groups: - name: EC2-Alerts rules: - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name!~"bac-p-trends-scraper-injector-01a.*|Jenkins-slave-07|bac-p-etl-airflow-dp-worker.*|bac-p-advertisement-reco.*|devops-p-jenkins-sonar-slave-01c|bac-p-redis-master-01a|jenkins-slave-03|devops-p-jenkins-slave-01a|bac-p-watcher-consumer|bac-p-watcher-web|bac-p-presto-gateway|data-p-emr-airflow-worker.*|bac-p-advertisement-fy-hbase-v2|bac-p-cms-hbase|data-p-ingestion-web.*|bac-p-hbase-osm.*|supplier-platform-promotions.*|bac-p-referral-hbase.*|bac-p-reseller-tracking-hbase.*|bac-p-trends-scraper-post-processor.*|bac-p-pc-scheduler.*|.+mongodb.*|.+mongo.*|bac-p-engagement-hbase.*|.*bac-p-cdp-flink.*|.*bac-p-mini-url-hbase.*|bac-p-graylog-kafka-new.*|devops-p-prometheus-new-01b.*|bac-p-notification-store-hbase.*|bac-p-manifest-mongodb.*|bac-p-ab-hbase.*|meesho-prod-eks-application-stack-ng.*|bac-p-ab-bonus-ctqct-hbase|platform-p-hbase.*|bac-p-hbase-communicator-data.*|bac-p-osm-hbase.*|bac-p-hbase-communicator.*|bac-p-advertisement-hbase|bac-p-mongo-invoice.*|devops-p-prometheus-new-setup.*|bac-p-advertisement-hbase-fy.*|devops-p-prometheus-01b.*"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 30 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 30% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"bac-p-osm-hbase.*|bac-p-advertisement-hbase-fy.*|bac-p-advertisement-fy-hbase-v2|bac-p-advertisement-reco"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 15 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 15% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"data-p-emr-airflow-worker.*|bac-p-presto-gateway|bac-p-watcher-consumer|bac-p-redis-master-01a|bac-p-display-ads-hbase|bac-p-watcher-web"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 30 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 30% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"bac-p-trends-scraper-post-processor.*|supplier-platform-promotions.*"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 25 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 25% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"bac-p-engagement-hbase.*|bac-p-hbase-communicator.*|devops-p-jenkins-sonar-slave-01c|jenkins-slave-03|devops-p-jenkins-slave-01a|bac-p-notification-store-hbase.*"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 10 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"bac-p-trends-scraper-injector-01a|bac-p-etl-airflow-dp-worker.*|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|data-p-ingestion-web.*|bac-p-referral-hbase.*|bac-p-reseller-tracking-hbase.*|bac-p-mongo-invoice|bac-p-graylog-kafka-new|bac-p-ab-hbase.*|devops-p-prometheus-new-setup|bac-p-ab-bonus-ctqct-hbase|platform-p-hbase-master|bac-p-hbase-communicator-data.*|bac-p-advertisement-hbase|bac-p-cdp-flink.*|bac-p-cms-hbase"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 20 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 20% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"bac-p-mini-url-hbase.*"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 18 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 18% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"Jenkins-slave-07|devops-p-prometheus-01b.*|bac-p-manifest-mongodb.*|bac-p-hbase-osm.*|bac-p-pc-scheduler.*|devops-p-prometheus-new-01b.*|platform-p-hbase-node.*|platform-p-hbase"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 15 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 15% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfDiskSpace expr: node_filesystem_free_bytes{job=~'node_exporter', mountpoint=~".*/.*",name=~"meesho-prod-eks-application-stack-ng.*|.+mongodb.*|.+mongo.*"} / node_filesystem_size_bytes{job=~'node_exporter', mountpoint=~".*/.*"} * 100 < 15 for: 2m labels: severity: critical annotations: summary: "Out of disk space (instance {{ $labels.private_ip }})" description: "Disk is almost full (< 15% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: CPU-High-80% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name !~"dp-mb-sec-wk-mix.*|bac-p-redis-master-01a|bac-p-display-ads-hbase|data-p-kafka-connect-mongo-01g|data-p-kafka-connect-mongo-01a|bac-p-competition-product-enricher.*|communicator-scheduler-campaign|bac-p-search-preprocessor-worker.*|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|data-platform-starburst-presto-model.*|bac-p-vision-consumer-new|bac-p-watcher-consumer|bac-p-watcher-web|bac-p-presto-gateway|kafka-ui|bac-p-ums-user-profile|communicator-consumer-notification-campaign.*|bac-p-ofs-partial-catalogs-indexer|supplier-platform-promotions.*|bac-p-trends-mongo-01b.*|bac-p-recommendation.*|bac-p-trends-scraper-injector-01a.*|qwest-text-search-faust-worker.*|data-p-messaging-api|bac-p-farmiso|bac-p-ingestion|bac-p-ab-hbase.*|platform-p-kafka-cluster-monitor.*|bac-p-cms-scheduler.*|platform-p-qwest-07c-2a.*|meesho-prod-poc-cluster-vminsert_select-instance-group.*|bac-p-communicator-consumer-for-you.*|platform-p-qwest-07c-1a.*|platform-p-kafka-graylog-cluster-broker.*|bac-p-graylog-kafka-new-02b.