Add yamls for metrics-based-autoscaling user guide.

ai-ml/gke-slurm/metrics-autoscaling/autoscaling-metrics.yaml

@@ -0,0 +1,65 @@
+# 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.
+
+# [START gke_ai_ml_gke_slurm_metrics_autoscaling_keda]
+
+apiVersion: monitoring.googleapis.com/v1
+kind: PodMonitoring
+metadata:
+  name: slurm-metrics-exporter
+  namespace: slurm
+spec:
+  selector:
+    matchLabels:
+      app: slurmctld
+  endpoints:
+  - port: 6817
+    path: /metrics/partitions
+    interval: 5s
+---
+apiVersion: keda.sh/v1alpha1
+kind: ClusterTriggerAuthentication
+metadata:
+  name: google-workload-identity-auth
+  namespace: slurm
+spec:
+  podIdentity:
+    provider: gcp
+---
+apiVersion: keda.sh/v1alpha1
+kind: ScaledObject
+metadata:
+  name: slurm-worker-cpu-nodes-scaler
+  namespace: slurm
+spec:
+  scaleTargetRef:
+    apiVersion: slinky.slurm.net/v1beta1
+    kind: NodeSet
+    name: slurm-worker-cpu-nodes
+  minReplicaCount: 1
+  maxReplicaCount: 10
+  pollingInterval: 5
+  cooldownPeriod: 30
+  triggers:
+  - type: prometheus
+    metadata:
+      serverAddress: https://monitoring.googleapis.com/v1/projects/PROJECT_ID/location/global/prometheus
+      query: |
+        sum(slurm_partition_jobs_pending{project_id="PROJECT_ID",partition="cpu-partition",cluster="CLUSTER_NAME"})+sum(slurm_partition_nodes_alloc{project_id="PROJECT_ID",partition="cpu-partition",cluster="CLUSTER_NAME"})
+      threshold: "1.0"
+    authenticationRef:
+      kind: ClusterTriggerAuthentication
+      name: google-workload-identity-auth
+
+# [END gke_ai_ml_gke_slurm_metrics_autoscaling_keda]

ai-ml/gke-slurm/metrics-autoscaling/pv-pvc.yaml

@@ -0,0 +1,50 @@
+# 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.
+
+# [START gke_ai_ml_gke_slurm_metrics_autoscaling_pv_pvc]
+
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: PV_NAME
+spec:
+  storageClassName: ""
+  capacity:
+    storage: 1Ti
+  accessModes:
+    - ReadWriteMany
+  persistentVolumeReclaimPolicy: Retain
+  volumeMode: Filesystem
+  csi:
+    driver: filestore.csi.storage.gke.io
+    volumeHandle: "modeInstance/INSTANCE_ZONE/INSTANCE_NAME/SHARE_NAME"
+    volumeAttributes:
+      ip: INSTANCE_IP
+      volume: SHARE_NAME
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: PVC_NAME
+  namespace: slurm
+spec:
+  accessModes:
+    - ReadWriteMany
+  storageClassName: ""
+  resources:
+    requests:
+      storage: 1Ti
+  volumeName: PV_NAME
+
+# [END gke_ai_ml_gke_slurm_metrics_autoscaling_pv_pvc]

ai-ml/gke-slurm/metrics-autoscaling/values.yaml

@@ -0,0 +1,147 @@
+# 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.
+
+# [START gke_ai_ml_gke_slurm_metrics_autoscaling_values]
+
+imagePullPolicy: IfNotPresent
+
+controller:
+  slurmctld:
+    image:
+      repository: gcr.io/gke-release/slinky/slurmctld
+      tag: TAG
+  reconfigure:
+    image:
+      repository: gcr.io/gke-release/slinky/slurmctld
+      tag: TAG
+  logfile:
+    image:
+      repository: docker.io/library/alpine
+      tag: latest
+  persistence:
+    enabled: true
+    existingClaim: ""
+    storageClassName: null
+    accessModes:
+    - ReadWriteOnce
+    resources:
+      requests:
+        storage: 4Gi
+  extraConf: null
+
+  metadata:
+    labels:
+      app: slurmctld
+  extraConfMap:
+    SlurmctldDebug: verbose
+    MetricsType: metrics/openmetrics
+  metrics:
+    enabled: true
+    serviceMonitor:
+      enabled: false
+
+restapi:
+  replicas: 1
+  slurmrestd:
+    image:
+      repository: gcr.io/gke-release/slinky/slurmrestd
+      tag: TAG
+  podSpec:
+    nodeSelector:
+      kubernetes.io/os: linux
+
+loginsets:
+  slinky:
+    enabled: true
+    replicas: 1
+    podSpec:
+      tolerations:
+        - key: "login-pool"
+          operator: "Equal"
+          value: "login-pods"
+          effect: "NoSchedule"
+      volumes:
+        - name: home-vol
+          persistentVolumeClaim:
+            claimName: PVC_NAME
+    login:
+      image:
+        repository: gcr.io/gke-release/slinky/login
+        tag: TAG
+      volumeMounts:
+        - name: home-vol
+          mountPath: /home
+
+nodesets:
+  slinky:
+    enabled: false
+  cpu-nodes:
+    enabled: true
+    replicas: 1
+    updateStrategy:
+      type: RollingUpdate
+    slurmd:
+      args: [" -N ${POD_NAME#slurm-worker-}"]
+      env:
+        - name: POD_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.name
+      image:
+        repository: gcr.io/gke-release/slinky/slurmd
+        tag: TAG
+      imagePullPolicy: IfNotPresent
+      volumeMounts:
+        - name: home-vol
+          mountPath: /home
+    logfile:
+      image:
+        repository: docker.io/library/alpine
+        tag: latest
+    partition:
+      enabled: true
+      useResourceLimits: true
+      updateStrategy:
+        type: RollingUpdate
+        rollingUpdate:
+          maxUnavailable: 25%
+    podSpec:
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      tolerations:
+        - key: "slurm-pool"
+          operator: "Equal"
+          value: "cpu-nodes"
+          effect: "NoSchedule"
+      nodeSelector:
+        kubernetes.io/os: linux
+      volumes:
+        - name: home-vol
+          persistentVolumeClaim:
+            claimName: PVC_NAME
+    taintKubeNodes: false
+
+partitions:
+  all:
+    enabled: false
+  cpu-partition:
+    enabled: true
+    nodesets:
+      - cpu-nodes
+    configMap:
+      State: UP
+      Default: "YES"
+      MaxTime: UNLIMITED
+
+# [END gke_ai_ml_gke_slurm_metrics_autoscaling_values]