[autoscaler] Add documentation for multi node type autoscaling (#10405)

This commit is contained in:
Eric Liang
2020-08-28 19:57:21 -07:00
committed by GitHub
parent 2a204260a8
commit f6a1698bab
6 changed files with 176 additions and 53 deletions
+1 -1
View File
@@ -42,7 +42,7 @@ docker:
# 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 value must be less than 1.0 for scaling to happen.
# 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.
@@ -18,16 +18,11 @@ available_node_types:
InstanceType: m4.xlarge
resources: {"CPU": 4}
max_workers: 5
cpu_4_spot:
node_config:
InstanceType: m4.xlarge
InstanceMarketOptions:
MarketType: spot
resources: {"CPU": 4}
max_workers: 20
cpu_16_ondemand:
cpu_16_spot:
node_config:
InstanceType: m4.4xlarge
InstanceMarketOptions:
MarketType: spot
resources: {"CPU": 16, "Custom1": 1}
max_workers: 10
gpu_1_ondemand:
@@ -35,17 +30,21 @@ available_node_types:
InstanceType: p2.xlarge
resources: {"CPU": 4, "GPU": 1, "Custom2": 2}
max_workers: 4
worker_setup_commands:
- pip install tensorflow-gpu # Example command.
gpu_8_ondemand:
node_config:
InstanceType: p2.8xlarge
resources: {"CPU": 32, "GPU": 8}
max_workers: 2
worker_setup_commands:
- pip install tensorflow-gpu # Example command.
# Specify the node type of the head node (as configured above).
head_node_type: cpu_4_ondemand
# Specify the default type of the worker node (as configured above).
worker_default_node_type: cpu_4_spot
worker_default_node_type: cpu_16_spot
# The default settings for the head node. This will be merged with the per-node
# type configs given above.