Example Configurations

This section will define a handful of example configurations for common scenarios. These examples serve as a basis for you to modify for your specific deployment.

Minimum Configuration for Deployment

The following configuration is a reduced set that brings up services with minimum features enabled. This includes no configuration for email (SMTP), only local accounts (no SSO/LDAP/AD), no TLS certificates, etc. This should NOT be used for production deployments but it helpful for getting an initial deployment that can be then modified.

Minimum Configuration
# Minimum default values for tiledb-cloud-enterprise.
# This is a YAML-formatted file.

# REQUIRED: Set the docker registry image credentials to pull TileDB Cloud docker images
# The password should be provided to you by your account representative
imageCredentials:
  password: ""

##################################
# TileDB Cloud REST API settings #
##################################
tiledb-cloud-rest:
  
  # Config ingress, be sure to set the url to where you want to expose the api
  ingress:
    url:
      # REQUIRED: Change this to the hostname you'd like the API service to be at
      - api.tiledb.example.com
    # optional TLS
    tls: []
    #  - secretName: chart-example-tls
    #    hosts:
    #      - chart-example.local

  resources:
    # REQUIRED:
    # Set the resource limits for the REST service.
    # We recommend a minimum of 8 cpus and 24 GB of ram on the worker nodes
    # We set REST to slightly below this to allow for other pods on the same worker node.
    # These setting effect the number of concurrent operations
    # limits:
    #  cpu: 100m
    #  memory: 128Mi
    requests:
      # cpu: 16000m
      # memory: 16Gi
      cpu: 7000m
      memory: 17Gi
  resourcesDind:
    # Set the resources for the Docker-in-Docker pod, this is where the UDFs run
    # The resources here directly effect the number of concurrent UDFs that can be run
    requests:
      memory: 6Gi
  restConfig:
    # REQUIRED: Set the private dockerhub registry credentials, these are the same as the `imageCredentials` above
    ContainerRegistry:
      DockerhubPassword: ""
    
    # REQUIRED: Set the initial passwords for the internal users of Rest
    # Replace "secret" with a strong password
    # This config can be removed after the first run of Rest  
    ComputationUserInitialPassword: "secret"
    PrometheusUserInitialPassword: "secret"
    CronUserInitialPassword: "secret"
    UIUserInitialPassword: "secret"
    DebugUserInitialPassword: "secret"
    
    # REQUIRED: Set the signing secret(s) for api tokens, this should be a secure value
    # We recommend creating a random value with `openssl rand -hex 32`
    # This is a list of token signing secrets. Zero element of the list is used
    # for signing, the rest are used for validation.
    # This mechanism provides a way to rotate signing secrets.
    # In case there are active tokens signed with a key and this key is removed from
    # the list, the tokens are invalidated.
    TokenSigningSecrets:
      - "Secret"
    
    # REQUIRED: This is needed for the TileDB Jupyterlab Prompt User Options extension
    CorsAllowedOrigins:
      - "https://jupyterhub.tiledb.example.com"
    # REQUIRED: Define supported storage types and locations, if you want to use NFS
    # enable "local"
    StorageLocationsSupported:
      - "s3"
      #- "local"
      #- "hdfs"
      #- "azure"
      #- "gcs"

    # REQUIRED: Configure main database. It is recommended to host a MariaDB or MySQL instance outside of the kubernetes cluster
    Databases:
      # `main` is a required database configuration
      main:
        Driver: mysql
        Host: "{{ .Release.Name }}-mariadb.{{ .Release.Namespace }}.svc.cluster.local"
        Port: 3306
        Schema: tiledb_rest
        Username: tiledb_user
        Password: password

  # It is not recommend to run the database inside k8s for production use, but it is helpful for testing
  mariadb:
    # Set to true if you wish to deploy a database inside k8s for testing
    enabled: false
    image:
      repository: bitnami/mariadb
      tag: 10.5.8
      pullPolicy: IfNotPresent
    auth:
      # Auth parameters much match with the restConfig.Databases.main above
      database: tiledb_rest
      username: tiledb_user
      password: password
      rootPassword: changeme
    primary:
      # Enable persistence if you wish to save the database, again running in k8s is not recommend for production use
      persistence:
        enabled: false
      # Set security context to user id of mysqld user in tiledb-mariadb-server
      podSecurityContext:
        enabled: true
        fsGroup: 999
      containerSecurityContext:
        enabled: true
        runAsUser: 999

####################################
# TileDB Cloud UI Console settings #
####################################
tiledb-cloud-ui:

  # REQUIRED: set the url of the jupyterhub server
  config:
    # REQUIRED: Set a secret here with `openssl rand -hex 32`
    SessionKey: "secret"
    RestServer:
      # REQUIRED: This needs to be set to
      # the same value as restConfig.UIUserInitialPassword
      Password: "secret"
    JupyterhubURL: "https://jupyterhub.tiledb.example.com"
    # SSOOkta:
      # Domain: "domain-name.okta.com"
      # ClientID: "client_id"
      # ClientSecret: "secret"

