Files
unkin-agent cdaab736b5 Bump jellyfin-ha to v0.4.0 (#483)
The deployed v0.3.3 build returns 500 from /Shows/NextUp on PostgreSQL, breaking the home screen, and lets replicas diverge: library-visibility and shared-config changes never propagate, user data (resume, played state, favourites, ratings) is overwritten between pods, and eight scheduled tasks run on every replica instead of only the scan leader. v0.4.0 carries the fixes.

- Pin cheeztv and fafflix to jellyfin-ha:v0.4.0.

No config change needed: cross-pod invalidation reuses the transcode-store Redis connection string both apps already set.

Reviewed-on: #483
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>
2026-09-22 22:57:06 +10:00

310 lines
13 KiB
YAML

---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: cheeztv
namespace: cheeztv
annotations:
configmap.reloader.stakater.com/auto: "true"
spec:
# HA: two replicas coordinate transcode session ownership through Valkey and
# resume each other's HLS segments off the shared RWX transcode PVC. Stable
# pod names (cheeztv-0/1) are the lease owner identity, hence StatefulSet.
replicas: 2
serviceName: cheeztv
podManagementPolicy: Parallel
updateStrategy:
type: RollingUpdate
selector:
matchLabels:
app: cheeztv
template:
metadata:
labels:
app: cheeztv
spec:
securityContext:
# Group-write the shared RWX volumes and grant the render/video groups so
# the runAsUser 1000 process can open the Intel DRI render node injected
# by the device plugin.
fsGroup: 1000
supplementalGroups:
- 44
- 105
- 109
seccompProfile:
type: RuntimeDefault
affinity:
# Spread the two replicas across nodes for node-level HA. Soft so a
# single-GPU-node cluster still schedules both (i915 has 4 shared slots).
podAntiAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- weight: 100
podAffinityTerm:
labelSelector:
matchLabels:
app: cheeztv
topologyKey: kubernetes.io/hostname
initContainers:
# Seed the fork's PostgreSQL provider (database.xml) and Intel iGPU
# hardware transcode settings (encoding.xml) before Jellyfin starts.
# Runs as root to chown into the shared config volume; mirrors the fork
# Helm chart's inject-db-config. Each file is written only when absent so
# admin changes persisted to the shared RWX /config survive pod restarts.
- name: inject-config
image: busybox:1.37.0
command:
- sh
- -c
- |
mkdir -p /config/config
chown 1000:1000 /config/config
chmod 775 /config/config
if [ ! -e /config/config/database.xml ]; then
cat > /config/config/database.xml << 'DBEOF'
<?xml version="1.0" encoding="utf-8"?>
<DatabaseConfigurationOptions>
<DatabaseType>Jellyfin-PostgreSQL</DatabaseType>
<LockingBehavior>NoLock</LockingBehavior>
</DatabaseConfigurationOptions>
DBEOF
chown 1000:1000 /config/config/database.xml
chmod 664 /config/config/database.xml
fi
# VAAPI on the Intel render node the device plugin injects
# (/dev/dri/renderD128 — ffmpeg's default DRM node, reachable via
# the render/video supplementalGroups). Without this the attached
# iGPU is idle and every transcode runs in software. Omitted
# elements fall back to the fork's EncodingOptions defaults.
if [ ! -e /config/config/encoding.xml ]; then
cat > /config/config/encoding.xml << 'ENCEOF'
<?xml version="1.0" encoding="utf-8"?>
<EncodingOptions xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<EncodingThreadCount>-1</EncodingThreadCount>
<HardwareAccelerationType>vaapi</HardwareAccelerationType>
<VaapiDevice>/dev/dri/renderD128</VaapiDevice>
<EnableHardwareEncoding>true</EnableHardwareEncoding>
<AllowHevcEncoding>true</AllowHevcEncoding>
<AllowAv1Encoding>false</AllowAv1Encoding>
<EnableIntelLowPowerH264HwEncoder>false</EnableIntelLowPowerH264HwEncoder>
<EnableIntelLowPowerHevcHwEncoder>false</EnableIntelLowPowerHevcHwEncoder>
<EnableTonemapping>false</EnableTonemapping>
<EnableVppTonemapping>false</EnableVppTonemapping>
<HardwareDecodingCodecs>
<string>h264</string>
<string>hevc</string>
<string>vc1</string>
<string>vp9</string>
</HardwareDecodingCodecs>
</EncodingOptions>
ENCEOF
chown 1000:1000 /config/config/encoding.xml
chmod 664 /config/config/encoding.xml
fi
resources:
requests:
cpu: 10m
memory: 32Mi
limits:
cpu: 100m
memory: 64Mi
volumeMounts:
- name: config
mountPath: /config
# Render the SSO/LDAP plugin configs into the shared config volume,
# substituting the client secret and LDAP bind password from the
# VSO-synced oauth-credentials Secret (never committed). Plugin configs
# are fully managed here so they are overwritten every start; the login
# button branding is written only when absent so admin edits survive.
- name: inject-plugin-config
image: busybox:1.37.0
command:
- sh
- -c
- |
mkdir -p /config/plugins/configurations /config/config
chown 1000:1000 /config/plugins /config/plugins/configurations /config/config
esc() { printf '%s' "$1" | sed -e 's/[&|\\]/\\&/g'; }
cs=$(esc "${CLIENT_SECRET}")
lp=$(esc "${LDAP_BIND_PASSWORD}")
sed "s|@@CLIENT_SECRET@@|${cs}|" /templates/SSO-Auth.xml > /config/plugins/configurations/SSO-Auth.xml
sed "s|@@LDAP_BIND_PASSWORD@@|${lp}|" /templates/LDAP-Auth.xml > /config/plugins/configurations/LDAP-Auth.xml
