added repo

2026-08-26 03:39:42 +05:30
parent 45c25a95af
commit b8575bb8b9
6889 changed files with 1217125 additions and 0 deletions
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_HBASE_READ_FAILURE_EKS
+    expr: increase(sum(HBASE_READ_FAILURE_value) by (table,operation) [1m]) >= 1
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_HBASE_READ_FAILURE on {{ $labels.service }}"
+      description: "EKS AB_HBASE_READ_FAILURE on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_HBASE_READ_FAILURE_FOR_SCAN_USER_AUDIENCE_MAP_EKS
+    expr: increase(sum(HBASE_READ_FAILURE_value{table="user_audience_map",operation="scan"}) by (table,operation) [1h]) >= 1
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_HBASE_READ_FAILURE_FOR_SCAN_USER_AUDIENCE_MAP on {{ $labels.service }}"
+      description: "EKS AB_HBASE_READ_FAILURE_FOR_SCAN_USER_AUDIENCE_MAP on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_KAFKA_PRODUCER_AVG_LATENCY_EKS
+    expr: avg(kafka_producer_producer_metrics_request_latency_avg{app=~"prd-ab-service-read|prd-ab-service-write|prd-ab-worker-create|prd-ab-worker-abacus"})[1m] >= 100
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_KAFKA_PRODUCER_AVG_LATENCY on {{ $labels.service }}"
+      description: "EKS AB_KAFKA_PRODUCER_AVG_LATENCY on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AUDIENCE_ENTITY_MAP_MQ_SEND_EVENT_FAILURES_EKS
+    expr: sum(increase(MQ_PRODUCER_SEND_EVENT_FAILURE_value{topic="entity.audience.map.update.topic"})[1m]) > 0
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AUDIENCE_ENTITY_MAP_MQ_SEND_EVENT_FAILURES on {{ $labels.service }}"
+      description: "EKS AUDIENCE_ENTITY_MAP_MQ_SEND_EVENT_FAILURES on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AUDIENCE_REFRESH_REDIS_QUEUE_LAG_EKS
+    expr: sum(REDIS_QUEUE_SIZE_value) by (queue) [1h] >= 200
+    for: 10m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AUDIENCE_REFRESH_REDIS_QUEUE_LAG on {{ $labels.service }}"
+      description: "EKS AUDIENCE_REFRESH_REDIS_QUEUE_LAG on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -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-ab-service-read_prd-ab-service-read-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50000
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      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 }}"
@@ -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-ab-service-read_prd-ab-service-read-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 600
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      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 }}"
@@ -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-ab-service-read_prd-ab-service-read-primary_80"}[1m])) by (cluster, envoy_cluster_name, le, job)) >= 40
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-read
+      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 }}"
@@ -0,0 +1,16 @@
+groups:
+  - name: EKS-App-Alerts
+    rules:
+      - alert: EKS-ab-service-read-POD_Memory_Crossed_Threshold-Alerts
+        expr: sum(container_memory_working_set_bytes{pod=~"prd-ab-service-read-.*",image!=""}) by (pod) / sum(kube_pod_container_resource_limits{pod=~"prd-ab-service-read-.*", resource=~'memory', job=~'kube-state-metrics-p-.*'}) by (pod) * 100 > 85
+        for: 1m
+        labels:
+          severity: critical
+          bu: dataengg
+          team: data-platform-experimentation
+          service: ab-service-read
+          env: prd
+          priority: p0
+        annotations:
+          summary: High Memory Utilisation for EKS Pod - {{ $labels.pod }}
+          description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been utilising Memory over {{ $value }}% in the last 1 min.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_HBASE_CALL_QUEUE_TOO_BIG_EKS
+    expr: sum(increase(HBase_RegionServer_IPC_exceptions_callQueueTooBig{cluster="bac-p-ab-hbase"})[1m]) by (cluster) >= 3000
+    for: 2m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-write
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_HBASE_CALL_QUEUE_TOO_BIG on {{ $labels.service }}"
