chore: import upstream snapshot with attribution

python/ray/tests/test_cli_patterns/test_multi_node.yaml

@@ -0,0 +1,43 @@
+cluster_name: default
+
+max_workers: 5
+
+docker:
+    image: anyscale/ray-ml:latest
+    container_name: ray_container
+    pull_before_run: true
+
+setup_commands: []
+
+head_setup_commands: []
+
+# Cloud-provider specific configuration.
+provider:
+    type: aws
+    region: us-west-2
+    availability_zone: us-west-2a
+
+available_node_types:
+    worker_node_max_specified:
+        resources: {}
+        min_workers: 2
+        max_workers: 3
+        node_config:
+            InstanceType: m5.large
+    worker_node_max_unspecified:
+        resources: {}
+        min_workers: 2
+        node_config:
+            InstanceType: m5.large
+    head_node:
+        resources: {}
+        node_config:
+            InstanceType: m5.large
+        min_workers: 0
+        max_workers: 0
+
+head_node_type: head_node
+
+# How Ray will authenticate with newly launched nodes.
+auth:
+    ssh_user: ubuntu

python/ray/tests/test_cli_patterns/test_no_head.yaml

@@ -0,0 +1,123 @@
+# 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: 0
+
+# The maximum number of workers nodes to launch in addition to the head
+# node. This takes precedence over min_workers.
+max_workers: 2
+
+# 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
+# scale up the cluster in chunks of upscaling_speed*currently_running_nodes.
+# This number should be > 0.
+upscaling_speed: 1.0
+
+# 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: "rayproject/ray-ml:latest-gpu" # You can change this to latest-cpu if you don't need GPU support and want a faster startup
+    # image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
+    container_name: "ray_container"
+    # If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
+    # if no cached version is present.
+    pull_before_run: True
+    run_options: []  # Extra options to pass into "docker run"
+
+    # Example of running a GPU head with CPU workers
+    # head_image: "rayproject/ray-ml:latest-gpu"
+    # Allow Ray to automatically detect GPUs
+
+    # worker_image: "rayproject/ray-ml:latest-cpu"
+    # worker_run_options: []
+
+# 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 will be launched in the first listed availability zone and will
+    # be tried in the subsequent availability zones if launching fails.
+    availability_zone: us-west-2a,us-west-2b
+    # Whether to allow node reuse. If set to False, nodes will be terminated
+    # instead of stopped.
+    cache_stopped_nodes: True # If not present, the default is 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 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:
+    foo: bar
+
+# 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",
+}
+
+# Files or directories to copy from the head node to the worker nodes. The format is a
+# list of paths. The same path on the head node will be copied to the worker node.
+# This behavior is a subset of the file_mounts behavior. In the vast majority of cases
+# you should just use file_mounts. Only use this if you know what you're doing!
+cluster_synced_files: []
+
+# Whether changes to directories in file_mounts or cluster_synced_files in the head node
+# should sync to the worker node continuously
+file_mounts_sync_continuously: False
+
+# Patterns for files to exclude when running rsync up or rsync down
+rsync_exclude:
+    - "**/.git"
+    - "**/.git/**"
+
+# Pattern files to use for filtering out files when running rsync up or rsync down. The file is searched for
+# in the source directory and recursively through all subdirectories. For example, if .gitignore is provided
+# as a value, the behavior will match git's behavior for finding and using .gitignore files.
+rsync_filter:
+    - ".gitignore"
+
+# 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: []
+    # Note: if you're developing Ray, you probably want to create a Docker image 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).
+    # Uncomment the following line if you want to run the nightly version of ray (as opposed to the latest)
+    # - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl
+
+# 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
+    - ulimit -n 65536; ray start --head --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:
+    - ray stop
+    - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076

