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/demand/offers/admin-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-admin", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin
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/demand/offers/admin-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-admin", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin
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/demand/offers/admin-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-admin", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin
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/demand/offers/admin-panel-promotions-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-admin-panel-promotions", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin-panel-promotions
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/demand/offers/admin-panel-promotions-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-admin-panel-promotions_prd-admin-panel-promotions_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin-panel-promotions
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/demand/offers/admin-panel-promotions-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-admin-panel-promotions", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin-panel-promotions
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/demand/offers/admin-panel-promotions-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-admin-panel-promotions_prd-admin-panel-promotions_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin-panel-promotions
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/demand/offers/admin-panel-promotions-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-admin-panel-promotions", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 1.25
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin-panel-promotions
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/demand/offers/admin-panel-promotions-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-admin-panel-promotions_prd-admin-panel-promotions_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1250
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: admin-panel-promotions
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/demand/offers/consent-manager-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-consent-manager", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: consent-manager
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/demand/offers/consent-manager-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-consent-manager", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: consent-manager
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/demand/offers/consent-manager-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-consent-manager", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: consent-manager
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/demand/offers/meesho-pow-webviews/custom_alerts/meesho-pow-webviews-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-meesho-pow-webviews_prd-meesho-pow-webviews_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: meesho-pow-webviews
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/demand/offers/meesho-pow-webviews/custom_alerts/meesho-pow-webviews-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-meesho-pow-webviews_prd-meesho-pow-webviews_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 25
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: meesho-pow-webviews
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/demand/offers/meesho-pow-webviews/custom_alerts/meesho-pow-webviews-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-meesho-pow-webviews_prd-meesho-pow-webviews_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 10000
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: meesho-pow-webviews
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/demand/offers/offers-event-service-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-offers-event-service", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-event-service
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/demand/offers/offers-event-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-offers-event-service_prd-offers-event-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-event-service
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/demand/offers/offers-event-service-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-offers-event-service", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-event-service
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/demand/offers/offers-event-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-offers-event-service_prd-offers-event-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-event-service
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/demand/offers/offers-event-service-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-offers-event-service", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.04
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-event-service
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/demand/offers/offers-event-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-offers-event-service_prd-offers-event-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-event-service
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/demand/offers/offers-offer-platform-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-offers-offer-platform_prd-offers-offer-platform-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 2000
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform
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/demand/offers/offers-offer-platform-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-offers-offer-platform_prd-offers-offer-platform-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform
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/demand/offers/offers-offer-platform-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-offers-offer-platform_prd-offers-offer-platform-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 200
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform
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/demand/offers/offers-offer-platform-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-offers-offer-platform-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform-worker
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/demand/offers/offers-offer-platform-worker-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-offers-offer-platform-worker_prd-offers-offer-platform-worker_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform-worker
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/demand/offers/offers-offer-platform-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-offers-offer-platform-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform-worker
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/demand/offers/offers-offer-platform-worker-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-offers-offer-platform-worker_prd-offers-offer-platform-worker_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform-worker
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/demand/offers/offers-offer-platform-worker-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-offers-offer-platform-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 1.0
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform-worker
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/demand/offers/offers-offer-platform-worker-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-offers-offer-platform-worker_prd-offers-offer-platform-worker_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform-worker
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/demand/offers/offers-offer-platform/custom_alerts/FY_CACHE_HIT_BELOW_THRESHOLD_ALERT_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY_CACHE_HIT_BELOW_THRESHOLD_ALERT_EKS_EKS
