diff --git a/ci/stress_tests/application_cluster_template.yaml b/ci/stress_tests/application_cluster_template.yaml index e0e1618e2..833c52f87 100644 --- a/ci/stress_tests/application_cluster_template.yaml +++ b/ci/stress_tests/application_cluster_template.yaml @@ -33,8 +33,9 @@ idle_timeout_minutes: 5 # Cloud-provider specific configuration. provider: type: aws - region: us-east-1 - availability_zone: us-east-1a + region: us-west-2 + availability_zone: us-west-2a + cache_stopped_nodes: false # How Ray will authenticate with newly launched nodes. auth: @@ -50,7 +51,7 @@ auth: # http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances head_node: InstanceType: <<>> - ImageId: ami-0757fc5a639fe7666 + ImageId: ami-07728e9e2742b0662 # Deep Learning AMI (Ubuntu 16.04) # You can provision additional disk space with a conf as follows BlockDeviceMappings: @@ -66,7 +67,7 @@ head_node: # http://boto3.readthedocs.io/en/latest/reference/services/ec2.html#EC2.ServiceResource.create_instances worker_nodes: InstanceType: <<>> - ImageId: ami-0757fc5a639fe7666 + ImageId: ami-07728e9e2742b0662 # Deep Learning AMI (Ubuntu 16.04) # Run workers on spot by default. Comment this out to use on-demand. # InstanceMarketOptions: @@ -87,7 +88,7 @@ file_mounts: { # List of shell commands to run to set up nodes. setup_commands: - wget --quiet https://s3-us-west-2.amazonaws.com/ray-wheels/releases/<<>>/<<>>/ray-<<>>-<<>>-manylinux1_x86_64.whl - - source activate tensorflow_p36 && pip install -U ray-<<>>-<<>>-manylinux1_x86_64.whl[rllib] + - source activate tensorflow_p36 && pip install -U ray-<<>>-<<>>-manylinux1_x86_64.whl - source activate tensorflow_p36 && pip install ray[rllib] ray[debug] # Consider uncommenting these if you also want to run apt-get commands during setup # - sudo pkill -9 apt-get || true @@ -103,10 +104,10 @@ worker_setup_commands: [] # Command to start ray on the head node. You don't need to change this. head_start_ray_commands: - - ray stop + - source activate tensorflow_p36 && ray stop - ulimit -n 65536; source activate tensorflow_p36 && OMP_NUM_THREADS=1 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: - - ray stop + - source activate tensorflow_p36 && ray stop - ulimit -n 65536; source activate tensorflow_p36 && OMP_NUM_THREADS=1 ray start --address=$RAY_HEAD_IP:6379 --object-manager-port=8076