feat(supervisor): add node affinity rules for large machine worker pool scheduling

apps/supervisor/src/env.ts

@@ -91,6 +91,7 @@ const Env = z.object({
   KUBERNETES_MEMORY_REQUEST_RATIO: z.coerce.number().min(0).max(1).default(1), // Ratio of memory limit, so 1 = 100% of memory limit
   KUBERNETES_MEMORY_OVERHEAD_GB: z.coerce.number().min(0).optional(), // Optional memory overhead to add to the limit in GB
   KUBERNETES_SCHEDULER_NAME: z.string().optional(), // Custom scheduler name for pods
+  KUBERNETES_LARGE_MACHINE_POOL_LABEL: z.string().optional(), // if set, large-* presets affinity for machinepool=<value>
 
   // Placement tags settings
   PLACEMENT_TAGS_ENABLED: BoolEnv.default(false),

apps/supervisor/src/workloadManager/kubernetes.ts

@@ -95,6 +95,7 @@ export class KubernetesWorkloadManager implements WorkloadManager {
           },
           spec: {
             ...this.addPlacementTags(this.#defaultPodSpec, opts.placementTags),
+            affinity: this.#getNodeAffinity(opts.machine),
             terminationGracePeriodSeconds: 60 * 60,
             containers: [
               {
@@ -356,4 +357,55 @@ export class KubernetesWorkloadManager implements WorkloadManager {
       },
     };
   }
+
+  #isLargeMachine(preset: MachinePreset): boolean {
+    return preset.name.startsWith("large-");
+  }
+
+  #getNodeAffinity(preset: MachinePreset): k8s.V1Affinity | undefined {
+    if (!env.KUBERNETES_LARGE_MACHINE_POOL_LABEL) {
+      return undefined;
+    }
+
+    if (this.#isLargeMachine(preset)) {
+      // soft preference for the large-machine pool, falls back to standard if unavailable
+      return {
+        nodeAffinity: {
+          preferredDuringSchedulingIgnoredDuringExecution: [
+            {
+              weight: 100,
+              preference: {
+                matchExpressions: [
+                  {
+                    key: "machinepool",
+                    operator: "In",
+                    values: [env.KUBERNETES_LARGE_MACHINE_POOL_LABEL],
+                  },
+                ],
+              },
+            },
+          ],
+        },
+      };
+    }
+
+    // not schedulable in the large-machine pool
+    return {
+      nodeAffinity: {
+        requiredDuringSchedulingIgnoredDuringExecution: {
+          nodeSelectorTerms: [
+            {
+              matchExpressions: [
+                {
+                  key: "machinepool",
+                  operator: "NotIn",
+                  values: [env.KUBERNETES_LARGE_MACHINE_POOL_LABEL],
+                },
+              ],
+            },
+          ],
+        },
+      },
+    };
+  }
 }