[{"id":"IL-0312","title":{"en":"Gadget's main Postgres did not start again after a restart to raise max_connections, and the platform went down","ko":"max_connections 를 올리려고 재시작한 주 PostgreSQL 데이터베이스가 다시 올라오지 않아 Gadget 의 모든 앱 요청이 멈췄다"},"org":"Gadget","org_slug":"gadget","date":"2024-12-13","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0312","shared_components":["linux-kernel"]},{"id":"IL-0440","title":{"en":"Pods on Cybozu's Neco Kubernetes platform got frequent no such host and i/o timeout DNS errors from dropped packets","ko":"파드가 보낸 DNS 쿼리 패킷이 노드에서 버려져 클러스터 내부 서비스의 이름 조회가 no such host 와 i/o timeout 으로 자주 실패했다"},"org":"Cybozu","org_slug":"cybozu","date":"2024-08-20","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0440","shared_components":["linux-kernel"]},{"id":"IL-0386","title":{"en":"After a move to Google Cloud, Postgres connection timeouts and memcached i/o timeouts spiked on GKE nodes","ko":"Google Cloud 로 옮긴 뒤 GKE 노드에서 Postgres 연결 타임아웃과 memcached i/o timeout 이 간헐적으로 튀었다"},"org":"incident.io","org_slug":"incident-io","date":"2023-09-26","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0386","shared_components":["cni-plugin"]},{"id":"IL-0176","title":{"en":"Prometheus in a 235-node Kubernetes cluster crash-looped because over two million series exhausted host memory and the kernel OOM killer chose it first, as Burstable QoS gave it oom_score_adj 999","ko":"시계열 급증으로 호스트 메모리가 바닥나자 oom_score_adj 999 를 받은 Prometheus 컨테이너가 커널 OOM Killer 에게 먼저 죽어 CrashLoopBackOff 에 빠졌다."},"org":"LINE","org_slug":"line","date":"2020-07-10","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0176","shared_components":["linux-kernel"]},{"id":"IL-0578","title":{"en":"Static content behind an HAProxy load balancer in an OpenStack Octavia amphora was delayed by tens of seconds","ko":"HAProxy 로드 밸런서를 거치는 정적 콘텐츠 전송이 수십 초씩 늦어졌다"},"org":"GMO Pepabo","org_slug":"gmo-pepabo","date":"2020-06-26","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0578","shared_components":["linux-kernel"]},{"id":"IL-0064","title":{"en":"CPU-heavy pods packed onto one Google Cloud node drove it to kernel panics, and the crash moved from node to node until the site was down","ko":"CPU 를 많이 쓰는 파드가 Google Cloud 노드 하나에 몰려 노드가 커널 패닉으로 죽었고, 다시 배치된 파드가 다음 노드를 또 죽이며 웹사이트와 API 가 멈췄다."},"org":"Moonlight","org_slug":"moonlight","date":"2019-01-18","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0064","shared_components":["linux-kernel"]}]