[autoscaler] Usability improvements in logging (#10764)

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

@@ -0,0 +1,158 @@
+# A cluster setup for ML / RLlib workloads. Note that this uses pytorch by default.
+# If you want to use tensorflow, change pytorch_p36 to tensorflow_p36 below.
+#
+# Important: Make sure to run "source activate pytorch_p36" in your sessions to
+# activate the right conda environment. Otherwise you won't be able to import ray.
+#
+cluster_name: ml
+
+# 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: 0
+
+# 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: 0
+
+# 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
+
+# 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., 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.
+    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:0.8.7-gpu"
+    # head_run_options:
+    #     - --runtime=nvidia
+
+    # worker_image: "rayproject/ray:0.8.7"
+    # worker_run_options: []
+
+# 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 max value allowed is 1.0, which is the most conservative setting.
+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
+    # 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:
+    InstanceType: m4.16xlarge
+    ImageId: latest_dlami
+
+    # 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: latest_dlami
+
+    # Comment this in to use spot nodes.
+    # 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",
+}
+
+# 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
+
+# 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 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).
+    - source activate pytorch_p36 && pip install -U ray
+    - source activate pytorch_p36 && pip install -U ray[rllib] ray[tune] ray[debug]
+    # Consider uncommenting these if you also want to run apt-get commands during setup
+    # - sudo pkill -9 apt-get || true
+    # - sudo pkill -9 dpkg || true
+    # - sudo dpkg --configure -a
+
+# 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 pytorch_p36 && ray stop
+    - ulimit -n 65536; source activate pytorch_p36 && 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:
+    - source activate pytorch_p36 && ray stop
+    - ulimit -n 65536; source activate pytorch_p36 && ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076

python/ray/autoscaler/cli_logger.py

@@ -698,9 +698,9 @@ class _CliLogger():
             raise ValueError("Non-interactive confirm without --yes.")
 
         if default:
-            yn_str = cf.limeGreen("Y") + "/" + cf.red("n")
+            yn_str = "Y/n"
         else:
-            yn_str = cf.limeGreen("y") + "/" + cf.red("N")
+            yn_str = "y/N"
 
         confirm_str = cf.underlined("Confirm [" + yn_str + "]:") + " "
 

python/ray/autoscaler/commands.py

@@ -154,8 +154,6 @@ def create_or_update_cluster(config_file: str,
         raise NotImplementedError("Unsupported provider {}".format(
             config["provider"]))
 
-    cli_logger.success("Cluster configuration valid")
-
     printed_overrides = False
 
     def handle_cli_override(key, override):
@@ -244,8 +242,8 @@ def _bootstrap_config(config: Dict[str, Any],
 
     provider_cls = importer(config["provider"])
 
-    with cli_logger.timed(  # todo: better message
-            "Bootstrapping {} config",
+    with cli_logger.timed(
+            "Checking {} environment settings",
             PROVIDER_PRETTY_NAMES.get(config["provider"]["type"])):
         resolved_config = provider_cls.bootstrap_config(config)
 

python/ray/tests/test_cli_patterns/test_ray_attach.txt

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

python/ray/tests/test_cli_patterns/test_ray_exec.txt

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

python/ray/tests/test_cli_patterns/test_ray_submit.txt

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

python/ray/tests/test_cli_patterns/test_ray_up.txt

@@ -1,7 +1,6 @@
-Cluster configuration valid
 Cluster: test-cli
 
-Bootstrapping AWS config
+Checking AWS environment settings
 AWS config
   IAM Profile: .+ \[default\]
   EC2 Key pair \(head & workers\): .+ \[default\]

python/ray/tests/test_cli_patterns/test_ray_up_record.txt

@@ -1,6 +1,5 @@
-.+\.py.*Cluster configuration valid
 .+\.py.*Cluster: test-cli
-.+\.py.*Bootstrapping AWS config
+.+\.py.*Checking AWS environment settings
 .+\.py.*Creating new IAM instance profile ray-autoscaler-v1 for use as the default\.
 .+\.py.*Creating new IAM role ray-autoscaler-v1 for use as the default instance role\.
 .+\.py.*Creating new key pair __test-cli_key-1 for use as the default\.