gitadmin/devops-infra-helm-charts-gcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added repo

Browse Source
This commit is contained in:
Your Name
2026-08-26 03:39:42 +05:30
parent 45c25a95af
commit b8575bb8b9
6889 changed files with 1217125 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-fulfilment-service-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-gateway-fulfilment-service_prd-gateway-fulfilment-service_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-fulfilment-service
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-fulfilment-service-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-gateway-fulfilment-service_prd-gateway-fulfilment-service_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-fulfilment-service
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-fulfilment-service-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-gateway-fulfilment-service_prd-gateway-fulfilment-service_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-fulfilment-service
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-service-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-gateway-service_prd-gateway-service_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-service
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-service-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-gateway-service_prd-gateway-service_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-service
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-service-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-gateway-service_prd-gateway-service_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1500
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-service
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-service-clevertap-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-gateway-service-clevertap_prd-gateway-service-clevertap_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-service-clevertap
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-service-clevertap-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-gateway-service-clevertap_prd-gateway-service-clevertap_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-service-clevertap
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/gateway-service-clevertap-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-gateway-service-clevertap_prd-gateway-service-clevertap_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 400
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: gateway-service-clevertap
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-fallback/custom_alerts/manifest-fallback-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-fallback_prd-manifest-fallback_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 15
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-fallback
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-fallback/custom_alerts/manifest-fallback-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-fallback_prd-manifest-fallback_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-fallback
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-fallback/custom_alerts/manifest-fallback-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-manifest-fallback_prd-manifest-fallback_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-fallback
env: prd
priority: p1
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-file-upload/custom_alerts/manifest-file-upload-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-file-upload_prd-manifest-file-upload_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 3
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-file-upload
env: prd
priority: p2
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-file-upload/custom_alerts/manifest-file-upload-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-file-upload_prd-manifest-file-upload_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-file-upload
env: prd
priority: p2
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-file-upload/custom_alerts/manifest-file-upload-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-manifest-file-upload_prd-manifest-file-upload_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 180000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-file-upload
env: prd
priority: p2
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-serving/custom_alerts/manifest-serving-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-serving_prd-manifest-serving_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-serving
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-serving/custom_alerts/manifest-serving-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-serving_prd-manifest-serving_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-serving
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-serving/custom_alerts/manifest-serving-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-manifest-serving_prd-manifest-serving_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 60
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-serving
env: prd
priority: p0
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-serving/custom_alerts/manifest-serving-Latency_P99_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-manifest-serving_prd-manifest-serving_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 400
for: 2m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-serving
env: prd
priority: p0
annotations:
summary: "EKS Latency_P99_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-supply_prd-manifest-supply_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-supply_prd-manifest-supply_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-manifest-supply_prd-manifest-supply_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-manifest-supply_prd-manifest-supply_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 5000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_CP_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_CP_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_CP_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 4
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_CP_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_CP_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_DH_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_DH_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_DEL_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) > 1.5
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_DH_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_DH_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_DTDC_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_DTDC_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_DTDC_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 4
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_DTDC_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_DTDC_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_ECOM_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_ECOM_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_ECOM_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 1.5
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_ECOM_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_ECOM_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_ML_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_ML_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_meeshologistics_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 10
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_ML_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_ML_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_SF_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_SF_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_SF_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 1.2
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_SF_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_SF_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_LATENCY_XB_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_LATENCY_XB_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_XB_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) > 1.5
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_LATENCY_XB_FWD on {{ $labels.service }}"
description: "EKS P99_LATENCY_XB_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/manifest-supply/custom_alerts/manifest-supply-P99_Latency_Alert_DH_FWD.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_DH_FWD_EKS
expr: avg by (cluster)(OUT_manifest_carrier_DEL_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) > 1500
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: manifest-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_DH_FWD on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_DH_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/marketplace-web-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-marketplace-web_prd-marketplace-web_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: marketplace-web
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/marketplace-web-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-marketplace-web_prd-marketplace-web_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: marketplace-web
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/marketplace-web-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-marketplace-web_prd-marketplace-web_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: marketplace-web
env: prd
priority: p1
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-qwest-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-qwest_prd-order-qwest_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-qwest
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-qwest-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-order-qwest_prd-order-qwest_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 550
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-qwest
env: prd
priority: p1
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-qwest-index-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-qwest-index_prd-order-qwest-index_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-qwest-index
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-qwest-index-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-qwest-index_prd-order-qwest-index_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-qwest-index
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-qwest-index-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-order-qwest-index_prd-order-qwest-index_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-qwest-index
env: prd
priority: p1
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-qwest/custom_alerts/order-qwest-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-qwest_prd-order-qwest_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 15
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-qwest
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-search-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-search_prd-order-search_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-search
env: prd
priority: p2
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-search-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-search_prd-order-search_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-search
env: prd
priority: p2
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-search-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-order-search_prd-order-search_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-search
env: prd
priority: p2
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-order-state-management", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 500
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management
env: prd
priority: p1
annotations:
summary: "EKS HTTP 4XX Alert on {{ $labels.service }}"
description: "EKS HTTP 4XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-state-management_prd-order-state-management-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-order-state-management", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management
