fix: faulty service values references in k8s agent (#50)

* add k8s glue deployment

* more docs

* bump

* disabled by default

* run helm-docs

* fix service references

* fix readme

* add values file where k8sagent enabled

* empty files

* newline

* fix linter

Co-authored-by: Valeriano Manassero <14011549+valeriano-manassero@users.noreply.github.com>

charts/clearml/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: clearml
 description: MLOps platform
 type: application
-version: "3.4.0"
+version: "3.4.1"
 appVersion: "1.1.1"
 home: https://clear.ml
 icon: https://raw.githubusercontent.com/allegroai/clearml/master/docs/clearml-logo.svg

charts/clearml/README.md

@@ -1,6 +1,6 @@
 # ClearML Ecosystem for Kubernetes
 
-![Version: 3.4.0](https://img.shields.io/badge/Version-3.4.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.1.1](https://img.shields.io/badge/AppVersion-1.1.1-informational?style=flat-square)
+![Version: 3.4.1](https://img.shields.io/badge/Version-3.4.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.1.1](https://img.shields.io/badge/AppVersion-1.1.1-informational?style=flat-square)
 
 MLOps platform
 
@@ -170,6 +170,7 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
 | agentk8sglue.image.tag | string | `"aws-latest-1.21"` |  |
 | agentk8sglue.maxPods | int | `10` |  |
 | agentk8sglue.podTemplate.nodeSelector | object | `{}` |  |
+| agentk8sglue.podTemplate.resources | object | `{}` |  |
 | agentk8sglue.podTemplate.tolerations | object | `{}` |  |
 | agentk8sglue.queue | string | `"aws-instances"` |  |
 | agentservices.affinity | object | `{}` |  |

charts/clearml/ci/README.md

@@ -0,0 +1,7 @@
+Place values files with different values in this directory to ensure these cases are tested by the CI as well.
+
+https://github.com/helm/chart-testing/blob/main/doc/ct_install.md
+
+```
+"Charts may have multiple custom values files matching the glob pattern '*-values.yaml' in a directory named 'ci' in the root of the chart's directory. The chart is installed and tested for each of these files. If no custom values file is present, the chart is installed and tested with defaults."
+```

charts/clearml/ci/default-values.yaml

@@ -0,0 +1 @@
+# empty so default values.yaml gets tested

charts/clearml/ci/k8sagent-values.yaml

@@ -0,0 +1,2 @@
+agentk8sglue:
+  enabled: true

charts/clearml/templates/configmap-agentk8s-template.yaml

@@ -10,13 +10,15 @@ data:
       namespace: {{ .Release.namespace }}
     spec:
       containers:
-      - env: 
+      - resources:
+          {{- toYaml .Values.agentk8sglue.podTemplate.resources | nindent 10 }}
+        env: 
         - name: CLEARML_API_HOST
-          value: "http://{{ include "clearml.fullname" . }}-apiserver:{{ .Values.clearml.apiserver.service.port }}"
+          value: "http://{{ include "clearml.fullname" . }}-apiserver:{{ .Values.apiserver.service.port }}"
         - name: CLEARML_WEB_HOST
           value: "http://{{ include "clearml.fullname" . }}-webserver"
         - name: CLEARML_FILES_HOST
-          value: "http://{{ include "clearml.fullname" . }}-fileserver:{{ .Values.clearml.fileserver.service.port }}"
+          value: "http://{{ include "clearml.fullname" . }}-fileserver:{{ .Values.fileserver.service.port }}"
         - name: CLEARML_API_ACCESS_KEY
           valueFrom:
             secretKeyRef:

charts/clearml/templates/deployment-agentk8s.yaml

@@ -25,11 +25,11 @@ spec:
             mountPath: /root/template
         env:
           - name: CLEARML_API_HOST
-            value: "http://{{ include "clearml.fullname" . }}-apiserver:{{ .Values.clearml.apiserver.service.port }}"
+            value: "http://{{ include "clearml.fullname" . }}-apiserver:{{ .Values.apiserver.service.port }}"
           - name: CLEARML_WEB_HOST
             value: "http://{{ include "clearml.fullname" . }}-webserver"
           - name: CLEARML_FILES_HOST
-            value: "http://{{ include "clearml.fullname" . }}-fileserver:{{ .Values.clearml.fileserver.service.port }}"
+            value: "http://{{ include "clearml.fullname" . }}-fileserver:{{ .Values.fileserver.service.port }}"
           - name: K8S_GLUE_MAX_PODS
             value: "{{.Values.agentk8sglue.maxPods}}"
           - name: K8S_GLUE_QUEUE

charts/clearml/values.yaml

@@ -307,6 +307,9 @@ agentk8sglue:
   queue: aws-instances  # create this queue manually in the UI first for it to work
   id: k8s-agent
   podTemplate:
+    resources: {}
+      # limits:
+      #   nvidia.com/gpu: 1
     tolerations: {}
       # - key: "nvidia.com/gpu"
       #   operator: Exists