[{"id":"IL-0039","title":{"en":"New Kubernetes worker nodes could not join any cluster because a package URL hardcoded in kops nodeup broke","ko":"CentOS 저장소 재구성으로 kops nodeup 에 하드코딩된 container-selinux 패키지 주소가 깨져 새 워커 노드가 클러스터에 합류하지 못했다"},"org":"FREE NOW","org_slug":"free-now","date":"2019-09-19","severity":"unknown","root_cause":"dependency-failure","url":"https://benchlet.com/incidentlib/app/cases/IL-0039","shared_components":["node-image","node-pool"]},{"id":"IL-0103","title":{"en":"During an EKS node AMI update, Istio sidecars crash-looped because hundreds of pods restarting at once overloaded the external certificate authority behind istiod","ko":"EKS 노드 AMI 업데이트로 파드가 한꺼번에 다시 뜨자 인증서 요청이 몰린 외부 CA 가 과부하에 걸려 Istio 사이드카가 CrashLoopBackOff 에 빠졌다."},"org":"Tetrate (unnamed U.S. federal customer)","org_slug":"tetrate-unnamed-u-s-federal-customer","date":"2025-02-26","severity":"sev1","root_cause":"dependency-failure","url":"https://benchlet.com/incidentlib/app/cases/IL-0103","shared_components":["node-image"]},{"id":"IL-0025","title":{"en":"Failed boots, InfiniBand link flapping, NCCL hangs and throughput sags while bringing up a 4,088-GPU H100 training cluster","ko":"H100 4,088개 클러스터를 구축하는 동안 InfiniBand 배선 오류, 링크 플래핑, GPU 와 PCIe 하드웨어 결함이 학습을 멈추거나 늦췄다"},"org":"Imbue","org_slug":"imbue","date":"2024-06-25","severity":"unknown","root_cause":"dependency-failure","url":"https://benchlet.com/incidentlib/app/cases/IL-0025","shared_components":["gpu-driver"]}]