value(storage_str, 'storage') | ||
| component_storage[component] += storage_gb |
There was a problem hiding this comment.
please compare the storage with the live pvcs on the cluster. 100 GB for pipeline is not right.
|
/lgtm |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: juliusvonkohout The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
|
For the follow up PR:
|
Pull Request Template for Kubeflow Manifests
✏️ Summary of Changes
✅ Contributor Checklist