Alert CRD

apiVersion: v1
kind: Secret
metadata:
  name: http-endpoint
  namespace: wave-autoscale
type: Opaque
stringData:
  url: "https://hooks.example.com/webhook"
---
apiVersion: v1
kind: Secret
metadata:
  name: http-headers
  namespace: wave-autoscale
type: Opaque
stringData:
  # Must be a JSON object string — key/value pairs of HTTP headers.
  headers: '{"Authorization":"Bearer <token>","Content-Type":"application/json"}'

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlertChannel
metadata:
  name: oncall-http
spec:
  http:
    urlSecretRef:
      name: http-endpoint
      key: url
    method: POST
    headersSecretRef:
      name: http-headers
      key: headers

apiVersion: v1
kind: Secret
metadata:
  name: slack-webhook-url
  namespace: wave-autoscale
type: Opaque
stringData:
  url: "https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXX"
---
apiVersion: wavek8s.com/v1alpha1
kind: WaveAlertChannel
metadata:
  name: oncall-slack-webhook
spec:
  slackWebhook:
    webhookUrlSecretRef:
      name: slack-webhook-url
      key: url

apiVersion: v1
kind: Secret
metadata:
  name: slack-bot-token
  namespace: wave-autoscale
type: Opaque
stringData:
  token: "xoxb-your-bot-token-here"
---
apiVersion: wavek8s.com/v1alpha1
kind: WaveAlertChannel
metadata:
  name: oncall-slack-webapi
spec:
  slackWebApi:
    tokenSecretRef:
      name: slack-bot-token
      key: token
    channel: "#alerts"

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlert
metadata:
  name: high-cpu-prod-api
spec:
  title: High CPU/memory on prod/api
  eventType: deployment_workload_metrics
  eventTargets:
    specific:
      - resourceType: Deployment
        namespace: prod
        name: api
  eventRuleExpression: "evaluation_period_minutes >= 1 && ( max(cpu_utilization_arr) >= 80 || avg(memory_utilization_arr) >= 80 )"
  eventRuleCheckIntervalMin: 5
  alertMessages:
    - channelRef: oncall-http
      message: "${namespace}/${workload_name} CPU/memory exceeded 80% over the evaluation window"

# Target all resources of a given type:
eventTargets:
  all:
    resourceType: Deployment
 
# Target specific named resources:
eventTargets:
  specific:
    - resourceType: Deployment
      namespace: prod
      name: api
 
# 대상이 없는(targetless) 이벤트 유형은 빈 specific 목록을 사용합니다:
eventTargets:
  specific: []

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlert
metadata:
  name: pods-stuck-pending
spec:
  title: Pending 5분 초과 Pod
  eventType: pending_pod_duration
  eventTargets:
    specific: []
  eventRuleExpression: "pending_duration_minutes >= 5"
  alertMessages:
    - channelRef: oncall-slack-webhook
      message: "Pod ${namespace}/${pod_name}이(가) ${pending_duration_minutes}분째 Pending 상태입니다"

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlert
metadata:
  name: crashloop-only
spec:
  title: CrashLoopBackOff
  eventType: pod_container_failure
  eventTargets:
    specific: []
  eventRuleExpression: "transition_type == 'CrashLoopBackOff'"
  alertMessages:
    - channelRef: oncall-slack-webhook
      message: "Pod ${namespace}/${pod_name}의 컨테이너 ${container_name} 장애 발생: ${transition_type}"

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlert
metadata:
  name: pvc-nearly-full
spec:
  title: PVC 사용량 80% 초과
  eventType: pv_usage
  eventTargets:
    all:
      resourceType: Pvc
  eventRuleExpression: "usage_percent >= 80 && minutes_since_last_alert >= 30"
  alertMessages:
    - channelRef: oncall-slack-webhook
      message: "PVC ${namespace}/${pvc_name} 사용량: ${usage_percent}%"

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlert
metadata:
  name: sizing-drift
spec:
  title: Smart Sizing 추천 20% 이상 차이
  eventType: smart_sizing_recommendation
  eventTargets:
    all:
      resourceType: Deployment
  eventRuleExpression: "cpu_request_delta_abs_percent >= 20 || memory_request_delta_abs_percent >= 20"
  alertMessages:
    - channelRef: oncall-slack-webhook
      message: "Smart Sizing - ${namespace}/${workload_name}/${container_name}: CPU ${current_cpu_request} -> ${recommended_cpu_request} cores, 메모리 ${current_memory_request} -> ${recommended_memory_request} MiB"

apiVersion: wavek8s.com/v1alpha1
kind: WaveAlert
metadata:
  name: oom-kill-risk
spec:
  title: OOM-kill 위험
  eventType: oom_kill_risk
  eventTargets:
    specific: []
  eventRuleExpression: "minutes_since_last_alert >= 10"
  alertMessages:
    - channelRef: oncall-slack-webhook
      message: "Pod ${namespace}/${pod_name}의 컨테이너 ${container_name} 메모리 ${utilization}% - OOM-kill 위험"