env: prd
priority: p1
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-state-management_prd-order-state-management-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-order-state-management", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.2
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management
env: prd
priority: p1
annotations:
summary: "EKS Latency/Response Time P99 Alert on {{ $labels.service }}"
description: "EKS Latency/Response Time P99 Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-order-state-management_prd-order-state-management-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 200
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-cron-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-order-state-management-cron", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 > 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-cron
env: prd
priority: p1
annotations:
summary: "EKS HTTP 4XX Alert on {{ $labels.service }}"
description: "EKS HTTP 4XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-cron-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-order-state-management-cron", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 > 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-cron
env: prd
priority: p1
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-order-state-management-read", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS HTTP 4XX Alert on {{ $labels.service }}"
description: "EKS HTTP 4XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-order-state-management-read", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-order-state-management-read", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.25
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS Latency/Response Time P99 Alert on {{ $labels.service }}"
description: "EKS Latency/Response Time P99 Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 250
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read/custom_alerts/Minimum_Request_Count_Breached.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Minimum_Request_Count_Breached_EKS
expr: sum(rate(envoy_cluster_upstream_rq_total{bu=~"supply",cluster=~"p-supply-cluster",envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read-primary_80"})) < 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS Minimum_Request_Count_Breached on {{ $labels.service }}"
description: "EKS Minimum_Request_Count_Breached on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read/custom_alerts/order-state-management-read-HTTP_4XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read/custom_alerts/order-state-management-read-HTTP_5XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read/custom_alerts/order-state-management-read-Latency_P99_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 250
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS Latency_P99_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-read/custom_alerts/order-state-management-read-Minimum_Request_Count_Breached_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Minimum_Request_Count_Breached_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq_total{bu=~"supply",cluster=~"p-supply-cluster",envoy_cluster_name=~"prd-order-state-management-read_prd-order-state-management-read-primary_80"})) < 9
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-read
env: prd
priority: p0
annotations:
summary: "EKS Minimum_Request_Count_Breached_EKS on {{ $labels.service }}"
description: "EKS Minimum_Request_Count_Breached_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-worker-2-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-order-state-management-worker-2", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-worker-2
env: prd
priority: p1
annotations:
summary: "EKS HTTP 4XX Alert on {{ $labels.service }}"
description: "EKS HTTP 4XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-state-management-worker-2-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-order-state-management-worker-2", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-state-management-worker-2
env: prd
priority: p1
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-sync-consumer-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-order-sync-consumer", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-sync-consumer
env: prd
priority: p0
annotations:
summary: "EKS HTTP 4XX Alert on {{ $labels.service }}"
description: "EKS HTTP 4XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/order-sync-consumer-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-order-sync-consumer", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: order-sync-consumer
env: prd
priority: p0
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-edd-worker-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-osm-edd-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-edd-worker
env: prd
priority: p2
annotations:
summary: "EKS HTTP 4XX Alert on {{ $labels.service }}"
description: "EKS HTTP 4XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-edd-worker-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-osm-edd-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-edd-worker
env: prd
priority: p2
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-HTTP_5XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 30
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-read-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply-read_prd-osm-supply-read_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply-read
env: prd
priority: p2
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-read-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply-read_prd-osm-supply-read_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply-read
env: prd
priority: p2
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-read-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-osm-supply-read_prd-osm-supply-read_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply-read
env: prd
priority: p2
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-read/custom_alerts/osm-supply-read-HTTP_4XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply-read_prd-osm-supply-read-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply-read
env: prd
priority: p2
annotations:
summary: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-read/custom_alerts/osm-supply-read-HTTP_5XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply-read_prd-osm-supply-read-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply-read
env: prd
priority: p2
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply-read/custom_alerts/osm-supply-read-P99_Latency_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-osm-supply-read_prd-osm-supply-read-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply-read
env: prd
priority: p2
annotations:
summary: "EKS P99_Latency_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply/custom_alerts/osm-supply-HTTP_4XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply/custom_alerts/osm-supply-HTTP_5XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/osm-supply/custom_alerts/osm-supply-P99_Latency_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-osm-supply_prd-osm-supply-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: osm-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/packaging-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-packaging_prd-packaging_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: packaging
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/packaging-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-packaging_prd-packaging_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: packaging
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/packaging/custom_alerts/packaging-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-packaging_prd-packaging_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: packaging
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/pdf-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-pdf_prd-pdf-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: pdf
env: prd
priority: p2
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/pdf-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-pdf_prd-pdf-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: pdf
env: prd
priority: p2
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/pdf-Latency_P99_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-pdf_prd-pdf-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 30000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: pdf
env: prd
priority: p2
annotations:
summary: "EKS Latency_P99_Alert_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-returns-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-poa-returns_prd-poa-returns_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-returns
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-returns-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-poa-returns_prd-poa-returns_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-returns
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-returns-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-poa-returns_prd-poa-returns_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 10000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-returns
env: prd
priority: p2
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-supply-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-poa-supply_prd-poa-supply_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-supply-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-poa-supply_prd-poa-supply_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 2m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-supply-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-poa-supply_prd-poa-supply_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-supply/custom_alerts/poa-supply-HTTP_4XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-poa-supply_prd-poa-supply-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-supply/custom_alerts/poa-supply-HTTP_5XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-poa-supply_prd-poa-supply-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 2m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-supply
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/poa-supply/custom_alerts/poa-supply-P99_Latency_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-poa-supply_prd-poa-supply-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 3000
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: poa-supply
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/post-order-aggregator-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-post-order-aggregator_prd-post-order-aggregator_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: post-order-aggregator
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/post-order-aggregator-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-post-order-aggregator_prd-post-order-aggregator_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 2m
labels:
severity: critical
bu: supply
team: fulfilment
service: post-order-aggregator
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/post-order-aggregator-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-post-order-aggregator_prd-post-order-aggregator_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 1m
labels:
severity: critical
bu: supply
team: fulfilment
service: post-order-aggregator
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/supply/fulfilment/post-order-aggregator/custom_alerts/post-order-aggregator-HTTP_4XX_Alert_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-post-order-aggregator_prd-post-order-aggregator-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 5m
labels:
severity: critical
bu: supply
team: fulfilment
service: post-order-aggregator
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"

Some files were not shown because too many files have changed in this diff Show More