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/web/admin-panel-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-admin-panel", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 600
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel
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/web/admin-panel-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel_prd-admin-panel_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 600
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-admin-panel", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel
env: prd
priority: p0
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel_prd-admin-panel_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-admin-panel", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 7.5
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel
env: prd
priority: p0
annotations:
summary: "EKS Latency/Response Time P99 Alert on {{ $labels.service }}"
description: "EKS Latency/Response Time P99 Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-admin-panel_prd-admin-panel_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 7500
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-acquisition-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-admin-panel-acquisition_prd-admin-panel-acquisition_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: warning
bu: demand
team: web
service: admin-panel-acquisition
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/web/admin-panel-acquisition-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-admin-panel-acquisition_prd-admin-panel-acquisition_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 30
for: 1m
labels:
severity: warning
bu: demand
team: web
service: admin-panel-acquisition
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/web/admin-panel-acquisition-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-admin-panel-acquisition_prd-admin-panel-acquisition_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 10000
for: 1m
labels:
severity: warning
bu: demand
team: web
service: admin-panel-acquisition
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/web/admin-panel-cataloging-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-admin-panel-cataloging_prd-admin-panel-cataloging_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: warning
bu: demand
team: web
service: admin-panel-cataloging
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/web/admin-panel-cataloging-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-admin-panel-cataloging_prd-admin-panel-cataloging_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 30
for: 1m
labels:
severity: warning
bu: demand
team: web
service: admin-panel-cataloging
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/web/admin-panel-cataloging-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-admin-panel-cataloging_prd-admin-panel-cataloging_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 10000
for: 1m
labels:
severity: warning
bu: demand
team: web
service: admin-panel-cataloging
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/web/admin-panel-communications-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-communications_prd-admin-panel-communications_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-communications
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-communications-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-communications_prd-admin-panel-communications_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-communications
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-communications-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-admin-panel-communications_prd-admin-panel-communications_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 60000
for: 2m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-communications
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-container-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-container_prd-admin-panel-container_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-container
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-container-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-container_prd-admin-panel-container_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-container
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-container-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-admin-panel-container_prd-admin-panel-container_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1250
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-container
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-discovery-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-admin-panel-discovery", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-discovery
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/web/admin-panel-discovery-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-discovery_prd-admin-panel-discovery_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-discovery
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-discovery-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-admin-panel-discovery", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-discovery
env: prd
priority: p0
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-discovery-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-discovery_prd-admin-panel-discovery_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-discovery
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-discovery-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-admin-panel-discovery", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 5
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-discovery
env: prd
priority: p0
annotations:
summary: "EKS Latency/Response Time P99 Alert on {{ $labels.service }}"
description: "EKS Latency/Response Time P99 Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-discovery-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-admin-panel-discovery_prd-admin-panel-discovery_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 5000
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-discovery
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-user-growth-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-admin-panel-user-growth", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-user-growth
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/web/admin-panel-user-growth-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-user-growth_prd-admin-panel-user-growth_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-user-growth
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-user-growth-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-admin-panel-user-growth", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-user-growth
env: prd
priority: p0
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-user-growth-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-user-growth_prd-admin-panel-user-growth_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-user-growth
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-user-growth-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-admin-panel-user-growth", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 1.25
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-user-growth
env: prd
priority: p0
annotations:
summary: "EKS Latency/Response Time P99 Alert on {{ $labels.service }}"
description: "EKS Latency/Response Time P99 Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-user-growth-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-admin-panel-user-growth_prd-admin-panel-user-growth_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1250
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-user-growth
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-v2-HTTP_4XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[4].*", service=~"prd-admin-panel-v2", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-v2
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/web/admin-panel-v2-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-v2_prd-admin-panel-v2_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-v2
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-v2-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-admin-panel-v2", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-v2
env: prd
priority: p0
annotations:
summary: "EKS HTTP 5XX Alert on {{ $labels.service }}"
description: "EKS HTTP 5XX Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-v2-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-admin-panel-v2_prd-admin-panel-v2_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-v2
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-v2-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-admin-panel-v2", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 5
for: 1m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-v2
env: prd
priority: p0
annotations:
summary: "EKS Latency/Response Time P99 Alert on {{ $labels.service }}"
description: "EKS Latency/Response Time P99 Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/admin-panel-v2-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-admin-panel-v2_prd-admin-panel-v2_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 10000
for: 2m
labels:
severity: critical
bu: demand
team: web
service: admin-panel-v2
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/community-frontend/mandatory_alerts/community-frontend-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-frontend_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 2m
labels:
severity: critical
bu: demand
team: web
service: community-frontend
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/web/community-frontend/mandatory_alerts/community-frontend-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-frontend_.*", envoy_response_code=~"[5].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 2m
labels:
severity: critical
bu: demand
team: web
service: community-frontend
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/web/community-frontend/mandatory_alerts/community-frontend-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-frontend_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 2m
labels:
