tutorial/demo/cluster_config.yaml at 7cdeedc6470f2dd16be614c71fd80b6fa1702bd5 · ray-project/tutorial · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
# An unique identifier for the head node and workers of this cluster.
cluster_name: ray-demo

# 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: 5

# 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

# Whether or not to autoscale aggressively. If this is enabled, if at any point
#   we would start more workers, we start at least enough to bring us to
#   initial_workers.
autoscaling_mode: default

# 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: 0.8

# If a node is idle for this many minutes, it will be removed.
idle_timeout_minutes: 5

# Cloud-provider specific configuration.
provider:
    type: aws
    region: us-west-2
    # 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-2a,us-west-2b

# 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-02c253ecf7eaba73e  # Deep Learning AMI (Ubuntu 16.04) Version 24.2

    # You can provision additional disk space with a conf as follows
    BlockDeviceMappings:
        - DeviceName: /dev/sda1
          Ebs:
              VolumeSize: 100

    # 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-0b294f219d14e6a82 # Deep Learning AMI (Ubuntu) Version 21.0

    # 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: {
    "/home/ubuntu/ray_api_demo.ipynb": "./ray_api_demo.ipynb",
    "/home/ubuntu/rllib_demo.ipynb": "./rllib_demo.ipynb",
    "/home/ubuntu/utils.py": "./utils.py",
}

# List of shell commands to run to set up nodes.
setup_commands:
    - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc
    - pip install -U ray ray[rllib] ray[tune] ray[debug]
    - pip install aiohttp psutil gym opencv-python
    - pip install lz4

# Custom commands that will be run on the head node after common setup.
head_setup_commands:
    - pip install RISE
    - pip install boto3==1.4.8  # 1.4.8 adds InstanceMarketOptions
    - pip install -U tensorflow

# 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:
    - ray stop
    - ulimit -n 65536; ray start --head --redis-port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml --include-webui

# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
    - ray stop
    - ulimit -n 65536; ray start --redis-address=$RAY_HEAD_IP:6379 --object-manager-port=8076