[{"id":"IL-0194","title":{"en":"After a kube-apiserver restart, pod LIST requests from every pod of a Vector DaemonSet nearly tripled etcd memory and restarted all master nodes","ko":"kube-apiserver 재시작 뒤 Vector DaemonSet 의 파드 list 요청이 한꺼번에 몰려 etcd 메모리가 세 배 가까이 늘고 마스터 노드가 연쇄적으로 재시작했다."},"org":"Palark","org_slug":"palark","date":"2023-03-23","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0194","shared_components":["kube-apiserver","telemetry-agent","etcd"]},{"id":"IL-0204","title":{"en":"An etcd memory spike overloaded the control plane of a Render Frankfurt cluster, and DNS then failed because CoreDNS ran on the rebooted control plane nodes and could not start without the API server","ko":"Render 프랑크푸르트 클러스터에서 etcd 메모리 급증으로 컨트롤 플레인이 과부하에 걸렸고, 컨트롤 플레인 노드를 재부팅하자 그 위의 CoreDNS 가 다시 뜨지 못해 DNS 가 멈췄다."},"org":"Render","org_slug":"render","date":"2024-12-17","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0204","shared_components":["kube-apiserver","etcd"]},{"id":"IL-0076","title":{"en":"Kubernetes masters went down after Dex filled etcd with AuthRequest objects and deleting its namespace started an endless list-and-timeout loop","ko":"dex의 AuthRequest 리소스가 끝없이 쌓였고, 이를 치우려고 네임스페이스를 지우자 목록 조회 타임아웃과 재시도가 반복되며 쿠버네티스 마스터가 내려갔다"},"org":"Fullstaq","org_slug":"fullstaq","date":"2019-06-01","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0076","shared_components":["kube-apiserver","etcd"]},{"id":"IL-0042","title":{"en":"Application logs stopped reaching Elasticsearch and OpenSearch for hours and were lost when OpenSearch ran out of disk space","ko":"OpenSearch 디스크가 가득 찬 동안 fluent-bit 가 로그를 처리하지 못해 Elasticsearch 와 OpenSearch 에 애플리케이션 로그가 들어오지 않았다."},"org":"UK Ministry of Justice","org_slug":"uk-ministry-of-justice","date":"2024-07-25","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0042","shared_components":["telemetry-agent"]},{"id":"IL-0110","title":{"en":"A Grafana Agent pod's high memory use and crash-looping Hangfire pods drove a Kubernetes node into system OOM and NotReady, twice in one day","ko":"Grafana Agent 파드가 메모리를 많이 쓰던 노드에 Hangfire 파드가 함께 올라가 시스템 OOM 으로 CrashLoopBackOff 를 반복했고, 노드가 응답을 멈추고 NotReady 가 됐다."},"org":"DFDS","org_slug":"dfds","date":"2024-03-13","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0110","shared_components":["telemetry-agent"]},{"id":"IL-0168","title":{"en":"Simultaneous cluster auto-upgrades overloaded Scaleway's Kubernetes API, and a node authentication retry loop kept Kapsule and Kosmos nodes NotReady in FR-PAR","ko":"새 쿠버네티스 릴리스 뒤 많은 Kapsule 클러스터가 동시에 자동 업그레이드되면서 Kubernetes API 가 과부하로 OOM 이 났고, 새 노드 인증 방식의 재시도가 혼잡을 키워 노드가 Not Ready 가 됐다."},"org":"Scaleway","org_slug":"scaleway","date":"2024-02-13","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0168","shared_components":["kube-apiserver"]},{"id":"IL-0043","title":{"en":"Application logs missing in Kibana after a newer Fluent Bit version changed its chunk drop strategy","ko":"새 버전 fluent-bit에서 청크를 버리는 방식이 바뀌어 Kibana의 애플리케이션 로그에 긴 공백이 생겼다"},"org":"UK Ministry of Justice","org_slug":"uk-ministry-of-justice","date":"2023-08-04","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0043","shared_components":["telemetry-agent"]},{"id":"IL-0195","title":{"en":"The kube-apiservers of a cluster with more than 200 nodes ran out of memory and crashed one after another under mass LIST requests from Cilium agents","ko":"200개가 넘는 노드의 고객 클러스터에서 Cilium 파드가 LIST 요청을 한꺼번에 쏟아내 kube-apiserver 가 메모리를 다 쓰고 죽기를 되풀이했다."},"org":"Palark","org_slug":"palark","date":"2023-06-07","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0195","shared_components":["kube-apiserver"]},{"id":"IL-0165","title":{"en":"Some LKE users in Frankfurt could not reach their kube-apiservers with kubectl after backend services failed under memory constraints","ko":"프랑크푸르트 LKE 의 백엔드 서비스가 메모리 부족으로 실패해 일부 사용자가 kubectl 로 kube-apiserver 에 접속하지 못했다"},"org":"Linode","org_slug":"linode","date":"2023-05-25","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0165","shared_components":["kube-apiserver"]},{"id":"IL-0026","title":{"en":"Kubernetes nodes hit SystemOOM because fluentd-sumologic log shipper pods had no memory limits","ko":"메모리 제한이 없는 fluentd-sumologic 파드가 메모리를 다 써서 운영 쿠버네티스 노드 두 대에 이틀 연속 SystemOOM 이 났다"},"org":"Blue Matador","org_slug":"blue-matador","date":"2019-06-15","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0026","shared_components":["telemetry-agent"]},{"id":"IL-0002","title":{"en":"CI builder pods could not get AWS IAM credentials because kubelet fell minutes behind its API rate limit","ko":"빌더 파드가 노드 한 대에 몰리자 kubelet 이 기본 API QPS 한도에 막혀 파드 상태를 늦게 갱신했고, CI 빌드가 AWS IAM 자격 증명을 받지 못해 실패했다"},"org":"Zalando","org_slug":"zalando","date":"2019-06-11","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0002","shared_components":["kube-apiserver"]},{"id":"IL-0031","title":{"en":"Kubernetes API server OOM-killed, leaving the Skipper ingress without routes; the talk points to a misconfigured CronJob manifest","ko":"API 서버가 OOMKill로 죽자 Skipper 인그레스가 라우트를 잃었고, 고객 트래픽이 끊기며 IAM 서비스에서 404 오류가 났다"},"org":"Zalando","org_slug":"zalando","date":"2018-12-05","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0031","shared_components":["kube-apiserver"]}]