146 agentadd affinity config (#147)

* Added: affinity parameter

* Changed: bump version

charts/clearml-agent/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: clearml-agent
 description: MLOps platform Task running agent
 type: application
-version: "3.2.0"
+version: "3.3.0"
 appVersion: "1.24"
 kubeVersion: ">= 1.21.0-0 < 1.27.0-0"
 home: https://clear.ml
@@ -21,6 +21,4 @@ keywords:
 annotations:
   artifacthub.io/changes: |
     - kind: added
-      description: securityContext parameter for agent pod
+      description: affinity parameter
-    - kind: added
-      description: support for kubernetes 1.26

charts/clearml-agent/README.md

@@ -1,6 +1,6 @@
 # ClearML Kubernetes Agent
 
-![Version: 3.2.0](https://img.shields.io/badge/Version-3.2.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.24](https://img.shields.io/badge/AppVersion-1.24-informational?style=flat-square)
+![Version: 3.3.0](https://img.shields.io/badge/Version-3.3.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.24](https://img.shields.io/badge/AppVersion-1.24-informational?style=flat-square)
 
 MLOps platform Task running agent
 
@@ -30,10 +30,12 @@ Kubernetes: `>= 1.21.0-0 < 1.27.0-0`
 
 | Key | Type | Default | Description |
 |-----|------|---------|-------------|
-| agentk8sglue | object | `{"annotations":{},"apiServerUrlReference":"https://api.clear.ml","basePodTemplate":{"annotations":{},"env":[],"fileMounts":[],"hostAliases":{},"initContainers":[],"labels":{},"nodeSelector":{},"resources":{},"schedulerName":"","securityContext":{},"tolerations":[],"volumeMounts":[],"volumes":[]},"clearmlcheckCertificate":true,"containerCustomBashScript":"","customBashScript":"","debugMode":false,"defaultContainerImage":"ubuntu:18.04","extraEnvs":[],"fileMounts":[],"fileServerUrlReference":"https://files.clear.ml","image":{"repository":"allegroai/clearml-agent-k8s-base","tag":"1.24-21"},"labels":{},"nodeSelector":{},"queue":"default","replicaCount":1,"securityContext":{},"serviceExistingAccountName":"","volumeMounts":[],"volumes":[],"webServerUrlReference":"https://app.clear.ml"}` | This agent will spawn queued experiments in new pods, a good use case is to combine this with GPU autoscaling nodes. https://github.com/allegroai/clearml-agent/tree/master/docker/k8s-glue |
+| agentk8sglue | object | `{"affinity":{},"annotations":{},"apiServerUrlReference":"https://api.clear.ml","basePodTemplate":{"affinity":{},"annotations":{},"env":[],"fileMounts":[],"hostAliases":{},"initContainers":[],"labels":{},"nodeSelector":{},"resources":{},"schedulerName":"","securityContext":{},"tolerations":[],"volumeMounts":[],"volumes":[]},"clearmlcheckCertificate":true,"containerCustomBashScript":"","customBashScript":"","debugMode":false,"defaultContainerImage":"ubuntu:18.04","extraEnvs":[],"fileMounts":[],"fileServerUrlReference":"https://files.clear.ml","image":{"repository":"allegroai/clearml-agent-k8s-base","tag":"1.24-21"},"labels":{},"nodeSelector":{},"queue":"default","replicaCount":1,"securityContext":{},"serviceExistingAccountName":"","tolerations":[],"volumeMounts":[],"volumes":[],"webServerUrlReference":"https://app.clear.ml"}` | This agent will spawn queued experiments in new pods, a good use case is to combine this with GPU autoscaling nodes. https://github.com/allegroai/clearml-agent/tree/master/docker/k8s-glue |
+| agentk8sglue.affinity | object | `{}` | affinity setup for Agent pod (example in values.yaml comments) |
 | agentk8sglue.annotations | object | `{}` | annotations setup for Agent pod (example in values.yaml comments) |
 | agentk8sglue.apiServerUrlReference | string | `"https://api.clear.ml"` | Reference to Api server url |
-| agentk8sglue.basePodTemplate | object | `{"annotations":{},"env":[],"fileMounts":[],"hostAliases":{},"initContainers":[],"labels":{},"nodeSelector":{},"resources":{},"schedulerName":"","securityContext":{},"tolerations":[],"volumeMounts":[],"volumes":[]}` | base template for pods spawned to consume ClearML Task |
+| agentk8sglue.basePodTemplate | object | `{"affinity":{},"annotations":{},"env":[],"fileMounts":[],"hostAliases":{},"initContainers":[],"labels":{},"nodeSelector":{},"resources":{},"schedulerName":"","securityContext":{},"tolerations":[],"volumeMounts":[],"volumes":[]}` | base template for pods spawned to consume ClearML Task |
+| agentk8sglue.basePodTemplate.affinity | object | `{}` | affinity setup for pods spawned to consume ClearML Task |
 | agentk8sglue.basePodTemplate.annotations | object | `{}` | annotations setup for pods spawned to consume ClearML Task (example in values.yaml comments) |
 | agentk8sglue.basePodTemplate.env | list | `[]` | environment variables for pods spawned to consume ClearML Task (example in values.yaml comments) |
 | agentk8sglue.basePodTemplate.fileMounts | list | `[]` | file definition for pods spawned to consume ClearML Task (example in values.yaml comments) |
@@ -61,6 +63,7 @@ Kubernetes: `>= 1.21.0-0 < 1.27.0-0`
 | agentk8sglue.replicaCount | int | `1` | Glue Agent number of pods |
 | agentk8sglue.securityContext | object | `{}` | Web Server pod security context |
 | agentk8sglue.serviceExistingAccountName | string | `""` | if set, don't create a serviceAccountName but use defined existing one |
+| agentk8sglue.tolerations | list | `[]` | tolerations setup for Agent pod (example in values.yaml comments) |
 | agentk8sglue.volumeMounts | list | `[]` | volume mounts definition for Glue Agent (example in values.yaml comments) |
 | agentk8sglue.volumes | list | `[]` | volumes definition for Glue Agent (example in values.yaml comments) |
 | agentk8sglue.webServerUrlReference | string | `"https://app.clear.ml"` | Reference to Web server url |