*|bac-p-graylog-kafka-new-03b.*|front-p-pow-01c.*|front-p-pow-01b.*|bac-p-ab.*|bac-p-pdf.*|bac-p-communicator-01a.*|bac-p-communicator-01b.*|bac-p-community.*|bac-p-hbase-communicator|bac-p-inventory.*|bac-p-manifest.*|bac-p-merchandising.*|bac-p-merchandising-consumer-2.*|bac-p-pricing.*|bac-p-sms.*|bac-p-storefront.*|bac-p-supply-ios-01b|bac-p-taxonomy|bac-p-taxonomy-new|bac-p-ums.*|backend-p-file-service.*|devops-p-prometheus-01b|front-p-supply-panel-02b|front-p-supply-panel-01c|front-p-supply-panel-01b.*|bac-p-supplyapi.*|platform-p-qwest-01a.*|platform-p-qwest-01b.*|platform-p-qwest-01c.*|platform-p-qwest-02a.*|platform-p-qwest-02a-vs.*|platform-p-qwest-02b.*|platform-p-qwest-02b-vs.*|platform-p-qwest-02c.*|platform-p-qwest-02c-vs.*|platform-p-qwest-03a.*|platform-p-qwest-03a-sq.*|platform-p-qwest-03b-sq.*|platform-p-qwest-03c.*|platform-p-qwest-03c-sq.*|platform-p-qwest-04a-sq.*|platform-p-qwest-05a.*|platform-p-qwest-05b.*|bac-p-cis.*|platform-p-qwest-05c.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name !~"dp-mb-sec-wk-mix.*|bac-p-redis-master-01a|bac-p-competition-product-enricher.*|communicator-scheduler-campaign|bac-p-search-preprocessor-worker.*|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|communicator-consumer-notification-campaign.*|data-platform-starburst-presto-model.*|bac-p-vision-consumer-new|bac-p-ums-user-profile|supplier-platform-promotions.*|bac-p-trends-mongo-01b.*|bac-p-trends-scraper-injector-01a.*|bac-p-recommendation.*|qwest-text-search-faust-worker.*|meesho-prod-poc-cluster-vminsert_select-instance-group.*|data-p-messaging-api|data-p-kafka-connect-mongo-01a|data-p-kafka-connect-mongo-01g|bac-p-farmiso|bac-p-ab-hbase.*|bac-p-ingestion.*|platform-p-kafka-cluster-monitor.*|bac-p-cms-scheduler.*|platform-p-qwest-07c-2a.*|platform-p-qwest-07c-1a.*|bac-p-communicator-consumer-for-you.*|bac-p-ab.*|bac-p-graylog-kafka-new-03b.*|bac-p-communicator-01a.*|bac-p-communicator-01b.*|bac-p-community.*|bac-p-pdf.*|bac-p-hbase-communicator|bac-p-inventory.*|bac-p-manifest.*|bac-p-merchandising.*|bac-p-merchandising-consumer-2.*|bac-p-pricing.*|bac-p-sms.*|bac-p-storefront.*|bac-p-supply-ios-01b|bac-p-taxonomy|bac-p-taxonomy-new|bac-p-ums.*|backend-p-file-service.*|devops-p-prometheus-01b|front-p-supply-panel-02b|front-p-supply-panel-01c|front-p-supply-panel-01b|bac-p-supplyapi.*|platform-p-kafka-graylog-cluster-broker.*|platform-p-qwest-01a.*|platform-p-qwest-01b.*|platform-p-qwest-01c.*|platform-p-qwest-02a.*|platform-p-qwest-02a-vs.*|platform-p-qwest-02b.*|platform-p-qwest-02b-vs.*|platform-p-qwest-02c.*|platform-p-qwest-02c-vs.*|platform-p-qwest-03a.*|platform-p-qwest-03a-sq.*|platform-p-qwest-03b-sq.*|platform-p-qwest-03c.*|platform-p-qwest-03c-sq.*|platform-p-qwest-04a-sq.*|platform-p-qwest-05a.*|platform-p-qwest-05b.*|front-p-pow-01c.*|front-p-pow-01b.*|bac-p-cis.*|bac-p-graylog-kafka-new-02b.*|bac-p-ofs-partial-catalogs-indexer|kafka-ui|bac-p-presto-gateway|bac-p-watcher-consumer|bac-p-display-ads-hbase|bac-p-watcher-web|platform-p-qwest-05c.*"}[5m]))))) > 80 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-80% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"data-platform-starburst-presto-model.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"data-platform-starburst-presto-model.*"}[5m]))))) > 80 for: 5m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-60% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"bac-p-display-ads-hbase"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"bac-p-display-ads-hbase"}[5m]))))) > 60 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-80% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="iowait",name =~"kafka-ui"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="idle",name =~"kafka-ui"}[5m]))))) > 80 for: 30m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-95% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"data-p-kafka-connect-mongo-01g"}[10m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"data-p-kafka-connect-mongo-01g"}[10m]))))) > 95 for: 10m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-85% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"bac-p-competition-product-enricher.*|communicator-scheduler-campaign|communicator-consumer-notification-campaign"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"bac-p-competition-product-enricher.*|communicator-scheduler-campaign|communicator-consumer-notification-campaign"}[5m]))))) > 85 for: 20m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-97% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"dp-mb-sec-wk-mix.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"dp-mb-sec-wk-mix.*"}[5m]))))) > 97 for: 10s labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-90% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"data-p-kafka-connect-mongo-01a"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"data-p-kafka-connect-mongo-01a"}[5m]))))) > 90 for: 10s labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-80_mongo expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name=~".