diff --git a/cmd/root.go b/cmd/root.go index 5e0056a1d4..06acc69a16 100644 --- a/cmd/root.go +++ b/cmd/root.go @@ -52,7 +52,7 @@ var ( logging.Fatal("cmd.Help function failed: %s", err) } }, - Version: "v1.82.0", + Version: "v1.83.0", Annotations: annotation, } ) diff --git a/community/modules/compute/gke-nodeset/versions.tf b/community/modules/compute/gke-nodeset/versions.tf index 72397b7d06..6d2551543a 100644 --- a/community/modules/compute/gke-nodeset/versions.tf +++ b/community/modules/compute/gke-nodeset/versions.tf @@ -22,6 +22,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:gke-nodeset/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-nodeset/v1.83.0" } } diff --git a/community/modules/compute/gke-partition/versions.tf b/community/modules/compute/gke-partition/versions.tf index c11a338361..6ad0eb64df 100644 --- a/community/modules/compute/gke-partition/versions.tf +++ b/community/modules/compute/gke-partition/versions.tf @@ -22,6 +22,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:gke-partition/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-partition/v1.83.0" } } diff --git a/community/modules/compute/htcondor-execute-point/versions.tf b/community/modules/compute/htcondor-execute-point/versions.tf index 76d5f74aa2..98d6022265 100644 --- a/community/modules/compute/htcondor-execute-point/versions.tf +++ b/community/modules/compute/htcondor-execute-point/versions.tf @@ -29,6 +29,6 @@ terraform { } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:htcondor-execute-point/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:htcondor-execute-point/v1.83.0" } } diff --git a/community/modules/compute/mig/versions.tf b/community/modules/compute/mig/versions.tf index 372e8526f7..15b06f81e3 100644 --- a/community/modules/compute/mig/versions.tf +++ b/community/modules/compute/mig/versions.tf @@ -22,6 +22,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:mig/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:mig/v1.83.0" } } diff --git a/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-dynamic/versions.tf b/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-dynamic/versions.tf index 5194503dd3..cbbf95a857 100644 --- a/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-dynamic/versions.tf +++ b/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-dynamic/versions.tf @@ -17,6 +17,6 @@ terraform { required_version = "= 1.12.2" provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-dynamic/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-dynamic/v1.83.0" } } diff --git a/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-tpu/versions.tf b/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-tpu/versions.tf index 19b1a7c2c0..da694e7d9d 100644 --- a/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-tpu/versions.tf +++ b/community/modules/compute/schedmd-slurm-gcp-v6-nodeset-tpu/versions.tf @@ -18,6 +18,6 @@ terraform { required_version = "= 1.12.2" provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-tpu/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-tpu/v1.83.0" } } diff --git a/community/modules/compute/schedmd-slurm-gcp-v6-nodeset/versions.tf b/community/modules/compute/schedmd-slurm-gcp-v6-nodeset/versions.tf index a1cc095715..d8b1fe0537 100644 --- a/community/modules/compute/schedmd-slurm-gcp-v6-nodeset/versions.tf +++ b/community/modules/compute/schedmd-slurm-gcp-v6-nodeset/versions.tf @@ -24,6 +24,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset/v1.83.0" } } diff --git a/community/modules/compute/schedmd-slurm-gcp-v6-partition/versions.tf b/community/modules/compute/schedmd-slurm-gcp-v6-partition/versions.tf index 14db7c388a..1b70ec9aea 100644 --- a/community/modules/compute/schedmd-slurm-gcp-v6-partition/versions.tf +++ b/community/modules/compute/schedmd-slurm-gcp-v6-partition/versions.tf @@ -18,6 +18,6 @@ terraform { required_version = "= 1.12.2" provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-partition/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-partition/v1.83.0" } } diff --git a/community/modules/database/slurm-cloudsql-federation/versions.tf