mirror of
https://github.com/kubernetes-sigs/node-feature-discovery.git
synced 2025-03-20 07:12:43 +00:00
fb6484fb8d
This patch mitigates inadvertent termination of nfd-master pods by the liveness probe on big clusters. With a recent change nfd-master started to wait (block) for informer caches to sync before starting the main loop. Consequently, this change also made the gRPC health enpoint to not respond until the caches have been synced. In big clusters the syncing the NodeFeature object cache takes a long time as the objects are big and there's (at least) one per each node in the cluster. Thus, in big clusters, the liveness probe kicks in and kills the nfd-master pod before it's ready.
46 lines
1 KiB
YAML
46 lines
1 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
labels:
|
|
app: nfd
|
|
name: nfd-master
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: nfd-master
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: nfd-master
|
|
spec:
|
|
serviceAccount: nfd-master
|
|
enableServiceLinks: false
|
|
tolerations: []
|
|
containers:
|
|
- name: nfd-master
|
|
image: gcr.io/k8s-staging-nfd/node-feature-discovery:master
|
|
imagePullPolicy: Always
|
|
resources:
|
|
limits:
|
|
cpu: 300m
|
|
memory: 4Gi
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
startupProbe:
|
|
grpc:
|
|
port: 8082
|
|
failureThreshold: 30
|
|
livenessProbe:
|
|
grpc:
|
|
port: 8082
|
|
readinessProbe:
|
|
grpc:
|
|
port: 8082
|
|
failureThreshold: 10
|
|
command:
|
|
- "nfd-master"
|
|
ports:
|
|
- name: metrics
|
|
containerPort: 8081
|