mirror of
https://gitlab.kube.huskypup.net/Scooby/Homelabv4.git
synced 2026-08-21 11:36:50 +00:00
Scooby Husky
a1d6091122
Postgres refuses to replay WAL past a checkpoint recorded with higher max_connections/max_wal_senders/etc than the recovering instance's own settings: 'recovery aborted because of insufficient parameter settings: max_connections = 100 is a lower setting than on the primary server, where its value was 200' - confirmed live on all 3 VPS clusters (they had no postgresql.parameters block at all, defaulting to CNPG's 100). Copied home's full postgresql.parameters block to remove any other potential mismatch (max_wal_senders, max_worker_processes are subject to the same check). Bumped memory requests/limits to match home too - shared_buffers: 512MB needs headroom the previous 256Mi/1Gi didn't have.
101 lines
3.7 KiB
YAML
101 lines
3.7 KiB
YAML
---
|
|
# CNPG "replica cluster" - continuously replays WAL shipped from home's
|
|
# pg-authentik cluster (infrastructure/authentik/manifests/cnpg-cluster.yaml)
|
|
# via VPS MinIO's cnpg-backups/pg-authentik bucket path. Unlike Vault's
|
|
# raft-restore CronJob (Vault has no native continuous-replication-into-
|
|
# object-store feature), CNPG's replica-cluster mode is a first-class
|
|
# built-in mechanism - no custom restore scripting needed, matches the
|
|
# plan's intent directly.
|
|
#
|
|
# While spec.replica.enabled is true, this cluster is a read-only standby
|
|
# in continuous recovery - the -rw service exists but is NOT writable
|
|
# (same "nothing accepts writes in normal operation" discipline as Vault/
|
|
# Gitea). Promoting it to a real writable primary during an actual
|
|
# incident is a deliberate manual step:
|
|
# kubectl -n authentik patch cluster pg-authentik --type merge \
|
|
# -p '{"spec":{"replica":{"enabled":false}}}'
|
|
# then scale the authentik Deployment(s) up from 0.
|
|
#
|
|
# vps-minio-secret is a plain Secret copied here manually (kubectl, not
|
|
# git) from the vps-minio-root-secret in the minio namespace - this
|
|
# cluster has no Vault/ESO of its own:
|
|
# kubectl -n authentik create secret generic vps-minio-secret \
|
|
# --from-literal=accesskey=<vps minio root user> \
|
|
# --from-literal=secretkey=<vps minio root password>
|
|
apiVersion: postgresql.cnpg.io/v1
|
|
kind: Cluster
|
|
metadata:
|
|
name: pg-authentik
|
|
namespace: authentik
|
|
spec:
|
|
imageName: ghcr.io/cloudnative-pg/postgresql:16
|
|
instances: 1
|
|
|
|
# shared_buffers: 512MB above needs headroom - matches home's requests/limits.
|
|
resources:
|
|
requests:
|
|
memory: "512Mi"
|
|
cpu: "25m"
|
|
limits:
|
|
memory: "2Gi"
|
|
cpu: "250m"
|
|
|
|
storage:
|
|
size: 5Gi
|
|
storageClass: local-path
|
|
|
|
# Must match (or exceed) home's max_connections/max_wal_senders/etc -
|
|
# Postgres refuses to replay WAL past a checkpoint recorded with higher
|
|
# values than the recovering instance's own settings ("recovery aborted
|
|
# because of insufficient parameter settings: max_connections = 100 is
|
|
# a lower setting than on the primary server, where its value was 200",
|
|
# confirmed live 2026-08-18). Copied from
|
|
# infrastructure/authentik/manifests/cnpg-cluster.yaml.
|
|
postgresql:
|
|
parameters:
|
|
max_connections: "200"
|
|
shared_buffers: "512MB"
|
|
effective_cache_size: "1536MB"
|
|
maintenance_work_mem: "128MB"
|
|
checkpoint_completion_target: "0.9"
|
|
wal_buffers: "16MB"
|
|
default_statistics_target: "100"
|
|
random_page_cost: "1.1"
|
|
effective_io_concurrency: "200"
|
|
work_mem: "2621kB"
|
|
min_wal_size: "1GB"
|
|
max_wal_size: "4GB"
|
|
|
|
bootstrap:
|
|
recovery:
|
|
source: home-backup
|
|
|
|
externalClusters:
|
|
- name: home-backup
|
|
barmanObjectStore:
|
|
# serverName defaults to the externalClusters[].name ("home-backup")
|
|
# here, NOT the source Postgres cluster's actual name - but home's
|
|
# barmanObjectStore backup: block (on the pg-authentik Cluster
|
|
# itself) defaults serverName to its own metadata.name
|
|
# ("pg-authentik"). Without this override, recovery looks for
|
|
# backups under the wrong server-name prefix and finds none -
|
|
# "no target backup found" despite the backup genuinely existing
|
|
# (confirmed live 2026-08-18).
|
|
serverName: pg-authentik
|
|
destinationPath: s3://cnpg-backups/pg-authentik
|
|
endpointURL: http://vps-minio.minio.svc.cluster.local:9000
|
|
s3Credentials:
|
|
accessKeyId:
|
|
name: vps-minio-secret
|
|
key: accesskey
|
|
secretAccessKey:
|
|
name: vps-minio-secret
|
|
key: secretkey
|
|
|
|
replica:
|
|
enabled: true
|
|
source: home-backup
|
|
|
|
monitoring:
|
|
enablePodMonitor: false # no Prometheus on the VPS cluster
|