  # REQUIRED: Config ingress, be sure to set the hostname to where you want to expose the UI
  ingress:
    enabled: true
    # REQUIRED: Set URL for web console
    url: 
      - console.tiledb.example.com
    # optional TLS
    tls: []

#########################################
# TileDB Cloud Hosted Notebook Settings #
#########################################
jupyterhub:
  # REQUIRED: Set the private registry credentials, these are the same as the `imageCredentials` above
  imagePullSecret:
    password: ""
  
  proxy:
    # REQUIRED: Set a signing secret here with `openssl rand -hex 32`
    secretToken: "Secret"
  # The pre-puller is used to to ensure the docker images for notebooks are prepulled to each node
  # This can improve notebook startup time, but add additional storage requirements to the nodes
  # If you wish to use dedicated k8s node groups for notebooks, see:
  # https://zero-to-jupyterhub.readthedocs.io/en/0.8.2/optimization.html?highlight=labels#using-a-dedicated-node-pool-for-users

  hub:
    config:
      CryptKeeper:
        # REQUIRED: Set the jupyterhub auth secret for persistence, this should be a secure value
        # We recommend creating a random value with `openssl rand -hex 32`
        keys:
          - "Secret"
      TileDBCloud:
        # REQUIRED: Set the oauth2 secret, this should be a secure value
        # We recommend creating a random value with `openssl rand -hex
        client_secret: "Secret"
        # REQUIRED: Set the domain for the jupyterhub and the oauth2 service
        # it is likely you just need to replace `example.com` with your own internal domain
        # This should match the ingress settings above and the hydra settings below
        oauth_callback_url: "http://jupyterhub.tiledb.example.com/hub/oauth_callback"
        token_url: "http://oauth2.tiledb.example.com/oauth2/token"
        authorize_url: "http://oauth2.tiledb.example.com/oauth2/auth"
        userdata_url: "http://oauth2.tiledb.example.com/userinfo"
     
    # REQUIRED: Set the domain for the REST API and the oauth2 service
    # it is likely you just need to replace `example.com` with your own internal domain
    # This should match the tiledb-cloud-rest settings above and the hydra settings below
    extraEnv:
      OAUTH2_AUTHORIZE_URL: "https://oauth2.tiledb.example.com/oauth2/auth"
      OAUTH2_USERDATA_URL: "https://oauth2.tiledb.example.com/userinfo"
      TILEDB_REST_HOST: "https://api.tiledb.example.com"
      # Uncomment to disable SSL validation. Useful when testing deployments
      # TILEDB_REST_IGNORE_SSL_VALIDATION: "true"

  ingress:
    enabled: true
    # REQUIRED: set the ingress domain for hosted notebooks
    hosts:
      - "jupyterhub.tiledb.example.com"
    # optional TLS
    tls: []

########################################
# TileDB Cloud Oauth2 Service Settings #
########################################
hydra:
  hydra:
    # REQUIRED: Set the domain for the jupyterhub
    # it is likely you just need to replace `example.com` with your own internal domain
    # This should match the ingress settings above and the hydra settings below
    dangerousAllowInsecureRedirectUrls:
      - http://jupyterhub.tiledb.example.com/hub/oauth_callback
    config:
      # Optionally set the internal k8s cluster IP address space to allow non-ssl connections from
      # This defaults to all private IP spaces
      # serve:
        # tls:
          # allow_termination_from:
            # Set to cluster IP
            # - 172.20.0.0/12 
      secrets:
        # REQUIRED: Set the oauth2 secret, this should be a secure value
        # We recommend creating a random value with `openssl rand -hex 32`
        system: 
          - "secret"
        cookie:
          - "Secret"
      # REQUIRED: Set MariaDB Database connection, this defaults to the in k8s development settings. 
      # You will need to set this to the same connection parameters as the tiledb-cloud-rest section
      dsn: "mysql://tiledb_user:password@tcp(tiledb-cloud-mariadb.tiledb-cloud.svc.cluster.local:3306)/tiledb_rest?parseTime=true"
      urls:
        self:
          # REQUIRED: Update the domain for the oauth2 service and the web console ui
          # It is likely you can just replace `example.com` with your own internal domain
          issuer: "https://oauth2.tiledb.example.com/"
          public: "https://oauth2.tiledb.example.com/"
        login: "https://console.tiledb.example.com/oauth2/login"
        consent: "https://console.tiledb.example.com/oauth2/consent"

  # Configure ingress for oauth2 service
  ingress:
    public:
      hosts:
        # REQUIRED: set the ingress domain for oauth2 service
        - host: "oauth2.tiledb.example.com"
          paths:
           - path: /
             pathType: ImplementationSpecific
      # optional TLS
      tls: []

