[autoscaler]/[docker] Cleanup YAMLs & Use RAY docker images (#10108)

This commit is contained in:
Ian Rodney
2020-08-17 09:49:28 -07:00
committed by GitHub
parent 053188dfbe
commit a079f46c25
11 changed files with 31 additions and 41 deletions
+3 -5
View File
@@ -23,7 +23,7 @@ autoscaling_mode: default
# 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
image: "" # e.g., rayproject/ray:0.8.7
container_name: "" # e.g. ray_docker
# If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
# if no cached version is present.
@@ -31,11 +31,11 @@ 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_image: "rayproject/ray:0.8.7-gpu"
# head_run_options:
# - --runtime=nvidia
# worker_image: "ubuntu:18.04"
# worker_image: "rayproject/ray:0.8.7"
# worker_run_options: []
# The autoscaler will scale up the cluster to this target fraction of resource
@@ -129,8 +129,6 @@ setup_commands:
# 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
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp27-cp27mu-manylinux1_x86_64.whl
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp35-cp35m-manylinux1_x86_64.whl
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp36-cp36m-manylinux1_x86_64.whl
# Consider uncommenting these if you also want to run apt-get commands during setup
# - sudo pkill -9 apt-get || true
@@ -23,17 +23,17 @@ autoscaling_mode: default
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled.
docker:
image: "tensorflow/tensorflow:1.12.0-gpu-py3"
image: "rayproject/ray:0.8.7-gpu"
container_name: "ray-nvidia-docker-test" # e.g. ray_docker
run_options:
- --runtime=nvidia
# # Example of running a GPU head with CPU workers
# head_image: "tensorflow/tensorflow:1.13.1-gpu-py3"
# head_image: "rayproject/ray:0.8.7-gpu"
# head_run_options:
# - --runtime=nvidia
# worker_image: "tensorflow/tensorflow:1.13.1-py3"
# worker_image: "rayproject/ray:0.8.7"
# worker_run_options: []
# The autoscaler will scale up the cluster to this target fraction of resource
@@ -104,10 +104,10 @@ file_mounts: {
}
# List of shell commands to run to set up nodes.
setup_commands:
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp27-cp27mu-manylinux1_x86_64.whl
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp35-cp35m-manylinux1_x86_64.whl
# NOTE: rayproject/ray:0.8.7 has ray 0.8.7 bundled
# setup_commands:
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp36-cp36m-manylinux1_x86_64.whl
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp37-cp37m-manylinux1_x86_64.whl
# Custom commands that will be run on the head node after common setup.
head_setup_commands:
@@ -23,7 +23,7 @@ autoscaling_mode: default
# 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
image: "" # e.g., rayproject/ray:0.8.7
container_name: "" # e.g. ray_docker
# If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
# if no cached version is present.
@@ -31,11 +31,11 @@ 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_image: "rayproject/ray:0.8.7-gpu"
# head_run_options:
# - --runtime=nvidia
# worker_image: "ubuntu:18.04"
# worker_image: "rayproject/ray:0.8.7"
# worker_run_options: []
# The autoscaler will scale up the cluster to this target fraction of resource
@@ -23,17 +23,17 @@ autoscaling_mode: default
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled.
docker:
image: "tensorflow/tensorflow:1.13.1-gpu-py3"
image: "rayproject/ray:0.8.7-gpu"
container_name: "ray-nvidia-docker-test" # e.g. ray_docker
run_options:
