added repo

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
@@ -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-config-service_prd-config-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 4600
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: config-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 }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-config-service_prd-config-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 150
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: config-service
env: prd
priority: p0
annotations:
summary: "EKS Latency_P99_Alert_EKS_Contour on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_EKS_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -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-config-service_prd-config-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 80
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: config-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 }}\n LABELS: {{ $labels }}"
@@ -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-location-service_prd-location-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: location-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 }}\n LABELS: {{ $labels }}"
@@ -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-location-service_prd-location-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 2
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: location-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 }}\n LABELS: {{ $labels }}"
@@ -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-location-service_prd-location-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 25
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: location-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 }}\n LABELS: {{ $labels }}"
@@ -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-product-aggregator_prd-product-aggregator-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: product-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 }}\n LABELS: {{ $labels }}"
@@ -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-product-aggregator_prd-product-aggregator-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: product-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 }}\n LABELS: {{ $labels }}"
@@ -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-product-aggregator_prd-product-aggregator-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: product-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 }}\n LABELS: {{ $labels }}"
@@ -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-product-aggregator-fallback_prd-product-aggregator-fallback-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: product-aggregator-fallback
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 }}"
@@ -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-product-aggregator-fallback_prd-product-aggregator-fallback-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: product-aggregator-fallback
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 }}"
@@ -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-product-aggregator-fallback_prd-product-aggregator-fallback-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: product-aggregator-fallback
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 }}"
@@ -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-rx-fa-collections_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-fa-collections
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 }}"
@@ -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-rx-fa-collections_.*", envoy_response_code=~"[5].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 250
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-fa-collections
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 }}"
@@ -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-rx-fa-collections_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1500
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-fa-collections
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 }}"
@@ -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-rx-fa-recommendations_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-fa-recommendations
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 }}"
@@ -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-rx-fa-recommendations_.*", envoy_response_code=~"[5].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 250
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-fa-recommendations
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 }}"
@@ -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-rx-fa-recommendations_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1500
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-fa-recommendations
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 }}"
@@ -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-rx-feed-aggregator_prd-rx-feed-aggregator-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-feed-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 }}"
@@ -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-rx-feed-aggregator_prd-rx-feed-aggregator-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-feed-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 }}"
@@ -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-rx-feed-aggregator_prd-rx-feed-aggregator-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: rx-feed-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 }}"
@@ -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-storefront-int-app-feed_prd-storefront-int-app-feed-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-app-feed
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 }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_1m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-app-feed_prd-storefront-int-app-feed-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5000
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-app-feed
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_2m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-app-feed_prd-storefront-int-app-feed-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 6000
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-app-feed
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_5m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-app-feed_prd-storefront-int-app-feed-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1500
for: 5m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-app-feed
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_Non_2XX_Alert_Per_API_For_You_EKS
expr: sum by (uri,env)(CONTROLLER_execTime_count{service="storefront-int-app-feed",httpCode!~"2[0-9]{2}", uri=~".*/*/for-you.*"}) >= 60
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-app-feed
env: prd
priority: p0
annotations:
summary: "EKS HTTP_Non_2XX_Alert_Per_API_For_You on {{ $labels.service }}"
description: "EKS HTTP_Non_2XX_Alert_Per_API_For_You on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -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-storefront-int-search", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
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 }}"
@@ -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-storefront-int-search_prd-storefront-int-search-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
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 }}"
@@ -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-storefront-int-search", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 150
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
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 }}"
@@ -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-storefront-int-search", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 1200
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
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 }}"
@@ -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-storefront-int-search_prd-storefront-int-search-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1200
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
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 }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_1m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-search_prd-storefront-int-search-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5000
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_2m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-search_prd-storefront-int-search-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 6000
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_5m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-search_prd-storefront-int-search-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 2000
for: 5m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-search
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Per_API_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-secondary_prd-storefront-int-secondary-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-secondary
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Per_API_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Per_API_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -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-storefront-int-secondary_prd-storefront-int-secondary-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 4000
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-secondary
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 }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_1m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-secondary_prd-storefront-int-secondary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5000
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-secondary
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_2m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-secondary_prd-storefront-int-secondary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 6000
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-secondary
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_5m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-int-secondary_prd-storefront-int-secondary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1000
for: 5m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-int-secondary
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -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-storefront-primary_prd-storefront-primary-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1500
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-primary
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 }}"
@@ -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-storefront-primary_prd-storefront-primary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-primary
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 }}"
@@ -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-storefront-primary_prd-storefront-primary-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 300
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-primary
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 }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_Non_2XX_Alert_Per_API_Product_EKS
expr: sum by (uri,env)(CONTROLLER_execTime_count{service="storefront-primary",httpCode!~"2[0-9]{2}", uri=~".*2.0/product.*"}) >= 60
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-primary
env: prd
priority: p0
annotations:
summary: "EKS HTTP_Non_2XX_Alert_Per_API_Product on {{ $labels.service }}"
description: "EKS HTTP_Non_2XX_Alert_Per_API_Product on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_Non_2XX_Alert_Per_API_Variation_EKS
expr: sum by (uri,env)(CONTROLLER_execTime_count{service="storefront-primary",httpCode!~"2[0-9]{2}", uri=~".*1.0/variation.*"}) >= 60
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-primary
env: prd
priority: p0
annotations:
summary: "EKS HTTP_Non_2XX_Alert_Per_API_Variation on {{ $labels.service }}"
description: "EKS HTTP_Non_2XX_Alert_Per_API_Variation on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -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-storefront-secondary", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 1200
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-secondary
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 }}"
@@ -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-storefront-secondary_prd-storefront-secondary-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 12000
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-secondary
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 }}"
@@ -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-storefront-secondary", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-secondary
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 }}"
@@ -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-storefront-secondary_prd-storefront-secondary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-secondary
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 }}"
@@ -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-storefront-secondary", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 1200
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-secondary
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 }}"
@@ -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-storefront-secondary_prd-storefront-secondary-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 850
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-secondary
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 }}"
@@ -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-storefront-wishlist_prd-storefront-wishlist-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-wishlist
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 }}"
@@ -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-storefront-wishlist_prd-storefront-wishlist-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-wishlist
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 }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_1m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-wishlist_prd-storefront-wishlist-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1500
for: 1m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-wishlist
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_1m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_2m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-wishlist_prd-storefront-wishlist-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1800
for: 2m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-wishlist
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_2m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_5m_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-storefront-wishlist_prd-storefront-wishlist-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 300
for: 5m
labels:
severity: critical
bu: demand
team: shopping-platform
service: storefront-wishlist
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour_5m on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"