+      description: "EKS AB_HBASE_CALL_QUEUE_TOO_BIG on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_HBASE_WRITE_FAILURE_EKS
+    expr: increase(sum(HBASE_WRITE_FAILURE_value) by (table,operation)[1m]) >= 1
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-write
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_HBASE_WRITE_FAILURE on {{ $labels.service }}"
+      description: "EKS AB_HBASE_WRITE_FAILURE on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_HBASE_WRITE_FAILURE_FOR_DELETE_USER_AUDIENCE_MAP_EKS
+    expr: increase(sum(HBASE_WRITE_FAILURE_value{operation="deleteBulk",table="user_audience_map"}) by (table,operation)[1h]) >= 1
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-write
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_HBASE_WRITE_FAILURE_FOR_DELETE_USER_AUDIENCE_MAP on {{ $labels.service }}"
+      description: "EKS AB_HBASE_WRITE_FAILURE_FOR_DELETE_USER_AUDIENCE_MAP on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: AB_HBASE_WRITE_FAILURE_FOR_UPDATE_USER_AUDIENCE_MAP_EKS
+    expr: increase(sum(HBASE_WRITE_FAILURE_value{operation="updateBulk",table="user_audience_map"}) by (table,operation)[1h]) >= 1
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-write
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS AB_HBASE_WRITE_FAILURE_FOR_UPDATE_USER_AUDIENCE_MAP on {{ $labels.service }}"
+      description: "EKS AB_HBASE_WRITE_FAILURE_FOR_UPDATE_USER_AUDIENCE_MAP on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: HTTP_4XX_Alert_Contour_EKS_EKS
+    expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-ab-service-write_prd-ab-service-write-primary_80",envoy_response_code=~"[4].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-write
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}"
+      description: "EKS HTTP_4XX_Alert_Contour_EKS on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+- name: EKS-App-Alerts
+  rules:
+  - alert: HTTP_5XX_Alert_Contour_EKS_EKS
+    expr: sum(rate(envoy_cluster_upstream_rq{envoy_cluster_name=~"prd-ab-service-write_prd-ab-service-write-primary_80",envoy_response_code=~"[5].*"}[1m])) by (cluster, envoy_cluster_name, job) * 60 >= 50
+    for: 1m
+    labels:
+      severity: critical
+      bu: dataengg
+      team: data-platform-experimentation
+      service: ab-service-write
+      env: prd
+      priority: p0
+    annotations:
+      summary: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}"
+      description: "EKS HTTP_5XX_Alert_Contour_EKS on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+  - name: EKS-App-Alerts
+    rules:
+      - alert: P99_Latency_Dynamic_Audience_Add_Alert_EKS
+        expr: histogram_quantile(0.99, sum(rate(CONTROLLER_execTime_bucket{uri=~"(/v2/entity/dynamic-audience/add)",service="ab-service-write"}[1m])) by (le, service, uri)) >= 500
+        for: 3m
+        labels:
+          severity: critical
+          bu: dataengg
+          team: data-platform-experimentation
+          service: ab-service-write
+          env: prd
+          priority: p0
+        annotations:
+          summary: "EKS P99_Dynamic_Audience_Add_Latency_Alert on {{ $labels.service }}"
+          description: "EKS P99_Dynamic_Audience_Add_Latency_Alert on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
@@ -0,0 +1,16 @@
+groups:
+  - name: EKS-App-Alerts
+    rules:
+      - alert: P99_Latency_Dynami_Audience_Add_Alert_EKS
+        expr: histogram_quantile(0.99, sum(rate(CONTROLLER_execTime_bucket{uri=~"(/v2/entity/audience/update/bulk)",service="ab-service-write"}[1m])) by (le, service, uri)) >= 1500
+        for: 3m
+        labels:
+          severity: critical
+          bu: dataengg
+          team: data-platform-experimentation
+          service: ab-service-write
+          env: prd
+          priority: p0
+        annotations:
+          summary: "EKS P99_Update_Audience_Bulk_Latency_Alert on {{ $labels.service }}"
+          description: "EKS P99_Update_Audience_Bulk_Latency_Alert on {{ $labels.service }}  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"