mirror of
https://github.com/rubenhensen/k8scd.git
synced 2026-11-15 14:29:09 +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
1.2 KiB
YAML
40 lines
1.2 KiB
YAML
apiVersion: argoproj.io/v1alpha1
|
|
kind: Application
|
|
metadata:
|
|
name: external-snapshotter
|
|
namespace: argocd
|
|
spec:
|
|
project: default
|
|
source:
|
|
repoURL: https://github.com/kubernetes-csi/external-snapshotter.git
|
|
targetRevision: v8.2.1
|
|
path: deploy/kubernetes/snapshot-controller
|
|
kustomize:
|
|
patches:
|
|
# Ride out dqlite stalls of up to ~40s instead of restarting when a
|
|
# lease renewal takes over 10s (docs/upgrade-k8s-1.33.md).
|
|
- target:
|
|
kind: Deployment
|
|
name: snapshot-controller
|
|
patch: |-
|
|
- op: add
|
|
path: /spec/template/spec/containers/0/args/-
|
|
value: --leader-election-lease-duration=60s
|
|
- op: add
|
|
path: /spec/template/spec/containers/0/args/-
|
|
value: --leader-election-renew-deadline=40s
|
|
- op: add
|
|
path: /spec/template/spec/containers/0/args/-
|
|
value: --leader-election-retry-period=5s
|
|
destination:
|
|
server: https://kubernetes.default.svc
|
|
namespace: kube-system
|
|
syncPolicy:
|
|
automated:
|
|
selfHeal: true
|
|
prune: true
|
|
syncOptions:
|
|
- CreateNamespace=true
|
|
automated:
|
|
selfHeal: true
|