Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Hello! I Am New To Clearml. I Have Clearml Installation With Helm Chart. I Am Using K8S Agent. I Have Configured A Queue For The Agent. I Have Created A Simple Task With A Simple Python Script. When I Execute This Task In The Agent Log I Get An Error: Err

Hello! I am new to clearml. I have clearml installation with helm chart. I am using k8s agent. I have configured a queue for the agent. I have created a simple task with a simple python script. When I execute this task in the agent log I get an error: ERROR: Could not push back task [8e22ae7fa7064996b851172660da63e3] to k8s pending queue k8s_scheduler [3b8a0ee70fd34cb49f688e85bd351685], error: Validation error (Cannot skip setting execution queue for a task that is not enqueued or does not have execution queue set). What am I doing wrong?

  
  
Posted 2 months ago
Votes Newest

Answers 3


Hi guys, i have the same issue:

ERROR: Could not push back task [bcfb8fdb35ec47dbbdfe4df2a003b6b1] to k8s pending queue k8s_scheduler [9680e8b47e644286895ad8760937ee51], error: Validation error (Cannot skip setting execution queue for a task that is not enqueued or does not have execution queue set

I only changed in values:

  queue: "cpu"
  createQueueIfNotExists: false

  replicaCount: 1
  apiServerUrlReference: "
"
  fileServerUrlReference: "
"
  webServerUrlReference: "
"

queue with the same name created in ui

  
  
Posted 17 days ago

# -- Global parameters section
global:
  # -- Images registry
  imageRegistry: "docker.io"

# -- Private image registry configuration
imageCredentials:
  # -- Use private authentication mode
  enabled: false
  # -- If this is set, chart will not generate a secret but will use what is defined here
  existingSecret: ""
  # -- Registry name
  registry: docker.io
  # -- Registry username
  username: someone
  # -- Registry password
  password: pwd
  # -- Email
  email: someone@host.com

# -- ClearMl generic configurations
clearml:
  # -- If this is set, chart will not generate a secret but will use what is defined here
  existingAgentk8sglueSecret: ""
  # -- Agent k8s Glue basic auth key
  agentk8sglueKey: "*****"
  # -- Agent k8s Glue basic auth secret
  agentk8sglueSecret: "*******"

  # -- If this is set, chart will not generate a secret but will use what is defined here
  existingClearmlConfigSecret: ""
  # The secret should be defined as the following example
  #
  # apiVersion: v1
  # kind: Secret
  # metadata:
  #   name: secret-name
  # stringData:
  #   clearml.conf: |-
  #     sdk {
  #     }
  # -- ClearML configuration file
  clearmlConfig: |-
    sdk {
    }

# -- This agent will spawn queued experiments in new pods, a good use case is to combine this with
# GPU autoscaling nodes.
# 

agentk8sglue:
  # -- Glue Agent image configuration
  image:
    registry: ""
    repository: "allegroai/clearml-agent-k8s-base"
    tag: "1.24-21"

  # -- Glue Agent number of pods
  replicaCount: 1

  # -- Glue Agent pod resources
  resources: {}

  # -- Glue Agent pod initContainers configs
  initContainers:
    # -- Glue Agent initcontainers pod resources
    resources: {}

  # -- Add the provided map to the annotations for the ServiceAccount resource created by this chart
  serviceAccountAnnotations: {}
  # -- If set, do not create a serviceAccountName and use the existing one with the provided name
  serviceExistingAccountName: ""

  # -- Check certificates validity for evefry UrlReference below.
  clearmlcheckCertificate: false

  # -- Reference to Api server url
  apiServerUrlReference: "
"
  # -- Reference to File server url
  fileServerUrlReference: "clearml-fileserver:8081"
  # -- Reference to Web server url
  webServerUrlReference: "clearml-webserver:8080"

  # -- default container image for ClearML Task pod
  defaultContainerImage: ubuntu:18.04
  # -- ClearML queue this agent will consume. Multiple queues can be specified with the following format: queue1,queue2,queue3
  queue: gpu
  # -- if ClearML queue does not exist, it will be create it if the value is set to true
  createQueueIfNotExists: false
  # -- labels setup for Agent pod (example in values.yaml comments)
  labels: {}
    # schedulerName: scheduler
  # -- annotations setup for Agent pod (example in values.yaml comments)
  annotations: {}
    # key1: value1
  # -- Extra Environment variables for Glue Agent
  extraEnvs: []
    # - name: PYTHONPATH
    #   value: "somepath"
  # -- container securityContext setup for Agent pod (example in values.yaml comments)
  podSecurityContext: {}
    #  runAsUser: 1001
    #  fsGroup: 1001
  # -- container securityContext setup for Agent pod (example in values.yaml comments)
  containerSecurityContext: {}
    #  runAsUser: 1001
    #  fsGroup: 1001
  # -- additional existing ClusterRoleBindings
  additionalClusterRoleBindings: []
    # - privileged
  # -- additional existing RoleBindings
  additionalRoleBindings: []
    # - privileged
  # -- 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"
    #   nfs:
    #    server: 192.168.0.1
    #    path: /var/nfs/mount
  # -- volume mounts definition for Glue Agent (example in values.yaml comments)
  volumeMounts: []
    # - name: yourvolume
    #   mountPath: /yourpath
    #   subPath: userfolder

