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/dataengg/data-platform/inhouse-ingestion-HTTP_4XX_Alert_Contour.yaml.bak
+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-inhouse-ingestion_prd-inhouse-ingestion-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 110000
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: inhouse-ingestion
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/dataengg/data-platform/inhouse-ingestion-HTTP_5XX_Alert.yaml
+16
View File
@@ -0,0 +1,16 @@
groups:
- name: EKS-App-Alerts
rules:
- alert: HTTP_5XX_Alert_EKS
expr: sum(nginx_ingress_controller_requests{cluster!="prod-ops-cluster", status=~"[5].*", service=~"prd-inhouse-ingestion", job=~"kubernetes-service-endpoints"}) by (cluster, service, ingress, job) >= 500
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: inhouse-ingestion
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/dataengg/data-platform/inhouse-ingestion-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-inhouse-ingestion_prd-inhouse-ingestion-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: inhouse-ingestion
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/dataengg/data-platform/inhouse-ingestion-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-inhouse-ingestion", job=~"kubernetes-service-endpoints"}) by (cluster, service, le, ingress, namespace, job)) >= 0.75
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: inhouse-ingestion
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/dataengg/data-platform/inhouse-ingestion-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-inhouse-ingestion_prd-inhouse-ingestion-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 450
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: inhouse-ingestion
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/dataengg/data-platform/messaging-api-external-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-messaging-api-external_prd-messaging-api-external-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: messaging-api-external
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/dataengg/data-platform/messaging-api-external-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-messaging-api-external_prd-messaging-api-external-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: messaging-api-external
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/dataengg/data-platform/messaging-api-external-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-messaging-api-external_prd-messaging-api-external-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: messaging-api-external
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/dataengg/data-platform/messaging-api-internal-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-messaging-api-internal_prd-messaging-api-internal-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 450
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: messaging-api-internal
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/dataengg/data-platform/messaging-api-internal-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-messaging-api-internal_prd-messaging-api-internal-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: messaging-api-internal
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/dataengg/data-platform/messaging-api-internal-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-messaging-api-internal_prd-messaging-api-internal-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 125
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: messaging-api-internal
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/dataengg/data-platform/metastore-HTTP_4XX_Alert.yaml.bak
+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-metastore", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: metastore
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/dataengg/data-platform/metastore-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-metastore_prd-metastore-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: metastore
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/dataengg/data-platform/metastore-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-metastore", job=~"kubernetes-pods"}[1m])) by (cluster, service, ingress, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: metastore
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/dataengg/data-platform/metastore-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-metastore_prd-metastore-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: metastore
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/dataengg/data-platform/metastore-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-metastore", job=~"kubernetes-pods"}[1m])) by (cluster, service, le, ingress, namespace, job)) >= 0.75
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: metastore
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/dataengg/data-platform/metastore-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-metastore_prd-metastore-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 0.75
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: metastore
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/dataengg/data-platform/model-metastore-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-model-metastore_prd-model-metastore-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: model-metastore
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/dataengg/data-platform/model-metastore-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-model-metastore_prd-model-metastore-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: model-metastore
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/dataengg/data-platform/model-metastore-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-model-metastore_prd-model-metastore-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
for: 1m
labels:
severity: critical
bu: dataengg
team: data-platform
service: model-metastore
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 }}"