groups: - name: RDS-Alerts rules: - alert: cpuUsage70% expr: aws_rds_cpuutilization_maximum{job="aws_rds", dbinstance_identifier !~ "bac-p-payments-slave-02|data-p-emr-airflow-prism-new-upgraded|data-p-metabase-presto-ext-rds|bac-p-live-commerce|bac-p-data-platform-presto-gateway|supply-prod-admin-slave|bac-p-cis|data-p-metabase-rds|supply-prod"} offset 10m > 70 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "CPU utilization of the RDS {{ $labels.dbinstance_identifier }} is greater than 70" description: "CPU Utilization of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }}" - alert: cpuUsage50% expr: aws_rds_cpuutilization_maximum{job="aws_rds", dbinstance_identifier =~ "supply-prod"} offset 10m > 50 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "CPU utilization of the RDS {{ $labels.dbinstance_identifier }} is greater than 50" description: "CPU Utilization of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }}" - alert: cpuUsage85% expr: aws_rds_cpuutilization_maximum{job="aws_rds", dbinstance_identifier =~ "bac-p-data-platform-presto-gateway|data-p-metabase-presto-ext-rds"} offset 10m > 85 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "CPU utilization of the RDS {{ $labels.dbinstance_identifier }} is greater than 85" description: "CPU Utilization of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }}" - alert: cpuUsage80% expr: aws_rds_cpuutilization_maximum{job="aws_rds", dbinstance_identifier =~ "data-p-metabase-rds|bac-p-data-platform-presto-gateway|bac-p-live-commerce"} offset 10m > 80 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "CPU utilization of the RDS {{ $labels.dbinstance_identifier }} is greater than 80" description: "CPU Utilization of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }}" - alert: cpuUsage90% expr: aws_rds_cpuutilization_maximum{job="aws_rds", dbinstance_identifier =~ "supply-prod-admin-slave|bac-p-cis|bac-p-payments-slave-02"} offset 10m > 90 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "CPU utilization of the RDS {{ $labels.dbinstance_identifier }} is greater than 90" description: "CPU Utilization of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }}" ################################## RDS FreeStorage ################################# - alert: freeStorage_300G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier !~ 'data-p-metabase-presto-rds-perf-cmr-1909|metabase-presto-rds-perf-cmr-1909|bac-p-ab-service|bac-p-content-new|bac-p-price-recommendation-new|bac-p-price-recommendation-data-slave-new|bac-p-grafana-dp|bac-p-price-data-slave-new|bac-p-tracking-new|bac-p-tracking-new-slave|bac-preprod-ab-rds|bac-p-whatsapp-client-eks|bac-p-content-data-slave-new|bac-p-eks-presto-resource-group|data-p-metabase-presto-rds-perf-cmr-1208|data-p-metabase-presto-ext-rds|bac-p-transact-slave-02|bac-p-supplier-return-assurance |bac-p-supplier-return-assurance-slave|bac-p-meesholink|bac-p-price-new|bac-p-supplier-detail-new|bac-p-ab-service-pre-prod|bac-p-inventory-data-slave-new|bac-p-inventory-new|bac-p-transact|bac-p-sx-support.*|data-p-metabase-presto-nrt-rds|data-p-metabase-presto-rds-perf-dataops-756|data-p-rds-airflow-etl-2-4|data-p-superset-dashboard|bac-p-supplier-incentives-data.*|bac-p-supplier-detail-data.*|bac-p-producer-fulfilment.*|bac-p-growth.*|bac-p-farmiso-gcp.*|bac-p-display-ads.*|bac-p-di-metastore|bac-p-app-dbs-metabase|bac-p-farmiso-relay-new|bac-p-supplier-optin-slave|bac-p-fraud-supplier-platform|bac-p-fraud-supplier-platform-slave|bac-p-supplier-optin-data-slave|bac-p-relay|bac-p-offer-platform-data-slave|bac-p-relay-data-slave1|bac-p-supplier-optin|bac-p-loyalty-earn-engine|bac-p-loyalty-earn-engine-slave.*|bac-p-loyalty-earn-engine-data-slave|bac-p-offer-platform|bac-p-offer-platform-slave|bac-p-datahub.*|bac-p-supplier-data-platform|bac-p-taxonomy-new-data-slave|bac-p-vmextractor.*|bac-p-live-commerce.*|data-p-sb-presto-rds-slave.*|bac-p-listing-go-live.*|bac-p-review|bac-p-shipment-service.*|data-p-hive-metastore-slave.*|bac-p-ct-qct-v2.*|bac-p-payments.*|bac-p-address.*|bac-p-data-platform-presto-gateway.*|bac-p-community.*|bac-p-community-data-slave.*|bac-p-pow.*|bac-p-supplier-orders-data-slave.*|bac-p-supplier-business-partner.*|data-p-sb-presto-rds|bac-p-supplier-payment-dummy-new|bac-p-order-service.*|bac-p-review-slave-02|data-p-metabase-rds-temp|data-p-metabase-presto-rds|bac-p-wallet|data-p-emr-airflow-prism|data-p-emr-airflow-prism-new|bac-p-payments-slave-01|bac-p-wallet-slave-01|bac-p-supplier-ums-slave|bac-p-cis-slave-01|bac-p-review-data-slave-01|bac-p-cis|bac-p-supplier-ums|supply-prod|bac-p-whatsapp-client|bac-p-cdp-slave-01|bac-p-cdp|bac-p-tracking-slave-01|front-p-catalog|bac-p-supply-order-slave|bac-p-tracking-01|bac-p-supply-payment-slave|supply-prod-admin-slave|supply-prod-heevo-slave-01|data-p-hive-metastore|front-p-webviews|bac-p-supplier-orders-slave|data-p-metabase-rds|data-p-metabase-main-rds|hive-metastore|data-p-emr-airflow|data-p-metabase-presto-rds-restored-perf-dataops-195|bac-p-supplier-incentives|bac-p-supplier-incentives-slave.