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/communications/communicator-HTTP_4XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -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-communicator_prd-communicator-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 600
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: communicator
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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/communicator-HTTP_5XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Per_API_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-communicator_prd-communicator-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: communicator
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/communicator-Latency_P99_Alert_EKS_Contour_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS_Contour_EKS_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-communicator_prd-communicator-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 300
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: communicator
env: prd
priority: p0
annotations:
summary: "EKS Latency_P99_Alert_EKS_Contour_EKS on {{ $labels.service }}"
description: "EKS Latency_P99_Alert_EKS_Contour_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/communicator-admin-HTTP_4XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -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-communicator-admin_prd-communicator-admin-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: communicator-admin
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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/communicator-admin-HTTP_5XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Per_API_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-communicator-admin_prd-communicator-admin-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: communicator-admin
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/communicator-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-communicator-consumer", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: communicator-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/demand/communications/community-web-eks/mandatory_alerts/community-web-eks-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-community-web-eks_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 2m
labels:
severity: critical
bu: demand
team: communications
service: community-web-eks
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/demand/communications/community-web-eks/mandatory_alerts/community-web-eks-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-community-web-eks_.*", envoy_response_code=~"[5].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: community-web-eks
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/demand/communications/community-web-eks/mandatory_alerts/community-web-eks-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-community-web-eks_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: community-web-eks
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/demand/communications/gamification-service/mandatory_alerts/gamification-service-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-gamification-service_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 15
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: gamification-service
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/demand/communications/gamification-service/mandatory_alerts/gamification-service-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-gamification-service_.*", envoy_response_code=~"[5].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: gamification-service
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/demand/communications/gamification-service/mandatory_alerts/gamification-service-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-gamification-service_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: gamification-service
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/demand/communications/leaderboard-service-eks/mandatory_alerts/leaderboard-service-eks-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-leaderboard-service-eks_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 2m
labels:
severity: critical
bu: demand
team: communications
service: leaderboard-service-eks
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/demand/communications/leaderboard-service-eks/mandatory_alerts/leaderboard-service-eks-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-leaderboard-service-eks_.*", envoy_response_code=~"[5].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: leaderboard-service-eks
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/demand/communications/leaderboard-service-eks/mandatory_alerts/leaderboard-service-eks-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-leaderboard-service-eks_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: leaderboard-service-eks
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/demand/communications/login-service-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-login-service_prd-login-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 800
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: login-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/login-service-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-login-service_prd-login-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: login-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/login-service-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: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-login-service_prd-login-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: login-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 }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/notification-store-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-notification-store-web_prd-notification-store-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: notification-store-web
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/demand/communications/notification-store-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-notification-store-web_prd-notification-store-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: notification-store-web
