# An unique identifier for the head node and workers of this cluster.
cluster_name: default

# The minimum number of workers nodes to launch in addition to the head
# node. This number should be >= 0.
min_workers: 2

# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers.
max_workers: 2

# The initial number of worker nodes to launch in addition to the head
# node. When the cluster is first brought up (or when it is refreshed with a
# subsequent `ray up`) this number of nodes will be started.
initial_workers: 2

autoscaling_mode: aggressive

# This executes all commands on all nodes in the docker container,
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled.
docker:
    image: "" # e.g., tensorflow/tensorflow:1.5.0-py3
    container_name: "" # e.g. ray_docker
    run_options: []  # Extra options to pass into "docker run"

    # Example of running a GPU head with CPU workers
    # head_image: "tensorflow/tensorflow:1.13.1-py3"
    # head_run_options:
    #     - --runtime=nvidia

    # worker_image: "ubuntu:18.04"
    # worker_run_options: []

# The autoscaler will scale up the cluster to this target fraction of resource
# usage. For example, if a cluster of 10 nodes is 100% busy and
# target_utilization is 0.8, it would resize the cluster to 13. This fraction
# can be decreased to increase the aggressiveness of upscaling.
# This value must be less than 1.0 for scaling to happen.
target_utilization_fraction: 1.0

# If a node is idle for this many minutes, it will be removed.
idle_timeout_minutes: 60

# Cloud-provider specific configuration.
provider:
    type: aws
    region: us-west-1
    # Availability zone(s), comma-separated, that nodes may be launched in.
    # Nodes are currently spread between zones by a round-robin approach,
    # however this implementation detail should not be relied upon.
    availability_zone: us-west-1a,us-west-1c
    # use_internal_ips: True

# How Ray will authenticate with newly launched nodes.
auth:
    ssh_user: ubuntu
# By default Ray creates a new private keypair, but you can also use your own.
# If you do so, make sure to also set "KeyName" in the head and worker node
# configurations below.
#    ssh_private_key: /path/to/your/key.pem

# Provider-specific config for the head node, e.g. instance type. By default
# Ray will auto-configure unspecified fields such as SubnetId and KeyName.
# For more documentation on available fields, see:
# http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances
head_node:
    InstanceType: m5.large
    ImageId: ami-0f56279347d2fa43e

    # You can provision additional disk space with a conf as follows
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 40

    # NetworkInterfaces:
    #     - AssociatePublicIpAddress: True
    # Additional options in the boto docs.

# Provider-specific config for worker nodes, e.g. instance type. By default
# Ray will auto-configure unspecified fields such as SubnetId and KeyName.
# For more documentation on available fields, see:
# http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances
worker_nodes:
    InstanceType: m5.large
    ImageId: ami-0f56279347d2fa43e

    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 40
    # Run workers on spot by default. Comment this out to use on-demand.
    # InstanceMarketOptions:
    #    MarketType: spot
        # Additional options can be found in the boto docs, e.g.
        #   SpotOptions:
        #       MaxPrice: MAX_HOURLY_PRICE

    # Additional options in the boto docs.

# Files or directories to copy to the head and worker nodes. The format is a
# dictionary from REMOTE_PATH: LOCAL_PATH, e.g.
file_mounts: {
#    "/path1/on/remote/machine": "/path1/on/local/machine",
#    "/path2/on/remote/machine": "/path2/on/local/machine",
}

# List of commands that will be run before `setup_commands`. If docker is
# enabled, these commands will run outside the container and before docker
# is setup.
initialization_commands: []

# List of shell commands to run to set up nodes.
setup_commands:
    - |
        wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh
        bash ~/miniconda.sh -b -p ~/miniconda -f -u
        $HOME/miniconda/bin/conda init bash
        source ~/.bashrc
        conda create --name modin --yes
        conda activate modin
        conda install --yes -c intel/label/modin -c conda-forge {{CONDA_PACKAGES}}

        pip install colorful cloudpickle
        # ray now executes "ray stop" which expects "ray" to be in $PATH
        # so place a symlink to current "ray" binary to /usr/local/bin
        sudo ln -s `which ray` /usr/local/bin/ray
        echo 'export MODIN_RAY_CLUSTER=True' >> ~/.bashrc

    # Consider uncommenting these if you also want to run apt-get commands during setup
    # - sudo pkill -9 apt-get || true
    # - sudo pkill -9 dpkg || true
    # - sudo dpkg --configure -a

# Custom commands that will be run on the head node after common setup.
head_setup_commands:
    - |
        source ~/.bashrc
        conda activate modin
        echo 'export MODIN_REDIS_ADDRESS="localhost:6379"' >> ~/.bashrc

# 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:
    - |
        source ~/.bashrc
        conda activate modin
        ray stop

        export MEMORY_STORE_SIZE=$(awk "/MemFree/ { printf \"%d \\n\", \$2*1024*0.8}" /proc/meminfo)
        export TMPDIR="$(dirname $(mktemp tmp.XXXXXXXXXX -ut))"
        echo 'export MEMORY_STORE_SIZE=$(awk "/MemFree/ { printf \"%d \\n\", \$2*1024*0.8}" /proc/meminfo)' >> ~/.bashrc
        echo 'export TMPDIR="$(dirname $(mktemp tmp.XXXXXXXXXX -ut))"' >> ~/.bashrc

        ulimit -n 65536; ray start --head --redis-shard-ports=6380 --port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml --object-store-memory=$MEMORY_STORE_SIZE --plasma-directory=$TMPDIR

# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
    - |
        source ~/.bashrc
        conda activate modin
        ray stop

        export MEMORY_STORE_SIZE=$(awk "/MemFree/ { printf \"%d \\n\", \$2*1024*0.8}" /proc/meminfo)
        export TMPDIR="$(dirname $(mktemp tmp.XXXXXXXXXX -ut))"
        echo 'export MEMORY_STORE_SIZE=$(awk "/MemFree/ { printf \"%d \\n\", \$2*1024*0.8}" /proc/meminfo)' >> ~/.bashrc
        echo 'export TMPDIR="$(dirname $(mktemp tmp.XXXXXXXXXX -ut))"' >> ~/.bashrc

        ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076 --object-store-memory=$MEMORY_STORE_SIZE --plasma-directory=$TMPDIR