Feature/multiplequeues (#286)

* copy changes

* add workflow when push

* update readme

* update readme

* delete test workflow

* bump chart version to 5.2.0

* test ci

* delete test ci

* bump kubeversion

* update readme

* Update Chart.yaml

---------

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

charts/clearml-agent/Chart.yaml

@@ -2,9 +2,9 @@ apiVersion: v2
 name: clearml-agent
 description: MLOps platform Task running agent
 type: application
-version: "5.1.5"
+version: "5.2.0"
 appVersion: "1.24"
-kubeVersion: ">= 1.21.0-0 < 1.30.0-0"
+kubeVersion: ">= 1.21.0-0 < 1.31.0-0"
 home: https://clear.ml
 icon: https://raw.githubusercontent.com/allegroai/clearml/master/docs/clearml-logo.svg
 sources:
@@ -21,4 +21,6 @@ keywords:
 annotations:
   artifacthub.io/changes: |
     - kind: fixed
-      description: Use existingClearmlConfigSecret in deployment template
+      description: Support for 1.30 kubernetes
+    - kind: added
+      description: Support for multiple queues

charts/clearml-agent/README.md

@@ -1,6 +1,6 @@
 # ClearML Kubernetes Agent
 
-![Version: 5.1.5](https://img.shields.io/badge/Version-5.1.5-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: 5.2.0](https://img.shields.io/badge/Version-5.2.0-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)
 
 MLOps platform Task running agent
 
@@ -47,13 +47,13 @@ Before issuing helm upgrade:
 
 ## Requirements
 
-Kubernetes: `>= 1.21.0-0 < 1.30.0-0`
+Kubernetes: `>= 1.21.0-0 < 1.31.0-0`
 
 ## Values
 
 | Key | Type | Default | Description |
 |-----|------|---------|-------------|
-| agentk8sglue | object | `{"additionalClusterRoleBindings":[],"additionalRoleBindings":[],"affinity":{},"annotations":{},"apiServerUrlReference":"https://api.clear.ml","basePodTemplate":{"affinity":{},"annotations":{},"containerSecurityContext":{},"env":[],"fileMounts":[],"hostAliases":[],"initContainers":[],"labels":{},"nodeSelector":{},"podSecurityContext":{},"priorityClassName":"","resources":{},"schedulerName":"","tolerations":[],"volumeMounts":[],"volumes":[]},"clearmlcheckCertificate":true,"containerSecurityContext":{},"defaultContainerImage":"ubuntu:18.04","extraEnvs":[],"fileMounts":[],"fileServerUrlReference":"https://files.clear.ml","image":{"registry":"","repository":"allegroai/clearml-agent-k8s-base","tag":"1.24-21"},"initContainers":{"resources":{}},"labels":{},"nodeSelector":{},"podSecurityContext":{},"queue":"default","replicaCount":1,"resources":{},"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 | object | `{"additionalClusterRoleBindings":[],"additionalRoleBindings":[],"affinity":{},"annotations":{},"apiServerUrlReference":"https://api.clear.ml","basePodTemplate":{"affinity":{},"annotations":{},"containerSecurityContext":{},"env":[],"fileMounts":[],"hostAliases":[],"initContainers":[],"labels":{},"nodeSelector":{},"podSecurityContext":{},"priorityClassName":"","resources":{},"schedulerName":"","tolerations":[],"volumeMounts":[],"volumes":[]},"clearmlcheckCertificate":true,"containerSecurityContext":{},"createQueueIfNotExists":true,"defaultContainerImage":"ubuntu:18.04","extraEnvs":[],"fileMounts":[],"fileServerUrlReference":"https://files.clear.ml","image":{"registry":"","repository":"allegroai/clearml-agent-k8s-base","tag":"1.24-21"},"initContainers":{"resources":{}},"labels":{},"nodeSelector":{},"podSecurityContext":{},"queue":"default","replicaCount":1,"resources":{},"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.additionalClusterRoleBindings | list | `[]` | additional existing ClusterRoleBindings |
 | agentk8sglue.additionalRoleBindings | list | `[]` | additional existing RoleBindings |
 | agentk8sglue.affinity | object | `{}` | affinity setup for Agent pod (example in values.yaml comments) |
@@ -78,6 +78,7 @@ Kubernetes: `>= 1.21.0-0 < 1.30.0-0`
 | agentk8sglue.basePodTemplate.volumes | list | `[]` | volumes definition for pods spawned to consume ClearML Task (example in values.yaml comments) |
 | agentk8sglue.clearmlcheckCertificate | bool | `true` | Check certificates validity for evefry UrlReference below. |
 | agentk8sglue.containerSecurityContext | object | `{}` | container securityContext setup for Agent pod (example in values.yaml comments) |
+| agentk8sglue.createQueueIfNotExists | bool | `true` | if ClearML queue does not exist, it will be create it if the value is set to true |
 | agentk8sglue.defaultContainerImage | string | `"ubuntu:18.04"` | default container image for ClearML Task pod |
 | agentk8sglue.extraEnvs | list | `[]` | Extra Environment variables for Glue Agent |
 | agentk8sglue.fileMounts | list | `[]` | file definition for Glue Agent (example in values.yaml comments) |
@@ -88,7 +89,7 @@ Kubernetes: `>= 1.21.0-0 < 1.30.0-0`
 | agentk8sglue.labels | object | `{}` | labels setup for Agent pod (example in values.yaml comments) |
 | agentk8sglue.nodeSelector | object | `{}` | nodeSelector setup for Agent pod (example in values.yaml comments) |
 | agentk8sglue.podSecurityContext | object | `{}` | container securityContext setup for Agent pod (example in values.yaml comments) |
-| agentk8sglue.queue | string | `"default"` | ClearML queue this agent will consume |
+| agentk8sglue.queue | string | `"default"` | ClearML queue this agent will consume. Multiple queues can be specified with the following format: queue1,queue2,queue3 |
 | agentk8sglue.replicaCount | int | `1` | Glue Agent number of pods |
 | agentk8sglue.resources | object | `{}` | Glue Agent pod resources |
 | agentk8sglue.serviceExistingAccountName | string | `""` | if set, don't create a serviceAccountName but use defined existing one |