python/ray/tests/test_cli_patterns/test_no_workers.yaml

@@ -0,0 +1,124 @@
+
+# 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: 0
+
+# The maximum number of workers nodes to launch in addition to the head
+# node. This takes precedence over min_workers.
+max_workers: 2
+
+# 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
+# scale up the cluster in chunks of upscaling_speed*currently_running_nodes.
+# This number should be > 0.
+upscaling_speed: 1.0
+
+# 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: "rayproject/ray-ml:latest-gpu" # You can change this to latest-cpu if you don't need GPU support and want a faster startup
+    # image: rayproject/ray:latest-gpu   # use this one if you don't need ML dependencies, it's faster to pull
+    container_name: "ray_container"
+    # If true, pulls latest version of image. Otherwise, `docker run` will only pull the image
+    # if no cached version is present.
+    pull_before_run: True
+    run_options: []  # Extra options to pass into "docker run"
+
+    # Example of running a GPU head with CPU workers
+    # head_image: "rayproject/ray-ml:latest-gpu"
+    # Allow Ray to automatically detect GPUs
+
+    # worker_image: "rayproject/ray-ml:latest-cpu"
+    # worker_run_options: []
+
+# 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 will be launched in the first listed availability zone and will
+    # be tried in the subsequent availability zones if launching fails.
+    availability_zone: us-west-2a,us-west-2b
+    # Whether to allow node reuse. If set to False, nodes will be terminated
+    # instead of stopped.
+    cache_stopped_nodes: True # If not present, the default is 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:
+    baz: qux
+
+
+# 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",
+}
+
+# Files or directories to copy from the head node to the worker nodes. The format is a
+# list of paths. The same path on the head node will be copied to the worker node.
+# This behavior is a subset of the file_mounts behavior. In the vast majority of cases
+# you should just use file_mounts. Only use this if you know what you're doing!
+cluster_synced_files: []
+
+# Whether changes to directories in file_mounts or cluster_synced_files in the head node
+# should sync to the worker node continuously
+file_mounts_sync_continuously: False
+
+# Patterns for files to exclude when running rsync up or rsync down
+rsync_exclude:
+    - "**/.git"
+    - "**/.git/**"
+
+# Pattern files to use for filtering out files when running rsync up or rsync down. The file is searched for
+# in the source directory and recursively through all subdirectories. For example, if .gitignore is provided
+# as a value, the behavior will match git's behavior for finding and using .gitignore files.
+rsync_filter:
+    - ".gitignore"
+
+# 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: []
+    # Note: if you're developing Ray, you probably want to create a Docker image 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).
+    # Uncomment the following line if you want to run the nightly version of ray (as opposed to the latest)
+    # - pip install -U https://s3-us-west-2.amazonaws.com/ray-wheels/latest/ray-3.0.0.dev0-cp37-cp37m-manylinux2014_x86_64.whl
+
+# 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
+    - ulimit -n 65536; ray start --head --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:
+    - ray stop
+    - ulimit -n 65536; ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076

python/ray/tests/test_cli_patterns/test_ray_attach.txt

@@ -0,0 +1,3 @@
+Checking AWS environment settings
+Fetched IP: .+
+ubuntu@ip-.+:~\$ exit

python/ray/tests/test_cli_patterns/test_ray_attach_with_ip.txt

@@ -0,0 +1,4 @@
+Checking AWS environment settings
+Attaching to node with IP: .+
+Fetched IP: .+
+ubuntu@ip-.+:~\$ exit

python/ray/tests/test_cli_patterns/test_ray_cluster_dump.txt

@@ -0,0 +1,16 @@
+You are about to create a cluster dump\. This will collect data from cluster nodes\.
+
+The dump will contain this information:
+
+  - The logfiles of your Ray session
+    This usually includes Python outputs \(stdout/stderr\)
+  - Debug state information on your Ray cluster
+    e\.g\. number of workers, drivers, objects, etc\.
+  - Your installed Python packages \(`pip freeze`\)
+
+If you are concerned about leaking private information, extract the archive and inspect its contents before sharing it with anyone\.
+Retrieving cluster information from ray cluster file: .+
+Checking AWS environment settings
+Collecting data from remote node: .+
+This is a test!
+Created archive: .+