+mongodb.*|.+mongo.*"}[5m])) + avg by(instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name=~".+mongodb.*|.+mongo.*"}[5m]))))) > 80 for: 10s labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-85% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name =~"qwest-text-search-faust-worker.*|bac-p-presto-gateway|bac-p-merchandising-consumer-2.*|platform-p-qwest-01c.*|bac-p-communicator-consumer-for-you.*|platform-p-qwest-07c-2a.*|bac-p-ingestion.*|data-p-messaging-api.*|platform-p-qwest-07c-1a.*|bac-p-merchandising"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name =~"qwest-text-search-faust-worker.*|bac-p-merchandising|platform-p-qwest-01c.*|data-p-messaging-api.*|bac-p-merchandising-consumer-2.*|bac-p-communicator-consumer-for-you.*|platform-p-qwest-07c-2a.*|bac-p-ingestion.*|bac-p-presto-gateway|platform-p-qwest-07c-1a.*"}[5m]))))) > 85 for: 5m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-90% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name=~"bac-p-search-preprocessor-worker.*|bac-p-vision-consumer-new|bac-p-ofs-partial-catalogs-indexer|platform-p-kafka-graylog-cluster-broker.*|platform-p-kafka-cluster-monitor.*|bac-p-graylog-kafka-new-02b.*|bac-p-graylog-kafka-new-03b.*|platform-p-qwest-05c.*|bac-p-merchandising-consumer-2.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name=~"bac-p-search-preprocessor-worker.*|bac-p-vision-consumer-new|bac-p-ofs-partial-catalogs-indexer|platform-p-kafka-graylog-cluster-broker.*|bac-p-graylog-kafka-new-03b.*|platform-p-kafka-cluster-monitor.*|platform-p-qwest-05c.*|bac-p-graylog-kafka-new-02b.*|bac-p-merchandising-consumer-2.*"}[5m]))))) > 90 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-60% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait", name =~ "bac-p-pdf.*|bac-p-recommendation.*|front-p-pow.*|supplier-platform-promotions.*|meesho-prod-poc-cluster-vminsert_select-instance-group.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle", name =~ "bac-p-pdf.*|bac-p-recommendation.*|front-p-pow.*|supplier-platform-promotions.*|meesho-prod-poc-cluster-vminsert_select-instance-group.*"}[5m]))))) > 60 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-30% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait", name =~ "bac-p-cms-scheduler.*|bac-p-trends-mongo-01b.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle", name =~ "bac-p-cms-scheduler.*|bac-p-trends-mongo-01b.*"}[5m]))))) > 30 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-65% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait", name =~ "bac-p-ab-hbase.*|bac-p-communicator-01a.*|bac-p-communicator-01b.*|bac-p-community.*|bac-p-hbase-communicator|bac-p-inventory.*|bac-p-manifest.*|bac-p-pricing.*|bac-p-sms.*|bac-p-taxonomy-consumer-.*|backend-p-file-service.*|devops-p-prometheus-01b|front-p-supply-panel-01b|front-p-supply-panel-01c|front-p-supply-panel-02b.*|platform-p-qwest-01a.*|platform-p-qwest-01b.*|platform-p-qwest-02a.*|platform-p-qwest-02a-vs.*|platform-p-qwest-02b.*|platform-p-qwest-02b-vs.*|platform-p-qwest-02c.*|platform-p-qwest-02c-vs.*|platform-p-qwest-03a.*|platform-p-qwest-03a-sq.*|platform-p-qwest-03b-sq.*|platform-p-qwest-03c.*|platform-p-qwest-03c-sq.*|platform-p-qwest-04a-sq.*|platform-p-qwest-05a.*|platform-p-qwest-05b.*|"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle", name =~ "bac-p-ab-hbase.*|bac-p-communicator-01a.*|bac-p-communicator-01b.*|bac-p-community.*|bac-p-hbase-communicator|bac-p-inventory.*|bac-p-manifest.*|bac-p-pricing.*|bac-p-sms.*|bac-p-taxonomy-consumer-.*|backend-p-file-service.*|devops-p-prometheus-01b|front-p-supply-panel-01b|front-p-supply-panel-01c|front-p-supply-panel-02b.*|platform-p-qwest-01a.*|platform-p-qwest-01b.*|platform-p-qwest-02a.*|platform-p-qwest-02a-vs.*|platform-p-qwest-02b.*|platform-p-qwest-02b-vs.*|platform-p-qwest-02c.*|platform-p-qwest-02c-vs.*|platform-p-qwest-03a.*|platform-p-qwest-03a-sq.*|platform-p-qwest-03b-sq.*|platform-p-qwest-03c.*|platform-p-qwest-03c-sq.*|platform-p-qwest-04a-sq.*|platform-p-qwest-05a.*|platform-p-qwest-05b.*|"}[5m]))))) > 65 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-60% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name=~"bac-p-taxonomy"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name=~"bac-p-taxonomy"}[5m]))))) > 60 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-70% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name=~"bac-p-trends-scraper-injector-01a.*|bac-p-redis-master-01a|bac-p-taxonomy-new|bac-p-watcher-consumer|bac-p-watcher-web|prod-ops-.*"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name=~"bac-p-trends-scraper-injector-01a.*|bac-p-redis-master-01a|bac-p-taxonomy-new|bac-p-watcher-consumer|bac-p-watcher-web|prod-ops-.*"}[5m]))))) > 70 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: CPU-High-75% expr: (100 * (1 - (avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{job=~'node_exporter', mode="iowait",name=~"bac-p-storefront.*|bac-p-supplyapi.*|bac-p-ab.*|bac-p-ums-user-profile"}[5m])) + avg by(alerts,instance, job, private_ip, team, status, name, priority) (irate(node_cpu_seconds_total{mode="idle",name=~"bac-p-storefront.