Infrastructure

Kubernetes · Network · Kafka · DB · Storage · 관측 파이프라인

Ready 노드

4/ 5

Pressure 1개

재시작 발생 서비스

1/ 8

확인 필요

총 Pod 배치

29/ 60

경고 이벤트

5건 (최근)

노드 상태 (시뮬레이션)

워커 노드별 CPU · Memory · Disk · Pod 배치

노드상태CPUMemoryDiskPod
worker-1Ready63%67%36%6 / 12
worker-2Pressure66%89%52%4 / 12
worker-3Ready62%64%69%6 / 12
worker-4Ready66%86%58%7 / 12
worker-5Ready72%72%71%6 / 12

Pod 상태 이벤트

Not Ready · Pending · CrashLoopBackOff · OOMKilled

  • FailedScheduling · Marathon Service0/5 nodes are available: insufficient cpu3분 전
  • OOMKilled · Crew ServiceContainer was OOMKilled, restarting11분 전
  • OOMKilled · Crew ServiceContainer was OOMKilled, restarting21분 전
  • OOMKilled · Marathon ServiceContainer was OOMKilled, restarting24분 전
  • ProbeFailed · Course Recommendation AIReadiness probe failed: HTTP 50328분 전