From 5ed4686903728b6fc11315d4340dd09ad3a2f95e Mon Sep 17 00:00:00 2001 From: Feidias Ioannidis Date: Wed, 29 Oct 2025 16:16:41 +0000 Subject: [PATCH 1/2] Update WP naming convention --- src/xpk/core/nodepool.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/xpk/core/nodepool.py b/src/xpk/core/nodepool.py index 58889c439..6c26c0ab2 100644 --- a/src/xpk/core/nodepool.py +++ b/src/xpk/core/nodepool.py @@ -267,7 +267,9 @@ def run_gke_node_pool_create_command( placement_args = '' if system.requires_workload_policy and is_topology_valid(system.topology): - placement_policy = f'{args.cluster}-placement-policy' + placement_policy = ( + f'{system.device_type}-{system.topology}-placement-policy' + ) ensure_resource_policy_exists(placement_policy, args, system.topology) placement_args = f' --placement-policy={placement_policy}' From 8d7e7f6304f068fdb0abc98c78627d8ae320f7a6 Mon Sep 17 00:00:00 2001 From: Feidias Ioannidis Date: Wed, 29 Oct 2025 16:28:40 +0000 Subject: [PATCH 2/2] Fix goldens --- goldens/Basic_cluster_create.txt | 4 ++-- goldens/Cluster_create_with_gb200-4.txt | 4 ++-- goldens/NAP_cluster-create.txt | 4 ++-- goldens/NAP_cluster-create_with_pathways.txt | 4 ++-- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/goldens/Basic_cluster_create.txt b/goldens/Basic_cluster_create.txt index 2969b5285..863dd67af 100644 --- a/goldens/Basic_cluster_create.txt +++ b/goldens/Basic_cluster_create.txt @@ -51,8 +51,8 @@ gcloud beta container node-pools describe 0 --cluster golden-cluster --project=g kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true [XPK] Existing node pool names ['0'] [XPK] Task: `Retrieve resource policy` is implemented by the following command not running since it is a dry run. -gcloud compute resource-policies describe golden-cluster-placement-policy --project=golden-project --region=us-central1 -[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=tpu7x-standard-4t --host-maintenance-interval=AS_NEEDED --spot --placement-policy=golden-cluster-placement-policy --enable-gvnic --node-version=0 --num-nodes=1 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --max-pods-per-node 15 +gcloud compute resource-policies describe tpu7x-8-2x2x1-placement-policy --project=golden-project --region=us-central1 +[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=tpu7x-standard-4t --host-maintenance-interval=AS_NEEDED --spot --placement-policy=tpu7x-8-2x2x1-placement-policy --enable-gvnic --node-version=0 --num-nodes=1 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --max-pods-per-node 15 [XPK] Breaking up a total of 1 commands into 1 batches [XPK] Pretending all the jobs succeeded [XPK] Create or delete node pool request complete. diff --git a/goldens/Cluster_create_with_gb200-4.txt b/goldens/Cluster_create_with_gb200-4.txt index e66dc5f17..71ab55fef 100644 --- a/goldens/Cluster_create_with_gb200-4.txt +++ b/goldens/Cluster_create_with_gb200-4.txt @@ -53,8 +53,8 @@ gcloud beta container node-pools describe 0 --cluster golden-cluster --project=g kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true [XPK] Existing node pool names ['0'] [XPK] Task: `Retrieve resource policy` is implemented by the following command not running since it is a dry run. -gcloud compute resource-policies describe golden-cluster-placement-policy --project=golden-project --region=us-central1 -[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=a4x-highgpu-4g --host-maintenance-interval=AS_NEEDED --reservation-affinity=specific --reservation=golden-reservation --placement-policy=golden-cluster-placement-policy --enable-gvnic --num-nodes=2 --accelerator type=nvidia-gb200,count=4,gpu-driver-version=latest --no-enable-autoupgrade --scopes="https://www.googleapis.com/auth/cloud-platform" +gcloud compute resource-policies describe gb200-4-1x72-placement-policy --project=golden-project --region=us-central1 +[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=a4x-highgpu-4g --host-maintenance-interval=AS_NEEDED --reservation-affinity=specific --reservation=golden-reservation --placement-policy=gb200-4-1x72-placement-policy --enable-gvnic --num-nodes=2 --accelerator type=nvidia-gb200,count=4,gpu-driver-version=latest --no-enable-autoupgrade --scopes="https://www.googleapis.com/auth/cloud-platform" [XPK] Breaking up a total of 1 commands into 1 batches [XPK] Pretending all the jobs succeeded [XPK] Create or delete node pool request complete. diff --git a/goldens/NAP_cluster-create.txt b/goldens/NAP_cluster-create.txt index dc7158bbd..de6f0df1a 100644 --- a/goldens/NAP_cluster-create.txt +++ b/goldens/NAP_cluster-create.txt @@ -51,8 +51,8 @@ gcloud beta container node-pools describe 0 --cluster golden-cluster --project=g kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true [XPK] Existing node pool names ['0'] [XPK] Task: `Retrieve resource policy` is implemented by the following command not running since it is a dry run. -gcloud compute resource-policies describe golden-cluster-placement-policy --project=golden-project --region=us-central1 -[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=tpu7x-standard-4t --host-maintenance-interval=AS_NEEDED --placement-policy=golden-cluster-placement-policy --enable-gvnic --node-version=0 --num-nodes=1 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --max-pods-per-node 15 +gcloud compute resource-policies describe tpu7x-8-2x2x1-placement-policy --project=golden-project --region=us-central1 +[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=tpu7x-standard-4t --host-maintenance-interval=AS_NEEDED --placement-policy=tpu7x-8-2x2x1-placement-policy --enable-gvnic --node-version=0 --num-nodes=1 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --max-pods-per-node 15 [XPK] Breaking up a total of 1 commands into 1 batches [XPK] Pretending all the jobs succeeded [XPK] Create or delete node pool request complete. diff --git a/goldens/NAP_cluster-create_with_pathways.txt b/goldens/NAP_cluster-create_with_pathways.txt index 87684b13e..6398dbcee 100644 --- a/goldens/NAP_cluster-create_with_pathways.txt +++ b/goldens/NAP_cluster-create_with_pathways.txt @@ -51,8 +51,8 @@ gcloud beta container node-pools describe 0 --cluster golden-cluster --project=g kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true [XPK] Existing node pool names ['0'] [XPK] Task: `Retrieve resource policy` is implemented by the following command not running since it is a dry run. -gcloud compute resource-policies describe golden-cluster-placement-policy --project=golden-project --region=us-central1 -[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=tpu7x-standard-4t --host-maintenance-interval=AS_NEEDED --placement-policy=golden-cluster-placement-policy --enable-gvnic --node-version=0 --num-nodes=1 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --max-pods-per-node 15 +gcloud compute resource-policies describe tpu7x-8-2x2x1-placement-policy --project=golden-project --region=us-central1 +[XPK] To complete NodepoolCreate-golden-cluster-np-0 we are executing gcloud beta container node-pools create golden-cluster-np-0 --location=us-central1 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --machine-type=tpu7x-standard-4t --host-maintenance-interval=AS_NEEDED --placement-policy=tpu7x-8-2x2x1-placement-policy --enable-gvnic --node-version=0 --num-nodes=1 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --max-pods-per-node 15 [XPK] To complete NodepoolCreate-cpu-np we are executing gcloud beta container node-pools create cpu-np --node-version=0 --cluster=golden-cluster --project=golden-project --node-locations=us-central1-a --location=us-central1 --num-nodes=1 --machine-type=n2-standard-64 --scopes=storage-full,gke-default,"https://www.googleapis.com/auth/cloud-platform" --enable-autoscaling --min-nodes=1 --max-nodes=20 [XPK] Breaking up a total of 2 commands into 1 batches [XPK] Pretending all the jobs succeeded