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-feed-entity-admin-service_prd-feed-entity-admin-service_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: feed-entity-admin-service
|
||||
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-feed-entity-admin-service_prd-feed-entity-admin-service_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: feed-entity-admin-service
|
||||
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: Controller_P99_Alert_Per_API_EKS
|
||||
expr: histogram_quantile(0.99, sum(rate(CONTROLLER_execTime_bucket{uri=~".*details.*",service="feed-entity-service"}[1m])) by (le, uri, env)) >= 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: feed-entity-service
|
||||
env: prd
|
||||
priority: p1
|
||||
annotations:
|
||||
summary: "EKS Controller_P99_Alert_Per_API on {{ $labels.service }}"
|
||||
description: "EKS Controller_P99_Alert_Per_API on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+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-feed-entity-service_prd-feed-entity-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: feed-entity-service
|
||||
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-feed-entity-service_prd-feed-entity-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: feed-entity-service
|
||||
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: P99_Latency_Alert_Contour_EKS
|
||||
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-feed-entity-service_prd-feed-entity-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 50
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: feed-entity-service
|
||||
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 }}"
|
||||
+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-link-resolver-service_prd-link-resolver-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: link-resolver-service
|
||||
env: prd
|
||||
priority: p3
|
||||
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-link-resolver-service_prd-link-resolver-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: link-resolver-service
|
||||
env: prd
|
||||
priority: p3
|
||||
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: Latency_P99_Alert_Contour_EKS
|
||||
expr: histogram_quantile(0.99, sum(rate(envoy_cluster_upstream_rq_time_bucket{envoy_cluster_name=~"prd-link-resolver-service_prd-link-resolver-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 120
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: link-resolver-service
|
||||
env: prd
|
||||
priority: p3
|
||||
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: HTTP_4XX_Alert_Contour_EKS
|
||||
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-merch-merchandising-admin_prd-merch-merchandising-admin-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 20
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: merch-merchandising-admin
|
||||
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 }}"
|
||||
+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-merch-merchandising-admin_prd-merch-merchandising-admin-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: merch-merchandising-admin
|
||||
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 }}"
|
||||
+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-merch-merchandising-admin_prd-merch-merchandising-admin-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 5000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: merch-merchandising-admin
|
||||
env: prd
|
||||
priority: p2
|
||||
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: HTTP_4XX_Alert_Contour_EKS
|
||||
expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-merch-merchandising-web_prd-merch-merchandising-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: merch-merchandising-web
|
||||
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 }}"
|
||||
+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-merch-merchandising-web_prd-merch-merchandising-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: merch-merchandising-web
|
||||
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 }}"
|
||||
+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-merch-merchandising-web_prd-merch-merchandising-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: merch-merchandising-web
|
||||
env: prd
|
||||
priority: p0
|
||||
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: ofs_catalog_event_topic_Consumer_Lag_Exceeded_200_EKS
|
||||
expr: sum(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpdiscoveryteam.inpx1m.*", name="OffsetLag",topic=~"ofs-catalog-event-topic", groupId=~"catalog_feed"})by(groupId,topic) > 200
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: organic-feed-consumer
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS ofs_catalog_event_topic_Consumer_Lag_Exceeded_200 on {{ $labels.service }}"
|
||||
description: "EKS ofs_catalog_event_topic_Consumer_Lag_Exceeded_200 on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+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-organic-feed-web_prd-organic-feed-web-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: organic-feed-web
|
||||
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 }}"
|
||||
+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-organic-feed-web_prd-organic-feed-web-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: organic-feed-web
|
||||
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 }}"
|
||||
+16
