Skip to content

[Subnet Prioritization] Add EnableSingleAvailabilityZone to Fleet Config #2973

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 5 commits into from
Closed

[Subnet Prioritization] Add EnableSingleAvailabilityZone to Fleet Config #2973

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a794f7d
[Subnet Prioritization] Add SingleAvailabilityZone to fleet_config.json
Allenz5 Jun 11, 2025
116282d
[Subnet Prioritization] Update unit test of generate_fleet_config_file
Allenz5 Jun 16, 2025
1b802b9
[Subnet Prioritization] Update CHANGELOG.md
Allenz5 Jun 16, 2025
26eec74
[Subnet Prioritization] Update format
Allenz5 Jun 16, 2025
c303657
[Subnet Prioritization] Set SingleAvailabilityZone as null if EnableS…
Allenz5 Jun 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ This file is used to list changes made in each version of the AWS ParallelCluste

**CHANGES**
- Ubuntu 20.04 is no longer supported.
- Add SingleAvailabilityZone parameter to fleet_config.json
Copy link
Contributor

@gmarciani gmarciani Jul 14, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Changelog entries must be more focus on the user experience than on the implementation details. A user does not care about where we inject the new parameter, but on the consequences of enabling it.


3.13.1
------
Expand Down
9 changes: 8 additions & 1 deletion ...allelcluster-slurm/files/default/head_node_slurm/slurm/pcluster_fleet_config_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,6 +99,9 @@ def generate_fleet_config_file(output_file: str, input_file: str):
queue_capacity_reservation=queue_capacity_reservation,
queue_capacity_type=queue_capacity_type,
queue_subnets=queue_config["Networking"]["SubnetIds"],
queue_single_availability_zone=queue_config.get("Networking", {}).get(
"EnableSingleAvailabilityZone", None
),
)
fleet_config[queue_name][compute_resource_name] = config_for_fleet

Expand All @@ -125,6 +128,7 @@ def _generate_compute_resource_fleet_config(
queue_capacity_reservation: str,
queue_capacity_type: str,
queue_subnets: List,
queue_single_availability_zone: bool,
):
"""
Generate compute resource config to add in the fleet-config.json, overriding values from the queue.
Expand Down Expand Up @@ -156,7 +160,10 @@ def _generate_compute_resource_fleet_config(
{
"Api": "create-fleet",
"Instances": copy.deepcopy(compute_resource_config["Instances"]),
"Networking": {"SubnetIds": queue_subnets},
"Networking": {
"SubnetIds": queue_subnets,
"SingleAvailabilityZone": queue_single_availability_zone,
},
}
)
allocation_strategy = compute_resource_config.get("AllocationStrategy", queue_allocation_strategy)
Expand Down
48 changes: 41 additions & 7 deletions test/unit/slurm/test_fleet_config_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,22 @@
CriticalError,
"Unable to find key 'Name' in the configuration file. Queue: q1",
),
(
{
"Scheduling": {
Copy link
Contributor

@gmarciani gmarciani Jul 14, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[Tests] what's the goal of adding this test case?