b/community/modules/database/slurm-cloudsql-federation/versions.tf index 4b577dfe6e..e8b34b0ed2 100644 --- a/community/modules/database/slurm-cloudsql-federation/versions.tf +++ b/community/modules/database/slurm-cloudsql-federation/versions.tf @@ -26,10 +26,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/file-system/nfs-server/versions.tf b/community/modules/file-system/nfs-server/versions.tf index 4674189c03..2e5e2771d9 100644 --- a/community/modules/file-system/nfs-server/versions.tf +++ b/community/modules/file-system/nfs-server/versions.tf @@ -30,7 +30,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:nfs-server/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:nfs-server/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/files/fsi-montecarlo-on-batch/versions.tf b/community/modules/files/fsi-montecarlo-on-batch/versions.tf index f9f1ad3156..82c579a6e7 100644 --- a/community/modules/files/fsi-montecarlo-on-batch/versions.tf +++ b/community/modules/files/fsi-montecarlo-on-batch/versions.tf @@ -35,9 +35,9 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.83.0" } } diff --git a/community/modules/internal/slurm-gcp/login/versions.tf b/community/modules/internal/slurm-gcp/login/versions.tf index 54172261e8..2c7b43a0b7 100644 --- a/community/modules/internal/slurm-gcp/login/versions.tf +++ b/community/modules/internal/slurm-gcp/login/versions.tf @@ -24,6 +24,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-controller/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-controller/v1.83.0" } } diff --git a/community/modules/project/service-enablement/versions.tf b/community/modules/project/service-enablement/versions.tf index d3e908a375..818ba78125 100644 --- a/community/modules/project/service-enablement/versions.tf +++ b/community/modules/project/service-enablement/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:service-enablement/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:service-enablement/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/pubsub/bigquery-sub/versions.tf b/community/modules/pubsub/bigquery-sub/versions.tf index 848e855be7..cf207c670d 100644 --- a/community/modules/pubsub/bigquery-sub/versions.tf +++ b/community/modules/pubsub/bigquery-sub/versions.tf @@ -26,10 +26,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.83.0" } required_version = "= 1.12.2" } diff --git a/community/modules/pubsub/topic/versions.tf b/community/modules/pubsub/topic/versions.tf index 8cc81d1ad9..6c46d24cf6 100644 --- a/community/modules/pubsub/topic/versions.tf +++ b/community/modules/pubsub/topic/versions.tf @@ -27,6 +27,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:topic/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:topic/v1.83.0" } } diff --git a/community/modules/scheduler/htcondor-access-point/versions.tf b/community/modules/scheduler/htcondor-access-point/versions.tf index 56788563d3..bc456970f6 100644 --- a/community/modules/scheduler/htcondor-access-point/versions.tf +++ b/community/modules/scheduler/htcondor-access-point/versions.tf @@ -30,7 +30,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:htcondor-access-point/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:htcondor-access-point/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/scheduler/htcondor-central-manager/versions.tf b/community/modules/scheduler/htcondor-central-manager/versions.tf index 62e02474d7..b1ef0a1031 100644 --- a/community/modules/scheduler/htcondor-central-manager/versions.tf +++ b/community/modules/scheduler/htcondor-central-manager/versions.tf @@ -26,7 +26,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:htcondor-central-manager/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:htcondor-central-manager/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/scheduler/htcondor-pool-secrets/versions.tf b/community/modules/scheduler/htcondor-pool-secrets/versions.tf index 9978df1473..4a69a2e82f 100644 --- a/community/modules/scheduler/htcondor-pool-secrets/versions.tf +++ b/community/modules/scheduler/htcondor-pool-secrets/versions.tf @@ -26,7 +26,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:htcondor-pool-secrets/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:htcondor-pool-secrets/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/scheduler/schedmd-slurm-gcp-v6-controller/versions.tf b/community/modules/scheduler/schedmd-slurm-gcp-v6-controller/versions.tf index 2e6a7dc860..0eeb550c7b 100644 --- a/community/modules/scheduler/schedmd-slurm-gcp-v6-controller/versions.tf +++ b/community/modules/scheduler/schedmd-slurm-gcp-v6-controller/versions.tf @@ -28,6 +28,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-controller/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-controller/v1.83.0" } } diff --git a/community/modules/scheduler/schedmd-slurm-gcp-v6-login/versions.tf b/community/modules/scheduler/schedmd-slurm-gcp-v6-login/versions.tf index 72891d5004..34e37c64af 100644 --- a/community/modules/scheduler/schedmd-slurm-gcp-v6-login/versions.tf +++ b/community/modules/scheduler/schedmd-slurm-gcp-v6-login/versions.tf @@ -18,6 +18,6 @@ terraform { required_version = "= 1.12.2" provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-login/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-login/v1.83.0" } } diff --git a/community/modules/scripts/wait-for-startup/versions.tf b/community/modules/scripts/wait-for-startup/versions.tf index 5ecca07549..7794957af2 100644 --- a/community/modules/scripts/wait-for-startup/versions.tf +++ b/community/modules/scripts/wait-for-startup/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:wait-for-startup/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:wait-for-startup/v1.83.0" } required_version = "= 1.12.2" diff --git a/community/modules/scripts/windows-startup-script/versions.tf b/community/modules/scripts/windows-startup-script/versions.tf index d8a5166744..eb29f600c7 100644 --- a/community/modules/scripts/windows-startup-script/versions.tf +++ b/community/modules/scripts/windows-startup-script/versions.tf @@ -16,7 +16,7 @@ terraform { provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:windows-startup-script/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:windows-startup-script/v1.83.0" } required_version = "= 1.12.2" diff --git a/examples/gke-a3-ultragpu/gke-a3-ultragpu.yaml b/examples/gke-a3-ultragpu/gke-a3-ultragpu.yaml index 3a91fe03d7..e1a09334b4 100644 --- a/examples/gke-a3-ultragpu/gke-a3-ultragpu.yaml +++ b/examples/gke-a3-ultragpu/gke-a3-ultragpu.yaml @@ -214,7 +214,7 @@ deployment_groups: # source: modules/network/private-service-access # use: [gke-a3-ultra-net-0] # settings: - # prefix_length: 24 + # prefix_length: 22 # # Firewall to allow Managed Lustre connection # - id: lustre_firewall_rule diff --git a/examples/gke-a4/gke-a4.yaml b/examples/gke-a4/gke-a4.yaml index 349d6959a2..8c033c7caa 100644 --- a/examples/gke-a4/gke-a4.yaml +++ b/examples/gke-a4/gke-a4.yaml @@ -229,7 +229,7 @@ deployment_groups: # source: modules/network/private-service-access # use: [gke-a4-net-0] # settings: - # prefix_length: 24 + # prefix_length: 22 # # Firewall to allow Managed Lustre connection # - id: lustre_firewall_rule diff --git a/examples/gke-a4x/gke-a4x.yaml b/examples/gke-a4x/gke-a4x.yaml index 5e1bb081b2..39a62484a4 100644 --- a/examples/gke-a4x/gke-a4x.yaml +++ b/examples/gke-a4x/gke-a4x.yaml @@ -232,7 +232,7 @@ deployment_groups: # source: modules/network/private-service-access # use: [gke-a4x-net-0] # settings: - # prefix_length: 24 + # prefix_length: 22 # # Firewall to allow Managed Lustre connection # - id: lustre_firewall_rule diff --git a/examples/gke-managed-lustre.yaml b/examples/gke-managed-lustre.yaml index 55a2fc1830..bef6772c1e 100644 --- a/examples/gke-managed-lustre.yaml +++ b/examples/gke-managed-lustre.yaml @@ -60,7 +60,7 @@ deployment_groups: source: modules/network/private-service-access use: [network] settings: - prefix_length: 24 + prefix_length: 22 # Firewall to allow Managed Lustre connection - id: lustre_firewall_rule diff --git a/examples/gke-tpu-7x/gke-tpu-7x-advanced.yaml b/examples/gke-tpu-7x/gke-tpu-7x-advanced.yaml index a2e8fc4439..7bf1cdb2d0 100644 --- a/examples/gke-tpu-7x/gke-tpu-7x-advanced.yaml +++ b/examples/gke-tpu-7x/gke-tpu-7x-advanced.yaml @@ -249,7 +249,7 @@ deployment_groups: # source: modules/network/private-service-access # use: [gke-tpu-7x-net-0] # settings: - # prefix_length: 24 + # prefix_length: 22 # # Firewall to allow Managed Lustre connection # - id: lustre_firewall_rule diff --git a/examples/gke-tpu-v6e/gke-tpu-v6e-advanced.yaml b/examples/gke-tpu-v6e/gke-tpu-v6e-advanced.yaml index d6c0f3f704..3e4bcbba77 100644 --- a/examples/gke-tpu-v6e/gke-tpu-v6e-advanced.yaml +++ b/examples/gke-tpu-v6e/gke-tpu-v6e-advanced.yaml @@ -249,7 +249,7 @@ deployment_groups: # source: modules/network/private-service-access # use: [gke-tpu-v6e-net-0] # settings: - # prefix_length: 24 + # prefix_length: 22 # # Firewall to allow Managed Lustre connection # - id: lustre_firewall_rule diff --git a/examples/machine-learning/a3-megagpu-8g/nccl-tests/import_pytorch_container.sh b/examples/machine-learning/a3-megagpu-8g/nccl-tests/import_pytorch_container.sh index 9a656947e6..1987de05ee 100644 --- a/examples/machine-learning/a3-megagpu-8g/nccl-tests/import_pytorch_container.sh +++ b/examples/machine-learning/a3-megagpu-8g/nccl-tests/import_pytorch_container.sh @@ -13,7 +13,25 @@ # See the License for the specific language governing permissions and # limitations under the License. -# This creates a file named "nvidia+pytorch+21.10-py3.sqsh", which +# This creates a file named "nvidia+pytorch+24.04-py3.sqsh", which # uses ~18 GB of disk space. This should be run on a filesystem that # can be seen by all worker nodes -enroot import docker://nvcr.io#nvidia/pytorch:24.04-py3 + +# Fix for non-interactive shells where XDG_RUNTIME_DIR is not set +if [ -z "$XDG_RUNTIME_DIR" ]; then + # Try creating a user-specific directory in /run (often fails for non-root) + XDG_RUNTIME_DIR="/run/user/$(id -u)" + export XDG_RUNTIME_DIR + + # Check if we can actually use it + if [ ! -d "$XDG_RUNTIME_DIR" ]; then + # Fallback to a guaranteed writable location in /tmp + XDG_RUNTIME_DIR="/tmp/enroot-runtime-$(id -u)" + export XDG_RUNTIME_DIR + mkdir -p "$XDG_RUNTIME_DIR" + chmod 700 "$XDG_RUNTIME_DIR" + fi +fi + +# Import the pytorch container +enroot import "docker://nvcr.io#nvidia/pytorch:24.04-py3" diff --git a/examples/machine-learning/a3-ultragpu-8g/nccl-tests/import_pytorch_container.sh b/examples/machine-learning/a3-ultragpu-8g/nccl-tests/import_pytorch_container.sh index ae8e3c8367..ad82fb2792 100644 --- a/examples/machine-learning/a3-ultragpu-8g/nccl-tests/import_pytorch_container.sh +++ b/examples/machine-learning/a3-ultragpu-8g/nccl-tests/import_pytorch_container.sh @@ -16,4 +16,22 @@ # This creates a file named "nvidia+pytorch+24.09-py3.sqsh", which # uses ~18 GB of disk space. This should be run on a filesystem that # can be seen by all worker nodes -enroot import docker://nvcr.io#nvidia/pytorch:24.09-py3 + +# Fix for non-interactive shells where XDG_RUNTIME_DIR is not set +if [ -z "$XDG_RUNTIME_DIR" ]; then + # Try creating a user-specific directory in /run (often fails for non-root) + XDG_RUNTIME_DIR="/run/user/$(id -u)" + export XDG_RUNTIME_DIR + + # Check if we can actually use it + if [ ! -d "$XDG_RUNTIME_DIR" ]; then + # Fallback to a guaranteed writable location in /tmp + XDG_RUNTIME_DIR="/tmp/enroot-runtime-$(id -u)" + export XDG_RUNTIME_DIR + mkdir -p "$XDG_RUNTIME_DIR" + chmod 700 "$XDG_RUNTIME_DIR" + fi +fi + +# Import the pytorch container +enroot import "docker://nvcr.io#nvidia/pytorch:24.09-py3" diff --git a/examples/ml-slurm-g4.yaml b/examples/ml-slurm-g4.yaml index 26ae7f1b61..531a247174 100644 --- a/examples/ml-slurm-g4.yaml +++ b/examples/ml-slurm-g4.yaml @@ -73,11 +73,11 @@ deployment_groups: enable_nvidia_dcgm: false nvidia_packages: # 1. Open Kernel Driver: Installs the open-source kernel components. - - nvidia-kernel-open-575 - # 2. Driver Metapackage: Pulls in the 580.xx driver version. - - cuda-drivers-575 - # 3. CUDA Toolkit: Installs the 12.9.1 toolkit. - - cuda-toolkit-12-9 + - nvidia-driver-590-open + # 2. Driver Metapackage: Pulls in the 590.xx driver version. + - cuda-drivers-590 + # 3. CUDA Toolkit: Installs the 12.8 toolkit (stable for 590). + - cuda-toolkit-12-8 - datacenter-gpu-manager tasks: @@ -98,10 +98,18 @@ deployment_groups: ansible.builtin.apt: update_cache: true - # Install the package + # Latest Ubuntu images pre-install a firmware package that conflicts + # with the NVIDIA repository version. + - name: Remove conflicting Ubuntu NVIDIA firmware + ansible.builtin.apt: + name: nvidia-firmware-590 + state: absent + + # Install the package with force-overwrite to handle any remaining file conflicts - name: Install NVIDIA fabric and CUDA ansible.builtin.apt: name: "{{ item }}" + dpkg_options: 'force-overwrite' loop: "{{ nvidia_packages }}" # This section will optionally freeze the packages with diff --git a/modules/compute/gke-node-pool/versions.tf b/modules/compute/gke-node-pool/versions.tf index 466ff92b89..8156bd1d4a 100644 --- a/modules/compute/gke-node-pool/versions.tf +++ b/modules/compute/gke-node-pool/versions.tf @@ -30,9 +30,9 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:gke-node-pool/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-node-pool/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:gke-node-pool/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-node-pool/v1.83.0" } } diff --git a/modules/compute/resource-policy/versions.tf b/modules/compute/resource-policy/versions.tf index 9f29d7e859..6db710f29f 100644 --- a/modules/compute/resource-policy/versions.tf +++ b/modules/compute/resource-policy/versions.tf @@ -27,7 +27,7 @@ terraform { } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:resource-policy/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:resource-policy/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/compute/vm-instance/versions.tf b/modules/compute/vm-instance/versions.tf index 938d71721b..dc542a4488 100644 --- a/modules/compute/vm-instance/versions.tf +++ b/modules/compute/vm-instance/versions.tf @@ -31,10 +31,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/file-system/cloud-storage-bucket/versions.tf b/modules/file-system/cloud-storage-bucket/versions.tf index 0dcbbba906..f8597bb694 100644 --- a/modules/file-system/cloud-storage-bucket/versions.tf +++ b/modules/file-system/cloud-storage-bucket/versions.tf @@ -30,10 +30,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.83.0" } required_version = "= 1.12.2" } diff --git a/modules/file-system/filestore/versions.tf b/modules/file-system/filestore/versions.tf index 11e2622436..1be0475fc2 100644 --- a/modules/file-system/filestore/versions.tf +++ b/modules/file-system/filestore/versions.tf @@ -26,10 +26,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/file-system/gke-persistent-volume/versions.tf b/modules/file-system/gke-persistent-volume/versions.tf index f2512b5ccf..7e655407a0 100644 --- a/modules/file-system/gke-persistent-volume/versions.tf +++ b/modules/file-system/gke-persistent-volume/versions.tf @@ -25,6 +25,6 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:gke-persistent-volume/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-persistent-volume/v1.83.0" } } diff --git a/modules/file-system/gke-storage/versions.tf b/modules/file-system/gke-storage/versions.tf index 8438d6ea93..405b99a2ab 100644 --- a/modules/file-system/gke-storage/versions.tf +++ b/modules/file-system/gke-storage/versions.tf @@ -16,6 +16,6 @@ terraform { required_version = "= 1.12.2" provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:gke-storage/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-storage/v1.83.0" } } diff --git a/modules/file-system/managed-lustre/README.md b/modules/file-system/managed-lustre/README.md index 78ccc07e5e..678a8f6755 100644 --- a/modules/file-system/managed-lustre/README.md +++ b/modules/file-system/managed-lustre/README.md @@ -32,7 +32,7 @@ that the correct subnetwork has private service access. source: modules/network/private-service-access use: [network] settings: - prefix_length: 24 + prefix_length: 22 - id: lustre source: modules/file-system/managed-lustre diff --git a/modules/file-system/managed-lustre/versions.tf