Alerts

alert: POD_CPU_IS_HIGH
expr: sum by(container, pod, namespace) (rate(container_cpu_usage_seconds_total{container!=""}[5m])) * 100 > 90
for: 1m
labels:
  severity: critical
annotations:
  description: Container {{ $labels.container }} CPU usage inside POD {{ $labels.pod}} is high in {{ $labels.namespace}}
  summary: POD {{ $labels.pod}} CPU Usage is high in {{ $labels.namespace}}

alert: POD_MEMORY_USAGE_IS_HIGH
expr: (sum by(container, pod, namespace) (container_memory_working_set_bytes{container!=""}) / sum by(container, pod, namespace) (container_spec_memory_limit_bytes > 0) * 100) > 80
for: 1m
labels:
  severity: critical
annotations:
  description: |-
    Container Memory usage is above 80%
      VALUE = {{ $value }}
      LABELS = {{ $labels }}
  summary: Container {{ $labels.container }} Memory usage inside POD {{ $labels.pod}} is high in {{ $labels.namespace}}

alert: NODE_CPU_IS_HIGH
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90
for: 1m
labels:
  severity: critical
annotations:
  description: node {{ $labels.kubernetes_node }} cpu is high
  summary: node cpu is greater than 80 precent

alert: NODE_DISK_SPACE_IS_LOW
expr: (100 * ((node_filesystem_avail_bytes{fstype!="rootfs",mountpoint="/"}) / (node_filesystem_size_bytes{fstype!="rootfs",mountpoint="/"}))) < 10
for: 1m
labels:
  severity: critical
annotations:
  description: node {{ $labels.node }} disk space is only {{ printf "%0.2f" $value }}% free.
  summary: node disk space remaining is less than 10 percent

alert: NODE_DOWN
expr: up{component="node-exporter"} == 0
for: 3m
labels:
  severity: warning
annotations:
  description: '{{ $labels.job }} job failed to scrape instance {{ $labels.instance }} for more than 3 minutes. Node Seems to be down'
  summary: Node {{ $labels.kubernetes_node }} is down

alert: NODE_MEMORY_LESS_THAN_10%
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 1m
labels:
  severity: critical
annotations:
  description: node {{ $labels.kubernetes_node }} memory left is low
  summary: node memory left is lesser than 10 precent

alert: front50:storageServiceSupport:cacheAge__value
expr: front50:storageServiceSupport:cacheAge__value > 300000
for: 2m
labels:
  severity: warning
annotations:
  description: front50 cacheAge for {{$labels.pod}} in namespace {{$labels.namespace}} has value = {{$value}}
  summary: front50 cacheAge too high

alert: jvm-memory-filling-up-for-oes-audit-client
expr: (sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_used_bytes{app="oes",area="heap",component="auditclient"}) / sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_max_bytes{app="oes",area="heap",component="auditclient"})) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    JVM memory is filling up for {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }} (> 80%)
      VALUE = {{ $value }}
  summary: JVM memory filling up for {{ $labels.component }} for pod {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }})

alert: jvm-memory-filling-up-for-oes-autopilot
expr: (sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_used_bytes{app="oes",area="heap",component="autopilot"}) / sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_max_bytes{app="oes",area="heap",component="autopilot"})) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    JVM memory is filling up for {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }} (> 80%)
      VALUE = {{ $value }}
  summary: JVM memory filling up for {{ $labels.component }} for pod {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }})

alert: jvm-memory-filling-up-for-oes-dashboard
expr: (sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_used_bytes{app="oes",area="heap",component="dashboard"}) / sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_max_bytes{app="oes",area="heap",component="autopilot"})) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    JVM memory is filling up for {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }} (> 80%)
      VALUE = {{ $value }}
  summary: JVM memory filling up for {{ $labels.component }} for pod {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }})

alert: jvm-memory-filling-up-for-oes-platform
expr: (sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_used_bytes{app="oes",area="heap",component="platform"}) / sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_max_bytes{app="oes",area="heap",component="platform"})) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    JVM memory is filling up for {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }} (> 80%)
      VALUE = {{ $value }}
  summary: JVM memory filling up for {{ $labels.component }} for pod {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }})

alert: jvm-memory-filling-up-for-oes-sapor
expr: (sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_used_bytes{app="oes",area="heap",component="sapor"}) / sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_max_bytes{app="oes",area="heap",component="sapor"})) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    JVM memory is filling up for {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }} (> 80%)
      VALUE = {{ $value }}
  summary: JVM memory filling up for {{ $labels.component }} for pod {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }})