@@ -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-organic-feed-web_prd-organic-feed-web-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: organic-feed-web
|
||||
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 }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: OFS_FY_CATALOG_RPS_ALERT_EKS
|
||||
expr: ((sum by (service, uri, cluster) (CONTROLLER_execTime_count{service="organic-feed-web", cluster="p-demand-cluster", uri="/api/v1/for-you/catalogs"})) / 30) >= 900
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: organic-feed-web
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS OFS_FY_CATALOG_RPS_ALERT_EKS on {{ $labels.service }}"
|
||||
description: "EKS OFS_FY_CATALOG_RPS_ALERT_EKS on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+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-reseller-tracking-service_prd-reseller-tracking-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 180
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: reseller-tracking-service
|
||||
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 }}"
|
||||
+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-reseller-tracking-service_prd-reseller-tracking-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 5
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: reseller-tracking-service
|
||||
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 }}"
|
||||
+16
@@ -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-tracking-service_prd-reseller-tracking-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 750
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: reseller-tracking-service
|
||||
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 }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: hulk_user_widget_group_ranking_v2_Consumer_Lag_Exceeded_15_Million_EKS
|
||||
expr: sum(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpdiscoveryteam.inpx1m.*", name="OffsetLag",topic=~"hulk_user-widget-group-ranking_v2", groupId=~"widget_aggregator_user_widget_group_ranking_v2"})by(groupId,topic) > 15000000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-consumer
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS hulk_user_widget_group_ranking_v2_Consumer_Lag_Exceeded_15_Million on {{ $labels.service }}"
|
||||
description: "EKS hulk_user_widget_group_ranking_v2_Consumer_Lag_Exceeded_15_Million on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: hulk_user_widget_ranking_v1_Consumer_Lag_Exceeded_150_Million_EKS
|
||||
expr: sum(kafka_consumer_group_ConsumerLagMetrics_Value{instance=~".*bacpdiscoveryteam.inpx1m.*", name="OffsetLag",topic=~"hulk_user-widget-ranking_v1", groupId=~"widget_aggregator_user_widget_ranking"})by(groupId,topic) > 150000000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-consumer
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS hulk_user_widget_ranking_v1_Consumer_Lag_Exceeded_150_Million on {{ $labels.service }}"
|
||||
description: "EKS hulk_user_widget_ranking_v1_Consumer_Lag_Exceeded_150_Million on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+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-widget-aggregator-service_prd-widget-aggregator-service-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-service
|
||||
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 }}"
|
||||
+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-widget-aggregator-service_prd-widget-aggregator-service-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 400
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-service
|
||||
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 }}"
|
||||
+16
@@ -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-widget-aggregator-service_prd-widget-aggregator-service-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 600
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-service
|
||||
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 }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: WidgetMetaExecutorThreadpool_EKS
|
||||
expr: sum by (instance) (executor_active_threads{service="widget-aggregator-service", name = "widgetMetaExecutor"}) > 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-service
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS WidgetMetaExecutorThreadpool on {{ $labels.service }}"
|
||||
description: "EKS WidgetMetaExecutorThreadpool on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: widgetAggregatorExecutorThreadpool_EKS
|
||||
expr: sum by (instance) (executor_active_threads{service="widget-aggregator-service", name = "widgetAggregatorExecutor"}) > 100
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-service
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS widgetAggregatorExecutorThreadpool on {{ $labels.service }}"
|
||||
description: "EKS widgetAggregatorExecutorThreadpool on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
groups:
|
||||
- name: EKS-App-Alerts
|
||||
rules:
|
||||
- alert: widgetAggregatorTomcatThreadCount_EKS
|
||||
expr: tomcat_threads_busy_threads{service="widget-aggregator-service"} > 150
|
||||
for: 1m
|
||||
labels:
|
||||
severity: critical
|
||||
bu: demand
|
||||
team: product-feed
|
||||
service: widget-aggregator-service
|
||||
env: prd
|
||||
priority: p0
|
||||
annotations:
|
||||
summary: "EKS widgetAggregatorTomcatThreadCount on {{ $labels.service }}"
|
||||
description: "EKS widgetAggregatorTomcatThreadCount on {{ $labels.service }} VALUE = {{ $value }}\n LABELS: {{ $labels }}"
|
||||
Reference in New Issue
Block a user