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/demand/communications/notification-store-web-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-notification-store-web_prd-notification-store-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: notification-store-web
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/demand/communications/ums-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-ums_prd-ums-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 8000
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: ums
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/communications/ums-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-ums_prd-ums-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 1000
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: ums
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/communications/ums-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-ums_prd-ums-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: ums
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/communications/ums-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-ums-fallback_prd-ums-fallback-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 4000
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: ums-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/ums-fallback-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-ums-fallback_prd-ums-fallback-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: ums-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/whatsapp-service-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-whatsapp-service_prd-whatsapp-service_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: whatsapp-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/whatsapp-service-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-whatsapp-service_prd-whatsapp-service_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: whatsapp-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/communications/whatsapp-service-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-whatsapp-service_prd-whatsapp-service_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: communications
service: whatsapp-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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-CONTROLLER_4XX_Alert_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: CONTROLLER_4XX_Alert_EKS
expr: sum by (service,uri,httpCode) (CONTROLLER_execTime_count{service="feed-aggregator",httpCode=~"[4].*"} ) >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator
env: prd
priority: p0
annotations:
summary: "EKS CONTROLLER_4XX_Alert on {{ $labels.service }}"
description: "EKS CONTROLLER_4XX_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-CONTROLLER_5XX_Alert_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: CONTROLLER_5XX_Alert_EKS
expr: sum by (service,uri,httpCode) (CONTROLLER_execTime_count{service="feed-aggregator",httpCode=~"[5].*"} ) >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator
env: prd
priority: p0
annotations:
summary: "EKS CONTROLLER_5XX_Alert on {{ $labels.service }}"
description: "EKS CONTROLLER_5XX_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-search-HTTP_4XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -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-feed-aggregator-search_prd-feed-aggregator-search-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 2m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-search
env: prd
priority: p1
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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-search-HTTP_5XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Per_API_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-feed-aggregator-search_prd-feed-aggregator-search-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 250
for: 2m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-search
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-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-feed-aggregator-search_prd-feed-aggregator-search-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1500
for: 2m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-search
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/demand/discovery-platform/feed-aggregator-secondary-CONTROLLER_4XX_Alert_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: CONTROLLER_4XX_Alert_EKS
expr: sum by (service,uri,httpCode) (CONTROLLER_execTime_count{service="feed-aggregator-secondary",httpCode=~"[4].*"} ) >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-secondary
env: prd
priority: p0
annotations:
summary: "EKS CONTROLLER_4XX_Alert on {{ $labels.service }}"
description: "EKS CONTROLLER_4XX_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-secondary-CONTROLLER_5XX_Alert_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: CONTROLLER_5XX_Alert_EKS
expr: sum by (service,uri,httpCode) (CONTROLLER_execTime_count{service="feed-aggregator-secondary",httpCode=~"[5].*"} ) >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-secondary
env: prd
priority: p0
annotations:
summary: "EKS CONTROLLER_5XX_Alert on {{ $labels.service }}"
description: "EKS CONTROLLER_5XX_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-secondary-HTTP_4XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -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-feed-aggregator-secondary_prd-feed-aggregator-secondary-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-secondary
env: prd
priority: p1
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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-secondary-HTTP_5XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Per_API_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-feed-aggregator-secondary_prd-feed-aggregator-secondary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 5m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-secondary
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/feed-aggregator-secondary-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(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster",service=~"prd-feed-aggregator-secondary", job=~"kubernetes-service-endpoints"}) by (cluster, service, le, ingress, namespace, job)) >= 0.75