python/ray/tests/test_cli_patterns/test_ray_complex.yaml

@@ -0,0 +1,75 @@
+auth:
+    ssh_user: ubuntu
+cluster_name: test-cli
+docker:
+    image: anyscale/ray-ml:latest
+    container_name: ray_container
+    pull_before_run: true
+    head_image: anyscale/ray-ml:head-default
+    worker_image: anyscale/ray-ml:worker-default
+max_workers:
+    10
+file_mounts:
+    ~/tests: .
+available_node_types:
+    head_node:
+        resources: {}
+        max_workers: 0
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+    default:
+        resources: {}
+        max_workers: 2
+        min_workers: 0
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+    worker_nodes:
+        resources: {}
+        max_workers: 2
+        min_workers: 1
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+        initialization_commands:
+            - echo what
+    worker_nodes1:
+        resources:
+            CPU: 2
+        labels:
+            foo: bar 
+        max_workers: 2
+        min_workers: 1
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+        worker_setup_commands:
+            - echo worker1
+        docker:
+            worker_image: anyscale/ray-ml:worker_nodes1
+            pull_before_run: true
+head_node_type: head_node
+head_setup_commands:
+    - echo head
+head_start_ray_commands:
+    - ray stop
+    - ray start --head --autoscaling-config=~/ray_bootstrap_config.yaml
+idle_timeout_minutes: 5
+initialization_commands:
+    - echo init
+provider:
+    availability_zone: us-west-2a
+    key_pair:
+        key_name: __test-cli
+    region: us-west-2
+    type: aws
+setup_commands:
+    - echo a
+    - echo b
+    - echo ${echo hi}
+worker_setup_commands:
+    - echo worker
+worker_start_ray_commands:
+    - ray stop
+    - ray start --address=$RAY_HEAD_IP

python/ray/tests/test_cli_patterns/test_ray_dashboard.txt

@@ -0,0 +1,6 @@
+Attempting to establish dashboard locally at http://localhost:8265/ connected to remote port 8265
+Checking AWS environment settings
+Fetched IP: .+
+Forwarding ports
+ubuntu@ip-.+:~\$ exit
+Successfully established connection.

python/ray/tests/test_cli_patterns/test_ray_exec.txt

@@ -0,0 +1,3 @@
+Checking AWS environment settings
+Fetched IP: .+
+This is a test!

python/ray/tests/test_cli_patterns/test_ray_start.txt

@@ -0,0 +1,34 @@
+
+Local node IP: .+
+
+--------------------
+Ray runtime started.
+--------------------
+
+Next steps
+  Note: The following commands are intended for use on
+  the head node or within the cluster network\.
+
+  To add another node to this Ray cluster, run
+    ray start --address='.+'
+
+  To connect to this Ray cluster:
+    import ray
+    ray\.init\(\)
+
+  To submit a Ray job using the Ray Jobs CLI:
+    RAY_API_SERVER_ADDRESS='http://.+:8265' ray job submit --working-dir \. -- python my_script\.py
+
+  See https://docs\.ray\.io/en/latest/cluster/running-applications/job-submission/index\.html
+  for more information on submitting Ray jobs to the Ray cluster.
+
+  To terminate the Ray runtime, run
+    ray stop
+
+  To view the status of the cluster, use
+    ray status
+
+  To monitor and debug Ray, view the dashboard at
+    127.0.0.1:8265
+
+  If connection to the dashboard fails, check your firewall settings and network configuration.

