sonarr, radarr, jackett and qbittorrent all mounted their Longhorn config PVC at the renderer's default /data/config, but every one of these images runs with `-data=/config`. So the PVC held nothing but lost+found while the app wrote its entire configuration to the container's EPHEMERAL writable layer — destroyed on every pod recreation: restart, reschedule, image bump. Measured in-cluster before fixing, per app, rather than inferred: /data/config dev=2080 [lost+found] <- the Longhorn PVC /config dev=2053 [Sentry asp config.xml logs ...] <- the node's own disk and a marker file written to /config did not appear in /data/config, so they are demonstrably different storage. qbittorrent's /config sat on dev=66309 (/dev/nvme0n1p5), i.e. whichever node it happened to land on. This is the SAME failure catalog/plex.yaml:54 already records having fixed for Plex; plex was the only one of the five that was right. The live /config contents were copied onto each PVC BEFORE this landed, so jackett's API key and qbittorrent's credentials — which other apps reference — survive the move rather than being regenerated. catalog/sonarr.yaml:61 documented this as a latent bug and deliberately left it because it changes live on-disk state. It is being fixed now because all four pods had just been recreated, so their configs were freshly generated and nothing had accumulated to lose. Co-Authored-By: Claude Opus 5 <[email protected]>
160 lines
3.7 KiB
YAML
160 lines
3.7 KiB
YAML
---
|
|
# Namespace (trust zone; default-deny + policies apply)
|
|
apiVersion: v1
|
|
kind: Namespace
|
|
metadata:
|
|
name: vm-demo
|
|
labels:
|
|
homelab.keithjackson.dev/app-namespace: 'true'
|
|
annotations:
|
|
homelab.keithjackson.dev/backup-policy: daily-offcluster
|
|
---
|
|
# Default-deny baseline (R-NET-01): deny all, allow only DNS
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: NetworkPolicy
|
|
metadata:
|
|
name: default-deny
|
|
namespace: vm-demo
|
|
labels:
|
|
homelab.keithjackson.dev/baseline: default-deny
|
|
spec:
|
|
podSelector: {}
|
|
policyTypes:
|
|
- Ingress
|
|
- Egress
|
|
ingress: []
|
|
egress:
|
|
- to:
|
|
- namespaceSelector:
|
|
matchLabels:
|
|
kubernetes.io/metadata.name: kube-system
|
|
ports:
|
|
- protocol: UDP
|
|
port: 53
|
|
- protocol: TCP
|
|
port: 53
|
|
---
|
|
# CDI DataVolume (standalone; survives rebuild, R-STATE-01)
|
|
apiVersion: cdi.kubevirt.io/v1beta1
|
|
kind: DataVolume
|
|
metadata:
|
|
name: vm-demo-rootdisk
|
|
namespace: vm-demo
|
|
spec:
|
|
source:
|
|
registry:
|
|
url: docker://quay.io/containerdisks/fedora:41
|
|
storage:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
storageClassName: longhorn
|
|
resources:
|
|
requests:
|
|
storage: 6Gi
|
|
---
|
|
# KubeVirt VirtualMachine (R-PLAT-03)
|
|
apiVersion: kubevirt.io/v1
|
|
kind: VirtualMachine
|
|
metadata:
|
|
name: vm-demo
|
|
namespace: vm-demo
|
|
labels:
|
|
app.kubernetes.io/name: vm-demo
|
|
spec:
|
|
running: false
|
|
template:
|
|
metadata:
|
|
labels:
|
|
kubevirt.io/vm: vm-demo
|
|
homelab.keithjackson.dev/egress-class: internet
|
|
homelab.keithjackson.dev/auth-mode: none
|
|
spec:
|
|
domain:
|
|
cpu:
|
|
cores: 1
|
|
memory:
|
|
guest: 1536Mi
|
|
devices:
|
|
disks:
|
|
- name: rootdisk
|
|
disk:
|
|
bus: virtio
|
|
- name: cloudinit
|
|
disk:
|
|
bus: virtio
|
|
interfaces:
|
|
- name: default
|
|
masquerade: {}
|
|
resources:
|
|
requests:
|
|
memory: 1536Mi
|
|
networks:
|
|
- name: default
|
|
pod: {}
|
|
volumes:
|
|
- name: rootdisk
|
|
dataVolume:
|
|
name: vm-demo-rootdisk
|
|
- name: cloudinit
|
|
cloudInitNoCloud:
|
|
userData: "#cloud-config\npackage_update: true\npackages:\n - dnf-automatic\nwrite_files:\n - path: /etc/dnf/automatic.conf\n content: |\n [commands]\n upgrade_type = default\n random_sleep = 0\n download_updates = yes\n apply_updates = yes\nruncmd:\n - [ systemctl, enable, --now, dnf-automatic.timer ]\n"
|
|
---
|
|
# CiliumNetworkPolicy world egress allow (egress class governs the path; R-NET-05): vm-demo-allow-internet-egress
|
|
apiVersion: cilium.io/v2
|
|
kind: CiliumNetworkPolicy
|
|
metadata:
|
|
name: vm-demo-allow-internet-egress
|
|
namespace: vm-demo
|
|
labels:
|
|
app.kubernetes.io/name: vm-demo
|
|
spec:
|
|
endpointSelector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: vm-demo
|
|
egress:
|
|
- toEntities:
|
|
- world
|
|
---
|
|
# ServiceMonitor (R-OBS-01)
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: vm-demo
|
|
namespace: vm-demo
|
|
labels:
|
|
release: kube-prometheus-stack
|
|
app.kubernetes.io/name: vm-demo
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: vm-demo
|
|
namespaceSelector:
|
|
matchNames:
|
|
- vm-demo
|
|
endpoints:
|
|
- port: metrics
|
|
interval: 30s
|
|
---
|
|
# PrometheusRule SLI alerts (R-OBS-01)
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: vm-demo-slis
|
|
namespace: vm-demo
|
|
labels:
|
|
release: kube-prometheus-stack
|
|
app.kubernetes.io/name: vm-demo
|
|
spec:
|
|
groups:
|
|
- name: vm-demo.slis
|
|
rules:
|
|
- alert: vm-demo-down
|
|
expr: up{job="vm-demo"} == 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
service: vm-demo
|
|
annotations:
|
|
summary: vm-demo is down
|
|
description: 'vm-demo has been unreachable for 5m (SLI: up).'
|