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-secondary
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/discovery-platform/feed-aggregator-secondary-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-feed-aggregator-secondary_prd-feed-aggregator-secondary-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2000
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: feed-aggregator-secondary
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/discovery-platform/hero-product-web-HTTP_4XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -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-hero-product-web_prd-hero-product-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: hero-product-web
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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/hero-product-web-HTTP_5XX_Alert_Per_API_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Per_API_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-hero-product-web_prd-hero-product-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 2m
labels:
severity: critical
bu: demand
team: discovery-platform
service: hero-product-web
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Per_API_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-platform/hero-product-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-hero-product-web_prd-hero-product-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 200
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: hero-product-web
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/demand/discovery-platform/sort-and-filter-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-sort-and-filter_prd-sort-and-filter-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter
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/discovery-platform/sort-and-filter-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-sort-and-filter_prd-sort-and-filter-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 90
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter
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/discovery-platform/sort-and-filter-Latency_P99_Alert_Contour.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(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-sort-and-filter_prd-sort-and-filter-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter
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/discovery-platform/sort-and-filter-secondary-HTTP_4XX_Alert_contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-sort-and-filter-secondary_prd-sort-and-filter-secondary-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 2m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter-secondary
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/discovery-platform/sort-and-filter-secondary-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-sort-and-filter-secondary_prd-sort-and-filter-secondary-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 250
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter-secondary
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/discovery-platform/sort-and-filter-secondary-Latency_P99_Alert_Contour.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(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-sort-and-filter-secondary_prd-sort-and-filter-secondary-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter-secondary
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/discovery-platform/sort-and-filter-vs-HTTP_4XX_Alert_contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-sort-and-filter-vs_prd-sort-and-filter-vs-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter-vs
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/discovery-platform/sort-and-filter-vs-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-sort-and-filter-vs_prd-sort-and-filter-vs-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 90
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter-vs
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/discovery-platform/sort-and-filter-vs-Latency_P99_Alert_Contour.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(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-sort-and-filter-vs_prd-sort-and-filter-vs-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1200
for: 1m
labels:
severity: critical
bu: demand
team: discovery-platform
service: sort-and-filter-vs
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/discovery-ranking/FY_Ads_scale_up_anonymous_failure_rate.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY Ads scale up anonymous failure rate
expr: sum(rate(component_exec_failure_total{dag_label=~"ad_.*_scale_up_anon"})[1m]) > 50
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "FY Ads scale up anonymous failure rate on {{ $labels.service }}"
description: "FY Ads scale up experiment failure rate on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/FY_Ads_scale_up_experiment_failure_rate.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY Ads scale up experiment failure rate
expr: sum(rate(component_exec_failure_total{dag_label=~"ad.*", dag_label!~"ad.*_scale_up.*"})[1m]) > 20
for: 3m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "FY Ads scale up experiment failure rate on {{ $labels.service }}"
description: "FY Ads scale up experiment failure rate on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/FY_Ads_scale_up_failure_rate.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY Ads scale up failure rate
expr: sum(rate(component_exec_failure_total{dag_label=~"ad_.*_scale_up"})[1m]) by (dag_label) > 30
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "FY Ads scale up failure rate on {{ $labels.service }}"
description: "FY Ads scale up failure rate on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/FY_Organic_experiment_failure_rate.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY Organic experiment failure rate
expr: sum(rate(component_exec_failure_total{dag_label=~"gfr.*", dag_label!~"gfr.*_scale_up.*"})[1m]) > 20
for: 3m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "FY Organic experiment failure rate on {{ $labels.service }}"
description: "FY Organic experiment failure rate on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/FY_Organic_scale_up_anonymous_failure_rate.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY Organic scale up anonymous failure rate
