-
Notifications
You must be signed in to change notification settings - Fork 0
/
ray-aws.yaml
114 lines (92 loc) · 4.86 KB
/
ray-aws.yaml
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: streetfighter
# The minimum number of workers nodes to launch in addition to the head
#a node. This number should be >= 0.
min_workers: 1
# The maximum number of workers nodes to launch in addition to the head
# node. This takes precedence over min_workers.
max_workers: 1
# 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
# 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: eu-central-1
availability_zone: eu-central-1a
# 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: m4.16xlarge
ImageId: ami-e77f260c #ubuntu dl v7
# 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: m4.16xlarge
ImageId: ami-e77f260c
# 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",
"/home/ubuntu/retro": "/home/oddrune/retro/"
}
# List of shell commands to run to set up nodes.
setup_commands:
# Note: if you're developing Ray, you probably want to create an AMI that
# has your Ray repo pre-cloned. Then, you can replace the pip installs
# below with a git checkout <your_sha> (and possibly a recompile).
- echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc
- sudo pkill -9 apt-get || true && sudo pkill -9 dpkg || true && sudo dpkg --configure -a && sudo apt-get update && sudo apt-get install openssl libsdl1.2-dev libsdl-gfx1.2-dev libsdl-image1.2-dev cmake -y && sudo apt-get install openssl libsdl1.2-dev libsdl-gfx1.2-dev libsdl-image1.2-dev cmake -y
- conda env create --force -f $HOME/retro/env.yaml
- source activate retrogame && pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.4.0-cp36-cp36m-manylinux1_x86_64.whl
# Consider uncommenting these if you also want to run apt-get commands during setup
- source activate retrogame && pip install -e /home/ubuntu/retro/gym-rle
- cp -fr ~/retro ~/retro_run/
# Custom commands that will be run on the head node after common setup.
head_setup_commands:
- pip install boto3==1.4.8 # 1.4.8 adds InstanceMarketOptions
# Custom commands that will be run on worker nodes after common setup.
worker_setup_commands: []
# Command to start ray on the head node. You don't need to change this.
head_start_ray_commands:
- source activate retrogame && ray stop
- source activate retrogame && ulimit -n 65536 && ray start --head --redis-port=6379 --object-manager-port=8076 --autoscaling-config=~/ray_bootstrap_config.yaml
# Command to start ray on worker nodes. You don't need to change this.
worker_start_ray_commands:
- source activate retrogame && ray stop
- source activate retrogame && ulimit -n 65536 && ray start --redis-address=$RAY_HEAD_IP:6379 --object-manager-port=8076