alert: jvm-memory-filling-up-for-oes-visibility
expr: (sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_used_bytes{app="oes",area="heap",component="visibility"}) / sum by(instance, kubernetes_pod_name, component, kubernetes_namespace) (jvm_memory_max_bytes{app="oes",area="heap",component="visibility"})) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: |-
    JVM memory is filling up for {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }} (> 80%)
      VALUE = {{ $value }}
  summary: JVM memory filling up for {{ $labels.component }} for pod {{ $labels.kubernetes_pod_name }} in namespace {{ $labels.kubernetes_namespace }})

alert: oes-audit-client-latency-too-high
expr: sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_sum{component="auditclient"}[2m])) / sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_count{component="auditclient"}[2m])) > 0.5
for: 2m
labels:
  severity: warning
annotations:
  description: Latency of the component {{ $labels.component }} is {{ $value }} seconds for {{ $labels }}
  summary: Latency of the component {{ $labels.component }} in namespace {{$labels.kubernetes_namespace}} is high

alert: oes-autopilot-latency-too-high
expr: sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_sum{component="autopilot"}[2m])) / sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_count{component="autopilot"}[2m])) > 0.5
for: 2m
labels:
  severity: warning
annotations:
  description: Latency of the component {{ $labels.component }} is {{ $value }} seconds for {{ $labels }}
  summary: Latency of the component {{ $labels.component }} in namespace {{$labels.kubernetes_namespace}} is high

alert: oes-dashboard-latency-too-high
expr: sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_sum{component="dashboard"}[2m])) / sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_count{component="dashboard"}[2m])) > 0.5
for: 2m
labels:
  severity: warning
annotations:
  description: Latency of the component {{ $labels.component }} is {{ $value }} seconds for {{ $labels }}
  summary: Latency of the component {{ $labels.component }} in namespace {{$labels.kubernetes_namespace}} is high

alert: oes-platform-latency-too-high
expr: sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_sum{component="platform"}[2m])) / sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_count{component="platform"}[2m])) > 0.5
for: 2m
labels:
  severity: warning
annotations:
  description: Latency of the component {{ $labels.component }} is {{ $value }} seconds for {{ $labels }}
  summary: Latency of the component {{ $labels.component }} in namespace {{$labels.kubernetes_namespace}} is high

alert: oes-sapor-latency-too-high
expr: sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_sum{component="sapor"}[2m])) / sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_count{component="sapor"}[2m])) > 0.5
for: 2m
labels:
  severity: warning
annotations:
  description: Latency of the component {{ $labels.component }} is {{ $value }} seconds for {{ $labels }}
  summary: Latency of the component {{ $labels.component }} in namespace {{$labels.kubernetes_namespace}} is high

alert: oes-visibility-latency-too-high
expr: sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_sum{component="visibility"}[2m])) / sum by(kubernetes_pod_name, method, outcome, status, component, kubernetes_namespace, uri) (rate(http_server_requests_seconds_count{component="visibility"}[2m])) > 0.5
for: 2m
labels:
  severity: warning
annotations:
  description: Latency of the component {{ $labels.component }} is {{ $value }} seconds for {{ $labels }}
  summary: Latency of the component {{ $labels.component }} in namespace {{$labels.kubernetes_namespace}} is high

alert: oes-audit-client-scrape-target-is-down
expr: up{component="auditclient"} == 0
labels:
  severity: critical
annotations:
  description: The scrape target endpoint of component {{$labels.component}} in namespace {{$labels.kubernetes_namespace}} is down
  summary: oes-audit-client scrape target is down

alert: oes-autopilot-scrape-target-is-down
expr: up{component="autopilot"} == 0
labels:
  severity: critical
annotations:
  description: The scrape target endpoint of component {{$labels.component}} in namespace {{$labels.kubernetes_namespace}} is down
  summary: oes-autopilot scrape target is down

alert: oes-dashboard-scrape-target-is-down
expr: up{component="dashboard"} == 0
labels:
  severity: critical
annotations:
  description: The scrape target endpoint of component {{$labels.component}} in namespace {{$labels.kubernetes_namespace}} is down
  summary: oes-dashboard scrape target is down

