unkin-agent
42c1794d0e
The migrate Job was a PreSync hook but connects to postgres-rw, whose CNPG Cluster + generated postgres-app secret apply in the Sync phase (after all PreSync hooks). On a fresh install migrate ran before Postgres existed, failed, exhausted backoffLimit, failed PreSync, and blocked the Sync phase that creates the DB. - Move migrate off PreSync to a Sync-phase hook at sync-wave 1. - Put the CNPG Cluster + backup resources, VSO auth/secrets, and Certificate at wave 0 so the DB is Healthy (and creds/cert exist) before migrate runs. - Put the Deployment + Service/Gateway/HTTPRoute/PDB/VMServiceScrape at wave 2 so serve starts after migrate completes. - Add a writable /tmp emptyDir to the serve container and migrate Job (root FS is read-only) so codeload/staging writes cannot crash the process.
118 lines
3.0 KiB
YAML
118 lines
3.0 KiB
YAML
---
|
|
apiVersion: postgresql.cnpg.io/v1
|
|
kind: Cluster
|
|
metadata:
|
|
name: postgres
|
|
namespace: ghp
|
|
annotations:
|
|
# Wave 0: DB (and the generated postgres-app Secret) must be Healthy before
|
|
# the wave-1 migrate Job runs. ArgoCD gates on the Cluster's health status.
|
|
argocd.argoproj.io/sync-wave: "0"
|
|
spec:
|
|
affinity:
|
|
podAntiAffinityType: preferred
|
|
backup:
|
|
retentionPolicy: 30d
|
|
barmanObjectStore:
|
|
destinationPath: s3://cnpg-ghp
|
|
endpointURL: https://s3.ceph.unkin.net
|
|
endpointCA:
|
|
name: vault-ca-cert
|
|
key: ca.crt
|
|
s3Credentials:
|
|
accessKeyId:
|
|
name: cnpg-ghp-backup-s3
|
|
key: AWS_ACCESS_KEY_ID
|
|
secretAccessKey:
|
|
name: cnpg-ghp-backup-s3
|
|
key: AWS_SECRET_ACCESS_KEY
|
|
serverName: ghp
|
|
data:
|
|
compression: bzip2
|
|
jobs: 2
|
|
wal:
|
|
compression: zstd
|
|
maxParallel: 2
|
|
bootstrap:
|
|
initdb:
|
|
# No secret ref: CNPG mints the owner credentials and publishes them in the
|
|
# generated "postgres-app" Secret, which the Deployment reads to build the DSN.
|
|
database: ghp
|
|
encoding: UTF8
|
|
localeCType: C
|
|
localeCollate: C
|
|
owner: ghp
|
|
enablePDB: true
|
|
enableSuperuserAccess: false
|
|
failoverDelay: 0
|
|
imageName: ghcr.io/cloudnative-pg/postgresql:18.1-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: 500m
|
|
memory: 512Mi
|
|
requests:
|
|
cpu: 50m
|
|
memory: 256Mi
|
|
smartShutdownTimeout: 180
|
|
startDelay: 3600
|
|
stopDelay: 1800
|
|
storage:
|
|
resizeInUseVolumes: true
|
|
size: 20Gi
|
|
storageClass: cephrbd-fast-delete
|
|
switchoverDelay: 3600
|