  # -- file definition for Glue Agent (example in values.yaml comments)
  fileMounts: []
    # - name: "integration.py"
    #   folderPath: "/mnt/python"
    #   fileContent: |-
    #     def get_template(*args, **kwargs):
    #       print("args: {}".format(args))
    #       print("kwargs: {}".format(kwargs))
    #       return {
    #           "template": {
    #           }
    #       }

  # -- base template for pods spawned to consume ClearML Task
  basePodTemplate:
    # -- labels setup for pods spawned to consume ClearML Task (example in values.yaml comments)
    labels: {}
      # schedulerName: scheduler
    # -- annotations setup for pods spawned to consume ClearML Task (example in values.yaml comments)
    annotations: {}
      # key1: value1
    # -- initContainers definition for pods spawned to consume ClearML Task (example in values.yaml comments)
    initContainers: []
      # - name: volume-dirs-init-cntr
      #   image: busybox:1.35
      #  command:
      #    - /bin/bash
      #    - -c
      #    - >
      #      /bin/echo "this is an init";
    # -- schedulerName setup for pods spawned to consume ClearML Task
    schedulerName: "gpu"
    # -- volumes definition for pods spawned to consume ClearML Task (example in values.yaml comments)
    volumes: []
      # - name: "yourvolume"
      #   nfs:
      #    server: 192.168.0.1
      #    path: /var/nfs/mount
    # -- volume mounts definition for pods spawned to consume ClearML Task (example in values.yaml comments)
    volumeMounts: []
      # - name: yourvolume
      #   mountPath: /yourpath
      #   subPath: userfolder
    # -- file definition for pods spawned to consume ClearML Task (example in values.yaml comments)
    fileMounts: []
      # - name: "mounted-file.txt"
      #   folderPath: "/mnt/"
      #   fileContent: |-
      #     this is a test file
      #     with test content
    # -- environment variables for pods spawned to consume ClearML Task (example in values.yaml comments)
    env: []
      # # to setup access to private repo, setup secret with git credentials:
      # - name: CLEARML_AGENT_GIT_USER
      #   value: mygitusername
      # - name: CLEARML_AGENT_GIT_PASS
      #   valueFrom:
      #     secretKeyRef:
      #       name: git-password
      #       key: git-password
      # - name: CURL_CA_BUNDLE
      #   value: ""
      # - name: PYTHONWARNINGS
      #   value: "ignore:Unverified HTTPS request"
    # -- resources declaration for pods spawned to consume ClearML Task (example in values.yaml comments)
    resources:
      limits:
        nvidia.com/gpu: 1
    # -- priorityClassName setup for pods spawned to consume ClearML Task
    priorityClassName: ""
    # -- nodeSelector setup for pods spawned to consume ClearML Task (example in values.yaml comments)
    nodeSelector:
      nvidia.com/gpu.product: NVIDIA-RTX-4000-Ada-Generation
      # 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"
    # -- affinity setup for pods spawned to consume ClearML Task
    affinity: {}
    # -- securityContext setup for pods spawned to consume ClearML Task (example in values.yaml comments)
    podSecurityContext: {}
      #  runAsUser: 1001
      #  fsGroup: 1001
    # -- securityContext setup for containers spawned to consume ClearML Task (example in values.yaml comments)
    containerSecurityContext: {}
      #  runAsUser: 1001
      #  fsGroup: 1001
    # -- hostAliases setup for pods spawned to consume ClearML Task (example in values.yaml comments)
    hostAliases: []
    # - ip: "127.0.0.1"
    #   hostnames:
    #   - "foo.local"
    #   - "bar.local"

# -- Sessions internal service configuration
sessions:
  # -- Enable/Disable sessions portmode WARNING: only one Agent deployment can have this set to true
  portModeEnabled: false
  # -- specific annotations for session services
  svcAnnotations: {}
  # -- service type ("NodePort" or "ClusterIP" or "LoadBalancer")
  svcType: "NodePort"
  # -- External IP sessions clients can connect to
  externalIP: 0.0.0.0
  # -- starting range of exposed NodePorts
  startingPort: 30000
  # -- maximum number of NodePorts exposed
  maxServices: 20
  
  
Posted 2 months ago

Hi @<1843461294267568128:profile|KindArcticwolf58> - How did you execute this task?
The k8s_scheduler queue is an internal queue, not intended to be used for enqueuing task. I see you have configured the Agent to watch the gpu queue. Please make sure to create a queue with the same name on the control plane from the UI and restart the Agent, then enqueue the Task on this queue.

  
  
Posted 2 months ago
327 Views
3 Answers
2 months ago
17 days ago
Tags
Similar posts