chown 1000:1000 /config/plugins/configurations/SSO-Auth.xml /config/plugins/configurations/LDAP-Auth.xml
chmod 600 /config/plugins/configurations/SSO-Auth.xml /config/plugins/configurations/LDAP-Auth.xml
if [ ! -e /config/config/branding.xml ]; then
cp /templates/branding.xml /config/config/branding.xml
chown 1000:1000 /config/config/branding.xml
chmod 664 /config/config/branding.xml
fi
env:
- name: CLIENT_SECRET
valueFrom:
secretKeyRef:
name: oauth-credentials
key: client_secret
optional: true
- name: LDAP_BIND_PASSWORD
valueFrom:
secretKeyRef:
name: oauth-credentials
key: ldap_bind_password
optional: true
resources:
requests:
cpu: 10m
memory: 32Mi
limits:
cpu: 100m
memory: 64Mi
volumeMounts:
- name: config
mountPath: /config
- name: plugin-config
mountPath: /templates
readOnly: true
containers:
- name: cheeztv
image: artifactapi.k8s.syd1.au.unkin.net/docker-internal/jellyfin-ha:v0.4.0
imagePullPolicy: IfNotPresent
ports:
- name: http
containerPort: 8096
protocol: TCP
env:
# Pod identity for the Valkey transcode lease owner. The fork reads
# JELLYFIN_INSTANCE_ID (falling back to MachineName); the stable
# StatefulSet pod name gives each replica a unique lease identity so
# takeover can target a dead replica. JELLYFIN_HA_POD_NAME is set for
# parity with the fork Helm chart (nothing currently reads it).
- name: JELLYFIN_INSTANCE_ID
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: JELLYFIN_HA_POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
# Multiple replicas must not each answer UDP auto-discovery.
- name: JELLYFIN_Network__AutoDiscovery
value: "false"
# Config dir must differ from the data root (Jellyfin sanity check).
- name: JELLYFIN_CONFIG_DIR
value: /config/config
# Distributed transcode session store (cheeztv-ha additions).
- name: Jellyfin__TranscodeStore__RedisConnectionString
value: "valkey-cheeztv-valkey:6379,abortConnect=false"
- name: Jellyfin__TranscodeStore__LeaseDurationSeconds
value: "30"
# PostgreSQL main DB via the CNPG-generated app secret, routed through
# the PgBouncer pooler. Composed with $(VAR) expansion so the password
# is never rendered into the manifest; CNPG passwords are URL-safe.
- name: PGUSER
valueFrom:
secretKeyRef:
name: cheeztv-postgres-app
key: username
- name: PGPASSWORD
valueFrom:
secretKeyRef:
name: cheeztv-postgres-app
key: password
- name: PGDB
valueFrom:
secretKeyRef:
name: cheeztv-postgres-app
key: dbname
- name: POSTGRES_CONNECTION_STRING
value: "postgresql://$(PGUSER):$(PGPASSWORD)@cheeztv-postgres-pooler:5432/$(PGDB)"
- name: DATABASE_URL
value: "postgresql://$(PGUSER):$(PGPASSWORD)@cheeztv-postgres-pooler:5432/$(PGDB)"
livenessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 30
periodSeconds: 30
timeoutSeconds: 5
failureThreshold: 3
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: 10
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 3
resources:
requests:
cpu: "1"
memory: 1Gi
gpu.intel.com/i915: "1"
limits:
cpu: "4"
memory: 6Gi
# Intel iGPU (QSV/VA-API) slot. Requesting it pins the pod to a
# GPU-labelled node and injects /dev/dri/renderD* automatically, so
# no /dev/dri hostPath or privileged container is needed. VA-API is
# pre-enabled via the seeded encoding.xml (see inject-config), so
# transcodes use the iGPU on first boot with no manual UI step.
gpu.intel.com/i915: "1"
securityContext:
runAsUser: 1000
runAsGroup: 1000
volumeMounts:
- name: config
mountPath: /config
- name: transcode
# Fork's real transcode temp path. RWX so a surviving pod reads the
# in-flight .ts/.m3u8 segments of the pod it takes over. A per-pod
# volume here silently breaks HA takeover.
mountPath: /config/transcodes
- name: cache
mountPath: /cache
- name: media-tv
# Kids-only instance: mount just the tvshows/kids subtree of the
# shared TV subvolume (subPath kids) so cheeztv's library never
# exposes the adult tree. Path matches fafflix's /media/tv-kids
# mount so the same episode resolves identically across instances.
mountPath: /media/tv
subPath: kids
readOnly: true
- name: media-movies
# Kids-only instance: mount just the movies/kids subtree of the
# shared movies subvolume (subPath kids).
mountPath: /media/movies
subPath: kids
readOnly: true
volumes:
- name: plugin-config
configMap:
name: cheeztv-plugin-config
- name: config
persistentVolumeClaim:
claimName: cheeztv-config
- name: transcode
persistentVolumeClaim:
claimName: cheeztv-transcode
- name: media-tv
persistentVolumeClaim:
claimName: cheeztv-media-tv
- name: media-movies
persistentVolumeClaim:
claimName: cheeztv-media-movies
volumeClaimTemplates:
# Per-pod scratch cache — RWO, disposable, one PVC per replica.
- metadata:
name: cache
annotations:
# Exclude the per-pod cache PVCs from the cheeztv-config k8up Schedule
# (skipWithoutAnnotation is false cluster-wide). Cache is disposable and
# RWO — it would also fail to mount into the backup pod while in use.
k8up.io/backup: "false"
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 30Gi
storageClassName: cephrbd-fast-delete
volumeMode: Filesystem