alert: oes-platform-scrape-target-is-down
expr: up{component="platform"} == 0
labels:
  severity: critical
annotations:
  description: The scrape target endpoint of component {{$labels.component}} in namespace {{$labels.kubernetes_namespace}} is down
  summary: oes-platform scrape target is down

alert: oes-sapor-scrape-target-is-down
expr: up{component="sapor"} == 0
labels:
  severity: critical
annotations:
  description: The scrape target endpoint of component {{$labels.component}} in namespace {{$labels.kubernetes_namespace}} is down
  summary: oes-sapor scrape target is down

alert: oes-visibility-scrape-target-is-down
expr: up{component="visibility"} == 0
labels:
  severity: critical
annotations:
  description: The scrape target endpoint of component {{$labels.component}} in namespace {{$labels.kubernetes_namespace}} is down
  summary: oes-visibility scrape target is down

alert: igor-needs-attention
expr: igor:pollingMonitor:itemsOverThreshold__value > 0
labels:
  severity: crtical
annotations:
  description: Igor in namespace {{$labels.namespace}} needs human help
  summary: Igor needs attention

alert: clouddriver-caching-pod-may-be-evicted-soon
expr: (sum by(instance, area) (clouddriver_caching:jvm:memory:used__value) / sum by(instance, area) (clouddriver_caching:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: Clouddriver-caching JVM memory too high

alert: clouddriver-ro-pod-may-be-evicted-soon
expr: (sum by(instance, area) (clouddriver_ro:jvm:memory:used__value) / sum by(instance, area) (clouddriver_ro:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: Clouddriver-ro JVM memory too high

alert: clouddriver-rw-pod-may-be-evicted-soon
expr: (sum by(instance, area) (clouddriver_rw:jvm:memory:used__value) / sum by(instance, area) (clouddriver_rw:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: Clouddriver-rw JVM memory too high

alert: echo-scheduler-pod-may-be-evicted-soon
expr: (sum by(instance, area) (echo_scheduler:jvm:memory:used__value) / sum by(instance, area) (echo_scheduler:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: echo-scheduler JVM memory too high

alert: echo-worker-pod-may-be-evicted-soon
expr: (sum by(instance, area) (echo_worker:jvm:memory:used__value) / sum by(instance, area) (echo_worker:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: echo-worker JVM memory too high

alert: front50-pod-may-be-evicted-soon
expr: (sum by(instance, area) (front50:jvm:memory:used__value) / sum by(instance, area) (front50:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: Front50 JVM memory too high

alert: gate-pod-may-be-evicted-soon
expr: (sum by(instance, area) (gate:jvm:memory:used__value) / sum by(instance, area) (gate:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: gate JVM memory too high

alert: igor-pod-may-be-evicted-soon
expr: (sum by(instance, area) (igor:jvm:memory:used__value) / sum by(instance, area) (igor:jvm:memory:max__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: igor JVM memory too high

alert: orca-pod-may-be-evicted-soon
expr: (sum by(instance, area) (orca:jvm:gc:liveDataSize__value) / sum by(instance, area) (orca:jvm:gc:maxDataSize__value)) > 0.9
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: orca JVM memory too high

alert: kube-api-server-down
expr: up{job="kubernetes-apiservers"} == 0
for: 2m
labels:
  severity: critical
annotations:
  description: Kubernetes API Server service went down LABELS = {{ $labels }}
  summary: Kube API Server job {{ $labels.job }} is down

alert: kube-api-server-errors
expr: sum(rate(apiserver_request_total{code=~"^(?:5..)$",job="kubernetes-apiservers"}[2m])) / sum(rate(apiserver_request_total{job="kubernetes-apiservers"}[2m])) * 100 > 3
for: 2m
labels:
  severity: critical
annotations:
  description: |-
    Kubernetes API server is experiencing high error rate
      VALUE = {{ $value }}
      LABELS = {{ $labels }}
  summary: Kubernetes API server errors (instance {{ $labels.instance }})

