# Dedicated StorageClass for model weights on worker-1's local NVMe.
#
# Why not the default `longhorn` class (3 replicas, network-attached):
#
# 1. numberOfReplicas: 1 — model weights are re-downloadable from HuggingFace.
#    Replicating them 3x buys nothing; losing a replica costs a re-pull, not
#    data. The repo's "never delete a PVC without replicas/backups" rule exists
#    for irreplaceable data, which this is not.
#
# 2. dataLocality: strict-local — keeps the single replica on the SAME node as
#    the pod. All engines are pinned to worker-1, so weights are read from its
#    local 751GB NVMe instead of over the network from a control-plane node.
#    Removes ~60GB of network reads on every cold start.
#
# 3. diskSelector: llm — restricts this class to disks tagged `llm`, i.e. only
#    worker-1's disk. Equally important, worker-1's disk carries that tag so
#    UNTAGGED volumes (any ordinary cluster PVC) will not land on it. Before
#    tagging, worker-1 had been silently hosting a replica of cicd/runner-dind,
#    consuming GPU-node storage for general cluster workloads.
#
# The default 3-replica class also physically could not place this volume: all
# three control-plane disks were already at their over-provisioning ceiling
# (storage-over-provisioning-percentage=100, 30% reserved), so a 120Gi x3
# request failed with ReplicaSchedulingFailure on every node.
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
  name: longhorn-llm-local
provisioner: driver.longhorn.io
allowVolumeExpansion: true
reclaimPolicy: Delete
volumeBindingMode: Immediate
parameters:
  numberOfReplicas: "1"
  dataLocality: "strict-local"
  diskSelector: "llm"
  staleReplicaTimeout: "30"
  fsType: "ext4"