######################
# Ingress Controller #
######################
ingress-nginx:
  # This is provided for ease of testing, it is recommend to establish your own ingress which fits your environment
  enabled: false
  ## nginx configuration
  ## Ref: https://github.com/kubernetes/ingress/blob/master/controllers/nginx/configuration.md
  ##
  controller:
    name: controller
    autoscaling:
      enabled: true
      minReplicas: 2

    config:
      use-proxy-protocol: "true"
      log-format-escape-json: "true"
      log-format-upstream: '{ "time": "$time_iso8601", "remote_addr": "$proxy_protocol_addr", "x-forward-for": "$proxy_add_x_forwarded_for", "request_id": "$req_id", "remote_user": "$remote_user", "bytes_sent": $bytes_sent, "request_time": $request_time, "status": $status, "vhost": "$host", "request_proto": "$server_protocol", "path": "$uri", "request_query": "$args", "request_length": $request_length, "duration": $request_time, "method": "$request_method", "http_referrer": "$http_referer", "http_user_agent": "$http_user_agent" }'
      # Set timeouts to 1 hour
      proxy-send-timeout: "3600"
      proxy-read-timeout: "3600"
      send-timeout: "3600"
      client-max-body-size: "3076m"
      proxy-body-size: "3076m"
      proxy-buffering: "off"
      proxy-request-buffering: "off"
      proxy-http-version: "1.1"

    ingressClass: nginx

    ## Allows customization of the external service
    ## the ingress will be bound to via DNS
    publishService:
      enabled: true

    service:
      annotations:
        # Enable public facing load balancer
        service.beta.kubernetes.io/aws-load-balancer-scheme: "internet-facing"
        # Set any needed annotations. The default ones we have set are for aws ELB nginx
        service.beta.kubernetes.io/aws-load-balancer-proxy-protocol: '*'
        # Set aws-load-balancer-internal to allow all traffic from inside
        # the vpc only, the -internal makes it not accessible to the internet
        service.beta.kubernetes.io/aws-load-balancer: '0.0.0.0/0'
        # Set timeout to 1 hour
        service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: '3600'

      ## Set external traffic policy to: "Local" to preserve source IP on
      ## providers supporting it
      ## Ref: https://kubernetes.io/docs/tutorials/services/source-ip/#source-ip-for-services-with-typeloadbalancer
      externalTrafficPolicy: "Local"

      type: LoadBalancer

MinIO Usage for Deployment

MinIO is commonly used as a self-hosted object store. MinIO works well with TileDB Cloud.

Provided that after MinIO installation you have created:

  • A bucket called minio-tiledb-cloud-intermediate-result-storage

The configuration below shows only the section that needs to be modified for use with MinIO.

MinIO Configuration
# MinIO configuration values for tiledb-cloud-enterprise.
# This is a YAML-formatted file.

##################################
# TileDB Cloud REST API settings #
##################################
tiledb-cloud-rest:
  restConfig:
    # REQUIRED: Define supported storage types and locations, if you want to use NFS
    # enable "local"
    StorageLocationsSupported:
      - "s3"
      
    ArraySettings:
      # When enabled, AWS credentials will be auto-discovered
      # from the Environment, config file, EC2 metadata etc.
      AllowS3NoCredentials: false
      # Change to false avoid any region checks for s3 compatible storage.
      CheckS3Region: false

    ResultStorage:
      Config:
        # REQUIRED: Configure with MinIO access details for task results storage bucket 
        - "vfs.s3.aws_access_key_id": "key"
        - "vfs.s3.aws_secret_access_key": "secret"
      # REQUIRED: Set to a minio bucket location for task results storage
      Path: "s3://minio-tiledb-cloud-intermediate-result-storage"

    Workflows:
      BatchTaskParamsStorage:
        S3BatchTaskParamsStorage:
          # REQUIRED: Set to a minio bucket location for Task Graph Storage
          Bucket: "s3://minio-tiledb-cloud-intermediate-result-storage"
          Path: "argo-workflows"
  
    TileDBEmbedded:
      Config:
        - "vfs.s3.scheme": "http"
        - "vfs.s3.region": ""
        # REQUIRED: Set to your minio host
        - "vfs.s3.endpoint_override": "minio.example.com:9999"
        - "vfs.s3.use_virtual_addressing": "false"


##################
# Argo Workflows #
##################
argo-workflows:
  useStaticCredentials: true
  artifactRepository:
    s3:
      # insecure will disable TLS. Primarily used for minio installs not configured with TLS
      insecure: true
      # REQUIRED: The Bucket where the artifacts are stored
      bucket: 'minio-tiledb-cloud-intermediate-result-storage'
      # REQUIRED: Set to MinIO host 
      endpoint: minio.example.com:9999
      # REQUIRED: Configure with minio access details
      accessKeySecret:
        name: minio-secret
        key: MINIO_ACCESS_KEY_ID
      secretKeySecret:
        name: minio-secret
        key: MINIO_SECRET_ACCESS_KEY 

Last updated