alert: clouddriver-caching-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_caching:controller:invocations__total{service="spin-clouddriver-caching"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_caching:controller:invocations__count_total{service="spin-clouddriver-caching"}[5m])) > 5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: clouddriver-ro-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_ro:controller:invocations__total{service="spin-clouddriver-ro"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_ro:controller:invocations__count_total{service="spin-clouddriver-ro"}[5m])) > 1
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: clouddriver-rw-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_rw:controller:invocations__total{service="spin-clouddriver-rw"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_rw:controller:invocations__count_total{service="spin-clouddriver-rw"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is ({{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: clouddriver_ro_deck-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_ro_deck:controller:invocations__total{service="spin-clouddriver-ro-deck"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(clouddriver_ro_deck:controller:invocations__total{service="spin-clouddriver-ro-deck"}[5m])) > 5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: echo_scheduler-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(echo_scheduler:controller:invocations__total{service="spin-echo-scheduler"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(echo_scheduler:controller:invocations__count_total{service="spin-echo-scheduler"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: echo_worker-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(echo_worker:controller:invocations__total{service="spin-echo-worker"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(echo_worker:controller:invocations__count_total{service="spin-echo-worker"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: fiat-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(fiat:controller:invocations__total{service="spin-fiat"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(fiat:controller:invocations__count_total{service="spin-fiat"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: front50-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(front50:controller:invocations__total{service="spin-front50"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(front50:controller:invocations__count_total{service="spin-front50"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: gate-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(gate:controller:invocations__total{service="spin-gate"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(gate:controller:invocations__count_total{service="spin-gate"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: igor-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(igor:controller:invocations__total{service="spin-igor"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(igor:controller:invocations__count_total{service="spin-igor"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: orca-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(orca:controller:invocations__total{service="spin-orca"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(orca:controller:invocations__count_total{service="spin-orca"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: rosco-latency-too-high
expr: sum by(controller, instance, method, success, statusCode, service, namespace) (rate(rosco:controller:invocations__total{service="spin-rosco"}[5m])) / sum by(controller, instance, method, success, statusCode, service, namespace) (rate(rosco:controller:invocations__count_total{service="spin-rosco"}[5m])) > 0.5
for: 15m
labels:
  severity: warning
annotations:
  description: Latency of the Service {{$labels.service}} is {{$value}} seconds for {{ $labels }}
  summary: Latency of the service {{ $labels.service }} in namespace {{$labels.namespace}} is high

alert: orca-queue-depth-high
expr: (sum by(instance) (orca:queue:ready:depth__value{namespace!=""})) > 10
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} may be evicted soon
  summary: Orca queue depth is high

alert: orca-queue-lag-high
expr: sum by(instance, service, namespace) (rate(orca:controller:invocations__total[2m])) / sum by(instance, service, namespace) (rate(orca:controller:invocations__count_total[2m])) > 0.5
labels:
  severity: warning
annotations:
  description: Service {{$labels.service}} in namespace {{$labels.namespace}} has Lag value of {{$value}}
  summary: Orca queue lag is high

alert: prometheus-job-is-down
expr: up{job="prometheus"} == 0
for: 5m
labels:
  severity: warning
annotations:
  description: Default Prometheus Job is Down LABELS = {{ $labels }}
  summary: The Default Prometheus Job is Down (job {{ $labels.job}})

alert: clouddriver-caching-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-clouddriver-caching"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Clouddriver-caching Spinnaker service is down

alert: clouddriver-ro-deck-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-clouddriver-ro-deck"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Clouddriver-ro-deck Spinnaker service is down

alert: clouddriver-ro-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-clouddriver-ro"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Clouddriver-ro Spinnaker service is down

alert: clouddriver-rw-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-clouddriver-rw"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Clouddriver-rw Spinnaker service is down

alert: echo-scheduler-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-echo-scheduler"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Echo-Scheduler Spinnaker service is down

alert: echo-worker-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-echo-worker"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Echo-worker Spinnaker service is down

alert: fiat-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-fiat"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Fiat Spinnaker service is down

alert: front50-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-front50"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Front50 Spinnaker service is down

alert: gate-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-gate"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Gate Spinnaker services is down

alert: igor-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-igor"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Igor Spinnaker service is down

alert: orca-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-orca"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Orca Spinnaker service is down

alert: rosco-is-down
expr: up{job="opsmx_spinnaker_metrics",service="spin-rosco"} == 0
labels:
  severity: critical
annotations:
  description: Service {{$labels.service}} with pod name {{$labels.pod}} in namespace {{$labels.namespace}} is not responding
  summary: Rosco Spinnaker service is down

alert: pvc-storage-full
expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
for: 2m
labels:
  severity: warning
annotations:
  description: |-
    Volume is almost full (< 10% left)
      VALUE = {{ $value }}
      LABELS = {{ $labels }}
  summary: Kubernetes Volume running out of disk space for (persistentvolumeclaim {{ $labels.persistentvolumeclaim }} in namespace {{$labels.namespace}})