python/ray/tests/test_cli_patterns/test_ray_start_windows_osx.txt

@@ -0,0 +1,35 @@
+Usage stats collection is enabled by default without user confirmation because this terminal is detected to be non-interactive\..+
+
+Local node IP: .+
+
+--------------------
+Ray runtime started.
+--------------------
+
+Next steps
+  Note: The following commands are intended for use on
+  the head node or within the cluster network\.
+
+  To add another node to this Ray cluster, run
+    RAY_ENABLE_WINDOWS_OR_OSX_CLUSTER=1 ray start --address='.+'
+
+  To connect to this Ray cluster:
+    import ray
+    ray\.init\(\)
+
+  To submit a Ray job using the Ray Jobs CLI:
+    RAY_API_SERVER_ADDRESS='http://.+:8265' ray job submit --working-dir \. -- python my_script\.py
+
+  See https://docs\.ray\.io/en/latest/cluster/running-applications/job-submission/index\.html
+  for more information on submitting Ray jobs to the Ray cluster.
+
+  To terminate the Ray runtime, run
+    ray stop
+
+  To view the status of the cluster, use
+    ray status
+
+  To monitor and debug Ray, view the dashboard at
+    127.0.0.1:8265
+
+  If connection to the dashboard fails, check your firewall settings and network configuration.

python/ray/tests/test_cli_patterns/test_ray_status.txt

@@ -0,0 +1,23 @@
+======== Autoscaler status: .+
+Node status
+---------------------------------------------------------------
+Active:
+ \(no active nodes\)
+Idle:
+ 1 node_.+
+Pending:
+ \(no pending nodes\)
+Recent failures:
+ \(no failures\)
+
+Resources
+---------------------------------------------------------------
+Total Usage:
+ 0.0/3.0 CPU
+ 0.+
+ 0.+
+
+From request_resources:
+ \(none\)
+Pending Demands:
+ \(no resource demands\)

python/ray/tests/test_cli_patterns/test_ray_status_multinode.txt

@@ -0,0 +1,26 @@
+======== Autoscaler status: .+
+Node status
+---------------------------------------------------------------
+Active:
+ \(no active nodes\)
+Idle:
+ 1 node_.+
+ 1 node_.+
+ 1 node_.+
+ 1 node_.+
+Pending:
+ \(no pending nodes\)
+Recent failures:
+ \(no failures\)
+
+Resources
+---------------------------------------------------------------
+Total Usage:
+ 0.0/8.0 CPU
+ 0.+
+ 0.+
+
+From request_resources:
+ \(none\)
+Pending Demands:
+ \(no resource demands\)

python/ray/tests/test_cli_patterns/test_ray_status_multinode_v1.txt

@@ -0,0 +1,24 @@
+======== Autoscaler status: .+
+Node status
+---------------------------------------------------------------
+Active:
+ 1 node_.+
+ 1 node_.+
+ 1 node_.+
+ 1 node_.+
+Pending:
+ \(no pending nodes\)
+Recent failures:
+ \(no failures\)
+
+Resources
+---------------------------------------------------------------
+Total Usage:
+ 0.0/8.0 CPU
+ 0.+
+ 0.+
+
+From request_resources:
+ \(none\)
+Pending Demands:
+ \(no resource demands\)

python/ray/tests/test_cli_patterns/test_ray_status_v1.txt

@@ -0,0 +1,21 @@
+======== Autoscaler status: .+
+Node status
+---------------------------------------------------------------
+Active:
+ 1 node_.+
+Pending:
+ \(no pending nodes\)
+Recent failures:
+ \(no failures\)
+
+Resources
+---------------------------------------------------------------
+Total Usage:
+ 0.0/3.0 CPU
+ 0.+
+ 0.+
+
+From request_resources:
+ \(none\)
+Pending Demands:
+ \(no resource demands\)

python/ray/tests/test_cli_patterns/test_ray_submit.txt

@@ -0,0 +1,5 @@
+Checking AWS environment settings
+Fetched IP: .+
+Checking AWS environment settings
+Fetched IP: .+
+This is a test!

