openscapes.cluster.yaml

name: openscapes
provider: kubeconfig
kubeconfig:
  file: secrets/openscapes.yaml
hubs:
  - name: staging
    domain: staging.openscapes.2i2c.cloud
    template: daskhub
    auth0:
      connection: github
    config: &openscapesHubConfig
      scratchBucket:
        enabled: false
      basehub:
        nfsPVC:
          nfs:
            # from https://docs.aws.amazon.com/efs/latest/ug/mounting-fs-nfs-mount-settings.html
            mountOptions:
            - rsize=1048576
            - wsize=1048576
            - timeo=600
            - soft # We pick soft over hard, so NFS lockups don't lead to hung processes
            - retrans=2
            - noresvport
            serverIP: fs-b25253b5.efs.us-west-2.amazonaws.com
            baseShareName: /
          shareCreator:
            tolerations:
            - key: node-role.kubernetes.io/master
              operator: "Exists"
              effect: "NoSchedule"
        jupyterhub:
          custom:
            homepage:
              templateVars:
                org:
                  name: Openscapes
                  logo_url: https://www.openscapes.org/img/logo.png
                  url: https://www.openscapes.org/
                designed_by:
                  name: 2i2c
                  url: https://2i2c.org
                operated_by:
                  name: 2i2c
                  url: https://2i2c.org
                funded_by:
                  name: Openscapes
                  url: https://www.openscapes.org/
          singleuser:
            defaultUrl: /lab
            initContainers:
              # Need to explicitly fix ownership here, since EFS doesn't do anonuid
            - name: volume-mount-ownership-fix
              image: busybox
              command: ["sh", "-c", "id && chown 1000:1000 /home/jovyan && ls -lhd /home/jovyan"]
              securityContext:
                runAsUser: 0
              volumeMounts:
              - name: home
                mountPath: /home/jovyan
                subPath: "{username}"

            image:
              name: 783616723547.dkr.ecr.us-west-2.amazonaws.com/user-image
              tag: "d78bb6c"
            profileList:
              # The mem-guarantees are here so k8s doesn't schedule other pods
              # on these nodes.
              - display_name: "Small: m5.large"
                description: "~2 CPU, ~8G RAM"
                kubespawner_override:
                  # Expllicitly unset mem_limit, so it overrides the default memory limit we set in
                  # basehub/values.yaml
                  mem_limit: null
                  mem_guarantee: 7G
                  node_selector:
                    node.kubernetes.io/instance-type: m5.large
              - display_name: "Medium: m5.xlarge"
                description: "~4 CPU, ~15G RAM"
                kubespawner_override:
                  mem_limit: null
                  mem_guarantee: 13G
                  node_selector:
                    node.kubernetes.io/instance-type: m5.xlarge
              - display_name: "Large: m5.2xlarge"
                description: "~8 CPU, ~30G RAM"
                kubespawner_override:
                  mem_limit: null
                  mem_guarantee: 28G
                  node_selector:
                    node.kubernetes.io/instance-type: m5.2xlarge
              - display_name: "Huge: m5.8xlarge"
                description: "~32 CPU, ~128G RAM"
                kubespawner_override:
                  mem_limit: null
                  mem_guarantee: 120G
                  node_selector:
                    node.kubernetes.io/instance-type: m5.8xlarge
          scheduling:
            userPlaceholder:
              enabled: false
              replicas: 0
            userScheduler:
              enabled: false
          proxy:
            service:
              type: LoadBalancer
            https:
              enabled: true
            chp:
              nodeSelector: {}
              tolerations:
                - key:  "node-role.kubernetes.io/master"
                  effect: "NoSchedule"
            traefik:
              nodeSelector: {}
              tolerations:
                - key:  "node-role.kubernetes.io/master"
                  effect: "NoSchedule"
          hub:
            allowNamedServers: true
            networkPolicy:
              # FIXME: For dask gateway
              enabled: false
            readinessProbe:
              enabled: false
            nodeSelector: {}
            tolerations:
              - key:  "node-role.kubernetes.io/master"
                effect: "NoSchedule"
            config:
              Authenticator:
                admin_users:
                  - yuvipanda
                  - choldgraf
                  - GeorgianaElena
                  - amfriesz
                  - jules32
      dask-gateway:
        traefik:
          tolerations:
            - key:  "node-role.kubernetes.io/master"
              effect: "NoSchedule"
        controller:
          tolerations:
            - key:  "node-role.kubernetes.io/master"
              effect: "NoSchedule"
        gateway:
          tolerations:
            - key:  "node-role.kubernetes.io/master"
              effect: "NoSchedule"
            # TODO: figure out a replacement for userLimits.
          extraConfig:
            idle: |
              # timeout after 30 minutes of inactivity
              c.KubeClusterConfig.idle_timeout = 1800
  - name: prod
    domain: openscapes.2i2c.cloud
    template: daskhub
    auth0:
      connection: github
    config: *openscapesHubConfig