[{"id":"IL-0432","title":{"en":"AutoReserve notifications silently went unsent as Memorystore for Redis 3.2 rejected writes with OOM below its limit","ko":"Memorystore for Redis 가 메모리 단편화로 쓰기를 거부해 AutoReserve 예약 알림 일부가 조용히 빠졌다"},"org":"Hello Inc.","org_slug":"hello-inc","date":"2026-10-27","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0432","shared_components":["cache"]},{"id":"IL-0379","title":{"en":"InfluxDB Cloud queries in Azure West Europe slowed and timed out as storage pods fell behind and kept restarting","ko":"Azure West Europe 의 InfluxDB Cloud 에서 9월 27일부터 30일까지 쿼리가 느려지고 타임아웃됐다"},"org":"InfluxData","org_slug":"influxdata","date":"2026-09-27","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0379","shared_components":["database-replication"]},{"id":"IL-0290","title":{"en":"GitLab.com's Redis Sidekiq cluster ran out of memory and lost quorum, causing 500 errors and a 12 million job backlog","ko":"GitLab.com 의 Redis Sidekiq 클러스터에서 노드 여러 대가 메모리를 다 써 멈추고 쿼럼을 잃어, 웹과 Git 과 CI 전반에서 500 오류가 늘었다"},"org":"GitLab","org_slug":"gitlab","date":"2026-05-12","severity":"sev1","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0290","shared_components":["cache"]},{"id":"IL-0288","title":{"en":"ZooKeeperWait rose to thousands of seconds on three redundant ClickHouse instances, degrading a CDN77 data pipeline","ko":"CDN77 의 ClickHouse 데이터 파이프라인에서 이중화된 인스턴스 세 곳의 ZooKeeperWait 가 수천 초로 치솟아 복제가 한 시간 넘게 느려졌다"},"org":"CDN77","org_slug":"cdn77","date":"2026-03-09","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0288","shared_components":["database-replication"]},{"id":"IL-0305","title":{"en":"Replicas of one Intercom Vitess shard hit 100% CPU and fell up to 2.2 hours behind, serving stale inbox data","ko":"Intercom 의 PlanetScale 샤드 하나에서 복제본이 CPU 100% 로 주 데이터베이스를 따라가지 못해 받은편지함에 최대 2.2시간 전의 데이터가 보였다"},"org":"Intercom","org_slug":"intercom","date":"2026-01-27","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0305","shared_components":["database-replication"]},{"id":"IL-0581","title":{"en":"29CM product display servers lost pods and saturated Netty event loops on the first day of the Igu Week sale","ko":"이구위크 첫날 Redis 커넥션이 실패하며 29CM 상품 전시 서버의 파드가 다운되고 Netty 이벤트 루프가 포화됐다"},"org":"MUSINSA","org_slug":"musinsa","date":"2025-11-03","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0581","shared_components":["cache"]},{"id":"IL-0100","title":{"en":"PostHog's feature flags pods were packed onto Kubernetes nodes that were too small for their CPU requests, and CPU saturation above 90% caused three outages in ten days through Redis overload, connection pool exhaustion and slow queries","ko":"노드가 파드의 CPU 요청에 비해 작아 CPU 가 포화되면서 PostHog 기능 플래그 서비스에 열흘 사이 장애가 세 번 났다."},"org":"PostHog","org_slug":"posthog","date":"2025-10-21","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0100","shared_components":["cache"]},{"id":"IL-0067","title":{"en":"Redis filled its persistent volume, corrupted its append-only file and crash-looped on every restart","ko":"Redis 마스터의 50Mi 영구 볼륨이 가득 차 AOF 가 깨졌고, Redis 파드가 크래시 루프에 빠져 Klamm 운영 서비스가 멈췄다"},"org":"BC Government","org_slug":"bc-government","date":"2025-07-09","severity":"sev1","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0067","shared_components":["cache"]},{"id":"IL-0544","title":{"en":"Wasabi's database cache stopped responding when its queueing service filled up, and S3 failed in all regions","ko":"Wasabi 전 리전의 S3 와 사용자 서비스에 이틀에 걸쳐 세 차례 장애가 났다"},"org":"Wasabi","org_slug":"wasabi","date":"2024-08-06","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0544","shared_components":["cache"]},{"id":"IL-0202","title":{"en":"A burst of queries and database writes exhausted connection pools and memory on Honeycomb's ingest hosts, and Kubernetes crash-loop back-off kept failed hosts offline so ingest capacity stayed too low to recover","ko":"갑자기 몰린 쿼리와 데이터베이스 쓰기로 Honeycomb 수집 호스트가 메모리 부족으로 죽었고, 쿠버네티스 CrashLoopBackOff 가 용량 회복을 막아 US1 이벤트 수집이 한 시간 넘게 불안정했다"},"org":"Honeycomb","org_slug":"honeycomb","date":"2023-11-05","severity":"sev1","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0202","shared_components":["cache"]},{"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":["cache"]},{"id":"IL-0453","title":{"en":"Hakuna API latency spiked every day during the ElastiCache Redis backup as memory filled and the backup went forkless","ko":"하쿠나의 API latency 가 매일 ElastiCache Redis 백업 시간마다 치솟았다"},"org":"Hyperconnect","org_slug":"hyperconnect","date":"2022-12-12","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0453","shared_components":["cache"]},{"id":"IL-0212","title":{"en":"Many Slack users could not connect because a Vitess keyspace for channel membership was overloaded by cache-miss queries","ko":"캐시 적중률이 떨어지며 채널 멤버십 Vitess 키스페이스가 과부하에 빠져 많은 사용자가 Slack 에 접속하지 못했다"},"org":"Slack","org_slug":"slack","date":"2022-02-22","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0212","shared_components":["cache"]},{"id":"IL-0443","title":{"en":"A Repro Aurora MySQL reader restarted unexpectedly and writer insert latency rose about sevenfold for a day or more","ko":"Aurora MySQL reader 가 이유 없이 재시작한 뒤 writer 의 insert latency 가 7배쯤 오르고 replication lag 가 하루 넘게 이어졌다"},"org":"Repro","org_slug":"repro","date":"2019-11-11","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0443","shared_components":["database-replication"]},{"id":"IL-0297","title":{"en":"Mezmo users could not sign in and log indexing lagged after the auth cache's Redis servers were OOM killed","ko":"Mezmo 의 인증 캐시 Redis 서버가 OOM 으로 죽고 다시 뜨지 못해 로그인이 막히고 로그 색인이 늦어졌다"},"org":"Mezmo","org_slug":"mezmo","date":"2019-05-15","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0297","shared_components":["cache"]},{"id":"IL-0334","title":{"en":"Instapaper's RDS MySQL bookmarks table hit the 2TB ext3 file size limit, inserts failed and the service went down","ko":"RDS MySQL 의 bookmarks 테이블이 2TB 파일 크기 한도에 닿아 INSERT 가 실패하고 Instapaper 가 31시간 동안 멈췄다"},"org":"Instapaper","org_slug":"instapaper","date":"2017-02-09","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0334","shared_components":["database-replication"]},{"id":"IL-0520","title":{"en":"logs.cloud.gov trapped users in a login redirect loop because its full Redis session store stopped saving sessions","ko":"logs.cloud.gov 로그인이 리디렉션 루프에 빠지고 로그 검색 서비스가 하루 넘게 멈춤"},"org":"cloud.gov","org_slug":"cloud-gov","date":"2016-07-05","severity":"unknown","root_cause":"capacity","url":"https://benchlet.com/incidentlib/app/cases/IL-0520","shared_components":["cache"]}]