python/ray/tests/test_cli_patterns/test_ray_up.txt

@@ -0,0 +1,68 @@
+Cluster: test-cli
+
+Checking AWS environment settings
+AWS config
+  IAM Profile: .+ \[default\]
+  EC2 Key pair \(all available node types\): .+ \[default\]
+  VPC Subnets \(all available node types\): subnet-.+ \[default\]
+  EC2 Security groups \(all available node types\): sg-.+ \[default\]
+  EC2 AMI \(all available node types\): ami-.+ \[dlami\]
+
+No head node found\. Launching a new cluster\. Confirm \[y/N\]: y \[automatic, due to --yes\]
+
+
+Acquiring an up-to-date head node
+  Launched 1 nodes \[subnet_id=subnet-.+\]
+    Launched instance i-.+ \[state=pending, info=pending\]
+  Launched a new head node
+  Fetching the new head node
+
+<1/1> Setting up head node
+  Prepared bootstrap config
+  Autoscaler v2 is now enabled by default.+
+  New status: waiting-for-ssh
+  \[1/7\] Waiting for SSH to become available
+    Running `uptime` as a test\.
+    Fetched IP: .+
+    Success\.
+  Updating cluster configuration\. \[hash=.+\]
+  New status: syncing-files
+  \[2/7\] Processing file mounts
+    ~/tests/ from ./
+  \[3/7\] No worker file mounts to sync
+  New status: setting-up
+  \[4/7\] Running initialization commands
+  \[5/7\] Initializing command runner
+  \[6/7\] Running setup commands
+    \(0/4\) echo a
+    \(1/4\) echo b
+    \(2/4\) echo \${echo hi}
+    \(3/4\) echo head
+  \[7/7\] Starting the Ray runtime
+  New status: up-to-date
+
+-{60}
+Note: The output above is from the head node \(via `ray start`\)\.
+  Commands shown in 'Next steps' may only work from the head node
+  or from within the cluster network\.
+
+Useful commands for your local machine:
+  To terminate the cluster:
+    ray down .+
+
+  To retrieve the IP address of the cluster head:
+    ray get-head-ip .+
+
+  To port-forward the cluster's Ray Dashboard to the local machine:
+    ray dashboard .+
+
+  To submit a job to the cluster, port-forward the Ray Dashboard in another terminal and run:
+    ray job submit --address .+
+
+  To connect to a terminal on the cluster head for debugging:
+    ray attach .+
+
+  To monitor autoscaling:
+    ray exec .+ 'tail -n 100 -f /tmp/ray/session_latest/logs/monitor\*'
+
+

python/ray/tests/test_cli_patterns/test_ray_up_config.yaml

@@ -0,0 +1,45 @@
+auth:
+    ssh_user: ubuntu
+cluster_name: test-cli
+file_mounts:
+    ~/tests: .
+available_node_types:
+    head_node:
+        resources: {}
+        labels:
+            key1: value1
+        max_workers: 0
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+    worker_nodes:
+        resources: {}
+        max_workers: 2
+        min_workers: 1
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+head_node_type: head_node
+head_setup_commands:
+    - echo head
+head_start_ray_commands:
+    - ray stop
+    - ray start --head --autoscaling-config=~/ray_bootstrap_config.yaml
+idle_timeout_minutes: 5
+initialization_commands:
+    - echo init
+provider:
+    availability_zone: us-west-2a
+    key_pair:
+        key_name: __test-cli
+    region: us-west-2
+    type: aws
+setup_commands:
+    - echo a
+    - echo b
+    - echo ${echo hi}
+worker_setup_commands:
+    - echo worker
+worker_start_ray_commands:
+    - ray stop
+    - ray start --address=$RAY_HEAD_IP