b/modules/file-system/managed-lustre/versions.tf index bad4e63a43..cb1f35000e 100644 --- a/modules/file-system/managed-lustre/versions.tf +++ b/modules/file-system/managed-lustre/versions.tf @@ -26,10 +26,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:managed-lustre/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:managed-lustre/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:managed-lustre/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:managed-lustre/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/file-system/netapp-storage-pool/versions.tf b/modules/file-system/netapp-storage-pool/versions.tf index ab8a659992..ea99b56f37 100644 --- a/modules/file-system/netapp-storage-pool/versions.tf +++ b/modules/file-system/netapp-storage-pool/versions.tf @@ -27,10 +27,10 @@ terraform { } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:netapp-storage-pool/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:netapp-storage-pool/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:netapp-storage-pool/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:netapp-storage-pool/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/file-system/netapp-volume/versions.tf b/modules/file-system/netapp-volume/versions.tf index fe97fddf8b..79c06be154 100644 --- a/modules/file-system/netapp-volume/versions.tf +++ b/modules/file-system/netapp-volume/versions.tf @@ -22,10 +22,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:netapp-volume/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:netapp-volume/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:netapp-volume/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:netapp-volume/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/management/kubectl-apply/versions.tf b/modules/management/kubectl-apply/versions.tf index 93b8248c6f..9fb6fcbc51 100644 --- a/modules/management/kubectl-apply/versions.tf +++ b/modules/management/kubectl-apply/versions.tf @@ -35,7 +35,7 @@ terraform { } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:kubectl-apply/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:kubectl-apply/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/monitoring/dashboard/versions.tf b/modules/monitoring/dashboard/versions.tf index b8f3bcc454..5fe0b9b85b 100644 --- a/modules/monitoring/dashboard/versions.tf +++ b/modules/monitoring/dashboard/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:dashboard/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:dashboard/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/network/firewall-rules/versions.tf b/modules/network/firewall-rules/versions.tf index 6c62df2b74..bc84bfe6b6 100644 --- a/modules/network/firewall-rules/versions.tf +++ b/modules/network/firewall-rules/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:firewall-rules/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:firewall-rules/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/network/pre-existing-subnetwork/versions.tf b/modules/network/pre-existing-subnetwork/versions.tf index 0568b21968..d76e0a82d0 100644 --- a/modules/network/pre-existing-subnetwork/versions.tf +++ b/modules/network/pre-existing-subnetwork/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:pre-existing-subnetwork/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:pre-existing-subnetwork/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/network/pre-existing-vpc/versions.tf b/modules/network/pre-existing-vpc/versions.tf index a25d121cad..eb8e910100 100644 --- a/modules/network/pre-existing-vpc/versions.tf +++ b/modules/network/pre-existing-vpc/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:pre-existing-vpc/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:pre-existing-vpc/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/network/private-service-access/versions.tf b/modules/network/private-service-access/versions.tf index e484afb500..e38caa3330 100644 --- a/modules/network/private-service-access/versions.tf +++ b/modules/network/private-service-access/versions.tf @@ -26,11 +26,11 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/scheduler/batch-login-node/versions.tf