- --runtime=nvidia
# # Example of running a GPU head with CPU workers
# head_image: "tensorflow/tensorflow:1.13.1-gpu-py3"
# head_image: "rayproject/ray:0.8.7-gpu"
# head_run_options:
# - --runtime=nvidia
# worker_image: "ubuntu:18.04"
# worker_image: "rayproject/ray:0.8.7"
# worker_run_options: []
# The autoscaler will scale up the cluster to this target fraction of resource
@@ -79,8 +79,9 @@ file_mounts: {
}
# List of shell commands to run to set up nodes.
setup_commands:
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp37-cp37m-manylinux1_x86_64.whl
# NOTE: rayproject/ray:0.8.7 has ray 0.8.7 bundled
# setup_commands:
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp37-cp37m-manylinux1_x86_64.whl
# Custom commands that will be run on the head node after common setup.
head_setup_commands:
+3 -3
View File
@@ -23,7 +23,7 @@ autoscaling_mode: default
# 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
image: "" # e.g., rayproject/ray:0.8.7-gpu
container_name: "" # e.g. ray_docker
# If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
# if no cached version is present.
@@ -31,11 +31,11 @@ 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_image: "rayproject/ray:0.8.7-gpu"
# head_run_options:
# - --runtime=nvidia
# worker_image: "ubuntu:18.04"
# worker_image: "rayproject/ray:0.8.7"
# worker_run_options: []
# The autoscaler will scale up the cluster to this target fraction of resource
+1 -3
View File
@@ -23,7 +23,7 @@ autoscaling_mode: default
# 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
image: "" # e.g., rayproject/ray:0.8.7
container_name: "" # e.g. ray_docker
# If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
# if no cached version is present.
@@ -140,8 +140,6 @@ setup_commands:
&& echo 'export PATH="$HOME/anaconda3/bin:$PATH"' >> ~/.profile
# Install ray
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp27-cp27mu-manylinux1_x86_64.whl
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp35-cp35m-manylinux1_x86_64.whl
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp37-cp37m-manylinux1_x86_64.whl
@@ -23,17 +23,17 @@ autoscaling_mode: default
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled.
docker:
image: "tensorflow/tensorflow:1.13.1-gpu-py3"
image: "rayproject/ray:0.8.7-gpu"
container_name: "ray-nvidia-docker-test" # e.g. ray_docker
run_options:
- --runtime=nvidia
# # Example of running a GPU head with CPU workers
# head_image: "tensorflow/tensorflow:1.13.1-gpu-py3"
# head_image: "rayproject/ray:0.8.7-gpu"
# head_run_options:
# - --runtime=nvidia
# worker_image: "ubuntu:18.04"
# worker_image: "rayproject/ray:0.8.7"
# worker_run_options: []
@@ -133,16 +133,10 @@ initialization_commands:
done"
# 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
# Install ray
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp27-cp27mu-manylinux1_x86_64.whl
- pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp35-cp35m-manylinux1_x86_64.whl
# NOTE: rayproject/ray:0.8.7 has ray 0.8.7 bundled
# setup_commands:
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp36-cp36m-manylinux1_x86_64.whl
# - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.9.0.dev0-cp37-cp37m-manylinux1_x86_64.whl
# Custom commands that will be run on the head node after common setup.
head_setup_commands:
@@ -26,7 +26,7 @@ idle_timeout_minutes: 5
# and opens all the necessary ports to support the Ray cluster.
# Empty string means disabled. Assumes Docker is installed.
docker:
image: "" # e.g., tensorflow/tensorflow:1.5.0-py3
image: "" # e.g., rayproject/ray:0.8.7
container_name: "" # e.g. ray_docker
# If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
# if no cached version is present.
+1 -1
View File
@@ -188,7 +188,7 @@
"image": {
"type": "string",
"description": "the docker image name",
"default": "tensorflow/tensorflow:1.5.0-py3"
"default": "rayproject/ray:0.8.7"
},
"container_name": {
"type": "string",
@@ -22,7 +22,6 @@ head_node:
setup_commands:
- error me
# - echo 'export PATH="$HOME/anaconda3/envs/tensorflow_p36/bin:$PATH"' >> ~/.bashrc
# - source activate tensorflow_p27 && pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-0.4.0-cp27-cp27mu-manylinux1_x86_64.whl
# # Command to start ray on the head node. You don't need to change this.
head_start_ray_commands: