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.
40 lines
1.1 KiB
YAML
40 lines
1.1 KiB
YAML
apiVersion: argoproj.io/v1alpha1
|
|
kind: Application
|
|
metadata:
|
|
name: helm-envoy-gateway
|
|
namespace: argocd
|
|
finalizers:
|
|
- resources-finalizer.argocd.argoproj.io
|
|
spec:
|
|
project: default
|
|
source:
|
|
# No scheme, so Argo CD pulls the chart from the OCI registry.
|
|
repoURL: docker.io/envoyproxy
|
|
chart: gateway-helm
|
|
# v1.9 supports Kubernetes 1.33 to 1.36
|
|
targetRevision: v1.9.2
|
|
helm:
|
|
values: |
|
|
config:
|
|
envoyGateway:
|
|
provider:
|
|
kubernetes:
|
|
# Ride out dqlite stalls of up to ~40s instead of restarting
|
|
# when a lease renewal takes over 10s
|
|
# (docs/upgrade-k8s-1.33.md).
|
|
leaderElection:
|
|
leaseDuration: 60s
|
|
renewDeadline: 40s
|
|
retryPeriod: 5s
|
|
destination:
|
|
server: https://kubernetes.default.svc
|
|
namespace: envoy-gateway-system
|
|
syncPolicy:
|
|
syncOptions:
|
|
- CreateNamespace=true
|
|
# The bundled Gateway API CRDs are too big for client-side apply.
|
|
- ServerSideApply=true
|
|
automated:
|
|
prune: true
|
|
selfHeal: true
|