wehub-resource-sync
55 lines
1.4 KiB
YAML
55 lines
1.4 KiB
YAML
# Multitenancy variant of heterogeneous_memory_compute.yaml.
|
|
# Each tenant gets a full mirror of the original cluster's CPU+GPU pools,
|
|
# pinned to its subcluster via Ray node labels. The two tenants share the
|
|
# same Ray cluster but should run as if isolated.
|
|
cloud: {{env["ANYSCALE_CLOUD_NAME"]}}
|
|
|
|
advanced_instance_config:
|
|
IamInstanceProfile: {"Name": "ray-autoscaler-v1"}
|
|
|
|
head_node:
|
|
instance_type: m5.4xlarge
|
|
|
|
worker_nodes:
|
|
# tenant_a CPU pool — mirrors the original CPU pool.
|
|
- name: cpu-tenant-a
|
|
instance_type: m5.2xlarge
|
|
min_nodes: 10
|
|
max_nodes: 10
|
|
market_type: ON_DEMAND
|
|
labels:
|
|
ray-subcluster: tenant_a
|
|
|
|
# tenant_b CPU pool — mirrors the original CPU pool.
|
|
- name: cpu-tenant-b
|
|
instance_type: m5.2xlarge
|
|
min_nodes: 10
|
|
max_nodes: 10
|
|
market_type: ON_DEMAND
|
|
labels:
|
|
ray-subcluster: tenant_b
|
|
|
|
# tenant_a "GPU" pool (logical GPUs, no CPUs).
|
|
- name: gpu-tenant-a
|
|
instance_type: r5.4xlarge
|
|
min_nodes: 2
|
|
max_nodes: 2
|
|
market_type: ON_DEMAND
|
|
resources:
|
|
CPU: 0
|
|
GPU: 4
|
|
labels:
|
|
ray-subcluster: tenant_a
|
|
|
|
# tenant_b "GPU" pool (logical GPUs, no CPUs).
|
|
- name: gpu-tenant-b
|
|
instance_type: r5.4xlarge
|
|
min_nodes: 2
|
|
max_nodes: 2
|
|
market_type: ON_DEMAND
|
|
resources:
|
|
CPU: 0
|
|
GPU: 4
|
|
labels:
|
|
ray-subcluster: tenant_b
|