python/ray/tests/test_cli_patterns/test_ray_up_docker.txt

@@ -0,0 +1,68 @@
+Cluster: test-cli
+
+Checking AWS environment settings
+AWS config
+  IAM Profile: .+ \[default\]
+  EC2 Key pair \(all available node types\): .+ \[default\]
+  VPC Subnets \(all available node types\): subnet-.+ \[default\]
+  EC2 Security groups \(all available node types\): sg-.+ \[default\]
+  EC2 AMI \(all available node types\): ami-.+ \[dlami\]
+
+No head node found\. Launching a new cluster\. Confirm \[y/N\]: y \[automatic, due to --yes\]
+
+
+Acquiring an up-to-date head node
+  Launched 1 nodes \[subnet_id=subnet-.+\]
+    Launched instance i-.+ \[state=pending, info=pending\]
+  Launched a new head node
+  Fetching the new head node
+
+<1/1> Setting up head node
+  Prepared bootstrap config
+  Autoscaler v2 is now enabled by default.+
+  New status: waiting-for-ssh
+  \[1/7\] Waiting for SSH to become available
+    Running `uptime` as a test\.
+    Fetched IP: .+
+    Success\.
+  Updating cluster configuration\. \[hash=.+\]
+  New status: syncing-files
+  \[2/7\] Processing file mounts
+    ~/tests/ from ./
+  \[3/7\] No worker file mounts to sync
+  New status: setting-up
+  \[4/7\] Running initialization commands
+  \[5/7\] Initializing command runner
+  \[6/7\] Running setup commands
+    \(0/4\) echo a
+    \(1/4\) echo b
+    \(2/4\) echo \${echo hi}
+    \(3/4\) echo head
+  \[7/7\] Starting the Ray runtime
+  New status: up-to-date
+
+-{60}
+Note: The output above is from the head node \(via `ray start`\)\.
+  Commands shown in 'Next steps' may only work from the head node
+  or from within the cluster network\.
+
+Useful commands for your local machine:
+  To terminate the cluster:
+    ray down .+
+
+  To retrieve the IP address of the cluster head:
+    ray get-head-ip .+
+
+  To port-forward the cluster's Ray Dashboard to the local machine:
+    ray dashboard .+
+
+  To submit a job to the cluster, port-forward the Ray Dashboard in another terminal and run:
+    ray job submit --address .+
+
+  To connect to a terminal on the cluster head for debugging:
+    ray attach .+
+
+  To monitor autoscaling:
+    ray exec .+ 'tail -n 100 -f /tmp/ray/session_latest/logs/monitor\*'
+
+

python/ray/tests/test_cli_patterns/test_ray_up_docker_config.yaml

@@ -0,0 +1,48 @@
+auth:
+    ssh_user: ubuntu
+cluster_name: test-cli
+docker:
+    image: rayproject/ray:1.0.0
+    container_name: raydocker
+    pull_before_run: True
+    run_options: []
+file_mounts:
+    ~/tests: .
+available_node_types:
+    head_node:
+        resources: {}
+        max_workers: 0
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+    worker_nodes:
+        resources: {}
+        max_workers: 2
+        min_workers: 1
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+head_node_type: head_node
+head_setup_commands:
+    - echo head
+head_start_ray_commands:
+    - ray stop
+    - ray start --head --autoscaling-config=~/ray_bootstrap_config.yaml
+idle_timeout_minutes: 5
+initialization_commands:
+    - echo init
+provider:
+    availability_zone: us-west-2a
+    key_pair:
+        key_name: __test-cli
+    region: us-west-2
+    type: aws
+setup_commands:
+    - echo a
+    - echo b
+    - echo ${echo hi}
+worker_setup_commands:
+    - echo worker
+worker_start_ray_commands:
+    - ray stop
+    - ray start --address=$RAY_HEAD_IP

python/ray/tests/test_cli_patterns/test_ray_up_no_max_worker_config.yaml

@@ -0,0 +1,42 @@
+auth:
+    ssh_user: ubuntu
+cluster_name: test-cli
+file_mounts:
+    ~/tests: .
+available_node_types:
+    head_node:
+        resources: {}
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+    worker_nodes:
+        resources: {}
+        max_workers: 2
+        min_workers: 1
+        node_config:
+            ImageId: latest_dlami
+            InstanceType: t1.micro
+head_node_type: head_node
+head_setup_commands:
+    - echo head
+head_start_ray_commands:
+    - ray stop
+    - ray start --head --autoscaling-config=~/ray_bootstrap_config.yaml
+idle_timeout_minutes: 5
+initialization_commands:
+    - echo init
+provider:
+    availability_zone: us-west-2a
+    key_pair:
+        key_name: __test-cli
+    region: us-west-2
+    type: aws
+setup_commands:
+    - echo a
+    - echo b
+    - echo ${echo hi}
+worker_setup_commands:
+    - echo worker
+worker_start_ray_commands:
+    - ray stop
+    - ray start --address=$RAY_HEAD_IP