*|bac-p-supplyapi.*|bac-p-ab.*|bac-p-ums-user-profile"}[5m]))))) > 75 for: 3m labels: severity: critical annotations: summary: "High CPU Utilization (instance {{ $labels.private_ip }})" description: "CPU Utilization is: {{ $value }} \n LABELS: {{ $labels }}" - alert: OutOfMemory-80% expr: avg by(alerts, app, job, team, status)((node_memory_MemFree_bytes{job=~'node_exporter', name=~"data-p-model-airflow-worker.*" } + node_memory_Cached_bytes{name=~"data-p-model-airflow-worker.*" } + node_memory_Buffers_bytes{name=~"data-p-model-airflow-worker.*" }) / node_memory_MemTotal_bytes{name=~"data-p-model-airflow-worker.*" } * 100) < 20 for: 3m labels: severity: critical annotations: summary: "Low Average available memory for workernode of (app {{ $labels.app }})" description: "Machine Memory is filling up (< 20% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-80% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name !~ "offer-platform|bac-p-advertisement-hbase-v1|bac-p-relevance-service|dp-mb-sec-wk-mix.*|bac-p-redis-master-01a|data-platform-starburst-presto.*|bac-p-post-order-commn|bac-p-invoice-consumer|communicator-consumer-sms-campaign|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|bac-p-return-recon-service-cron|bac-p-order-search-cron|bac-p-presto-gateway|bac-p-product-similarity-api|data-p-kafka-connect-01a|platform-p-qwest-text-search-worker|bac-p-advertisement-spark-fy|bac-p-watcher-consumer|bac-p-watcher-web|bac-p-offer-service-worker|bac-p-supplier-payment-web|data-p-model-airflow-worker.*|bac-p-supplier-ums-cron|bac-p-communicator-consumer-for-you|discovery-platform-jobs|bac-p-taxonomy-admin|bac-p-advertisement-hbase|bac-p-search-indexer-analytics|bac-p-metabase-poc.*|bac-p-osm-supply|kafka-ui.*|bac-p-widgetaggregator.*|bac-p-ct-qct-v2-web.*|bac-p-campaign-performance.*|bac-p-onboarding-hbase.*|bac-p-discovery-elasticsearch-exporter.*|bac-p-marvel-flink.*|bac-p-cdp-hbase.*|bac-p-feedaggregator-search|bac-p-feedaggregator|bac-p-feedaggregator-secondary|bac-p-pdf.*|devops-p-prometheus.*|supplier-platform-promotions.*|front-p-pow.*|bac-p-sort-filter-consumer.*|front-p-pow-new.*|front-p-pow-new.*|front-p-pow.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter-secondary.*|bac-p-sort-and-filter.*|bac-p-sort-and-filter-vs.*|bac-p-price-aggregator|bac-p-marvel-flink-new.*|bac-p-farmiso.*|bac-p-farmiso-worker.*|platform-p-qwest-07c.*|bac-p-vision.*|bac-p-storefront.*|bac-p-reseller-tracking-consumer-02b.*|platform-p-qwest-01c.*|bac-p-order-state-management-cron.*|bac-p-vision-hbase.*|data-p-messaging-api.*|bac-p-supplier-sf.*|dataplatform-p-Prism-lake-master.*|dataplatform-datascience-master.*|dataplatform-p-Prism-LAKE-33-master.*|bac-p-search-indexer-sort-filter|bac-p-return-recon-service-worker|platform-p-qwest-cron-01a.*|bac-p-ct-qct-v2-cron|bac-p-cis.*"} + node_memory_Cached_bytes{name !~ "offer-platform|bac-p-advertisement-hbase-v1|bac-p-relevance-service|dp-mb-sec-wk-mix.*|bac-p-redis-master-01a|data-platform-starburst-presto.*|bac-p-post-order-commn|communicator-consumer-sms-campaign|bac-p-invoice-consumer|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|bac-p-return-recon-service-cron|bac-p-order-search-cron|bac-p-presto-gateway|bac-p-return-recon-service-worker|bac-p-product-similarity-api|data-p-kafka-connect-01a|platform-p-qwest-text-search-worker|bac-p-advertisement-spark-fy|bac-p-offer-service-worker|bac-p-supplier-payment-web|data-p-model-airflow-worker.*|bac-p-supplier-ums-cron|bac-p-communicator-consumer-for-you|discovery-platform-jobs|bac-p-taxonomy-admin|bac-p-advertisement-hbase|bac-p-search-indexer-analytics|bac-p-metabase-poc.*|kafka-ui.*|bac-p-widgetaggregator.*|bac-p-osm-supply|bac-p-campaign-performance.*|supplier-platform-promotions.*|bac-p-onboarding-hbase.*|bac-p-feedaggregator-search|bac-p-feedaggregator|bac-p-feedaggregator-secondary|bac-p-discovery-elasticsearch-exporter.*|bac-p-marvel-flink.*|bac-p-cdp-hbase.*|bac-p-pdf.*|bac-p-search-indexer-sort-filter|bac-p-sort-filter-consumer.*|devops-p-prometheus.*|bac-p-supplier-sf.*|front-p-pow.*|front-p-pow-new.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter-secondary.*|bac-p-sort-and-filter.*|bac-p-sort-and-filter-vs.*|bac-p-price-aggregator|bac-p-farmiso.*|bac-p-farmiso-worker.*|bac-p-vision.*|platform-p-qwest-07c.*|bac-p-storefront.*|bac-p-reseller-tracking-consumer-02b.*|platform-p-qwest-01c.*|bac-p-order-state-management-cron.*|bac-p-vision-hbase.*|data-p-messaging-api.*|dataplatform-p-Prism-lake-master.*|dataplatform-datascience-master.*|dataplatform-p-Prism-LAKE-33-master.*|bac-p-promo.*|platform-p-qwest-cron-01a.*|bac-p-ct-qct-v2-cron|bac-p-watcher-consumer|bac-p-watcher-web|bac-p-cis.*"} + node_memory_Buffers_bytes{name !~ "offer-platform|bac-p-advertisement-hbase-v1|bac-p-relevance-service|dp-mb-sec-wk-mix.*|bac-p-redis-master-01a|data-platform-starburst-presto.