[{"id":"IL-0101","title":{"en":"After Google forced a GKE control plane upgrade to 1.33.2 at a deprecation deadline, no new node could initialise, so autoscaling and spot node replacement stopped for 15 hours","ko":"자동 업그레이드를 꺼 둔 GKE 클러스터의 컨트롤 플레인이 지원 종료 기한에 1.33.2 로 강제 업그레이드된 뒤 새 노드가 모두 초기화에 실패해, 오토스케일링과 스팟 노드 복구가 15시간 멈췄다."},"org":"Wealthy","org_slug":"wealthy","date":"2025-09-14","severity":"sev1","root_cause":"upgrade-breaking-change","url":"https://benchlet.com/incidentlib/app/cases/IL-0101","shared_components":["dns-resolver"]},{"id":"IL-0120","title":{"en":"A daily scheduled OS update restarted systemd-networkd on cloud-hosted GPU nodes, which conflicted with OpenAI's networking agent and removed all routes, cutting capacity for ChatGPT and the API","ko":"클라우드 GPU 서버의 정기 OS 업데이트가 systemd-networkd 를 재시작해 자체 네트워크 에이전트와 충돌했고, 많은 GPU 노드의 라우트가 모두 지워져 ChatGPT 와 API 의 오류율이 크게 올랐다."},"org":"OpenAI","org_slug":"openai","date":"2025-06-09","severity":"unknown","root_cause":"upgrade-breaking-change","url":"https://benchlet.com/incidentlib/app/cases/IL-0120","shared_components":["node-image"]},{"id":"IL-0079","title":{"en":"A GKE node auto-upgrade to an ubuntu_containerd image with a kernel regression left kube-proxy unable to apply its ip6tables rules, so load balancer health checks failed and several clusters lost all ingress traffic","ko":"GKE 노드가 새 ubuntu_containerd 이미지로 자동 업그레이드된 뒤 커널에서 kube-proxy 가 쓰는 iptables 확장이 빠져, 여러 GKE 클러스터의 인그레스 트래픽이 완전히 끊겼다."},"org":"Altinity","org_slug":"altinity","date":"2025-05-17","severity":"unknown","root_cause":"upgrade-breaking-change","url":"https://benchlet.com/incidentlib/app/cases/IL-0079","shared_components":["node-image"]},{"id":"IL-0198","title":{"en":"An automatic Ubuntu security update restarted systemd-networkd, which flushed the IP rules Cilium relied on and cut more than 60 percent of Datadog's Kubernetes nodes off the network across regions and cloud providers","ko":"systemd 보안 패치가 Ubuntu 22.04 노드의 systemd-networkd 를 재시작해 Cilium 이 넣은 IP 규칙을 지웠고, 여러 리전과 세 클라우드의 Kubernetes 노드가 한꺼번에 네트워크를 잃었다."},"org":"Datadog","org_slug":"datadog","date":"2023-03-08","severity":"unknown","root_cause":"upgrade-breaking-change","url":"https://benchlet.com/incidentlib/app/cases/IL-0198","shared_components":["node-image"]}]