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

@@ -98,10 +98,12 @@ spec:
               value: "--namespace {{ .Release.Namespace }} --template-yaml /root/template/template.yaml \
                       --ports-mode --num-of-services {{ .Values.sessions.maxServices }} \
                       --base-port {{ .Values.sessions.startingPort }} \
-                      --gateway-address {{ .Values.sessions.externalIP }}"
+                      --gateway-address {{ .Values.sessions.externalIP }} \
+                      {{- if .Values.agentk8sglue.createQueueIfNotExists }} --create-queue{{- end }}"
             {{- else}}
             - name: K8S_GLUE_EXTRA_ARGS
-              value: "--namespace {{ .Release.Namespace }} --template-yaml /root/template/template.yaml"
+              value: "--namespace {{ .Release.Namespace }} --template-yaml /root/template/template.yaml \
+                {{- if .Values.agentk8sglue.createQueueIfNotExists }} --create-queue{{- end }}"
             {{- end }}
             {{ if or (.Values.clearml.clearmlConfig) (.Values.clearml.existingClearmlConfigSecret) }}
             - name: CLEARML_CONFIG_FILE

charts/clearml-agent/values.yaml

@@ -80,8 +80,10 @@ agentk8sglue:
 
   # -- default container image for ClearML Task pod
   defaultContainerImage: ubuntu:18.04
-  # -- ClearML queue this agent will consume
+  # -- ClearML queue this agent will consume. Multiple queues can be specified with the following format: queue1,queue2,queue3
   queue: default
+  # -- if ClearML queue does not exist, it will be create it if the value is set to true
+  createQueueIfNotExists: true
   # -- labels setup for Agent pod (example in values.yaml comments)
   labels: {}
     # schedulerName: scheduler