How to fix Flannel No Subnet Available in Kubernetes

# Check pod CIDR in cluster config:
kubectl cluster-info dump | grep -i "pod-network-cidr"

# View subnet allocations for each node:
kubectl get nodes -o jsonpath='{.items[*].spec.podCIDR}'

# Or more detailed:
kubectl get nodes -o json | jq '.items[] | {name: .metadata.name, podCIDR: .spec.podCIDR}'

# Check Flannel subnet data in etcd:
kubectl exec -it <etcd-pod> -n kube-system -- etcdctl get --prefix /coreos.com/network/subnets

# View Flannel config:
kubectl get cm kube-flannel-cfg -n kube-flannel -o yaml

# Extract Network:
kubectl get cm kube-flannel-cfg -n kube-flannel -o jsonpath='{.data.net-conf\.json}' | jq .Network

# Expected output: "10.244.0.0/16" or similar

# Also check SubnetLen (subnet size, default /24):
kubectl get cm kube-flannel-cfg -n kube-flannel -o jsonpath='{.data.net-conf\.json}' | jq .SubnetLen

# Count nodes:
kUBECTL_NODES=$(kubectl get nodes --no-headers | wc -l)
echo "Total nodes: $KUBECTL_NODES"

# Get pod CIDR:
POD_CIDR=$(kubectl cluster-info dump | grep "pod-network-cidr" | head -1 | cut -d= -f2)
echo "Pod CIDR: $POD_CIDR"

# For /16 with /24 subnets: 256 subnets max
# For /16 with /25 subnets: 512 subnets max

# If KUBECTL_NODES > 256, you need a larger CIDR or smaller subnets
if [ $KUBECTL_NODES -gt 256 ]; then
  echo "ERROR: Cluster has more than 256 nodes but using /16 CIDR with /24 subnets"
fi

# Get all allocated subnets from etcd:
kubectl exec -it <etcd-pod> -n kube-system -- etcdctl get --prefix /coreos.com/network/subnets | less

# Get existing nodes:
kubectl get nodes -o jsonpath='{.items[*].metadata.name}'

# Compare: if etcd has subnets for nodes that don't exist, they're stale

# Manually delete stale allocations (dangerous—do with caution):
kubectl exec <etcd-pod> -n kube-system -- etcdctl del /coreos.com/network/subnets/<stale-key>

# When creating cluster, use /14 instead of /16:
kubeadm init --pod-network-cidr=10.244.0.0/14  # 4x larger (1024 subnets with /24)

# Use smaller subnets (/25 = 512 subnets per /16):
kubectl patch cm kube-flannel-cfg -n kube-flannel -p '{"data":{"net-conf.json":"...SubnetLen: 25..."}}'

# Find nodes in NotReady state:
kubectl get nodes

# Drain pod before deletion:
kubectl drain <node-name> --ignore-daemonsets --delete-emptydir-data

# Delete the node:
kubectl delete node <node-name>

# Verify:
kubectl get nodes

# Restart the Flannel DaemonSet:
kubectl rollout restart daemonset/kube-flannel -n kube-flannel

# Watch for pod restarts:
kubectl get pods -n kube-flannel -w

# Check logs:
kubectl logs -n kube-flannel -l app=flannel -f

# Monitor node pod CIDR assignment:
watch kubectl get nodes -o wide

# Create Prometheus alert:
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: flannel-alerts
spec:
  groups:
  - name: flannel
    rules:
    - alert: FlannelSubnetExhaustion
      expr: |
        count(kube_node_labels{label_kubernetes_io_os="linux"}) > 240
      annotations:
        summary: "Approaching Flannel subnet limit (240+ nodes)"