*|bac-p-post-order-commn|communicator-consumer-sms-campaign|bac-p-invoice-consumer|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|bac-p-return-recon-service-cron|bac-p-return-recon-service-worker|bac-p-order-search-cron|bac-p-presto-gateway|platform-p-qwest-text-search-worker|data-p-kafka-connect-01a|bac-p-advertisement-spark-fy|bac-p-offer-service-worker|bac-p-product-similarity-api|bac-p-supplier-payment-web|data-p-model-airflow-worker.*|discovery-platform-jobs|bac-p-taxonomy-admin|bac-p-supplier-ums-cron|bac-p-communicator-consumer-for-you|bac-p-advertisement-hbase|bac-p-search-indexer-analytics|bac-p-metabase-poc.*|bac-p-osm-supply|kafka-ui.*|bac-p-widgetaggregator.*|bac-p-campaign-performance.*|bac-p-feedaggregator-search|bac-p-feedaggregator|bac-p-feedaggregator-secondary|bac-p-sort-filter-consumer.*|bac-p-onboarding-hbase.*|supplier-platform-promotions.*|bac-p-marvel-flink.*|bac-p-cdp-hbase.*|bac-p-pdf.*|front-p-pow.*|bac-p-search-indexer-sort-filter|bac-p-supplier-sf.*|devops-p-prometheus.*|front-p-pow-new.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter-secondary.*|bac-p-sort-and-filter.*|bac-p-sort-and-filter-vs.*|bac-p-price-aggregator|bac-p-vision.*|bac-p-farmiso.*|bac-p-farmiso-worker.*|platform-p-qwest-07c.*|bac-p-storefront.*|bac-p-reseller-tracking-consumer-02b.*|platform-p-qwest-01c.*|bac-p-ct-qct-v2-cron|bac-p-order-state-management-cron.*|bac-p-vision-hbase.*|data-p-messaging-api.*|dataplatform-p-Prism-lake-master.*|dataplatform-datascience-master.*|dataplatform-p-Prism-LAKE-33-master.*|platform-p-qwest-cron-01a.*|bac-p-cis.*|bac-p-watcher-consumer|bac-p-watcher-web"}) / node_memory_MemTotal_bytes{name !~ "offer-platform|bac-p-advertisement-hbase-v1|bac-p-relevance-service|dp-mb-sec-wk-mix.*|bac-p-redis-master-01a|data-platform-starburst-presto.*|communicator-scheduler-campaign|communicator-consumer-sms-campaign|bac-p-invoice-consumer|bac-p-post-order-commn|bac-p-live-commerce-service.*|bac-p-live-commerce-chat.*|bac-p-live-commerce-worker.*|bac-p-offer-service-worker|bac-p-return-recon-service-worker|data-p-kafka-connect-01a|bac-p-advertisement-spark-fy|bac-p-supplier-payment-web|data-p-model-airflow-worker.*|bac-p-supplier-ums-cron|bac-p-communicator-consumer-for-you|bac-p-advertisement-hbase|bac-p-search-indexer-analytics|bac-p-osm-supply|kafka-ui.*|bac-p-metabase-poc.*|bac-p-widgetaggregator.*|bac-p-campaign-performance.*|supplier-platform-promotions.*|bac-p-sort-filter-consumer.*|bac-p-onboarding-hbase.*|bac-p-marvel-flink.*|bac-p-cdp-hbase.*|bac-p-feedaggregator-search|bac-p-feedaggregator|bac-p-feedaggregator-secondary|bac-p-pdf.*|devops-p-prometheus.*|front-p-pow.*|front-p-pow-new.*|bac-p-supplier-sf.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter-secondary.*|bac-p-sort-and-filter.*|bac-p-sort-and-filter-vs.*|bac-p-search-indexer-sort-filter|bac-p-price-aggregator|bac-p-vision.*|bac-p-farmiso.*|bac-p-farmiso-worker.*|platform-p-qwest-07c.*|bac-p-storefront.*|bac-p-reseller-tracking-consumer-02b.*|platform-p-qwest-01c.*|bac-p-order-state-management-cron.*|bac-p-vision-hbase.*|data-p-messaging-api.*|dataplatform-p-Prism-lake-master.*|dataplatform-datascience-master.*|dataplatform-p-Prism-LAKE-33-master.*|bac-p-promo.*|platform-p-qwest-cron-01a.*|discovery-platform-jobs|bac-p-taxonomy-admin|bac-p-product-similarity-api|platform-p-qwest-text-search-worker|bac-p-ct-qct-v2-cron|bac-p-presto-gateway|bac-p-order-search-cron|bac-p-return-recon-service-cron|bac-p-cis.*|bac-p-watcher-consumer|bac-p-watcher-web"} * 100 < 20 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 20% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-85% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-campaign-performance.*|bac-p-post-order-commn|bac-p-invoice-consumer|bac-p-return-recon-service-cron|bac-p-return-recon-service-worker|bac-p-order-search-cron|bac-p-feedaggregator|bac-p-ct-qct-v2-cron|platform-p-qwest-text-search-worker|bac-p-communicator-consumer-for-you|bac-p-taxonomy-admin|bac-p-search-indexer-analytics|bac-p-advertisement-hbase|bac-p-cdp-hbase.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter|bac-p-sort-and-filter-vs.*|bac-p-storefront.*|bac-p-osm-supply|bac-p-reseller-tracking-consumer-02b.*|data-p-etl-01a.*|bac-p-vision-hbase.*|data-p-messaging-api.*|bac-p-order-state-management-cron.*"} + node_memory_Cached_bytes{name !~ "data-p-model-airflow-worker.*",name =~ "bac-p-campaign-performance.*|bac-p-post-order-commn|bac-p-invoice-consumer|bac-p-return-recon-service-cron|bac-p-feedaggregator|bac-p-return-recon-service-worker|bac-p-communicator-consumer-for-you|bac-p-taxonomy-admin|bac-p-search-indexer-analytics|bac-p-advertisement-hbase|bac-p-cdp-hbase.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter|bac-p-sort-and-filter-vs.*|bac-p-osm-supply|bac-p-storefront.*|bac-p-reseller-tracking-consumer-02b.*|platform-p-qwest-01c.*|data-p-etl-01a.*|bac-p-vision-hbase.*|platform-p-qwest-text-search-worker|data-p-messaging-api.*|bac-p-ct-qct-v2-cron|bac-p-order-search-cron|bac-p-order-state-management-cron.*"} + node_memory_Buffers_bytes{name !~ "data-p-model-airflow-worker.*",name =~ "bac-p-campaign-performance.