rock
3462096311
- Remove expand-replicas-job (blindly forced all volumes to 3 replicas, ignoring StorageClass settings) - Add diskSelector: 'storage' to longhorn and longhorn-cnpg StorageClasses so replicas only land on CP nodes (cp-1, cp-2, cp-3) - Tag all CP node disks with 'storage' via PostSync job (disk names are runtime-discovered, can't hardcode in Node CRs) - Disable scheduling on worker-1 Node CR — only longhorn-llm-local (diskSelector: 'llm') can use it - worker-1 is GPU-only: llm-models and comfyui use dedicated SCs
24 lines
1004 B
YAML
24 lines
1004 B
YAML
# Longhorn StorageClass - single unified `longhorn` storage class for the whole
|
|
# cluster. This is the only Longhorn class anything should reference.
|
|
apiVersion: storage.k8s.io/v1
|
|
kind: StorageClass
|
|
metadata:
|
|
name: longhorn
|
|
annotations:
|
|
storageclass.kubernetes.io/is-default-class: "true"
|
|
description: "Longhorn distributed storage - 3 replicas, CP nodes only"
|
|
argocd.argoproj.io/sync-options: Replace=true,Force=true
|
|
provisioner: driver.longhorn.io
|
|
allowVolumeExpansion: true
|
|
reclaimPolicy: Delete
|
|
volumeBindingMode: Immediate # Immediate binding for StatefulSets (matches deployed config)
|
|
parameters:
|
|
numberOfReplicas: "3" # HA across all 3 CP nodes
|
|
diskSelector: "storage" # Only schedule on CP node disks, not GPU worker
|
|
staleReplicaTimeout: "30"
|
|
fromBackup: ""
|
|
dataLocality: "disabled" # Match deployed config (not best-effort)
|
|
fsType: "ext4"
|
|
disableRevisionCounter: "true" # Performance optimization
|
|
unmapMarkSnapChainRemoved: "ignored"
|