Merge pull request #231 from DmitriGekhtman/dmitri/improve-kuberay-config

Clean up KubeRay GLUE example.

Author: asm582

doc/usage/examples/kuberay/config/aw-kuberay-glue.yaml

@@ -1,7 +1,7 @@
 apiVersion: mcad.ibm.com/v1beta1
 kind: AppWrapper
 metadata:
- name: raycluster-autoscaler
+ name: raycluster-glue
  namespace: default
 spec:
  priority: 9
@@ -20,76 +20,23 @@ spec:
  memory: 16G
  nvidia.com/gpu: 1
  generictemplate:
- # This config demonstrates KubeRay's Ray autoscaler integration.
- # The resource requests and limits in this config are too small for production!
- # For an example with more realistic resource configuration, see
- # ray-cluster.autoscaler.large.yaml.
  apiVersion: ray.io/v1alpha1
  kind: RayCluster
  metadata:
  labels:
  controller-tools.k8s.io: "1.0"
- # A unique identifier for the head node and workers of this cluster.
  name: glue-cluster
- # finalizers:
- # - kubernetes
  spec:
- # The version of Ray you are using. Make sure all Ray containers are running this version of Ray.
  rayVersion: '1.12.0'
- # If enableInTreeAutoscaling is true, the autoscaler sidecar will be added to the Ray head pod.
- # Ray autoscaler integration is supported only for Ray versions >= 1.11.0
- # Ray autoscaler integration is Beta with KubeRay >= 0.3.0 and Ray >= 2.0.0.
- enableInTreeAutoscaling: false
- # autoscalerOptions is an OPTIONAL field specifying configuration overrides for the Ray autoscaler.
- # The example configuration shown below below represents the DEFAULT values.
- # (You may delete autoscalerOptions if the defaults are suitable.)
- autoscalerOptions:
- # upscalingMode is "Default" or "Aggressive."
- # Conservative: Upscaling is rate-limited; the number of pending worker pods is at most the size of the Ray cluster.
- # Default: Upscaling is not rate-limited.
- # Aggressive: An alias for Default; upscaling is not rate-limited.
- upscalingMode: Default
- # idleTimeoutSeconds is the number of seconds to wait before scaling down a worker pod which is not using Ray resources.
- idleTimeoutSeconds: 60
- # image optionally overrides the autoscaler's container image.
- # If instance.spec.rayVersion is at least "2.0.0", the autoscaler will default to the same image as
- # the ray container. For older Ray versions, the autoscaler will default to using the Ray 2.0.0 image.
- ## image: "my-repo/my-custom-autoscaler-image:tag"
- # imagePullPolicy optionally overrides the autoscaler container's image pull policy.
- imagePullPolicy: Always
- # resources specifies optional resource request and limit overrides for the autoscaler container.
- # For large Ray clusters, we recommend monitoring container resource usage to determine if overriding the defaults is required.
- resources:
- limits:
- cpu: "500m"
- memory: "512Mi"
- requests:
- cpu: "500m"
- memory: "512Mi"
- ######################headGroupSpec#################################
- # head group template and specs, (perhaps 'group' is not needed in the name)
  headGroupSpec:
- # Kubernetes Service Type, valid values are 'ClusterIP', 'NodePort' and 'LoadBalancer'
  serviceType: ClusterIP
- # logical group name, for this called head-group, also can be functional
- # pod type head or worker
- # rayNodeType: head # Not needed since it is under the headgroup
- # the following params are used to complete the ray start: ray start --head --block ...
  rayStartParams:
- # Flag "no-monitor" will be automatically set when autoscaling is enabled.
  dashboard-host: '0.0.0.0'
  block: 'true'
- # num-cpus: '1' # can be auto-completed from the limits
- # Use `resources` to optionally specify custom resource annotations for the Ray node.
- # The value of `resources` is a string-integer mapping.
- # Currently, `resources` must be provided in the specific format demonstrated below:
- # resources: '"{\"Custom1\": 1, \"Custom2\": 5}"'
  num-gpus: '0'
- #pod template
  template:
  spec:
  containers:
- # The Ray head pod
  - name: ray-head
  image: projectcodeflare/codeflare-glue:latest
  env:
@@ -130,43 +77,21 @@ spec:
  memory: "16G"
  nvidia.com/gpu: "0"
  workerGroupSpecs:
- # the pod replicas in this group typed worker
  - replicas: 1
  minReplicas: 1
  maxReplicas: 1
- # logical group name, for this called small-group, also can be functional
  groupName: small-group
- # if worker pods need to be added, we can simply increment the replicas
- # if worker pods need to be removed, we decrement the replicas, and populate the podsToDelete list
- # the operator will remove pods from the list until the number of replicas is satisfied
- # when a pod is confirmed to be deleted, its name will be removed from the list below
- #scaleStrategy:
- # workersToDelete:
- # - raycluster-complete-worker-small-group-bdtwh
- # - raycluster-complete-worker-small-group-hv457
- # - raycluster-complete-worker-small-group-k8tj7
- # the following params are used to complete the ray start: ray start --block ...
  rayStartParams:
  block: 'true'
  num-gpus: '1'
- #pod template
  template:
- metadata:
- labels:
- key: value
- # annotations for pod
- annotations:
- key: value
- # finalizers:
- # - kubernetes
  spec:
  initContainers:
- # the env var $RAY_IP is set by the operator if missing, with the value of the head service name
  - name: init-myservice
  image: busybox:1.28
  command: ['sh', '-c', "until nslookup $RAY_IP.$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace).svc.cluster.local; do echo waiting for myservice; sleep 2; done"]
  containers:
- - name: machine-learning # must consist of lower case alphanumeric characters or '-', and must start and end with an alphanumeric character (e.g. 'my-name', or '123-abc'
+ - name: ray-worker
  image: projectcodeflare/codeflare-glue:latest
  env:
  - name: AWS_ACCESS_KEY_ID
@@ -184,8 +109,6 @@ spec:
  secretKeyRef:
  name: glue-s3-creds
  key: ENDPOINT_URL
- # environment variables to set in the container.Optional.
- # Refer to https://kubernetes.io/docs/tasks/inject-data-application/define-environment-variable-container/
  lifecycle:
  preStop:
  exec:
@@ -198,4 +121,4 @@ spec:
  requests:
  cpu: "4"
  memory: "16G"
- nvidia.com/gpu: "1"
+ nvidia.com/gpu: "1"