github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2026-01-24 22:14:35 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #126287 from devppratik/121793-update-node-monitor-grace-period

Browse Source 
node: Update Node Monitor Grace Period default duration to 50s
This commit is contained in:
Kubernetes Prow Robot
2024-08-13 21:03:16 -07:00
committed by GitHub
parent cc4ed1d3fa f8bf6b97b8
commit bb7411120a
7 changed files with 19 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
cmd/kube-controller-manager/app/options/nodelifecyclecontroller.go
View File

@@ -41,7 +41,8 @@ func (o *NodeLifecycleControllerOptions) AddFlags(fs *pflag.FlagSet) {
fs.DurationVar(&o.NodeMonitorGracePeriod.Duration, "node-monitor-grace-period", o.NodeMonitorGracePeriod.Duration,
"Amount of time which we allow running Node to be unresponsive before marking it unhealthy. "+
"Must be N times more than kubelet's nodeStatusUpdateFrequency, "+
"where N means number of retries allowed for kubelet to post node status.")
"where N means number of retries allowed for kubelet to post node status. "+
"This value should also be greater than the sum of HTTP2_PING_TIMEOUT_SECONDS and HTTP2_READ_IDLE_TIMEOUT_SECONDS")
fs.Float32Var(&o.NodeEvictionRate, "node-eviction-rate", 0.1, "Number of nodes per second on which pods are deleted in case of node failure when a zone is healthy (see --unhealthy-zone-threshold for definition of healthy/unhealthy). Zone refers to entire cluster in non-multizone clusters.")
fs.Float32Var(&o.SecondaryNodeEvictionRate, "secondary-node-eviction-rate", 0.01, "Number of nodes per second on which pods are deleted in case of node failure when a zone is unhealthy (see --unhealthy-zone-threshold for definition of healthy/unhealthy). Zone refers to entire cluster in non-multizone clusters. This value is implicitly overridden to 0 if the cluster size is smaller than --large-cluster-size-threshold.")
fs.Int32Var(&o.LargeClusterSizeThreshold, "large-cluster-size-threshold", 50, fmt.Sprintf("Number of nodes from which %s treats the cluster as large for the eviction logic purposes. --secondary-node-eviction-rate is implicitly overridden to 0 for clusters this size or smaller. Notice: If nodes reside in multiple zones, this threshold will be considered as zone node size threshold for each zone to determine node eviction rate independently.", names.NodeLifecycleController))