severity: critical
bu: demand
team: web
service: community-frontend
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/web/meesho-engagement-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-engagement_prd-meesho-engagement_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-engagement
env: prd
priority: p1
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho-engagement-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-engagement_prd-meesho-engagement_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-engagement
env: prd
priority: p1
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho-engagement-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-meesho-engagement_prd-meesho-engagement_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 8000
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-engagement
env: prd
priority: p1
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho-engagement/mandatory_alerts/meesho-engagement-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-engagement_.*",envoy_response_code=~"[4].*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-engagement
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/web/meesho-engagement/mandatory_alerts/meesho-engagement-HTTP_5XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-engagement_.*", 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: web
service: meesho-engagement
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/web/meesho-engagement/mandatory_alerts/meesho-engagement-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-meesho-engagement_.*", envoy_cluster_name!~".*canary.*"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1500
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-engagement
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/web/meesho-mba-front-end-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-meesho-mba-front-end_prd-meesho-mba-front-end_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-mba-front-end
env: prd
priority: p2
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/web/meesho-mba-front-end-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-meesho-mba-front-end_prd-meesho-mba-front-end_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-mba-front-end
env: prd
priority: p2
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/web/meesho-mba-front-end-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-meesho-mba-front-end_prd-meesho-mba-front-end_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 500
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-mba-front-end
env: prd
priority: p2
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/web/meesho-sputnik-HTTP_4XX_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-sputnik_prd-meesho-sputnik_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-sputnik
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/web/meesho-sputnik-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-meesho-sputnik_prd-meesho-sputnik_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-sputnik
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/web/meesho-sputnik-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-meesho-sputnik_prd-meesho-sputnik_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-sputnik
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/web/meesho-sputnik-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-sputnik_prd-meesho-sputnik_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-sputnik
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho-sputnik-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-meesho-sputnik_prd-meesho-sputnik_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 700
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-sputnik
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/web/meesho-sputnik-P99_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-meesho-sputnik_prd-meesho-sputnik_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 700
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-sputnik
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/web/meesho-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-meesho-web_prd-meesho-web_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-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/web/meesho-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-meesho-web_prd-meesho-web_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 150
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-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/web/meesho-web-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-meesho-web_prd-meesho-web_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 1500
for: 2m
labels:
severity: critical
bu: demand
team: web
service: meesho-web
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/web/meesho-web-views-HTTP_4XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_4XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-web-views_prd-meesho-web-views_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-web-views
env: prd
priority: p0
annotations:
summary: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_4XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho-web-views-HTTP_5XX_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-meesho-web-views_prd-meesho-web-views_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-web-views
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho-web-views-P99_Latency_Alert_Contour.yaml
+17
View File
@@ -0,0 +1,17 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: P99_Latency_Alert_Contour_EKS
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-meesho-web-views_prd-meesho-web-views_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2000
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-web-views
env: prd
priority: p0
annotations:
summary: "EKS P99_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS P99_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}
LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/meesho_web_views-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-meesho-web-views", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 200
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-web-views
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/web/meesho_web_views-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(rate(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-meesho-web-views", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-web-views
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/web/meesho_web_views-Latency_P99_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: Latency_P99_Alert_EKS
expr: histogram_quantile(0.99, sum(rate(nginx_ingress_controller_request_duration_seconds_bucket{cluster!="prod-ops-cluster", service=~"prd-meesho-web-views", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 1.25
for: 1m
labels:
severity: critical
bu: demand
team: web
service: meesho-web-views
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/web/pow-checkout/custom_alerts/pow-checkout-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-pow-checkout_prd-pow-checkout_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: web
service: pow-checkout
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/web/pow-checkout/custom_alerts/pow-checkout-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-pow-checkout_prd-pow-checkout_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 60
for: 1m
labels:
severity: critical
bu: demand
team: web
service: pow-checkout
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/web/pow-checkout/custom_alerts/pow-checkout-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-pow-checkout_prd-pow-checkout_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 800
for: 1m
labels:
severity: critical
bu: demand
team: web
service: pow-checkout
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/web/reseller-profile-front-end-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-reseller-profile-front-end_prd-reseller-profile-front-end_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
for: 1m
labels:
severity: critical
bu: demand
team: web
service: reseller-profile-front-end
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/web/reseller-profile-front-end-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-reseller-profile-front-end_prd-reseller-profile-front-end_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
for: 1m
labels:
severity: critical
bu: demand
team: web
service: reseller-profile-front-end
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/web/reseller-profile-front-end-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-reseller-profile-front-end_prd-reseller-profile-front-end_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 2000
for: 1m
labels:
severity: critical
bu: demand
team: web
service: reseller-profile-front-end
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/web/webviews-native/custom_alerts/webviews-native-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-webviews-native_prd-webviews-native_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 600
for: 1m
labels:
severity: critical
bu: demand
team: web
service: webviews-native
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/web/webviews-native/custom_alerts/webviews-native-HTTP_5XX_Latency_Alert_Contour.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Latency_Alert_Contour_EKS
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-webviews-native_prd-webviews-native_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 500
for: 1m
labels:
severity: critical
bu: demand
team: web
service: webviews-native
env: prd
priority: p0
annotations:
summary: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }}"
description: "EKS HTTP_5XX_Latency_Alert_Contour on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
helm-templates/victoria-metrics-alerts-config/configmap/demand/web/webviews-native/custom_alerts/webviews-native-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-webviews-native_prd-webviews-native_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 700
for: 1m
labels:
severity: critical
bu: demand
team: web
service: webviews-native
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 }}"