*|bac-p-supplier-orders|bac-p-merchandising.*|devops-p-grafana|devops-prod-vault|bac-p-fraud-supplier-platform-data-slave'} offset 10m / 1073741824 < 300 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 300G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_200G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-sx-support.*|bac-p-transact-slave-02|bac-p-relay|bac-p-address*|supply-prod|bac-p-payments.*|data-p-emr-airflow-prism-new|bac-p-review|supply-prod-admin-slave|bac-p-supplier-orders|bac-p-taxonomy-new-data-slave'} offset 10m / 1073741824 < 200 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 200G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_70G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-content-new|bac-p-content-data-slave-new|data-p-sb-presto-rds|bac-p-whatsapp-client|bac-p-supplier-ums-slave|bac-p-data-platform-presto-gateway|bac-p-supplier-ums'} offset 10m / 1073741824 < 70 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 70G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_50G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-pow.*|bac-p-farmiso-gcp.*|bac-p-grafana-dp|bac-p-price-data-slave-new|bac-p-supplier-optin-data-slave|bac-p-supplier-optin-slave|bac-p-data-platform-presto-gateway|bac-p-loyalty-earn-engine-slave.*|bac-p-loyalty-earn-engine-data-slave|data-p-sb-presto-rds-slave|bac-p-shipment-service|data-p-hive-metastore-slave|bac-p-data-platform-presto-gateway|bac-p-loyalty-earn-engine||bac-p-supplier-incentives-slave.*|bac-p-producer-fulfilment.*'} offset 10m / 1073741824 < 50 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 50G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_100G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-supplier-incentives-data.*|bac-p-price-new|bac-p-supplier-detail-data.*|bac-p-inventory-data-slave-new|bac-p-inventory-new|bac-p-tracking-new|bac-p-tracking-new-slave|front-p-catalog|bac-p-supplier-business-partner|bac-p-cdp|data-p-emr-airflow-prism|bac-p-cdp-slave-01|bac-p-community|bac-p-community-data-slave.*|data-p-metabase-presto-rds-restored-perf-dataops-195|bac-p-relay-data-slave1|bac-p-fraud-supplier-platform-slave|bac-p-fraud-supplier-platform'} offset 10m / 1073741824 < 100 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 100G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_150G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'data-p-metabase-presto-rds-perf-cmr-1909|bac-p-offer-platform-data-slave|bac-p-order-service.*|bac-p-review-slave-02|bac-p-supply-payment-slave|bac-p-supply-order-slave|bac-p-cis-slave-01|supply-prod-heevo-slave-01|bac-p-cis|bac-p-supplier-incentives|bac-p-review-data-slave-01|bac-p-fraud-supplier-platform-data-slave'} offset 10m / 1073741824 < 150 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 150G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_130G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-growth.*'} offset 10m / 1073741824 < 130 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 130G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_140G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-supplier-orders-data-slave|bac-p-transact|bac-p-supplier-orders-slave'} offset 10m / 1073741824 < 140 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 140G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_145G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-wallet|bac-p-wallet-slave-01'} offset 10m / 1073741824 < 145 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 145G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_180G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'front-p-webviews'} offset 10m / 1073741824 < 180 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 180G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_75G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'data-p-metabase-rds-temp|bac-p-supplier-detail-new|bac-p-offer-platform|data-p-hive-metastore|bac-p-tracking-slave-01|bac-p-tracking-01|data-p-metabase-rds|data-p-metabase-main-rds|hive-metastore|data-p-emr-airflow|bac-p-offer-platform-slave|devops-p-grafana|devops-prod-vault'} offset 10m / 1073741824 < 75 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 75G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_5G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-supplier-data-platform'} offset 10m / 1073741824 < 5 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 5G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_40G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'metabase-presto-rds-perf-cmr-1909|data-p-superset-dashboard'} offset 10m / 1073741824 < 40 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 40G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_35G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'data-p-metabase-presto-rds|data-p-metabase-presto-ext-rds|data-p-metabase-presto-nrt-rds|data-p-metabase-presto-rds-perf-dataops-756'} offset 10m / 1073741824 <35 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 35G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_10G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-display-ads.