"SlurmQueues": [
{
"Name": "q1",
"CapacityType": "SPOT",
"ComputeResources": [{"Instances": []}],
"Networking": {"SubnetIds": ["123"], "EnableSingleAvailabilityZone": None},
}
]
}
},
CriticalError,
"Unable to find key 'Name' in the configuration file. Queue: q1",
),
(
{
"Scheduling": {
Expand All @@ -70,7 +86,7 @@
"Name": "q1",
"CapacityType": "ONDEMAND",
"ComputeResources": [{"Name": "cr1", "Instances": []}],
"Networking": {"SubnetIds": ["123"]},
"Networking": {"SubnetIds": ["123"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand All @@ -89,7 +105,7 @@
{"Name": "cr1", "Instances": [{"InstanceType": "test"}]},
{"Name": "cr2", "InstanceType": "test"},
],
"Networking": {"SubnetIds": ["123"]},
"Networking": {"SubnetIds": ["123"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand All @@ -108,7 +124,7 @@
{"Name": "cr1", "Instances": [{"InstanceType": "test"}, {"InstanceType": "test-2"}]},
{"Name": "cr2", "InstanceType": "test"},
],
"Networking": {"SubnetIds": ["123", "456", "789"]},
"Networking": {"SubnetIds": ["123", "456", "789"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand All @@ -131,7 +147,7 @@
},
{"Name": "cr2", "InstanceType": "test", "SpotPrice": "10"},
],
"Networking": {"SubnetIds": ["123", "456", "789"]},
"Networking": {"SubnetIds": ["123", "456", "789"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand All @@ -147,7 +163,7 @@
"Name": "q1",
"CapacityType": "SPOT",
"ComputeResources": [{"Name": "cr1", "Instances": [{"InstanceType": "test"}]}],
"Networking": {"SubnetIds": ["123"]},
"Networking": {"SubnetIds": ["123"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand All @@ -165,7 +181,7 @@
"ComputeResources": [
{"Name": "cr1", "Instances": [{"InstanceType": "test"}], "SpotPrice": 10}
],
"Networking": {"SubnetIds": ["123"]},
"Networking": {"SubnetIds": ["123"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand Down Expand Up @@ -208,6 +224,24 @@
CriticalError,
"Unable to find key 'SubnetIds' in the configuration file. Queue: q1",
),
(
{
"Scheduling": {
"SlurmQueues": [
{
"Name": "q1",
"CapacityType": "SPOT",
"ComputeResources": [
{"Name": "cr1", "Instances": [{"InstanceType": "test"}], "SpotPrice": 10}
],
"Networking": {"SubnetIds": ["123"]},
}
]
}
},
None,
None,
),
(
{
"Scheduling": {
Expand All @@ -231,7 +265,7 @@
},
},
],
"Networking": {"SubnetIds": ["123"]},
"Networking": {"SubnetIds": ["123"], "EnableSingleAvailabilityZone": None},
}
]
}
Expand Down
15 changes: 10 additions & 5 deletions ...fleet_config_generator/test_generate_fleet_config_file/expected_outputs/fleet-config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,8 @@
"Networking": {
"SubnetIds": [
"subnet-0230367ab0e5123a4"
]
],
"SingleAvailabilityZone": true
},
"AllocationStrategy": "lowest-price"
}
Expand Down Expand Up @@ -57,7 +58,8 @@
"SubnetIds": [
"subnet-0230367ab0e5123a4",
"subnet-0b903123096649662"
]
],
"SingleAvailabilityZone": false
},
"AllocationStrategy": "lowest-price"
}
Expand All @@ -84,7 +86,8 @@
"Networking": {
"SubnetIds": [
"subnet-0230367ab0e5123a4"
]
],
"SingleAvailabilityZone": null
},
"AllocationStrategy": "capacity-optimized",
"MaxPrice": 10
Expand All @@ -100,7 +103,8 @@
"Networking": {
"SubnetIds": [
"subnet-0230367ab0e5123a4"
]
],
"SingleAvailabilityZone": null
},
"AllocationStrategy": "capacity-optimized"
}
Expand Down Expand Up @@ -131,7 +135,8 @@
"Networking": {
"SubnetIds": [
"subnet-0230367ab0e5123a4"
]
],
"SingleAvailabilityZone": null
}
}
}
Expand Down
3 changes: 3 additions & 0 deletions .../unit/slurm/test_fleet_config_generator/test_generate_fleet_config_file/sample_input.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,7 @@ Scheduling:
SecurityGroups: null
SubnetIds:
- subnet-0230367ab0e5123a4
EnableSingleAvailabilityZone: true
# queue ondemand without capacity reservations and with multiple subnets
- AllocationStrategy: lowest-price
CapacityReservationTarget: null
Expand Down Expand Up @@ -121,6 +122,7 @@ Scheduling:
SubnetIds:
- subnet-0230367ab0e5123a4
- subnet-0b903123096649662
EnableSingleAvailabilityZone: false
# queue spot
- AllocationStrategy: capacity-optimized
CapacityReservationTarget: null
Expand Down Expand Up @@ -191,6 +193,7 @@ Scheduling:
SecurityGroups: null
SubnetIds:
- subnet-0230367ab0e5123a4
EnableSingleAvailabilityZone: null
# queue for capacity-block
- CapacityReservationTarget:
CapacityReservationId: cr-987654
Expand Down
Loading