expr: (sum(rate(op_offer_cache_hit_total{job="kubernetes-pods",service=~"offers-offer-platform",cache_hit="redis"}[1m]))/(sum(rate(op_offer_cache_hit_total{job="kubernetes-pods",service=~"offers-offer-platform",cache_hit="redis"}[1m])) + sum(rate(op_offer_cache_hit_total{job="kubernetes-pods",service=~"offers-offer-platform",cache_hit="hbase"}[1m])))) * 100 < 90
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform
env: prd
priority: p1
annotations:
summary: "EKS FY_CACHE_HIT_BELOW_THRESHOLD_ALERT_EKS on {{ $labels.service }}"
description: "EKS FY_CACHE_HIT_BELOW_THRESHOLD_ALERT_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/offers/offers-offer-platform/custom_alerts/HBASE_AVG_TIME.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HBASE_AVG_TIME_EKS
expr: (sum by (service,method,parent) (HBASE_execTime_sum{service=~"offers-offer-platform"}))/ (sum by (service,parent,method) (HBASE_execTime_count{service=~"offers-offer-platform"})) > 100
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform
env: prd
priority: p1
annotations:
summary: "EKS HBASE_AVG_TIME on {{ $labels.service }}"
description: "EKS HBASE_AVG_TIME on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/offers/offers-offer-platform/custom_alerts/_Controller_P99_alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: offers-offer-platform-worker_Controller_P99_alert_EKS
expr: histogram_quantile(0.99, sum(rate(http_server_requests_seconds_bucket{job="kubernetes-pods",service="offers-offer-platform-worker",uri!~".*health.*|.*actuator.*|.*error.*", cluster="p-demand-cluster"}[1m])) by (le, uri,service)) >= 1000
for: 5m
labels:
severity: critical
bu: demand
team: offers
service: offers-offer-platform
env: prd
priority: p1
annotations:
summary: "EKS _Controller_P99_alert on {{ $labels.service }}"
description: "EKS _Controller_P99_alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/offers/offers-prism-ingestion-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-offers-prism-ingestion-service_prd-offers-prism-ingestion-service_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-prism-ingestion-service
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/demand/offers/offers-prism-ingestion-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-offers-prism-ingestion-service_prd-offers-prism-ingestion-service_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-prism-ingestion-service
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/demand/offers/offers-prism-ingestion-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-offers-prism-ingestion-service_prd-offers-prism-ingestion-service_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-prism-ingestion-service
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/demand/offers/offers-supplieradmin-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-offers-supplieradmin_prd-offers-supplieradmin_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplieradmin
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/demand/offers/offers-supplieradmin-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-offers-supplieradmin_prd-offers-supplieradmin_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplieradmin
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/demand/offers/offers-supplieradmin-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-offers-supplieradmin_prd-offers-supplieradmin_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2000
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplieradmin
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/demand/offers/offers-supplierconsumer-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-offers-supplierconsumer_prd-offers-supplierconsumer_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplierconsumer
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/demand/offers/offers-supplierconsumer-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-offers-supplierconsumer_prd-offers-supplierconsumer_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplierconsumer
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/demand/offers/offers-supplierconsumer-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-offers-supplierconsumer_prd-offers-supplierconsumer_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplierconsumer
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/demand/offers/offers-supplieroptin-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-offers-supplieroptin_prd-offers-supplieroptin_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplieroptin
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/demand/offers/offers-supplieroptin-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-offers-supplieroptin_prd-offers-supplieroptin_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplieroptin
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/demand/offers/offers-supplieroptin/custom_alerts/offers-supplieroptin-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-offers-supplieroptin_prd-offers-supplieroptin_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2000
for: 5m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplieroptin
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/demand/offers/offers-supplierworker-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-offers-supplierworker_prd-offers-supplierworker_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplierworker
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/demand/offers/offers-supplierworker-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-offers-supplierworker_prd-offers-supplierworker_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplierworker
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/demand/offers/offers-supplierworker-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-offers-supplierworker_prd-offers-supplierworker_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: offers-supplierworker
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/demand/offers/supplier-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-supplier", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: supplier
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/demand/offers/supplier-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-supplier", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: supplier
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/demand/offers/supplier-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-supplier", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: supplier
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/demand/offers/supplier-consent-manager-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-supplier-consent-manager_prd-supplier-consent-manager_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: supplier-consent-manager
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/demand/offers/supplier-consent-manager-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-supplier-consent-manager_prd-supplier-consent-manager_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: supplier-consent-manager
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/demand/offers/supplier-consent-manager-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-supplier-consent-manager_prd-supplier-consent-manager_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: supplier-consent-manager
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/demand/offers/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-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 30
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: worker
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/demand/offers/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-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: worker
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/demand/offers/worker-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-worker", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.500
for: 1m
labels:
severity: critical
bu: demand
team: offers
service: worker
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 }}"