Galeos93
commented
2 months ago After using a newer ray version (2.9.0), the issue was solved. Here is the yaml I used:
# Make sure to increase resource requests and limits before using this example in production.
# For examples with more realistic resource configuration, see
# ray-cluster.complete.large.yaml and
# ray-cluster.autoscaler.large.yaml.
apiVersion: ray.io/v1alpha1
kind: RayService
metadata:
name: rayservice-sample
spec:
serviceUnhealthySecondThreshold: 900 # Config for the health check threshold for Ray Serve applications. Default value is 900.
deploymentUnhealthySecondThreshold: 300 # Config for the health check threshold for Ray dashboard agent. Default value is 300.
# serveConfigV2 takes a yaml multi-line scalar, which should be a Ray Serve multi-application config. See https://docs.ray.io/en/latest/serve/multi-app.html.
# Only one of serveConfig and serveConfigV2 should be used.
serveConfigV2: |
applications:
- name: text_ml_app
import_path: text_ml.app
route_prefix: /summarize_translate
runtime_env:
working_dir: "https://github.com/ray-project/serve_config_examples/archive/36862c251615e258a58285934c7c41cffd1ee3b7.zip"
pip:
- torch
- transformers
deployments:
- name: Translator
num_replicas: 1
ray_actor_options:
num_cpus: 0.2
user_config:
language: french
- name: Summarizer
num_replicas: 1
ray_actor_options:
num_cpus: 0.2
rayClusterConfig:
rayVersion: '2.9.0' # should match the Ray version in the image of the containers
######################headGroupSpecs#################################
# Ray head pod template.
headGroupSpec:
# The `rayStartParams` are used to configure the `ray start` command.
# See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
# See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
rayStartParams:
dashboard-host: '0.0.0.0'
#pod template
template:
spec:
containers:
- name: ray-head
image: rayproject/ray:2.9.0
resources:
limits:
cpu: 1
memory: 2Gi
requests:
cpu: 1
memory: 2Gi
ports:
- containerPort: 6379
name: gcs-server
- containerPort: 8265 # Ray dashboard
name: dashboard
- containerPort: 10001
name: client
- containerPort: 8000
name: serve
workerGroupSpecs:
# the pod replicas in this group typed worker
- replicas: 1
minReplicas: 1
maxReplicas: 5
# logical group name, for this called small-group, also can be functional
groupName: small-group
# The `rayStartParams` are used to configure the `ray start` command.
# See https://github.com/ray-project/kuberay/blob/master/docs/guidance/rayStartParams.md for the default settings of `rayStartParams` in KubeRay.
# See https://docs.ray.io/en/latest/cluster/cli.html#ray-start for all available options in `rayStartParams`.
rayStartParams: {}
#pod template
template:
spec:
containers:
- name: ray-worker # must consist of lower case alphanumeric characters or '-', and must start and end with an alphanumeric character (e.g. 'my-name', or '123-abc'
image: rayproject/ray:2.9.0
lifecycle:
preStop:
exec:
command: ["/bin/sh","-c","ray stop"]
resources:
limits:
cpu: "1"
memory: "2Gi"
requests:
cpu: "500m"
memory: "2Gi"
What happened + What you expected to happen
I follow this tutorial to deploy an application using Ray Serve. I get the following error events upon executing
kubectl describe rayservice rayservice-sample:Also applying the command
kubectl logs kuberay-operator-7f85d8578-mj4bs | tee operator-logI get the following logs:I expected the rayservice to start without issues, as shown in the tutorial.
Versions / Dependencies
Reproduction script
I follow the tutorial in here after deploying an EKS cluster in AWS, using 2 nodes of t3.medium type. The service configuration I use is not the same as in the tutorial, I have set less resources:
Issue Severity
High: It blocks me from completing my task.