added repo
This commit is contained in:
+16
@@ -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 }}"
|
||||
+16
@@ -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 }}"
|
||||
+16
@@ -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 }}"
|
||||
+16
@@ -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 }}"
|
||||
+16
@@ -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 }}"
|
||||
Reference in New Issue
Block a user