cluster_name: long-running-node-failures-alex min_workers: 0 max_workers: 0 target_utilization_fraction: 0.8 idle_timeout_minutes: 5 # Cloud-provider specific configuration. provider: type: aws region: us-west-1 availability_zone: us-west-1a auth: ssh_user: ubuntu head_node: InstanceType: m5.2xlarge ImageId: ami-05fbe06ba1b862ef6 # DLAMI 7/1/19 BlockDeviceMappings: - DeviceName: /dev/sda1 Ebs: VolumeSize: 150 worker_nodes: InstanceType: m5.large ImageId: ami-05fbe06ba1b862ef6 # DLAMI 7/1/19 BlockDeviceMappings: - DeviceName: /dev/sda1 Ebs: VolumeSize: 150 # Run workers on spot by default. Comment this out to use on-demand. InstanceMarketOptions: MarketType: spot # List of shell commands to run to set up nodes. setup_commands: [] # Custom commands that will be run on the head node after common setup. head_setup_commands: [] # Custom commands that will be run on worker nodes after common setup. worker_setup_commands: [] # Command to start ray on the head node. You don't need to change this. head_start_ray_commands: [] # Command to start ray on worker nodes. You don't need to change this. worker_start_ray_commands: [] file_mounts: "$HOME/run.sh": "run.sh" "$HOME/workloads": "workloads"