2020-02-24 21:18:53 -08:00
|
|
|
cluster_name: ray-rllib-regression-tests
|
|
|
|
|
|
|
|
|
|
min_workers: 0
|
|
|
|
|
max_workers: 0
|
|
|
|
|
|
|
|
|
|
# Cloud-provider specific configuration.
|
|
|
|
|
provider:
|
|
|
|
|
type: aws
|
|
|
|
|
region: us-west-2
|
|
|
|
|
availability_zone: us-west-2a
|
|
|
|
|
cache_stopped_nodes: False
|
|
|
|
|
|
|
|
|
|
# How Ray will authenticate with newly launched nodes.
|
|
|
|
|
auth:
|
|
|
|
|
ssh_user: ubuntu
|
|
|
|
|
|
|
|
|
|
head_node:
|
2020-10-12 21:05:09 +02:00
|
|
|
InstanceType: p2.xlarge # Cheaper 1GPU K80 instance
|
2020-02-24 21:18:53 -08:00
|
|
|
ImageId: ami-07728e9e2742b0662 # Deep Learning AMI (Ubuntu 16.04)
|
|
|
|
|
|
|
|
|
|
# Set primary volume to 25 GiB
|
|
|
|
|
BlockDeviceMappings:
|
|
|
|
|
- DeviceName: /dev/sda1
|
|
|
|
|
Ebs:
|
|
|
|
|
VolumeSize: 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# List of shell commands to run to set up nodes.
|
2020-10-22 17:04:41 -07:00
|
|
|
setup_commands: []
|
2020-02-24 21:18:53 -08:00
|
|
|
|
|
|
|
|
# Command to start ray on the head node. You don't need to change this.
|
|
|
|
|
head_start_ray_commands:
|
|
|
|
|
- source activate tensorflow_p36 && ray stop
|
2020-10-12 21:05:09 +02:00
|
|
|
- ulimit -n 65536; source activate tensorflow_p36 && OMP_NUM_THREADS=1 ray start --head --redis-port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml
|
2020-02-24 21:18:53 -08:00
|
|
|
|
|
|
|
|
# Command to start ray on worker nodes. You don't need to change this.
|
|
|
|
|
worker_start_ray_commands:
|
|
|
|
|
- source activate tensorflow_p36 && ray stop
|
|
|
|
|
- ulimit -n 65536; source activate tensorflow_p36 && OMP_NUM_THREADS=1 ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
|
