Transit operators see API create and update calls become very slow…

Question

Transit operators see API create and update calls become very slow while read-mostly traffic still sometimes works. etcd disk latency alerts are firing. What is the best first interpretation?

Accepted Answer

etcd performance problems commonly surface as slow or failing API writes because the API server persists objects through etcd. — The API server stores the cluster's notebook in etcd—if that notebook's disk crawls, writing new pages feels stuck even when some reads still limp along. Fix etcd health and latency first.

Answer

Slow API writes always mean kube-proxy iptables rules need a full flush.

Answer

Disk latency in etcd only affects kubectl top and never object creates.

Answer

CNI VXLAN MTU mismatches uniquely cause etcd write latency alerts.

Transit operators see API create and update calls become very slow while read-mostly traffic still sometimes works. etcd disk latency alerts are firing. What is the best first interpretation?

Short Explanation

Full Explanation