fix(longhorn): enable worker-1 scheduling, 400Gi reserved

32 degraded + 3 faulted volumes from replica rebuild failures.
cp-1/cp-2 over-committed; worker-1 had 602Gi free but scheduling
disabled. Enable it with 400Gi reserved for LLM weights.

- Add worker-1 to longhorn-nodes.yaml (allowScheduling: true)
- Add worker-1 disk config to add-disks-job (storageReserved: 400Gi,
  evictionRequested: false)

k8s/infra/longhorn/longhorn-add-disks-job.yaml

@@ -117,6 +117,22 @@ spec:
             echo "  ✓ talos-cp-3 already has $CP3_DISKS disks configured"
           fi
 
+          # worker-1: enable scheduling, reserve 400Gi for LLM weights,
+          # clear eviction flag that was set when scheduling was disabled.
+          echo "Configuring worker-1 disk..."
+          kubectl -n longhorn-system patch nodes.longhorn.io worker-1 --type merge -p '{
+            "spec": {
+              "disks": {
+                "default-disk-1030400000000": {
+                  "allowScheduling": true,
+                  "evictionRequested": false,
+                  "storageReserved": 429496729600
+                }
+              }
+            }
+          }'
+          echo "  ✓ worker-1 disk configured (400Gi reserved)"
+
           echo
           echo "Waiting for disks to be ready..."
           sleep 10

k8s/infra/longhorn/longhorn-nodes.yaml

@@ -1,33 +1,25 @@
-# Longhorn Node CRDs for cp-2 and cp-3.
+# Longhorn Node CRDs — enable scheduling on nodes that need explicit opt-in.
-# These nodes have the control-plane taint, so Longhorn doesn't auto-discover them.
-# Explicit Node CRDs + the taint-toleration setting enable storage across all 3 nodes.
 #
-# `spec.disks` is deliberately absent. Longhorn owns disk identity: it names the
+# Control-plane nodes (cp-2, cp-3) have taints so Longhorn doesn't auto-discover.
-# entry itself (`default-disk-080400000000`, not `default-disk`) and writes
+# worker-1 was manually disabled; re-enabled 2026-09-28 to relieve degraded-volume
-# `storageReserved`, `diskType` and `evictionRequested` into it. Declaring a
+# pressure (400Gi reserved for LLM weights via the add-disks-job, ~300Gi available
-# `default-disk` key here never matched the live one, so the Application sat
+# for general replica scheduling).
-# OutOfSync and selfHeal kept trying to add a SECOND disk record pointing at the
-# same /var/lib/longhorn path — which is worse than the drift it was fixing.
 #
-# What these objects are actually for is `allowScheduling: true` on tainted
+# `spec.disks` deliberately absent — Longhorn owns disk identity and writes
-# control-plane nodes. That is all they need to declare.
+# storageReserved/diskType/evictionRequested itself. Disk-level config lives in
+# longhorn-add-disks-job.yaml. These objects only set `allowScheduling: true`.
 ---
 apiVersion: longhorn.io/v1beta2
 kind: Node
-metadata:
+metadata: { name: talos-cp-2, namespace: longhorn-system }
-  name: talos-cp-2
+spec: { name: talos-cp-2, allowScheduling: true, tags: [] }
-  namespace: longhorn-system
-spec:
-  name: talos-cp-2
-  allowScheduling: true
-  tags: []
 ---
 apiVersion: longhorn.io/v1beta2
 kind: Node
-metadata:
+metadata: { name: talos-cp-3, namespace: longhorn-system }
-  name: talos-cp-3
+spec: { name: talos-cp-3, allowScheduling: true, tags: [] }
-  namespace: longhorn-system
+---
-spec:
+apiVersion: longhorn.io/v1beta2
-  name: talos-cp-3
+kind: Node
-  allowScheduling: true
+metadata: { name: worker-1, namespace: longhorn-system }
-  tags: []
+spec: { name: worker-1, allowScheduling: true, tags: [] }