*|bac-p-post-order-commn|bac-p-invoice-consumer|bac-p-feedaggregator|bac-p-return-recon-service-cron|bac-p-return-recon-service-worker|bac-p-communicator-consumer-for-you|bac-p-taxonomy-admin|bac-p-search-indexer-analytics|bac-p-advertisement-hbase|bac-p-cdp-hbase.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter|bac-p-sort-and-filter-vs.*|bac-p-storefront.*|bac-p-osm-supply|bac-p-reseller-tracking-consumer-02b.*|platform-p-qwest-01c.*|data-p-etl-01a.*|bac-p-vision-hbase.*|data-p-messaging-api.*|platform-p-qwest-text-search-worker|bac-p-ct-qct-v2-cron|bac-p-order-search-cron|bac-p-order-state-management-cron.*"}) / node_memory_MemTotal_bytes{name !~ "data-p-model-airflow-worker.*",name =~ "bac-p-campaign-performance.*|bac-p-post-order-commn|bac-p-invoice-consumer|bac-p-return-recon-service-cron|bac-p-return-recon-service-worker|bac-p-feedaggregator|bac-p-communicator-consumer-for-you|bac-p-taxonomy-admin|bac-p-search-indexer-analytics|bac-p-advertisement-hbase|bac-p-cdp-hbase.*|bac-p-feed|bac-p-feed-optimiser|bac-p-feed-debezium|bac-p-sort-and-filter|bac-p-sort-and-filter-vs.*|bac-p-storefront.*|bac-p-osm-supply|bac-p-reseller-tracking-consumer-02b.*|data-p-etl-01a.*|bac-p-vision-hbase.*|data-p-messaging-api.*|platform-p-qwest-text-search-worker|bac-p-ct-qct-v2-cron|bac-p-order-search-cron|bac-p-order-state-management-cron.*"} * 100 < 15 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 15% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-90% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-advertisement-spark-fy|bac-p-vision|data-p-etl-01a.*|platform-p-qwest-07c.*|bac-p-widgetaggregator.*|bac-p-sort-filter-consumer.*|kafka-ui.*|bac-p-feedaggregator-search|bac-p-feedaggregator-secondary|platform-p-qwest-cron-01a.*|bac-p-discovery-elasticsearch-exporter.*|bac-p-search-indexer-sort-filter|bac-p-supplier-sf.*|platform-p-qwest-01c.*|bac-p-offer-service-worker|bac-p-marvel-flink-new.*"} + node_memory_Cached_bytes{name =~ "bac-p-advertisement-spark-fy|bac-p-vision|data-p-etl-01a.*|kafka-ui.*|bac-p-widgetaggregator.*|bac-p-sort-filter-consumer.*|platform-p-qwest-07c.*|platform-p-qwest-cron-01a.*|bac-p-supplier-sf.*|bac-p-search-indexer-sort-filter|bac-p-feedaggregator-search|bac-p-feedaggregator-secondary|platform-p-qwest-01c.*|bac-p-offer-service-worker|bac-p-marvel-flink-new.*"} + node_memory_Buffers_bytes{name =~ "bac-p-advertisement-spark-fy|bac-p-vision|data-p-etl-01a.*|kafka-ui.*|platform-p-qwest-07c.*|bac-p-widgetaggregator.*|bac-p-sort-filter-consumer.*|platform-p-qwest-cron-01a.*|bac-p-supplier-sf.*|bac-p-feedaggregator-search|bac-p-feedaggregator-secondary|bac-p-search-indexer-sort-filter|platform-p-qwest-01c.*|bac-p-offer-service-worker|bac-p-marvel-flink-new.*"}) / node_memory_MemTotal_bytes{name =~ "bac-p-advertisement-spark-fy|platform-p-qwest-07c.*|kafka-ui.*|bac-p-widgetaggregator.*|bac-p-sort-filter-consumer.*|bac-p-supplier-sf.*|platform-p-qwest-01c.*|bac-p-discovery-elasticsearch-exporter.*|bac-p-feedaggregator-search|bac-p-feedaggregator-secondary|platform-p-qwest-cron-01a.*|bac-p-search-indexer-sort-filter|data-p-etl-01a.*|bac-p-marvel-flink.*|bac-p-offer-service-worker|bac-p-vision|bac-p-marvel-flink-new.*"} * 100 < 10 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-95% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "dp-mb-sec-wk-mix.*|bac-p-sort-and-filter-secondary.*|bac-p-product-similarity-api"} + node_memory_Cached_bytes{name =~ "dp-mb-sec-wk-mix.*|bac-p-sort-and-filter-secondary.*|bac-p-product-similarity-api"} + node_memory_Buffers_bytes{name =~ "dp-mb-sec-wk-mix.*|bac-p-sort-and-filter-secondary.*|bac-p-product-similarity-api"}) / node_memory_MemTotal_bytes{name =~ "dp-mb-sec-wk-mix.*|bac-p-sort-and-filter-secondary.*|bac-p-product-similarity-api"} * 100 < 5 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (<5% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-85% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-advertisement-hbase-v1|bac-p-supplier-payment-web|communicator-consumer-sms-campaign|bac-p-presto-gateway|bac-p-price-aggregator|discovery-platform-jobs|data-p-kafka-connect-01a"} + node_memory_Cached_bytes{name =~ "bac-p-advertisement-hbase-v1|bac-p-supplier-payment-web|bac-p-presto-gateway|communicator-consumer-sms-campaign|bac-p-price-aggregator|discovery-platform-jobs|data-p-kafka-connect-01a"} + node_memory_Buffers_bytes{name =~ "bac-p-advertisement-hbase-v1|bac-p-supplier-payment-web|bac-p-presto-gateway|communicator-consumer-sms-campaign|bac-p-price-aggregator|discovery-platform-jobs|data-p-kafka-connect-01a"}) / node_memory_MemTotal_bytes{name =~ "bac-p-advertisement-hbase-v1|bac-p-supplier-payment-web|communicator-consumer-sms-campaign|bac-p-presto-gateway|bac-p-price-aggregator|discovery-platform-jobs|data-p-kafka-connect-01a"} * 100 < 15 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 15% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-80% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-cis.*"} + node_memory_Cached_bytes{name =~ "bac-p-cis.*"} + node_memory_Buffers_bytes{name =~ "bac-p-cis.*"}) / node_memory_MemTotal_bytes{name =~ "bac-p-cis.