mirror of
https://github.com/clearml/clearml-helm-charts
synced 2025-01-31 09:06:48 +00:00
257 lines
9.0 KiB
YAML
257 lines
9.0 KiB
YAML
# -- 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: "ACCESSKEY"
|
|
# -- Agent k8s Glue basic auth secret
|
|
agentk8sglueSecret: "SECRETKEY"
|
|
|
|
# -- If this is set, chart will not generate a secret but will use what is defined here
|
|
existingClearmlConfigSecret: ""
|
|
# -- 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.
|
|
# https://github.com/allegroai/clearml-agent/tree/master/docker/k8s-glue
|
|
agentk8sglue:
|
|
# -- Glue Agent image configuration
|
|
image:
|
|
repository: "allegroai/clearml-agent-k8s-base"
|
|
tag: "1.24-21"
|
|
|
|
# -- Glue Agent number of pods
|
|
replicaCount: 1
|
|
|
|
# -- if set, don't create a serviceAccountName but use defined existing one
|
|
serviceExistingAccountName: ""
|
|
|
|
# -- Check certificates validity for evefry UrlReference below.
|
|
clearmlcheckCertificate: true
|
|
|
|
# -- Enable Debugging logs for Agent pod
|
|
debugMode: false
|
|
|
|
# -- Reference to Api server url
|
|
apiServerUrlReference: "https://api.clear.ml"
|
|
# -- Reference to File server url
|
|
fileServerUrlReference: "https://files.clear.ml"
|
|
# -- Reference to Web server url
|
|
webServerUrlReference: "https://app.clear.ml"
|
|
|
|
# -- default container image for ClearML Task pod
|
|
defaultContainerImage: ubuntu:18.04
|
|
# -- ClearML queue this agent will consume
|
|
queue: default
|
|
# -- ClearML spawn tasks as jobs instead of pods
|
|
taskAsJob: false
|
|
# -- Custom Bash script for the Glue Agent
|
|
# -- 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
|
|
customBashScript: ""
|
|
# -- Custom Bash script for the Task Pods ran by Glue Agent
|
|
containerCustomBashScript: ""
|
|
# -- Extra Environment variables for Glue Agent
|
|
extraEnvs: []
|
|
# - name: PYTHONPATH
|
|
# value: "somepath"
|
|
# -- Web Server pod security context
|
|
securityContext: {}
|
|
# 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: ""
|
|
# -- 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: {}
|
|
# 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)
|
|
securityContext: {}
|
|
# 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
|
|
# -- Enable/Disable dynamic svc for sessions pods
|
|
dynamicSvcs: 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
|
|
# -- set interactive queue tags
|
|
setInteractiveQueuesTag: true
|
|
|
|
# -- Enterprise features (work only with an Enterprise license)
|
|
enterpriseFeatures:
|
|
# -- Enable/Disable Enterprise features
|
|
enabled: false
|
|
# -- Image tag override for enterprise version
|
|
agentImageTagOverride: "1.24-58"
|
|
# -- service account access every namespace flag
|
|
serviceAccountClusterAccess: false
|
|
# -- push env vars from Clear.ML Vault to task pods
|
|
applyVaultEnvVars: true
|
|
# -- GPU resource general counters
|
|
monitoredResources:
|
|
# -- Field name used by Agent to count minimum resources
|
|
minResourcesFieldName: "resources|limits|nvidia.com/gpu"
|
|
# -- Maximum resources counter
|
|
maxResources: 0
|
|
# -- Field name used by Agent to count maximum resources
|
|
maxResourcesFieldName: "resources|limits|nvidia.com/gpu"
|
|
# -- maximum concurrent consume ClearML Task pod
|
|
maxPods: 10
|
|
# -- Agent must use owner Token
|
|
useOwnerToken: true
|
|
# -- Create queues if they don't exist
|
|
createQueues: false
|
|
# -- ClearML queues and related template OVERRIDES used this agent will consume
|
|
queues:
|
|
# -- name of the queue will be used for this template
|
|
# default:
|
|
# -- overrides of the base template for this queue (must be declared even if empty!)
|
|
# templateOverrides: {}
|
|
## -- name of the queue will be used for this template
|
|
# default-gpu:
|
|
# # -- overrides of the base template for this queue
|
|
# templateOverrides:
|
|
# # -- resources declaration for pods spawned to consume ClearML Task
|
|
# resources:
|
|
# limits:
|
|
# nvidia.com/gpu: 1
|