[ { "kubernetes.container_name": "prometheus", "kubernetes.labels": { "app": "prometheus", "version": "2.39.1", "region": "asia-south1", "team": "monitoring-core" }, "kubernetes.annotations": [ "scrape=true", "team=monitoring", "retention=30d", "alerting=true", "autoscale=enabled" ], "alerts_fired": [ { "name": "HighCPU", "severity": "warning", "trigger_count": 1850 }, { "name": "DiskFull", "severity": "critical", "trigger_count": 743 }, { "name": "HighMemory", "severity": "warning", "trigger_count": 421 }, { "name": "NodeDown", "severity": "critical", "trigger_count": 98 }, { "name": "OOMKilled", "severity": "critical", "trigger_count": 122 } ], "kubernetes.container_image": "quay.io/prometheus/prometheus:v2.39.1", "count": 999999999 }, { "kubernetes.container_name": "grafana", "kubernetes.labels": { "app": "grafana", "tier": "ui", "cluster": "grafana-ha" }, "kubernetes.annotations": [ "persist=true", "theme=dark", "alerts=enabled", "usersync=true", "plugins=enabled" ], "dashboards": [ { "id": 12, "title": "Overview", "widgets": 42 }, { "id": 8, "title": "System Metrics", "widgets": 58 }, { "id": 22, "title": "API Performance", "widgets": 33 }, { "id": 30, "title": "User Analytics", "widgets": 29 }, { "id": 4, "title": "Kubernetes Health", "widgets": 61 } ], "kubernetes.container_image": "grafana/grafana:9.2.0", "count": 500000 }, { "kubernetes.container_name": "alertmanager", "kubernetes.labels": { "app": "alertmanager", "cluster": "main", "region": "us-central" }, "kubernetes.annotations": null, "routes": [ { "receiver": "team-a", "match": "warning", "deliveries": 12000 }, { "receiver": "team-b", "match": "critical", "deliveries": 8500 }, { "receiver": "team-c", "match": "info", "deliveries": 2300 }, { "receiver": "team-d", "match": "error", "deliveries": 5400 }, { "receiver": "team-e", "match": "fatal", "deliveries": 1200 } ], "kubernetes.container_image": "quay.io/prometheus/alertmanager:v0.25.0" }, { "kubernetes.container_name": "nginx", "kubernetes.labels": { "app": "nginx", "env": "prod", "role": "frontend" }, "kubernetes.annotations": [ "team=frontend" ], "access_logs": [ { "path": "/home", "status": 200, "response_time_ms": 123 }, { "path": "/login", "status": 403, "response_time_ms": 352 }, { "path": "/api", "status": 500, "response_time_ms": 640 }, { "path": "/settings", "status": 200, "response_time_ms": 145 }, { "path": "/dashboard", "status": 302, "response_time_ms": 98 } ], "kubernetes.container_image": "nginx:1.23" }, { "kubernetes.container_name": "redis", "kubernetes.labels": { "app": "redis", "role": "cache", "cluster": "redis-main" }, "kubernetes.annotations": [], "cache_keys": [ { "pattern": "session:*", "count": 1500000 }, { "pattern": "profile:*", "count": 800000 }, { "pattern": "cart:*", "count": 450000 }, { "pattern": "inventory:*", "count": 210000 }, { "pattern": "geo:*", "count": 120000 } ], "kubernetes.container_image": "redis:7" }, { "kubernetes.container_name": "mysql", "kubernetes.labels": { "app": "mysql", "tier": "database" }, "kubernetes.annotations": [ "backup=daily" ], "replicas": [ { "node": "db-1", "lag": "0s" }, { "node": "db-2", "lag": "2s" }, { "node": "db-3", "lag": "5s" }, { "node": "db-4", "lag": "0s" }, { "node": "db-5", "lag": "1s" } ], "kubernetes.container_image": "mysql:8.0" }, { "kubernetes.container_name": "fluent-bit", "kubernetes.labels": { "app": "fluent-bit", "type": "logging" }, "kubernetes.annotations": [ "ship-s3=true", "ship-es=true" ], "log_streams": [ { "name": "stdout", "rate": "500msg/s" }, { "name": "stderr", "rate": "120msg/s" }, { "name": "debug", "rate": "80msg/s" }, { "name": "audit", "rate": "40msg/s" }, { "name": "network", "rate": "50msg/s" } ], "kubernetes.container_image": "fluent/fluent-bit:2.2" }, { "kubernetes.container_name": "node-exporter", "kubernetes.labels": { "app": "node-exporter" }, "kubernetes.annotations": null, "metrics_collected": [ { "metric": "cpu_usage", "enabled": true }, { "metric": "memory_usage", "enabled": true }, { "metric": "disk_usage", "enabled": false }, { "metric": "load_avg", "enabled": true }, { "metric": "network_io", "enabled": true } ], "kubernetes.container_image": "quay.io/prometheus/node-exporter:v1.5" }, { "kubernetes.container_name": "kube-state-metrics", "kubernetes.labels": { "app": "kube-state-metrics" }, "kubernetes.annotations": [ "scrape=true" ], "resources_tracked": [ { "type": "pods", "count": 2000 }, { "type": "deployments", "count": 150 }, { "type": "statefulsets", "count": 45 }, { "type": "daemonsets", "count": 29 }, { "type": "jobs", "count": 120 } ], "kubernetes.container_image": "k8s.gcr.io/kube-state-metrics:v2.8" }, { "kubernetes.container_name": "apiserver", "kubernetes.labels": { "app": "kubernetes", "component": "apiserver" }, "audit_logs": [ { "event": "UserLogin", "count": 25000 }, { "event": "CreatePod", "count": 6000 }, { "event": "DeletePod", "count": 3100 }, { "event": "ScaleDeployment", "count": 950 }, { "event": "UpdateConfigMap", "count": 1200 } ], "kubernetes.annotations": [ "audit=enabled" ], "kubernetes.container_image": "k8s.gcr.io/kube-apiserver:v1.26" }, { "kubernetes.container_name": "coredns", "kubernetes.labels": { "app": "coredns" }, "dns_records": [ { "domain": "service.local", "queries": 1500000 }, { "domain": "cluster.local", "queries": 3400000 }, { "domain": "db.local", "queries": 980000 }, { "domain": "api.local", "queries": 1870000 }, { "domain": "auth.local", "queries": 450000 } ], "kubernetes.annotations": [], "kubernetes.container_image": "coredns/coredns:1.10" }, { "kubernetes.container_name": "etcd", "kubernetes.labels": { "app": "etcd", "role": "primary" }, "cluster_peers": [ { "name": "etcd-1", "state": "healthy" }, { "name": "etcd-2", "state": "healthy" }, { "name": "etcd-3", "state": "degraded" }, { "name": "etcd-4", "state": "healthy" }, { "name": "etcd-5", "state": "degraded" } ], "kubernetes.annotations": [ "storage=ssd" ], "kubernetes.container_image": "k8s.gcr.io/etcd:3.5" }, { "kubernetes.container_name": "vault", "kubernetes.labels": { "app": "vault", "env": "dev" }, "secrets_engines": [ { "engine": "kv", "enabled": true }, { "engine": "transit", "enabled": false }, { "engine": "pki", "enabled": true }, { "engine": "aws", "enabled": true }, { "engine": "gcp", "enabled": false } ], "kubernetes.annotations": null, "kubernetes.container_image": "hashicorp/vault:1.12" }, { "kubernetes.container_name": "rabbitmq", "kubernetes.labels": { "app": "rabbitmq" }, "queues": [ { "name": "emails", "messages": 40000 }, { "name": "events", "messages": 900000 }, { "name": "jobs", "messages": 320000 }, { "name": "notifications", "messages": 550000 }, { "name": "system-events", "messages": 78000 } ], "kubernetes.annotations": [ "mirroring=true" ], "kubernetes.container_image": "rabbitmq:3.11" }, { "kubernetes.container_name": "elasticsearch", "kubernetes.labels": { "app": "elasticsearch" }, "indices": [ { "name": "logs-2023", "docs": 120000000 }, { "name": "metrics-2023", "docs": 45000000 }, { "name": "apm-2023", "docs": 75000000 }, { "name": "audit-2023", "docs": 9000000 }, { "name": "security-2023", "docs": 22000000 } ], "kubernetes.annotations": null, "kubernetes.container_image": "elasticsearch:8.5" }, { "kubernetes.container_name": "kibana", "kubernetes.labels": { "app": "kibana" }, "users_active": [ { "user": "admin", "role": "superuser" }, { "user": "viewer", "role": "read-only" }, { "user": "editor", "role": "edit" }, { "user": "analyst", "role": "read" }, { "user": "auditor", "role": "read-only" } ], "kubernetes.annotations": [ "theme=dark" ], "kubernetes.container_image": "kibana:8.5" }, { "kubernetes.container_name": "tempo", "kubernetes.labels": { "app": "tempo" }, "trace_batches": [ { "batch": "A1", "count": 1400000 }, { "batch": "B7", "count": 2000000 }, { "batch": "C3", "count": 980000 }, { "batch": "D9", "count": 1540000 }, { "batch": "E2", "count": 760000 } ], "kubernetes.annotations": [], "kubernetes.container_image": "grafana/tempo:2.0" }, { "kubernetes.container_name": "loki", "kubernetes.labels": { "app": "loki" }, "log_streams": [ { "name": "app-logs", "entries": 50000000 }, { "name": "system-logs", "entries": 120000000 }, { "name": "debug-logs", "entries": 40000000 }, { "name": "audit-logs", "entries": 52000000 }, { "name": "trace-logs", "entries": 31000000 } ], "kubernetes.annotations": null, "kubernetes.container_image": "grafana/loki:2.7" }, { "kubernetes.container_name": "minio", "kubernetes.labels": { "app": "minio", "role": "storage" }, "buckets": [ { "bucket": "configs", "size_mb": 9876543 }, { "bucket": "backups", "size_mb": 45678921 }, { "bucket": "audit-logs", "size_mb": 18500000 }, { "bucket": "archive-2022", "size_mb": 78200000 }, { "bucket": "session-data", "size_mb": 1580000 } ], "kubernetes.annotations": [ "backup=weekly" ], "kubernetes.container_image": "minio/minio:2023" }, { "kubernetes.container_name": "consul", "kubernetes.labels": { "app": "consul" }, "services_registered": [ { "service": "api", "instances": 30 }, { "service": "web", "instances": 22 }, { "service": "auth", "instances": 15 }, { "service": "billing", "instances": 18 }, { "service": "warehouse", "instances": 9 } ], "kubernetes.annotations": [], "kubernetes.container_image": "consul:1.15" }, { "labels": "{ \"service\": \"api\", \"instances\": 300 }" }, { "kubernetes.container_name": "prometheus", "kubernetes.labels": { "app": "prometheus", "version": "2.39.1" }, "kubernetes.annotations": [ true, false, true ], "alerts_fired": [ { "name": "HighCPU", "severity": 1 }, { "name": "DiskFull", "severity": 2 } ], "cpu_load_samples": [ 82.5, 91.2, 88.1, 77.4, 69.0 ], "kubernetes.container_image": "quay.io/prometheus/prometheus:v2.39.1", "count": 150000 }, { "kubernetes.container_name": "grafana", "kubernetes.labels": { "app": "grafana", "tier": "ui" }, "kubernetes.annotations": [ false, true, false ], "dashboards": [ { "id": 12, "title": "Overview" }, { "id": 8, "title": "System Metrics" }, { "id": 27, "title": "Cluster Health" } ], "load_times_ms": [ 120, 95, 140, 150, 110 ], "kubernetes.container_image": "grafana/grafana:9.2.0", "count": 5 }, { "kubernetes.container_name": "nginx", "kubernetes.labels": { "app": "nginx", "env": "prod" }, "kubernetes.annotations": [ 1, 0, 1, 1 ], "access_logs": [ { "path": "/home", "status": 200 }, { "path": "/login", "status": 403 } ], "latency_histogram_ms": [ 10, 20, 35, 55, 85 ], "kubernetes.container_image": "nginx:1.23" }, { "kubernetes.container_name": "redis", "kubernetes.labels": { "app": "redis", "role": "cache" }, "kubernetes.annotations": [], "cache_keys": [ { "pattern": "session:*", "count": 150 }, { "pattern": "profile:*", "count": 80 }, { "pattern": "cart:*", "count": 60 } ], "memory_slots": [ 1024, 2048, 4096, 8192 ], "kubernetes.container_image": "redis:7" }, { "kubernetes.container_name": "mysql", "kubernetes.labels": { "app": "mysql", "tier": "database" }, "kubernetes.annotations": [ 1, 1, 0 ], "replicas": [ { "node": "db-1", "lag": 0 }, { "node": "db-2", "lag": 2 }, { "node": "db-3", "lag": 1 } ], "connection_pool_sizes": [ 100, 150, 200, 180, 175 ], "kubernetes.container_image": "mysql:8.0" }, { "kubernetes.container_name": "fluent-bit", "kubernetes.labels": { "app": "fluent-bit", "type": "logging" }, "kubernetes.annotations": [ true, true, false ], "log_streams": [ { "name": "stdout", "rate": 500 }, { "name": "stderr", "rate": 120 } ], "streams_active": [ 1, 1, 0, 1 ], "kubernetes.container_image": "fluent/fluent-bit:2.2" }, { "kubernetes.container_name": "node-exporter", "kubernetes.labels": { "app": "node-exporter" }, "kubernetes.annotations": null, "metrics_collected": [ { "metric": "cpu_usage", "enabled": true }, { "metric": "memory_usage", "enabled": true }, { "metric": "disk_usage", "enabled": false } ], "enabled_metrics_flags": [ 1, 1, 0, 1, 1 ], "kubernetes.container_image": "quay.io/prometheus/node-exporter:v1.5" }, { "kubernetes.container_name": "tempo", "kubernetes.labels": { "app": "tempo" }, "trace_batches": [ { "batch": "A1", "count": 1400 }, { "batch": "B7", "count": 2000 }, { "batch": "C3", "count": 900 } ], "batch_sizes": [ 1400, 2000, 900, 1800, 2300 ], "kubernetes.annotations": [], "kubernetes.container_image": "grafana/tempo:2.0" }, { "kubernetes.container_name": "loki", "kubernetes.labels": { "app": "loki" }, "log_streams": [ { "name": "app-logs", "entries": 50000 }, { "name": "system-logs", "entries": 120000 } ], "log_counts_hourly": [ 1200, 1400, 1500, 1700, 2000 ], "kubernetes.annotations": null, "kubernetes.container_image": "grafana/loki:2.7" }, { "kubernetes.container_name": "minio", "kubernetes.labels": { "app": "minio", "role": "storage" }, "buckets": [ { "bucket": "configs", "size_mb": 300 }, { "bucket": "backups", "size_mb": 2100 }, { "bucket": "logs", "size_mb": 12000 } ], "bucket_sizes": [ 300, 2100, 12000, 8750, 6432 ], "kubernetes.annotations": [ 0, 1 ], "kubernetes.container_image": "minio/minio:2023" } ]