*"} * 100 < 20 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 20% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-80% expr: (1 - (node_memory_MemAvailable_bytes{job=~'node_exporter', name=~"bac-p-pdf.*"} / (node_memory_MemTotal_bytes{name=~"bac-p-pdf.*"})))* 100 > 80 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 20% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-82% expr: (1 - (node_memory_MemAvailable_bytes{job=~'node_exporter', name=~"bac-p-ct-qct-v2-web.*"} / (node_memory_MemTotal_bytes{name=~"bac-p-ct-qct-v2-web.*"})))* 100 > 82 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 18% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-88% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-onboarding-hbase.*|"} + node_memory_Cached_bytes{name =~ "bac-p-onboarding-hbase.*|"} + node_memory_Buffers_bytes{name =~ "bac-p-onboarding-hbase.*|"}) / node_memory_MemTotal_bytes{name =~ "bac-p-onboarding-hbase.*|"} * 100 < 12 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 12% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-91% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "offer-platform"} + node_memory_Cached_bytes{name =~ "offer-platform"} + node_memory_Buffers_bytes{name =~ "offer-platform"}) / node_memory_MemTotal_bytes{name =~ "offer-platform"} * 100 < 9 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 9% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-60% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "devops-p-prometheus.*|supplier-platform-promotions.*"} + node_memory_Cached_bytes{name =~ "devops-p-prometheus.*|supplier-platform-promotions.*"} + node_memory_Buffers_bytes{name =~ "devops-p-prometheus.*|supplier-platform-promotions.*"}) / node_memory_MemTotal_bytes{name =~ "devops-p-prometheus.*|supplier-platform-promotions.*"} * 100 < 40 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 40% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-75% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-farmiso.*|bac-p-farmiso-worker.*|dataplatform-datascience-master.*"} + node_memory_Cached_bytes{name =~ "bac-p-farmiso.*|bac-p-farmiso-worker.*|dataplatform-datascience-master.*"} + node_memory_Buffers_bytes{name =~ "bac-p-farmiso.*|bac-p-farmiso-worker.*|dataplatform-datascience-master.*"}) / node_memory_MemTotal_bytes{name =~ "bac-p-farmiso.*|bac-p-farmiso-worker.*|dataplatform-datascience-master.*"} * 100 < 25 for: 1m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 25% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-70% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "dataplatform-p-Prism-lake-master.*|bac-p-redis-master-01a|bac-p-watcher-consumer|bac-p-watcher-web|dataplatform-p-Prism-LAKE-33-master.*"} + node_memory_Cached_bytes{name =~ "dataplatform-p-Prism-lake-master.*|bac-p-redis-master-01a|bac-p-watcher-consumer|bac-p-watcher-web|bac-p-promo.*|dataplatform-p-Prism-LAKE-33-master.*"} + node_memory_Buffers_bytes{name =~ "dataplatform-p-Prism-lake-master.*|bac-p-redis-master-01a|bac-p-watcher-consumer|bac-p-watcher-web|dataplatform-p-Prism-LAKE-33-master.*"}) / node_memory_MemTotal_bytes{name =~ "dataplatform-p-Prism-lake-master.*|bac-p-promo.*|bac-p-redis-master-01a|dataplatform-p-Prism-LAKE-33-master.*|bac-p-watcher-consumer|bac-p-watcher-web"} * 100 < 30 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (< 30% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-60% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "front-p-pow-new"} + node_memory_Cached_bytes{name =~ "front-p-pow-new"} + node_memory_Buffers_bytes{name =~ "front-p-pow-new"}) / node_memory_MemTotal_bytes{name =~ "front-p-pow-new"} * 100 < 40 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (<40% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-40% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "front-p-pow"} + node_memory_Cached_bytes{name =~ "front-p-pow"} + node_memory_Buffers_bytes{name =~ "front-p-pow"}) / node_memory_MemTotal_bytes{name =~ "front-p-pow"} * 100 < 60 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (<60% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-60% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "front-p-pow"} + node_memory_Cached_bytes{name =~ "front-p-pow"} + node_memory_Buffers_bytes{name =~ "front-p-pow"}) / node_memory_MemTotal_bytes{name =~ "front-p-pow"} * 100 < 40 for: 6m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (<40% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfMemory-90% expr: (node_memory_MemFree_bytes{job=~'node_exporter', name =~ "bac-p-relevance-service|data-platform-starburst-presto.*|bac-p-supplier-ums-cron"} + node_memory_Cached_bytes{name =~ "bac-p-relevance-service|data-platform-starburst-presto.*|bac-p-supplier-ums-cron"} + node_memory_Buffers_bytes{name =~ "bac-p-relevance-service|data-platform-starburst-presto.*|bac-p-supplier-ums-cron"}) / node_memory_MemTotal_bytes{name =~ "bac-p-relevance-service|data-platform-starburst-presto.