*|bac-p-di-metastore|bac-p-ct-qct-v2|bac-p-vmextractor.*'} offset 10m / 1073741824 < 10 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 10G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_15G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-preprod-ab-rds'} offset 10m / 1073741824 < 15 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 15G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} GB" - alert: freeStorage_30G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-ab-service|bac-p-eks-presto-resource-group|bac-p-price-recommendation-data-slave-new|bac-p-price-recommendation-new|bac-p-supplier-optin|bac-p-merchandising.*|bac-p-listing-go-live.*|bac-p-datahub.*'} offset 10m / 1073741824 < 30 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 30G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_25G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-farmiso-relay-new|bac-p-supplier-return-assurance|bac-p-supplier-return-assurance-slave'} offset 10m / 1073741824 < 25 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 25G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" - alert: freeStorage_20G expr: aws_rds_free_storage_space_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-live-commerce|bac-p-meesholink|bac-p-app-dbs-metabase|bac-p-ab-service-pre-prod|bac-p-whatsapp-client-eks|data-p-rds-airflow-etl-2-4'} offset 10m / 1073741824 < 20 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is less than 20G" description: "FreeStorage of the RDS {{ $labels.dbinstance_identifier }} is {{ $value }} bytes" ################################## RDS connections ################################# - alert: RDS_Connections_150+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier !~ "bac-p-pow-rds-new|front-p-catalog-new|bac-p-supply-payment-new-slave|bac-p-post-order-new-slave|bac-p-feed-slave-01|bac-p-sx-support.*|bac-p-feed-data-slave|bac-p-taxonomy-new-slave2|bac-p-taxonomy-new-data-slave|bac-p-taxonomy-new-slave04|bac-p-supplier-data-platform|bac-p-fraud-supplier-platform|bac-p-order-service-new-data-slave-01|bac-p-post-order-slave|data-p-sb-presto-rds|bac-p-loyalty-earn-engine|bac-p-order-service-new-slave-01|bac-p-communications|bac-p-feed-slave-02|bac-p-taxonomy-new-slave03|bac-p-data-platform-presto-gateway|bac-p-supplier-optin|bac-p-support|bac-p-wallet-new-rds|bac-p-wallet-v2|bac-p-price.*|bac-p-offer-platform|bac-p-taxonomy-new-slave01|bac-p-merchandising-data-slave1|bac-p-order-service-new|bac-p-taxonomy-new-slave02|bac-p-merchandising|bac-p-merchandising-data-slave|bac-p-taxonomy-new|bac-p-offer-service|bac-p-advertisement-new.*|bac-p-shipment-service.*|bac-p-supplier-detail.*|bac-p-ab-service.*|bac-p-inventory.*|bac-p-address.*|bac-p-cis|bac-p-community.*|bac-p-content|bac-p-ct-qct-v2|bac-p-discovery|bac-p-discovery-slave|bac-p-farmiso|bac-p-feed|bac-p-recommendation-service|bac-p-order-service|bac-p-ors.*|bac-p-payments.*|bac-p-pow-rds|bac-p-referral-earnings|bac-p-review.*|bac-p-supplier-ums|bac-p-taxonomy|bac-p-tracking-.*|bac-p-tracking-slave-01|bac-p-transact|bac-p-ums|bac-p-user-profile.*|bac-p-wallet|bac-p-whatsapp-client|data-p-emr-airflow-prism|data-p-metabase-rds|data-p-rds-airflow-etl|front-p-catalog|front-p-webviews|supply-prod|supply-prod-heevo-slave-01|bac-p-supply-order-slave|bac-p-supply-payment-slave|bac-p-taxonomy-slave2|bac-p-growth|bac-p-live-commerce|data-p-emr-airflow-prism-new|bac-p-wallet-new-updated-rds"} offset 10m > 150 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (150+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_200+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-ct-qct-v2|bac-p-ors|bac-p-ors-slave|bac-p-support|bac-p-data-platform-presto-gateway|bac-p-tracking-slave-01|bac-p-whatsapp-client|bac-p-recommendation-service"} offset 10m > 200 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (200+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1500+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-farmiso"} offset 10m > 1500 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1500+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1200+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-merchandising|bac-p-merchandising-data-slave1"} offset 10m > 1200 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1200+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_250+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-pow-rds-new|data-p-metabase-rds|bac-p-supplier-detail|bac-p-offer-service"} offset 10m > 250 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (250+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_400+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-pow-rds|bac-p-fraud-supplier-platform|bac-p-feed-data-slave|bac-p-order-service-new-slave-01"} offset 10m > 400 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (400+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_350+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-loyalty-earn-engine"} offset 