expr: sum(rate(component_exec_failure_total{dag_label=~"gfr.*_scale_up_anon"})[1m]) > 50
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "FY Organic scale up anonymous failure rate on {{ $labels.service }}"
description: "FY Organic scale up anonymous failure rate on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/FY_Organic_scale_up_failure_rate.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY Organic scale up failure rate
expr: sum(rate(component_exec_failure_total{dag_label=~"gfr.*_scale_up"})[1m]) by (dag_label) > 50
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "FY Organic scale up failure rate on {{ $labels.service }}"
description: "FY Organic scale up failure rate on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/dropout-net-cg-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-dropout-net-cg-web_prd-dropout-net-cg-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: dropout-net-cg-web
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/discovery-ranking/dropout-net-cg-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-dropout-net-cg-web_prd-dropout-net-cg-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: dropout-net-cg-web
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/discovery-ranking/dropout-net-cg-web-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-dropout-net-cg-web_prd-dropout-net-cg-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 80
for: 3m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: dropout-net-cg-web
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/discovery-ranking/dropout_net_Consumer_Lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Dropout net Consumer Lag
expr: sum (rate(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".ml.", name="OffsetLag", topic=~"ml.dropoutnet", groupId=~"dropoutnet-cg-consumer-group"}))by (groupId,topic) > 100
for: 2m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: dropout-net-cg-consumer
env: prd
priority: p0
annotations:
summary: "Dropout net Consumer Lag on {{ $labels.service }}"
description: "Dropout net Consumer Lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/fy-ibcg-web/custom_alerts/Latency_P99_Alert_EKS_Contour.yaml
+16
View File
@@ -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-fy-ibcg-service_prd-fy-ibcg-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 200
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: fy-ibcg-web
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 }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/fy-ibcg-web/custom_alerts/fy-ibcg-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-fy-ibcg-service_prd-fy-ibcg-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: fy-ibcg-web
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/discovery-ranking/fy-ibcg-web/custom_alerts/fy-ibcg-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-fy-ibcg-service_prd-fy-ibcg-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: fy-ibcg-web
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/discovery-ranking/offline-cg-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-offline-cg-web_prd-offline-cg-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: offline-cg-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/demand/discovery-ranking/offline-cg-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-offline-cg-web_prd-offline-cg-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: offline-cg-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/demand/discovery-ranking/offline-cg-web-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-offline-cg-web_prd-offline-cg-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: offline-cg-web
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/discovery-ranking/offline_cg_consumer_lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Offline cg consumer lag
expr: sum(rate(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpmlpatformnew.m4ywws.*", name="OffsetLag", topic=~"ds\\.offline_cg_data", groupId=~"offline_cg_v1"}))by(groupId,topic) > 10000
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: offline-cg-consumer
env: prd
priority: p0
annotations:
summary: "Offline cg consumer lag on {{ $labels.service }}"
description: "Offline cg consumer lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/pdp-iacg-web/custom_alerts/pdp-iacg-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-pdp-iacg-service_prd-pdp-iacg-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: pdp-iacg-web
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/discovery-ranking/pdp-iacg-web/custom_alerts/pdp-iacg-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-pdp-iacg-service_prd-pdp-iacg-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: pdp-iacg-web
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/discovery-ranking/pdp-iacg-web/custom_alerts/pdp-iacg-web-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-pdp-iacg-service_prd-pdp-iacg-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: pdp-iacg-web
env: prd
priority: p0
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/demand/discovery-ranking/pdp-iop-web/custom_alerts/pdp-iop-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-pdp-iop-service-web_prd-pdp-iop-service-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: pdp-iop-web
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/discovery-ranking/pdp-iop-web/custom_alerts/pdp-iop-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-pdp-iop-service-web_prd-pdp-iop-service-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: pdp-iop-web
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/discovery-ranking/pdp-iop-web/custom_alerts/pdp-iop-web-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-pdp-iop-service-web_prd-pdp-iop-service-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 170
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: pdp-iop-web
env: prd
priority: p0
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/demand/discovery-ranking/product-similarity-cg-api-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-product-similarity-cg-api_prd-product-similarity-cg-api-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: product-similarity-cg-api
