[autoscaler][docs] No more legacy autoscaler yamls (ray-project#27037)

Why are these changes needed?
This PR updates all autoscaler yaml examples/defaults to not use the legacy head_node and worker_node fields and deletes the explicit example-full-legacy yamls and the corresponding tests.

Related issue number
For ease of review, this PR is purely cosmetic/yaml editing (plus minor test changes to keep CI happy). It partially satisfies ray-project#20837. There will be 2 more follow up PRs (one to make the schema change and update the configs baked into unit tests, and another to clean up the legacy code).

Co-authored-by: Alex <alex@anyscale.com>

Author: wuisawesome

python/ray/autoscaler/aliyun/defaults.yaml

@@ -150,6 +150,3 @@ head_start_ray_commands:
 worker_start_ray_commands:
     - ray stop
     - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
-
-head_node: {}
-worker_nodes: {}

python/ray/autoscaler/aliyun/example-full.yaml

@@ -156,6 +156,3 @@ head_start_ray_commands:
 worker_start_ray_commands:
     - ray stop
     - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
-
-head_node: {}
-worker_nodes: {}

python/ray/autoscaler/aliyun/example-linux.yaml

@@ -159,6 +159,3 @@ head_start_ray_commands:
 worker_start_ray_commands:
     - ray stop
     - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
-
-head_node: {}
-worker_nodes: {}

python/ray/autoscaler/aws/defaults.yaml

@@ -142,6 +142,3 @@ head_start_ray_commands:
 worker_start_ray_commands:
     - ray stop
     - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
-
-head_node: {}
-worker_nodes: {}

python/ray/autoscaler/aws/development-example.yaml

@@ -1,13 +1,5 @@
 # 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
+cluster_name: development
 
 # The autoscaler will scale up the cluster faster with higher upscaling speed.
 # E.g., if the task requires adding more nodes then autoscaler will gradually
@@ -27,58 +19,27 @@ provider:
 # 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-0def3275  # Default Ubuntu 16.04 AMI.
-
-    # Set primary volume to 25 GiB
-    BlockDeviceMappings:
-        - DeviceName: /dev/sda1
-          Ebs:
-              VolumeSize: 50
-
-    # 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-0def3275  # Default Ubuntu 16.04 AMI.
 
-    # Set primary volume to 25 GiB
-    BlockDeviceMappings:
-        - DeviceName: /dev/sda1
-          Ebs:
-              VolumeSize: 50
-
-    # 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 shell commands to run to set up nodes.
+# Tell the autoscaler the allowed node types and the resources they provide.
+# The key is the name of the node type, which is just for debugging purposes.
+# The node config specifies the launch config and physical instance type.
+available_node_types:
+    # 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
+    ray.head.default:
+      node_config:
+        InstanceType: m4.16xlarge
+        ImageId: ami-0def3275  # Default Ubuntu 16.04 AMI.
+
+        # Set primary volume to 25 GiB
+        BlockDeviceMappings:
+            - DeviceName: /dev/sda1
+              Ebs:
+                  VolumeSize: 50
+
+# List of shell commands to install ray from source.
 setup_commands:
     # Consider uncommenting these if you run into dpkg locking issues
     # - sudo pkill -9 apt-get || true
@@ -101,12 +62,6 @@ setup_commands:
     - pip install boto3==1.4.8 cython==0.29.26 aiohttp grpcio psutil setproctitle
     - cd ray/python; pip install -e . --verbose
 
-# 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:
     - ray stop

python/ray/autoscaler/aws/example-full-legacy.yaml

@@ -169,6 +169,3 @@ head_start_ray_commands:
 worker_start_ray_commands:
     - ray stop
     - ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076
-
-head_node: {}
-worker_nodes: {}

python/ray/autoscaler/aws/example-full.yaml

@@ -16,16 +16,13 @@ auth:
 # VPC peering overview: https://docs.aws.amazon.com/vpc/latest/userguide/vpc-peering.html.
 # Setup VPC peering: https://docs.aws.amazon.com/vpc/latest/peering/create-vpc-peering-connection.html.
 # Configure VPC peering route tables: https://docs.aws.amazon.com/vpc/latest/peering/vpc-peering-routing.html.
-
-# To enable external SSH connectivity, you should also ensure that your VPC
-# is configured to assign public IPv4 addresses to every EC2 instance
-# assigned to it.
-head_node:
-    SecurityGroupIds:
-        - sg-1234abcd # Replace with an actual security group id.
-
-worker_nodes:
-    SecurityGroupIds:
-        - sg-1234abcd # Replace with an actual security group id.
-
-
+available_node_types:
+    ray.head.default:
+      node_config:
+        SecurityGroupIds:
+            - sg-1234abcd # Replace with an actual security group id.
+
+    ray.worker.default:
+      node_config:
+        SecurityGroupIds:
+            - sg-1234abcd # Replace with an actual security group id.

python/ray/autoscaler/aws/example-head-and-worker-security-group.yaml

@@ -18,38 +18,32 @@ provider:
 # How Ray will authenticate with newly launched nodes.
 auth:
     ssh_user: ubuntu
-# 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: m4.4xlarge
-    ImageId: ami-06d51e91cea0dac8d # Ubuntu 18.04
-    # You can provision additional disk space with a conf as follows
-    BlockDeviceMappings:
-        - DeviceName: /dev/sda1
-          Ebs:
-              VolumeSize: 20
-    # 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: m4.4xlarge
-    ImageId: ami-06d51e91cea0dac8d # Ubuntu 18.04
-    # 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
-# 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",
-}
+
+
+# Tell the autoscaler the allowed node types and the resources they provide.
+# The key is the name of the node type, which is just for debugging purposes.
+# The node config specifies the launch config and physical instance type.
+available_node_types:
+    ray.head.default:
+      node_config:
+        InstanceType: m4.4xlarge
+        ImageId: ami-06d51e91cea0dac8d # Ubuntu 18.04
+        # You can provision additional disk space with a conf as follows
+        BlockDeviceMappings:
+            - DeviceName: /dev/sda1
+              Ebs:
+                  VolumeSize: 20
+        # Additional options in the boto docs.
+    ray.worker.default:
+      node_config:
+        InstanceType: m4.4xlarge
+        ImageId: ami-06d51e91cea0dac8d # Ubuntu 18.04
+        # 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
 # 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.