added repo
This commit is contained in:
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Controller_Http_Non_2xx_alert_EKS
|
||||
expr: avg(sum by (service,uri,httpCode) (CONTROLLER_execTime_count{podNamespace=~"prd-advertisement",httpCode!~"2[0-9]{2}"} )) >= 200
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Controller_Http_Non_2xx_alert on {{ $labels.service }}"
|
||||
description: "EKS Controller_Http_Non_2xx_alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Controller_latency_p99_alert_EKS
|
||||
expr: avg(histogram_quantile(0.99, sum(rate(CONTROLLER_execTime_bucket{uri!~".*health.*",podNamespace=~"prd-advertisement"}[1m])) by (le))) >= 200
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Controller_latency_p99_alert on {{ $labels.service }}"
|
||||
description: "EKS Controller_latency_p99_alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Feed_Aggregator_Ads_Failures_Alert_EKS
|
||||
expr: max(sum(resilience4j_circuitbreaker_buffered_calls{kind="failed",name=~".*clp-ad-service-breaker*"})) >= 1000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Feed_Aggregator_Ads_Failures_Alert on {{ $labels.service }}"
|
||||
description: "EKS Feed_Aggregator_Ads_Failures_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Feed_Aggregator_Ads_Failures_Alerts_EKS
|
||||
expr: max(sum(resilience4j_circuitbreaker_buffered_calls{kind="failed",name=~".*clp-ad-service-breaker*"})) >= 1000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Feed_Aggregator_Ads_Failures_Alerts on {{ $labels.service }}"
|
||||
description: "EKS Feed_Aggregator_Ads_Failures_Alerts on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Feed_Aggregator_Ads_Short_Circuits_Alert_EKS
|
||||
expr: max(sum(resilience4j_circuitbreaker_state{name=~".*ad-service-breaker*",state!="closed",name=~ ".*collection-ad-service.*"}) by (name,state)) >= 1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Feed_Aggregator_Ads_Short_Circuits_Alert on {{ $labels.service }}"
|
||||
description: "EKS Feed_Aggregator_Ads_Short_Circuits_Alert on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Feed_Aggregator_Ads_Short_Circuits_Alerts_EKS
|
||||
expr: max(sum(resilience4j_circuitbreaker_state{name=~".*ad-service-breaker*",state!="closed",name=~ ".*collection-ad-service.*"}) by (name,state)) >= 1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Feed_Aggregator_Ads_Short_Circuits_Alerts on {{ $labels.service }}"
|
||||
description: "EKS Feed_Aggregator_Ads_Short_Circuits_Alerts on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Feed_Aggregator_Ads_Slow_Call_Percentage_Alert_EKS_EKS
|
||||
expr: max(resilience4j_circuitbreaker_slow_call_rate{name=~".*clp-ad-service-breaker*"}) >= 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Feed_Aggregator_Ads_Slow_Call_Percentage_Alert_EKS on {{ $labels.service }}"
|
||||
description: "EKS Feed_Aggregator_Ads_Slow_Call_Percentage_Alert_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: Feed_Aggregator_Ads_Slow_Call_Percentage_Alerts_EKS_EKS
|
||||
expr: max(resilience4j_circuitbreaker_slow_call_rate{name=~".*collection-ad-service-breaker*"}) >= 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: supply
|
||||
team: supplier-ads
|
||||
service: advertisement
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Feed_Aggregator_Ads_Slow_Call_Percentage_Alerts_EKS on {{ $labels.service }}"
|
||||
description: "EKS Feed_Aggregator_Ads_Slow_Call_Percentage_Alerts_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
Reference in New Issue
Block a user