*|bac-p-supplier-ums-cron"} * 100 < 10 for: 3m labels: severity: critical annotations: summary: "Out of memory (instance {{ $labels.private_ip }})" description: "Machine Memory is filling up (<10% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: OutOfInodes expr: node_filesystem_files_free{job=~'node_exporter', mountpoint ="/rootfs"} / node_filesystem_files{job=~'node_exporter', mountpoint ="/rootfs"} * 100 < 20 for: 30m labels: severity: critical annotations: summary: "Out of inodes (instance {{ $labels.private_ip }})." description: "Disk is almost running out of available inodes (< 20% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: FileDescriptor expr: (node_filefd_allocated{job="node_exporter"} / node_filefd_maximum{job="node_exporter"}) > 0.5 for: 2m labels: severity: critical annotations: summary: "FileDescriptor (instance {{ $labels.private_ip }})." description: "FileDescriptor is less than (< 50% left)\n VALUE = {{ $value }}\n LABELS: {{ $labels }}" - alert: NodeExporterDown expr: up{job="node_exporter"} != 1 for: 20m labels: severity: critical annotations: summary: "Instance {{ $labels.private_ip }} down" description: "{{ $labels.private_ip }} of job {{ $labels.job }} has been down for more than 1 minutes." - alert: InstanceDown expr: aws_ec2_status_check_failed_maximum{job="aws_ec2"} offset 10m > 0 for: 1m labels: severity: critical annotations: summary: "Instance {{ $labels.instance_id }} down" description: "{{ $labels.instance_id }} of job {{ $labels.job }} has been down for more than 1 minutes." - alert: HiveTCPconnections expr: node_sockstat_TCP_inuse{private_ip=~'172.31.63.135|172.31.57.131|172.31.57.199|172.31.52.164|172.31.54.95|172.31.52.155|172.31.55.248|10.20.20.158|172.31.109.7'} > 120 for: 1m labels: severity: critical bu: dataengg team: data-intelligence env: prd priority: p0 service: Hive annotations: summary: "TCP Connections are high for the instance {{ $labels.private_ip }} " description: "TCP Connections are high for the instance {{ $labels.private_ip }}" - alert: HiveTCPconnections expr: node_sockstat_TCP_inuse{private_ip=~'10.20.30.16|10.20.20.243'} > 120 for: 1m labels: severity: critical bu: datascience team: data-science env: prd priority: p0 service: Hive annotations: summary: "TCP Connections are high for the instance {{ $labels.private_ip }} " description: "TCP Connections are high for the instance {{ $labels.private_ip }}\n steps to fix: \n 1. ssh -i key ubuntu@ip \n 2. sudo systemctl restart hcatserver.service" - alert: ens_in_download expr: irate(node_network_receive_bytes_total{private_ip=~'10.20.30.16|10.20.20.243',device='ens5'}[5m])*8/(1024*1024) > 2 for: 1m labels: severity: critical bu: datascience team: data-science env: prd priority: p0 service: Hive annotations: summary: "High Nework Receive Bytes on ens {{ $labels.private_ip }} " description: "High Nework Receive Bytes on ens > 2MBpS{{ $labels.private_ip }}" - alert: ens_in_download expr: irate(node_network_receive_bytes_total{private_ip=~'172.31.52.164|172.31.54.95|10.20.20.158',device='ens5'}[5m])*8/(1024*1024) > 2 for: 1m labels: severity: critical bu: dataengg team: data-intelligence env: prd priority: p0 service: Hive annotations: summary: "High Nework Receive Bytes on ens {{ $labels.private_ip }} " description: "High Nework Receive Bytes on ens > 2MBpS{{ $labels.private_ip }}" - alert: ens_in_download expr: irate(node_network_receive_bytes_total{private_ip=~'172.31.63.135|172.31.57.131|172.31.57.199|172.31.109.7|172.31.52.155|172.31.55.248',device='ens5'}[5m])*8/(1024*1024) > 10 for: 1m labels: severity: critical bu: dataengg team: data-intelligence env: prd priority: p0 service: Hive annotations: summary: "High Nework Receive Bytes on ens {{ $labels.private_ip }} " description: "High Nework Receive Bytes on ens > 2MBpS{{ $labels.private_ip }}" - alert: ens_out_upload expr: irate(node_network_transmit_bytes_total{private_ip=~'10.20.30.16|10.20.20.243',device='ens5'}[5m])*8/(1024*1024) > 2 for: 1m labels: severity: critical bu: datascience team: data-science env: prd priority: p0 service: Hive annotations: summary: "High Nework Transmit Bytes on ens {{ $labels.private_ip }} " description: "High Nework Transmit Bytes on ens > 2MBpS{{ $labels.private_ip }}" - alert: ens_out_upload expr: irate(node_network_transmit_bytes_total{private_ip=~'172.31.52.164|172.31.54.95|10.20.20.158',device='ens5'}[5m])*8/(1024*1024) > 2 for: 1m labels: severity: critical bu: dataengg team: data-intelligence env: prd priority: p0 service: Hive annotations: summary: "High Nework Transmit Bytes on ens {{ $labels.private_ip }} " description: "High Nework Transmit Bytes on ens > 2MBpS{{ $labels.private_ip }}" - alert: ens_out_upload expr: irate(node_network_transmit_bytes_total{private_ip=~'172.31.63.135|172.31.57.131|172.31.57.199|172.31.109.7|172.31.52.155|172.31.55.248',device='ens5'}[5m])*8/(1024*1024) > 10 for: 1m labels: severity: critical bu: dataengg team: data-intelligence env: prd priority: p0 service: Hive annotations: summary: "High Nework Transmit Bytes on ens {{ $labels.private_ip }} " description: "High Nework Transmit Bytes on ens > 2MBpS{{ $labels.private_ip }}"