10m > 350 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (350+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_450+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-supplier-ums"} offset 10m > 450 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (450+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_550+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-order-service-new"} offset 10m > 550 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (550+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_900+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-supply-payment-new-slave|bac-p-post-order-new-slave"} offset 10m > 900 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (900+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_300+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-sx-support.*|front-p-catalog-new|bac-p-supplier-data-platform|bac-p-ab-service-slave-01|data-p-emr-airflow-prism-new|bac-p-communications|bac-p-feed-slave-02|data-p-emr-airflow-prism|data-p-rds-airflow-etl|bac-p-merchandising-data-slave"} offset 10m > 300 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (300+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_500+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-feed-slave-01|bac-p-address|bac-p-supplier-optin|bac-p-address-slave|bac-p-community-slave-01|bac-p-order-service-new-data-slave-01|bac-p-referral-earnings|bac-p-tracking-01|front-p-webviews"} offset 10m > 500 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (500+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_600+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-inventory|data-p-sb-presto-rds"} offset 10m > 600 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (600+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1800+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-live-commerce"} offset 10m > 1800 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1800+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_700+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "supply-prod-heevo-slave-01"} offset 10m > 700 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (700+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1100+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-wallet-new-rds"} offset 10m > 1100 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1100+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2000+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-price|bac-p-payments-slave-01"} offset 10m > 2000 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2000+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1000+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-cis|bac-p-taxonomy-new|bac-p-offer-platform|bac-p-taxonomy-new-slave04|bac-p-advertisement-new|bac-p-wallet-v2|bac-p-order-service|bac-p-review-slave-02|bac-p-growth|bac-p-post-order-slave"} offset 10m > 1000 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1000+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1600+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "front-p-catalog"} offset 10m > 1600 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1600+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_1300+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-taxonomy-new-slave03|bac-p-taxonomy-new-slave02|bac-p-taxonomy-new-slave2|bac-p-discovery"} offset 10m > 1300 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (1300+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2200+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-discovery-slave"} offset 10m > 2200 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2000+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2000+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-price|bac-p-community"} offset 10m > 2000 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2000+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2100+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-feed"} offset 10m > 2100 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2100+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2200+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-shipment-service"} offset 10m > 2200 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2200+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2700+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-wallet"} offset 10m > 2700 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2700+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_2500+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-ums|supply-prod|bac-p-taxonomy-new-data-slave|bac-p-wallet-new-updated-rds"} offset 10m > 2500 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (2500+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_3000+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-ab-service|bac-p-taxonomy-slave2"} offset 10m > 3000 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (3000+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_3200+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-review"} offset 