mirror of
https://github.com/rubenhensen/k8scd.git
synced 2026-11-15 22:29:09 +01:00
Ruben Hensen
858904384c
The snapshot-controller (1,059 restarts), the CNPG operator and Envoy Gateway restart whenever a lease renewal takes more than 10 seconds, which happens when heavy writes stall dqlite on the node's SSD. Raise lease duration, renew deadline and retry period from 15s/10s/2s to 60s/40s/5s so they ride out stalls of up to ~40 seconds. With one replica, or a standby, a slower takeover costs nothing here.
37 lines
1.1 KiB
YAML
37 lines
1.1 KiB
YAML
apiVersion: argoproj.io/v1alpha1
|
|
kind: Application
|
|
metadata:
|
|
name: cloudnative-pg
|
|
namespace: argocd
|
|
finalizers:
|
|
- resources-finalizer.argocd.argoproj.io
|
|
spec:
|
|
project: default
|
|
source:
|
|
chart: cloudnative-pg
|
|
repoURL: https://cloudnative-pg.github.io/charts
|
|
targetRevision: 0.29.1
|
|
helm:
|
|
values: |
|
|
config:
|
|
data:
|
|
# Swap the instance manager inside running pods on operator
|
|
# upgrades instead of restarting them. Both clusters have a
|
|
# single instance, so a restart means downtime.
|
|
ENABLE_INSTANCE_MANAGER_INPLACE_UPDATES: "true"
|
|
# Ride out dqlite stalls of up to ~40s instead of restarting when a
|
|
# lease renewal takes over 10s (docs/upgrade-k8s-1.33.md).
|
|
additionalArgs:
|
|
- --leader-lease-duration=60
|
|
- --leader-renew-deadline=40
|
|
destination:
|
|
server: https://kubernetes.default.svc
|
|
namespace: cnpg-system
|
|
syncPolicy:
|
|
syncOptions:
|
|
- CreateNamespace=true
|
|
- ServerSideApply=true
|
|
automated:
|
|
prune: true
|
|
selfHeal: true
|