Ben Vincent
f89e1c8260
Turn the single-replica jellyfin-ha app into a proper high-availability deployment so the fork's Redis-coordinated distributed transcoding and PostgreSQL main database can actually be exercised. - Replace the Deployment with a 2-replica StatefulSet for stable pod identity; set JELLYFIN_INSTANCE_ID from metadata.name (the fork's Redis transcode-lease owner id), add soft podAntiAffinity and a PDB minAvailable 1. - Move the main Jellyfin DB to PostgreSQL via a CloudNativePG trio (3-instance Cluster, PgBouncer Pooler, Ceph RGW barman backups) mirroring the litellm pattern; an init container writes database.xml selecting the fork's Jellyfin-PostgreSQL provider and the DSN is composed from the CNPG-generated app secret pointed at the pooler. - Share /config on an RWX cephfs PVC across replicas; keep /cache per-pod via a volumeClaimTemplate. - Fix the transcode mount to the fork's real path /config/transcodes on the RWX PVC (raid5) so a surviving pod can resume the segments of the pod it takes over. - Add Intel iGPU hardware transcoding via the gpu.intel.com/i915 device plugin resource plus render/video supplemental groups. - Switch the Service to sessionAffinity ClientIP to reduce transcode churn. - Disable UDP auto-discovery. Library scans still run on every replica; a single-scanner leader election is a planned follow-up.
120 lines
3.3 KiB
YAML
120 lines
3.3 KiB
YAML
---
|
|
# Main Jellyfin database. The jellyfin-ha fork's experimental EF Core provider
|
|
# moves the entire Jellyfin DB (incl. library items) off SQLite into PostgreSQL,
|
|
# which is what makes a shared-nothing multi-replica deployment possible. No
|
|
# bootstrap secret is given, so CNPG generates the jellyfin-postgres-app secret
|
|
# (username/password/dbname) that the StatefulSet composes its DSN from.
|
|
apiVersion: postgresql.cnpg.io/v1
|
|
kind: Cluster
|
|
metadata:
|
|
name: jellyfin-postgres
|
|
namespace: jellyfin
|
|
spec:
|
|
affinity:
|
|
podAntiAffinityType: preferred
|
|
backup:
|
|
retentionPolicy: 30d
|
|
barmanObjectStore:
|
|
# Dedicated per-cluster Ceph RGW bucket (cephrgw-operator provisions it).
|
|
destinationPath: s3://cnpg-jellyfin
|
|
endpointURL: https://s3.ceph.unkin.net
|
|
endpointCA:
|
|
name: vault-ca-cert
|
|
key: ca.crt
|
|
s3Credentials:
|
|
accessKeyId:
|
|
name: cnpg-jellyfin-backup-s3
|
|
key: AWS_ACCESS_KEY_ID
|
|
secretAccessKey:
|
|
name: cnpg-jellyfin-backup-s3
|
|
key: AWS_SECRET_ACCESS_KEY
|
|
serverName: jellyfin
|
|
data:
|
|
compression: bzip2
|
|
jobs: 2
|
|
wal:
|
|
compression: zstd
|
|
maxParallel: 2
|
|
bootstrap:
|
|
initdb:
|
|
database: jellyfin
|
|
encoding: UTF8
|
|
localeCType: C
|
|
localeCollate: C
|
|
owner: jellyfin
|
|
enablePDB: true
|
|
enableSuperuserAccess: false
|
|
failoverDelay: 0
|
|
# PG 17 — accepted by the fork's Npgsql/EF Core provider (needs PG14+); the
|
|
# provider generates its own migrations on first start.
|
|
imageName: ghcr.io/cloudnative-pg/postgresql:17-system-trixie
|
|
instances: 3
|
|
logLevel: info
|
|
maxSyncReplicas: 0
|
|
minSyncReplicas: 0
|
|
monitoring:
|
|
customQueriesConfigMap:
|
|
- key: queries
|
|
name: cnpg-default-monitoring
|
|
disableDefaultQueries: false
|
|
enablePodMonitor: false
|
|
postgresql:
|
|
parameters:
|
|
archive_mode: "on"
|
|
archive_timeout: 5min
|
|
dynamic_shared_memory_type: posix
|
|
effective_cache_size: 256MB
|
|
full_page_writes: "on"
|
|
log_destination: csvlog
|
|
log_directory: /controller/log
|
|
log_filename: postgres
|
|
log_rotation_age: "0"
|
|
log_rotation_size: "0"
|
|
log_truncate_on_rotation: "false"
|
|
logging_collector: "on"
|
|
max_connections: "200"
|
|
max_parallel_workers: "16"
|
|
max_replication_slots: "16"
|
|
max_worker_processes: "16"
|
|
shared_buffers: 128MB
|
|
shared_memory_type: mmap
|
|
ssl_max_protocol_version: TLSv1.3
|
|
ssl_min_protocol_version: TLSv1.3
|
|
wal_keep_size: 256MB
|
|
wal_level: logical
|
|
wal_log_hints: "on"
|
|
wal_receiver_timeout: 5s
|
|
wal_sender_timeout: 5s
|
|
syncReplicaElectionConstraint:
|
|
enabled: false
|
|
primaryUpdateMethod: restart
|
|
primaryUpdateStrategy: unsupervised
|
|
probes:
|
|
liveness:
|
|
isolationCheck:
|
|
connectionTimeout: 1000
|
|
enabled: true
|
|
requestTimeout: 1000
|
|
replicationSlots:
|
|
highAvailability:
|
|
enabled: true
|
|
slotPrefix: _cnpg_
|
|
synchronizeReplicas:
|
|
enabled: true
|
|
updateInterval: 30
|
|
resources:
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
requests:
|
|
cpu: 50m
|
|
memory: 512Mi
|
|
smartShutdownTimeout: 180
|
|
startDelay: 3600
|
|
stopDelay: 1800
|
|
storage:
|
|
resizeInUseVolumes: true
|
|
size: 10Gi
|
|
storageClass: cephrbd-fast-delete
|
|
switchoverDelay: 3600
|