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/discovery-ranking/product-similarity-cg-api-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-product-similarity-cg-api_prd-product-similarity-cg-api-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: product-similarity-cg-api
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/discovery-ranking/product-similarity-cg-api-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-product-similarity-cg-api_prd-product-similarity-cg-api-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 60
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: product-similarity-cg-api
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/discovery-ranking/product_similarity_Ads_Consumer_Lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Product similarity Ads Consumer Lag
expr: sum by (groupId,topic)(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpmlpatformnew.*", name="OffsetLag", topic=~"ad.fy-item-item-similarity", groupId=~"ad-fy-item-item-consumer-v1"}) > 10000000
for: 100m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: product-similarity-cg-consumer
env: prd
priority: p0
annotations:
summary: "Product similarity Ads Consumer Lag on {{ $labels.service }}"
description: "Product similarity Ads Consumer Lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/recent-explore-cg-web/custom_alerts/GRPC_failures_.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: GRPC_failures__EKS
expr: sum(rate(grpc_client_completed_total{service="recent-explore-cg-api", grpc_code="INTERNAL", grpc_method="retrieveFeatures"})) by (grpc_code, grpc_method) >= 10
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: recent-explore-cg-web
env: prd
priority: p0
annotations:
summary: "EKS GRPC_failures_ on {{ $labels.service }}"
description: "EKS GRPC_failures_ on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/relevance-service-DAG_component_failure_Alert_relevance-service_Telegraf_EKS.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: DAG_component_failure_Alert_relevance-service_Telegraf_EKS
expr: sum(rate(component_exec_failure_total)[1m]) by (component_name, dag_label) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "EKS DAG_component_failure_Alert_relevance-service_Telegraf on {{ $labels.service }}"
description: "EKS DAG_component_failure_Alert_relevance-service_Telegraf on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/relevance-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-relevance-web_prd-relevance-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
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/discovery-ranking/relevance-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-relevance-web_prd-relevance-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
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/discovery-ranking/relevance-web-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-relevance-web_prd-relevance-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
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/discovery-ranking/relevance-web/custom_alerts/RANKER_FAILURE_IN_RELEVANCE.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: RANKER_FAILURE_IN_RELEVANCE_EKS
expr: sum(rate(downstream_failure_total{service_name="ranker-model"})[1m]) by (cluster, service_name) >= 100
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "RANKER_FAILURE_IN_RELEVANCE on {{ $labels.service }}"
description: "RANKER_FAILURE_IN_RELEVANCE on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/relevance-web/custom_alerts/relevance-service-DAG_Latency_p99_Alert_Telegraf.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: DAG_Latency_p99_Alert_Telegraf_EKS
expr: histogram_quantile(0.99, sum(rate(dag_exec_time_seconds_bucket[1m])) by (le, dag_label)) >= 0.40
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "EKS DAG_Latency_p99_Alert_Telegraf on {{ $labels.service }}"
description: "EKS DAG_Latency_p99_Alert_Telegraf on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/relevance-web/custom_alerts/relevance-web-Model_Proxy_AD_latency_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Model_Proxy_AD_latency_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(HTTP_execTime_bucket{uri!~".*health.*",service="relevance-web",instance=~"100.64.*", host="model-proxy-svc-fy-ad.dsci-h2.meesho.com"}[1m])) by (le, external_service, method,host)) >= 250
for: 2m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "EKS Model_Proxy_AD_latency_Alert on {{ $labels.service }}"
description: "EKS Model_Proxy_AD_latency_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/relevance-web/custom_alerts/relevance-web-Model_Proxy_CT_latency_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Model_Proxy_CT_latency_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(HTTP_execTime_bucket{uri!~".*health.*",service="relevance-web",instance=~"100.64.*",host="model-proxy-svc-fy-ct.dsci-h2.meesho.com"}[1m])) by (le, external_service, method,host)) >= 250
for: 2m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "EKS Model_Proxy_CT_latency_Alert on {{ $labels.service }}"
description: "EKS Model_Proxy_CT_latency_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/relevance-web/custom_alerts/relevance-web-Model_Proxy_ORGANIC_latency_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Model_Proxy_ORGANIC_latency_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(HTTP_execTime_bucket{uri!~".*health.*",service="relevance-web",instance=~"100.64.*", host="model-proxy-svc-fy-organic.dsci-h2.meesho.com"}[1m])) by (le, external_service, method,host)) >= 250
for: 2m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: relevance-web
env: prd
priority: p0
annotations:
summary: "EKS Model_Proxy_ORGANIC_latency_Alert on {{ $labels.service }}"
description: "EKS Model_Proxy_ORGANIC_latency_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-consumer/custom_alerts/Catalog_Recommendation_Consumer_Lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Catalog Recommendation Consumer Lag
expr: sum by (groupId,topic)(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*$bacpdiscoveryteam.*", name="OffsetLag", topic=~"hulk-reco-feed_v2", groupId=~"vision_reco_catalog"})>100000