b/modules/scheduler/batch-login-node/versions.tf index 93448bf1e9..0c516a6557 100644 --- a/modules/scheduler/batch-login-node/versions.tf +++ b/modules/scheduler/batch-login-node/versions.tf @@ -22,7 +22,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:batch-login-node/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:batch-login-node/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/scheduler/gke-cluster/versions.tf b/modules/scheduler/gke-cluster/versions.tf index 291c546b9c..56b63cde85 100644 --- a/modules/scheduler/gke-cluster/versions.tf +++ b/modules/scheduler/gke-cluster/versions.tf @@ -30,10 +30,10 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:gke-cluster/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-cluster/v1.83.0" } provider_meta "google-beta" { - module_name = "blueprints/terraform/hpc-toolkit:gke-cluster/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:gke-cluster/v1.83.0" } } diff --git a/modules/scheduler/pre-existing-gke-cluster/versions.tf b/modules/scheduler/pre-existing-gke-cluster/versions.tf index 7d113c54a3..91cdacb627 100644 --- a/modules/scheduler/pre-existing-gke-cluster/versions.tf +++ b/modules/scheduler/pre-existing-gke-cluster/versions.tf @@ -23,7 +23,7 @@ terraform { } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:pre-existing-gke-cluster/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:pre-existing-gke-cluster/v1.83.0" } required_version = "= 1.12.2" diff --git a/modules/scripts/startup-script/versions.tf b/modules/scripts/startup-script/versions.tf index 0a74b2ea25..cd5e802e95 100644 --- a/modules/scripts/startup-script/versions.tf +++ b/modules/scripts/startup-script/versions.tf @@ -30,7 +30,7 @@ terraform { } } provider_meta "google" { - module_name = "blueprints/terraform/hpc-toolkit:startup-script/v1.82.0" + module_name = "blueprints/terraform/hpc-toolkit:startup-script/v1.83.0" } required_version = "= 1.12.2" diff --git a/tools/cloud-build/daily-tests/builds/gke-a2-highgpu-kueue-onspot.yaml b/tools/cloud-build/daily-tests/builds/gke-a2-highgpu-kueue-onspot.yaml index 04d00a6017..8b78202d9c 100644 --- a/tools/cloud-build/daily-tests/builds/gke-a2-highgpu-kueue-onspot.yaml +++ b/tools/cloud-build/daily-tests/builds/gke-a2-highgpu-kueue-onspot.yaml @@ -41,6 +41,8 @@ steps: - "PROJECT_ID=$PROJECT_ID" - "NUM_NODES=12" - "MIN_NODES=6" + - "ZONE=us-central1-b" + - "PROVISIONING_MODEL=SPOT" - "MACHINE_TYPE=a2-highgpu-2g" - "INSTANCE_PREFIX=a2hspgke" - "BUILD_ID=$BUILD_ID" @@ -50,12 +52,13 @@ steps: - -c - | set -e -u -o pipefail - echo "Sourcing find_available_zone.sh to determine zone." - source /workspace/tools/cloud-build/find_available_zone.sh - if [ -z "$${ZONE:-}" ]; then - echo "ERROR: ZONE not found" >&2 - exit 1 - fi + # Commenting out dynamically setting zone due to test failures. + # echo "Sourcing find_available_zone.sh to determine zone." + # source /workspace/tools/cloud-build/find_available_zone.sh + # if [ -z "$${ZONE:-}" ]; then + # echo "ERROR: ZONE not found" >&2 + # exit 1 + # fi REGION="$${ZONE%-*}" echo "Using ZONE=$${ZONE} and REGION=$${REGION}" diff --git a/tools/cloud-build/daily-tests/tests/hpc-enterprise-slurm.yml b/tools/cloud-build/daily-tests/tests/hpc-enterprise-slurm.yml index 86c8e652f8..57b84432bf 100644 --- a/tools/cloud-build/daily-tests/tests/hpc-enterprise-slurm.yml +++ b/tools/cloud-build/daily-tests/tests/hpc-enterprise-slurm.yml @@ -18,12 +18,12 @@ deployment_name: "enter-{{ build }}" # Manually adding the slurm_cluster_name for use in node names, which filters # non-alphanumeric chars and is capped at 10 chars. slurm_cluster_name: "enter{{ build[0:5] }}" -zone: europe-west4-c +zone: us-central1-a cli_deployment_vars: network_name: "{{ network }}" - region: europe-west4 + region: us-central1 zone: "{{ zone }}" - gpu_zones: "[europe-west4-a,europe-west4-b,europe-west4-c]" + gpu_zones: "[us-central1-a, us-central1-b, us-central1-c, us-central1-f]" lustre_instance_id: "lustre-instance-{{build}}" workspace: /workspace blueprint_yaml: "{{ workspace }}/examples/hpc-enterprise-slurm.yaml"