10m > 3200 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (3200+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_3500+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-taxonomy|bac-p-transact|bac-p-taxonomy-new-slave01"} offset 10m > 3500 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (3500+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_3800+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-user-profile-slave|bac-p-supply-order-slave"} offset 10m > 3800 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (3800+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_5000+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-supply-payment-slave|bac-p-payments"} offset 10m > 5000 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (5000+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_4300+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-user-profile"} offset 10m > 4300 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (4300+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: RDS_Connections_7500+ expr: aws_rds_database_connections_maximum {job="aws_rds",dbinstance_identifier =~ "bac-p-content"} offset 10m > 7500 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Number of connections of the RDS {{ $labels.dbinstance_identifier }} High (7500+)." description: "High Number of connections in the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." ################################## RDS IOPS ################################# - alert: IOPS_700+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"data-p-metabase-rds|bac-p-data-platform-presto-gateway|data-p-hive-metastore"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"data-p-metabase-rds|bac-p-data-platform-presto-gateway|data-p-hive-metastore"} offset 10m ) > 700 for: 3m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 700." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_2500+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-ab-service|bac-p-ab-service-slave-01|bac-p-review-slave-01|data-p-emr-airflow"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-ab-service|bac-p-ab-service-slave-01|bac-p-review-slave-01|data-p-emr-airflow"} offset 10m ) > 2500 for: 3m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 2500." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_4000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-cis"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-cis"} offset 10m ) > 4000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 4000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_12000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-payments-slave-01"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-payments-slave-01"} offset 10m ) > 12000 for: 3m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 12000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_5000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~""} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~""} offset 10m ) > 5000 for: 3m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 5000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_4000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-cis-slave-01"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-cis-slave-01"} offset 10m ) > 4000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 4000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_12000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-payments"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-payments"} offset 10m ) > 12000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 12000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_6000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-tracking-01"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-tracking-01"} offset 10m ) > 6000 for: 3m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 6000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_7000+ expr: ( aws_rds_write_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-tracking-slave-01|bac-p-content-slv-01|front-p-catalog|front-p-catalog-slave02"} offset 10m + aws_rds_read_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-tracking-slave-01|bac-p-content-slv-01|front-p-catalog"} offset 10m ) > 7000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 7000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_8000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"front-p-catalog-slave02"} offset 10m + aws_rds_write_iops_average{job="aws_rds",dbinstance_identifier=~"front-p-catalog-slave02"} offset 10m ) > 8000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 8000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_15000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-wallet"} offset 10m + aws_rds_write_iops_average{job="aws_rds",dbinstance_identifier=~"bac-p-wallet"} offset 10m ) > 15000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 15000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_9000+ expr: ( aws_rds_write_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-content|bac-p-wallet-slave-01"} offset 10m + aws_rds_read_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-content|bac-p-wallet-slave-01"} offset 10m ) > 9000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 9000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_9600+ expr: ( aws_rds_write_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-ums"} offset 10m + aws_rds_read_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-ums"} offset 10m ) > 9600 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 9000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_3500+ expr: ( aws_rds_write_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-review"} offset 10m + aws_rds_read_iops_average{job="aws_rds",dbinstance_identifier =~ "bac-p-review"} offset 10m ) > 3500 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 3500." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_12000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-ums-slave|supply-prod-admin-slave"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-ums-slave|supply-prod-admin-slave"} offset 10m ) > 12000 for: 10m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 12000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_28000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-supply-order-slave"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-supply-order-slave"} offset 10m ) > 28000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 28000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_45000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"bac-p-supply-payment-slave"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"bac-p-supply-payment-slave"} offset 10m ) > 45000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 45000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_13000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"supply-prod-heevo-slave-01"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"supply-prod-heevo-slave-01"} offset 10m ) > 13000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 13000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: IOPS_14000+ expr: (aws_rds_read_iops_average{job="aws_rds", dbinstance_identifier =~"supply-prod"} offset 10m + aws_rds_write_iops_average{job="aws_rds", dbinstance_identifier=~"supply-prod"} offset 10m ) > 14000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "IOPS of the RDS {{ $labels.dbinstance_identifier }} is greater than 14000." description: "IOPS of the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." ################################## RDS read replica ################################# - alert: Replication_Error expr: aws_rds_replica_lag_average{job="aws_rds"} offset 10m == -1 for: 2m labels: severity: critical resource: AWS RDS annotations: summary: "Replication error for RDS {{ $labels.dbinstance_identifier }}." description: "Replication error for RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: ReplicaLagAlert_5mins expr: aws_rds_replica_lag_average{job="aws_rds", dbinstance_identifier !~ 'bac-p-supply-payment-slave|supply-prod-heevo-slave-01|bac-p-data-platform-presto-gateway|bac-p-wallet-slave-01|front-p-catalog-slave02|bac-p-ums-slave' } offset 10m > 600 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "Replication lag of the RDS {{ $labels.dbinstance_identifier }} is greater than 300 seconds." description: "Replication Lag for the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: ReplicaAlert_10mins expr: aws_rds_replica_lag_average{job="aws_rds", dbinstance_identifier =~ 'supply-prod-heevo-slave-01'} offset 10m > 1000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "Replication lag of the RDS {{ $labels.dbinstance_identifier }} is greater than 1000 seconds." description: "Replication Lag for the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: ReplicaAlert_20mins expr: aws_rds_replica_lag_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-ums-slave'} offset 10m > 2000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "Replication lag of the RDS {{ $labels.dbinstance_identifier }} is greater than 2000 seconds." description: "Replication Lag for the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: ReplicaAlert_60mins expr: aws_rds_replica_lag_average{job="aws_rds", dbinstance_identifier =~ 'front-p-catalog-slave02'} offset 10m > 3600 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "Replication lag of the RDS {{ $labels.dbinstance_identifier }} is greater than 3600 seconds." description: "Replication Lag for the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}." - alert: ReplicaAlert_30mins expr: aws_rds_replica_lag_average{job="aws_rds", dbinstance_identifier =~ 'bac-p-wallet-slave-01'} offset 10m > 2000 for: 5m labels: severity: critical resource: AWS RDS annotations: summary: "Replication lag of the RDS {{ $labels.dbinstance_identifier }} is greater than 2000 seconds." description: "Replication Lag for the RDS {{ $labels.dbinstance_identifier }} : {{ $value }}."