for: 60m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-consumer
env: prd
priority: p0
annotations:
summary: "Catalog Recommendation Consumer Lag on {{ $labels.service }}"
description: "Catalog Recommendation Consumer Lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-consumer/custom_alerts/Vision_Retargating_Product_recommendation.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Vision Retargating Product recommendation
expr: sum(rate(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".bacpdiscoveryteam.", name="OffsetLag", topic=~"vision_retargeting-product-recommendation_v1", groupId=~"vision_retargeting_product_recommendations"}))by (groupId,topic)>100000
for: 40m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-consumer
env: prd
priority: p0
annotations:
summary: "Vision Retargating Product recommendation on {{ $labels.service }}"
description: "Vision Retargating Product recommendation on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-consumer/custom_alerts/Vision_Segment_Feed_Consumer_Data_Lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Vision Segment Feed Consumer Data Lag
expr: sum(rate(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpdiscoveryteam.*", name="OffsetLag", topic=~"hulk_segment-feed-data_v1", groupId=~"vision_segment_feed_data"}))by(groupId,topic)>25000
for: 5m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-consumer
env: prd
priority: p0
annotations:
summary: "Vision Segment Feed Consumer Data Lag on {{ $labels.service }}"
description: "Vision Segment Feed Consumer Data Lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-consumer/custom_alerts/Vision_User_Segment_Mapping_Consumer_Data_Lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Vision User Segment Mapping Consumer Data Lag
expr: sum(rate(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpdiscoveryteam.*", name="OffsetLag", topic=~"hulk_user-segment-mapping_v1", groupId=~"vision_user_segment_mapping"}))by(groupId,topic)>100000
for: 8m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-consumer
env: prd
priority: p0
annotations:
summary: "Vision User Segment Mapping Consumer Data Lag on {{ $labels.service }}"
description: "Vision User Segment Mapping Consumer Data Lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-consumer/custom_alerts/Vision_catalog_cache_Data_Lag.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Vision catalog cache Data Lag
expr: sum(rate(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*real-time.*", name="OffsetLag", topic=~"marvel.storefront_validated_catalogs", groupId=~"vision_rti_catalog_cache_updates"}))by(groupId,topic)>1160
for: 8m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-consumer
env: prd
priority: p0
annotations:
summary: "Vision catalog cache Data Lag on {{ $labels.service }}"
description: "Vision catalog cache Data Lag on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-recommendations/custom_alerts/vision-recommendations-CATALOG_HIDDEN_RATE_RECOMMENDED_CATALOGS_V1.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: CATALOG_HIDDEN_RATE_RECOMMENDED_CATALOGS_V1_EKS
expr: sum(rate(vision_catalog_invalid_hidden_value{parent="/api/v1/recommended-catalogs"})) by(parent) >= 11000
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-reco-web
env: prd
priority: p0
annotations:
summary: "EKS CATALOG_HIDDEN_RATE_RECOMMENDED_CATALOGS_V1 on {{ $labels.service }}"
description: "EKS CATALOG_HIDDEN_RATE_RECOMMENDED_CATALOGS_V1 on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision-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-vision-web_prd-vision-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-web
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/discovery-ranking/vision-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-vision-web_prd-vision-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-web
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/discovery-ranking/vision-web-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-vision-web_prd-vision-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-web
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/discovery-ranking/vision/custom_alerts/FY_CACHE_HIT_ALERT.yaml
+32
View File
@@ -0,0 +1,32 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: FY_CACHE_HIT_BELOW_THRESHOLD_ALERT_AD_Organic_EKS
expr: ((sum(rate(vision_relevance_fy_cache_hit_total{tenant_context =~ "AD|ORGANIC"})) by (tenant_context)) / (sum(rate(vision_relevance_fy_request_total{tenant_context =~ "AD|ORGANIC"})) by (tenant_context)) *100) <= 84
for: 12m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-web
env: prd
priority: p0
annotations:
summary: "EKS FY_CACHE_HIT_LESS_THAN_EIGHTY_FIVE_ALERT_EKS on {{ $labels.service }}"
description: "EKS FY_CACHE_HIT_LESS_THAN_EIGHTY_FIVE_ALERT_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }} :: https://grafana.meesho.com/d/lyblxtJ4z/sale-dashboard?orgId=1&from=now-30m&to=now&tab=query&viewPanel=8 "
rules:
- alert: FY_CACHE_HIT_BELOW_THRESHOLD_ALERT_CT_EKS
expr: ((sum(rate(vision_relevance_fy_cache_hit_total{tenant_context =~ "CT"})) by (tenant_context)) / (sum(rate(vision_relevance_fy_request_total{tenant_context =~ "CT"})) by (tenant_context)) *100) <= 80
for: 12m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-web
env: prd
priority: p0
annotations:
summary: "EKS FY_CACHE_HIT_LESS_THAN_EIGHTY_FIVE_ALERT_EKS on {{ $labels.service }}"
description: "EKS FY_CACHE_HIT_LESS_THAN_EIGHTY_FIVE_ALERT_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }} :: https://grafana.meesho.com/d/lyblxtJ4z/sale-dashboard?orgId=1&from=now-30m&to=now&tab=query&viewPanel=8 "
helm-templates/victoria-metrics-alerts-config/configmap/demand/discovery-ranking/vision/custom_alerts/vision-CATALOG_HIDDEN_RATE_FOR_YOU_V2.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: CATALOG_HIDDEN_RATE_FOR_YOU_V2_EKS
expr: sum(rate(vision_catalog_invalid_hidden_value{parent="/api/v2/for-you"})) by(parent) >= 28000
for: 1m
labels:
severity: critical
bu: demand
team: discovery-ranking
service: vision-web
env: prd
priority: p0
annotations:
summary: "EKS CATALOG_HIDDEN_RATE_FOR_YOU_V2 on {{ $labels.service }}"
description: "EKS CATALOG_HIDDEN_RATE_FOR_YOU_V2 on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"

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