python/ray/tests/test_cli_patterns/test_ray_up_record.txt

@@ -0,0 +1,103 @@
+.+\.py.*Cluster: test-cli
+.+\.py.*Checking AWS environment settings
+.+\.py.*Creating new IAM instance profile .+ for use as the default\.
+.+\.py.*Creating new IAM role .+ for use as the default instance role\.
+.+\.py.*Creating new key pair __test-cli_key-1 for use as the default\.
+.+\.py.*Created new security group ray-autoscaler.+ \[id=sg-.+\]
+.+\.py.*AWS config
+.+\.py.*IAM Profile: .+ \[default\]
+.+\.py.*EC2 Key pair \(all available node types\): __test-cli_key-1 \[default\]
+.+\.py.*VPC Subnets \(all available node types\): subnet-.+ \[default\]
+.+\.py.*EC2 Security groups \(all available node types\): sg-.+ \[default\]
+.+\.py.*EC2 AMI \(all available node types\): ami-dca37ea5 \[dlami\]
+.+\.py.*No head node found\. Launching a new cluster\. Confirm \[y/N\]: y \[automatic, due to --yes\]
+.+\.py.*Acquiring an up-to-date head node
+.+\.py.*Launched 1 nodes \[subnet_id=subnet-.+\]
+.+\.py.*Launched instance i-.+ \[state=pending, info=pending\]
+.+\.py.*Launched a new head node
+.+\.py.*Fetching the new head node
+.+\.py.*<1/1> Setting up head node
+.+\.py.*Prepared bootstrap config
+.+\.py.*Autoscaler v2 is now enabled by default.+
+.+\.py.*AWSNodeProvider: Set tag ray-node-status=waiting-for-ssh on \['.+'\]  \[LogTimer=.+\]
+.+\.py.*New status: waiting-for-ssh
+.+\.py.*\[1/7\] Waiting for SSH to become available
+.+\.py.*Running `uptime` as a test\.
+.+\.py.*Fetched IP: .+
+.+\.py.*NodeUpdater: .+: Got IP  \[LogTimer=.+\]
+.+\.py.*Running `uptime`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*Success\.
+.+\.py.*NodeUpdater: .+: Got remote shell  \[LogTimer=.+\]
+.+\.py.*Updating cluster configuration\. \[hash=.+\]
+.+\.py.*AWSNodeProvider: Set tag ray-node-status=syncing-files on \['.+'\]  \[LogTimer=.+\]
+.+\.py.*New status: syncing-files
+.+\.py.*\[2/7\] Processing file mounts
+.+\.py.*Running `mkdir -p ~/tests`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*Running `rsync.+`
+.+\.py.*`rsync`ed \./ \(local\) to ~/tests/ \(remote\)
+.+\.py.*~/tests/ from \./
+.+\.py.+NodeUpdater: i-.+: Synced \./ to ~/tests/  \[LogTimer=.+\]
+.+\.py.*Running `mkdir -p ~`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*Running `rsync.+`
+.+\.py.*`rsync`ed .+/ray-bootstrap-.+ \(local\) to ~/ray_bootstrap_config\.yaml \(remote\)
+.+\.py.*~/ray_bootstrap_config\.yaml from .+ray-bootstrap-.+
+.+\.py.*NodeUpdater: i-.+: Synced .+ray-bootstrap-.+ to ~/ray_bootstrap_config\.yaml  \[LogTimer=.+\]
+.+\.py.*Running `mkdir -p ~`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*Running `rsync.+`
+.+\.py.*`rsync`ed .+__test-cli_key-1\.pem \(local\) to ~/ray_bootstrap_key\.pem \(remote\)
+.+\.py.*~/ray_bootstrap_key\.pem from .+__test-cli_key-1\.pem
+.+\.py.*NodeUpdater: i-.+: Synced .+.pem to ~/ray_bootstrap_key\.pem  \[LogTimer=.+\]
