diff --git a/release/xgboost_tests/cluster_cpu_moderate-autoscaler.yaml b/release/xgboost_tests/cluster_cpu_moderate-autoscaler.yaml new file mode 100644 index 000000000..418023059 --- /dev/null +++ b/release/xgboost_tests/cluster_cpu_moderate-autoscaler.yaml @@ -0,0 +1,42 @@ +cluster_name: ray-xgboost-release-cpu-small + +min_workers: 31 +max_workers: 31 + +idle_timeout_minutes: 15 + +docker: + image: rayproject/ray-ml:1.2.0 + container_name: ray_container + pull_before_run: true + +provider: + type: aws + region: us-west-2 + availability_zone: us-west-2a + cache_stopped_nodes: false + +auth: + ssh_user: ubuntu + +head_node: + # 64 CPUs + InstanceType: m5.xlarge + ImageId: latest_dlami + +worker_nodes: + # 64 CPUs + InstanceType: m5.xlarge + ImageId: latest_dlami + +setup_commands: + - pip install pytest xgboost_ray + - sudo mkdir -p /data || true + - sudo chown ray:1000 /data || true + - sudo chown ray / + - rm -rf /data/classification.parquet || true + - python create_test_data.py /data/classification.parquet --seed 1234 --num-rows 1000000 --num-cols 40 --num-partitions 100 --num-classes 2 + +file_mounts: + /create_test_data.py : ./create_test_data.py + ~/_train.py : workloads/_train.py diff --git a/release/xgboost_tests/cluster_cpu_small-autoscaler.yaml b/release/xgboost_tests/cluster_cpu_small-autoscaler.yaml index 309694b24..c4571e278 100644 --- a/release/xgboost_tests/cluster_cpu_small-autoscaler.yaml +++ b/release/xgboost_tests/cluster_cpu_small-autoscaler.yaml @@ -33,8 +33,10 @@ setup_commands: - pip install pytest xgboost_ray - sudo mkdir -p /data || true - sudo chown ray:1000 /data || true + - sudo chown ray / - rm -rf /data/classification.parquet || true - - python ~/release-automation-xgboost_tests/create_test_data.py /data/classification.parquet --seed 1234 --num-rows 1000000 --num-cols 40 --num-partitions 100 --num-classes 2 + - python /create_test_data.py /data/classification.parquet --seed 1234 --num-rows 1000000 --num-cols 40 --num-partitions 100 --num-classes 2 file_mounts: - ~/create_test_data.py : ./create_test_data.py + /create_test_data.py : ./create_test_data.py + ~/_train.py : workloads/_train.py