charts/clearml-agent/templates/agentk8sglue-configmap.yaml

@@ -172,6 +172,17 @@ data:
             {{- toYaml . | nindent 10 }}
           {{- end }}
         {{- end }}
+        {{- if $value.templateOverrides.affinity }}
+          {{- with $value.templateOverrides.affinity }}
+        affinity:
+            {{- toYaml . | nindent 10 }}
+          {{- end }}
+        {{- else if $.Values.agentk8sglue.basePodTemplate.affinity }}
+          {{- with $.Values.agentk8sglue.basePodTemplate.affinity }}
+        affinity:
+            {{- toYaml . | nindent 10 }}
+          {{- end }}
+        {{- end }}
     {{- end }}
   secrets.yaml: |
     {{- range $key, $value := $.Values.enterpriseFeatures.queues }}
@@ -250,6 +261,10 @@ data:
       tolerations:
           {{- toYaml . | nindent 8 }}
         {{- end }}
+        {{- with .Values.agentk8sglue.basePodTemplate.affinity }}
+      affinity:
+          {{- toYaml . | nindent 8 }}
+        {{- end }}
 {{- end }}
 {{- if .Values.sessions.portModeEnabled }}
 {{- range untilStep 1 ( ( add .Values.sessions.maxServices 1 ) | int ) 1 }}

charts/clearml-agent/templates/agentk8sglue-deployment.yaml

@@ -177,6 +177,14 @@ spec:
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
+      {{- with .Values.agentk8sglue.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.agentk8sglue.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       volumes:
         - name: {{ include "clearml.name" . }}-pt
           configMap:

charts/clearml-agent/values.yaml

@@ -82,6 +82,10 @@ agentk8sglue:
   # -- nodeSelector setup for Agent pod (example in values.yaml comments)
   nodeSelector: {}
     # fleet: agent-nodes
+  # -- tolerations setup for Agent pod (example in values.yaml comments)
+  tolerations: []
+  # -- affinity setup for Agent pod (example in values.yaml comments)
+  affinity: {}
   # -- volumes definition for Glue Agent (example in values.yaml comments)
   volumes: []
     # - name: "yourvolume"
@@ -162,14 +166,16 @@ agentk8sglue:
     resources: {}
       # limits:
       #   nvidia.com/gpu: 1
+    # -- nodeSelector setup for pods spawned to consume ClearML Task (example in values.yaml comments)
+    nodeSelector: {}
+      # fleet: gpu-nodes
     # -- tolerations setup for pods spawned to consume ClearML Task (example in values.yaml comments)
     tolerations: []
       # - key: "nvidia.com/gpu"
       #   operator: Exists
       #   effect: "NoSchedule"
-    # -- nodeSelector setup for pods spawned to consume ClearML Task (example in values.yaml comments)
+    # -- affinity setup for pods spawned to consume ClearML Task
-    nodeSelector: {}
+    affinity: {}
-      # fleet: gpu-nodes
     # -- securityContext setup for pods spawned to consume ClearML Task (example in values.yaml comments)
     securityContext: {}
       #  runAsUser: 1001