mirror of
https://github.com/vale981/ray
synced 2025-03-06 18:41:40 -05:00
1ef2a6790c
* Add scalability tests * Network overhead cluster * Update xgboost tests * Document release tests * Don't raise on failed trial * Update to multi node yamls * Update yamls * Revert xgboost test changes * Fix import * Update release/tune_tests/scalability_tests/workloads/test_bookkeeping_overhead.py Co-authored-by: Richard Liaw <rliaw@berkeley.edu> * Pass aws credentials (WIP) * Update durable trainable example * Update xgboost sweep * Change xgboost scope, fix durable trainable stop condition * Fix max depth to limit total test length * Add cluster information to test descriptions. Update release checklist/process docs Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
53 lines
1.6 KiB
YAML
53 lines
1.6 KiB
YAML
cluster_name: ray-tune-scalability-tests-16x64_data
|
|
|
|
max_workers: 16
|
|
upscaling_speed: 16
|
|
|
|
idle_timeout_minutes: 0
|
|
|
|
docker:
|
|
image: anyscale/ray:nightly
|
|
container_name: ray_container
|
|
pull_before_run: true
|
|
|
|
provider:
|
|
type: aws
|
|
region: us-west-2
|
|
availability_zone: us-west-2a
|
|
cache_stopped_nodes: false
|
|
|
|
available_node_types:
|
|
cpu_64_ondemand:
|
|
node_config:
|
|
InstanceType: m5.16xlarge
|
|
resources: {"CPU": 64}
|
|
min_workers: 0
|
|
max_workers: 0
|
|
cpu_64_spot:
|
|
node_config:
|
|
InstanceType: m5.16xlarge
|
|
InstanceMarketOptions:
|
|
MarketType: spot
|
|
resources: {"CPU": 64}
|
|
min_workers: 15
|
|
max_workers: 15
|
|
|
|
auth:
|
|
ssh_user: ubuntu
|
|
|
|
head_node_type: cpu_64_ondemand
|
|
worker_default_node_type: cpu_64_spot
|
|
|
|
file_mounts: {
|
|
"~/release-automation-tune_scalability_tests": "."
|
|
}
|
|
|
|
setup_commands:
|
|
- ray install-nightly
|
|
- pip install pytest xgboost_ray
|
|
- mkdir -p ~/data || true
|
|
- rm -rf ~/data/train.parquet || true
|
|
- rm -rf ~/data/test.parquet || true
|
|
- cp -R /tmp/ray_tmp_mount/release-automation-tune_scalability_tests ~/release-automation-tune_scalability_tests || echo "Copy failed"
|
|
- python ~/release-automation-tune_scalability_tests/create_test_data.py ~/data/train.parquet --seed 1234 --num-rows 40000000 --num-cols 40 --num-partitions 128 --num-classes 2
|
|
- python ~/release-automation-tune_scalability_tests/create_test_data.py ~/data/test.parquet --seed 1234 --num-rows 10000000 --num-cols 40 --num-partitions 128 --num-classes 2
|