cluster-toolkit/examples/pfs-managed-lustre-slurm.yaml at main · GoogleCloudPlatform/cluster-toolkit · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
# Copyright 2026 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

---
blueprint_name: managed-lustre-slurm

vars:
  project_id:  ## Set GCP Project ID Here ##
  deployment_name: managed-lustre-slurm
  region: us-central1
  zone: us-central1-a
  compute_node_machine_type: c2-standard-4
  # Managed Lustre is only supported in specific regions and zones
  # Please refer https://cloud.google.com/managed-lustre/docs/locations
  # Managed-Lustre instance name. This should be unique for each deployment.
  lustre_instance_id: lustre-instance
  # The values of size_gib and per_unit_storage_throughput are co-related
  # Please refer https://cloud.google.com/managed-lustre/docs/create-instance#performance-tiers
  # Storage capacity of the lustre instance in GiB
  lustre_size_gib: 36000
  # Maximum throughput of the lustre instance in MBps per TiB
  per_unit_storage_throughput: 500
  kms_key: ""
  slurm_image:
    # Pinned to working version prior to July 10, 2026 due to Lustre client incompatibility on Rocky 9.8
    name: slurm-gcp-6-12-hpc-rocky-linux-9-20260519
    project: schedmd-slurm-public

# Documentation for each of the modules used below can be found at
# https://github.com/GoogleCloudPlatform/hpc-toolkit/blob/main/modules/README.md

deployment_groups:
- group: lustre
  modules:
  - id: network
    source: modules/network/vpc

  # Required for Managed Lustre instance
  - id: private_service_access
    source: modules/network/private-service-access
    use: [network]

  - id: lustre-gcp
    source: modules/file-system/managed-lustre
    use: [network, private_service_access]
    settings:
      name: $(vars.lustre_instance_id)
      local_mount: /lustre
      remote_mount: lustrefs
      size_gib: $(vars.lustre_size_gib)
      per_unit_storage_throughput: $(vars.per_unit_storage_throughput)
      kms_key: $(vars.kms_key)

- group: slurm-cluster
  modules:
  - id: lustre-nodeset
    source: community/modules/compute/schedmd-slurm-gcp-v6-nodeset
    use: [network]
    settings:
      node_count_dynamic_max: 2
      machine_type: $(vars.compute_node_machine_type)
      allow_automatic_updates: false
      instance_image: $(vars.slurm_image)

  - id: lustre_partition
    source: community/modules/compute/schedmd-slurm-gcp-v6-partition
    use:
    - lustre-nodeset
    settings:
      partition_name: lustre
      is_default: true

  - id: slurm_login
    source: community/modules/scheduler/schedmd-slurm-gcp-v6-login
    use: [network]
    settings:
      machine_type: n2-standard-4
      enable_login_public_ips: false
      instance_image: $(vars.slurm_image)

  - id: slurm_controller
    source: community/modules/scheduler/schedmd-slurm-gcp-v6-controller
    use:
    - network
    - lustre_partition
    - lustre-gcp
    - slurm_login
    settings:
      machine_type: n2-standard-4
      enable_controller_public_ips: false
      instance_image: $(vars.slurm_image)