added repo
This commit is contained in:
+16
@@ -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-manifest-supply_prd-manifest-supply_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
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 }}"
|
||||
+16
@@ -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-manifest-supply_prd-manifest-supply_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
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 }}"
|
||||
+16
@@ -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-manifest-supply_prd-manifest-supply_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
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 }}"
|
||||
+16
@@ -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-manifest-supply_prd-manifest-supply_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 5000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
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 }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_CP_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_CP_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 4
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_CP_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_CP_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_DH_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_DEL_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) > 1.5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_DH_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_DH_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_DTDC_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_DTDC_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 4
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_DTDC_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_DTDC_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_ECOM_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_ECOM_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 1.5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_ECOM_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_ECOM_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_ML_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_meeshologistics_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_ML_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_ML_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_SF_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_SF_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) >= 1.2
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_SF_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_SF_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_LATENCY_XB_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_XB_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) > 1.5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_LATENCY_XB_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_LATENCY_XB_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: P99_Latency_Alert_DH_FWD_EKS
|
||||
expr: avg by (cluster)(OUT_manifest_carrier_DEL_1{quantile="0.99", job="kubernetes-manifest-metrics"} != 0) > 1500
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: fulfilment
|
||||
service: manifest-supply
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS P99_Latency_Alert_DH_FWD on {{ $labels.service }}"
|
||||
description: "EKS P99_Latency_Alert_DH_FWD on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
Reference in New Issue
Block a user