+.+\.py.*\[3/7\] No worker file mounts to sync
+.+\.py.*AWSNodeProvider: Set tag ray-node-status=setting-up on \['.+'\]  \[LogTimer=.+\]
+.+\.py.*New status: setting-up
+.+\.py.*\[4/7\] Running initialization commands
+.+\.py.*Running `echo init`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*NodeUpdater: i-.+: Initialization commands succeeded \[LogTimer=.+\]
+.+\.py.*\[5/7\] Initializing command runner
+.+\.py.*\[6/7\] Running setup commands
+.+\.py.*\(0/4\) echo a
+.+\.py.*Running `echo a`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*\(1/4\) echo b
+.+\.py.*Running `echo b`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*\(2/4\) echo \${echo hi}
+.+\.py.*Running `echo \${echo hi}`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*\(3/4\) echo head
+.+\.py.*Running `echo head`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*NodeUpdater: i-.+: Setup commands succeeded \[LogTimer=.+\]
+.+\.py.*\[7/7\] Starting the Ray runtime
+.+\.py.*Running `export RAY_USAGE_STATS_ENABLED=1;export RAY_OVERRIDE_RESOURCES='{"CPU":1}';export RAY_OVERRIDE_LABELS='{"key1":"value1"}';export RAY_enable_autoscaler_v2=1; export RAY_CLOUD_INSTANCE_ID=i-.+; export RAY_NODE_TYPE_NAME=head_node; ray stop`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*Running `export RAY_USAGE_STATS_ENABLED=1;export RAY_OVERRIDE_RESOURCES='{"CPU":1}';export RAY_OVERRIDE_LABELS='{"key1":"value1"}';export RAY_enable_autoscaler_v2=1; export RAY_CLOUD_INSTANCE_ID=i-.+; export RAY_NODE_TYPE_NAME=head_node; ray start --head --autoscaling-config=~/ray_bootstrap_config\.yaml`
+.+\.py.*Full command is `ssh.+`
+.+\.py.*NodeUpdater: i-.+: Ray start commands succeeded \[LogTimer=.+\]
+.+\.py.*NodeUpdater: i-.+: Applied config .+  \[LogTimer=.+\]
+.+\.py.*AWSNodeProvider: Set tag ray-node-status=up-to-date on \['.+'\]  \[LogTimer=.+\]
+.+\.py.*AWSNodeProvider: Set tag ray-runtime-config=.+ on \['.+'\]  \[LogTimer=.+\]
+.+\.py.*AWSNodeProvider: Set tag ray-file-mounts-contents=.+ on \['.+'\]  \[LogTimer=.+\]
+.+\.py.*New status: up-to-date
+.+\.py.*-{60}
+.+\.py.*Note: The output above is from the head node \(via `ray start`\)\.
+.+\.py.*  Commands shown in 'Next steps' may only work from the head node
+.+\.py.*  or from within the cluster network\.
+.+\.py.*Useful commands for your local machine:
+.+\.py.*To terminate the cluster:
+.+\.py.*  ray down .+
+.+\.py.*To retrieve the IP address of the cluster head:
+.+\.py.*  ray get-head-ip .+
+.+\.py.*To port-forward the cluster's Ray Dashboard to the local machine:
+.+\.py.*  ray dashboard .+
+.+\.py.*To submit a job to the cluster, port-forward the Ray Dashboard in another terminal and run:
+.+\.py.*  ray job submit --address .+
+.+\.py.*To connect to a terminal on the cluster head for debugging:
+.+\.py.*  ray attach .+
+.+\.py.*To monitor autoscaling:
+.+\.py.*  ray exec .+ 'tail -n 100 -f /tmp/ray/session_latest/logs/monitor\*'