{ "leansignal_demand_export": "1.0", "exported_at": "2026-07-17T00:00:00Z", "source_tenant": "leansignal-catalog", "catalog": { "slug": "nodejs-otel-demand-extended", "integration": "nodejs", "variant": "extended", "title": "Node.js — Extended", "category": "SDK", "dashboards": 1, "panels": 14, "alerts": 10, "docs_url": "https://docs.leansignal.io/integrations/nodejs/" }, "demand": { "ref": "demand", "name": "Node.js — Extended (OpenTelemetry)", "description": "Deep runtime visibility: p99 and per-route HTTP, per-space V8 heap, GC rate by type, and heap limit, plus the full alert set including sustained heap growth (leak signal).", "dashboards": [ { "ref": "dash-nodejs", "name": "Node.js — Extended", "description": "Node.js/V8 runtime metrics (event-loop utilization & delay, V8 heap, GC pauses) plus HTTP server request metrics (extended variant).", "data": { "display": { "name": "Node.js — Extended" }, "panels": { "http_request_rate": { "kind": "Panel", "spec": { "display": { "name": "HTTP request rate", "description": "Inbound request throughput per instance." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "requests/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (rate(http_server_request_duration_seconds_count{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "http_error_rate": { "kind": "Panel", "spec": { "display": { "name": "HTTP 5xx error rate", "description": "Share of requests answered 5xx." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "percent-decimal" }, "min": 0, "max": 1 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (rate(http_server_request_duration_seconds_count{instance=~\"$instance\",http_response_status_code=~\"5..\"}[5m])) / sum by (instance) (rate(http_server_request_duration_seconds_count{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "http_latency_p95": { "kind": "Panel", "spec": { "display": { "name": "HTTP request duration p95", "description": "95th-percentile request latency per instance." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "seconds" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "histogram_quantile(0.95, sum by (instance, le) (rate(http_server_request_duration_seconds_bucket{instance=~\"$instance\"}[5m])))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "http_latency_p99": { "kind": "Panel", "spec": { "display": { "name": "HTTP request duration p99", "description": "Tail latency — compare with p95 to see how bad the worst requests get." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "seconds" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "histogram_quantile(0.99, sum by (instance, le) (rate(http_server_request_duration_seconds_bucket{instance=~\"$instance\"}[5m])))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "http_request_rate_by_route": { "kind": "Panel", "spec": { "display": { "name": "HTTP request rate by route", "description": "Service-level traffic per route, summed across the selected instances." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "requests/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (http_route) (rate(http_server_request_duration_seconds_count{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{http_route}}" } } } } ] } }, "eventloop_utilization": { "kind": "Panel", "spec": { "display": { "name": "Event-loop utilization", "description": "Share of time the loop is busy — Node’s single most important saturation signal." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "percent-decimal" }, "min": 0, "max": 1 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (nodejs_eventloop_utilization_ratio{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}}" } } } } ] } }, "eventloop_delay_p99": { "kind": "Panel", "spec": { "display": { "name": "Event-loop delay p99", "description": "How late timers fire — blocking work on the loop shows up here." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "seconds" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (nodejs_eventloop_delay_p99_seconds{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}}" } } } } ] } }, "eventloop_delay_p50": { "kind": "Panel", "spec": { "display": { "name": "Event-loop delay p50", "description": "Median loop delay — compare with p99 to separate spikes from constant pressure." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "seconds" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (nodejs_eventloop_delay_p50_seconds{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}}" } } } } ] } }, "heap_used": { "kind": "Panel", "spec": { "display": { "name": "V8 heap used", "description": "Absolute heap in use — the sawtooth is healthy GC behavior." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "bytes" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (v8js_memory_heap_used_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}}" } } } } ] } }, "heap_utilization": { "kind": "Panel", "spec": { "display": { "name": "V8 heap utilization", "description": "Heap used as a share of the pre-allocated heap." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "percent-decimal" }, "min": 0, "max": 1 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (v8js_memory_heap_used_bytes{instance=~\"$instance\"}) / sum by (instance) (v8js_memory_heap_limit_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}}" } } } } ] } }, "heap_used_by_space": { "kind": "Panel", "spec": { "display": { "name": "V8 heap used by space", "description": "new/old/code/large-object spaces — old-space growth is the leak signal." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "bytes" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, v8js_heap_space_name) (v8js_memory_heap_used_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · {{v8js_heap_space_name}}" } } } } ] } }, "heap_limit": { "kind": "Panel", "spec": { "display": { "name": "V8 heap limit (pre-allocated)", "description": "Summed pre-allocated heap-space size — the denominator of the utilization panel, not the --max-old-space-size ceiling." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "bytes" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (v8js_memory_heap_limit_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}}" } } } } ] } }, "gc_pause_p95": { "kind": "Panel", "spec": { "display": { "name": "GC pause duration p95", "description": "Collection pause latency — pauses block the event loop." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "seconds" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "histogram_quantile(0.95, sum by (instance, le) (rate(v8js_gc_duration_seconds_bucket{instance=~\"$instance\"}[5m])))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "gc_rate_by_type": { "kind": "Panel", "spec": { "display": { "name": "GC collections by type", "description": "Major vs minor vs incremental collections — frequent majors mean heap pressure." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "ops/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, v8js_gc_type) (rate(v8js_gc_duration_seconds_count{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{v8js_gc_type}}" } } } } ] } } }, "layouts": [ { "kind": "Grid", "spec": { "display": { "title": "HTTP", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/http_request_rate" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/http_error_rate" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/http_latency_p95" } }, { "x": 12, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/http_latency_p99" } }, { "x": 0, "y": 16, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/http_request_rate_by_route" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Event Loop", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/eventloop_utilization" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/eventloop_delay_p99" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/eventloop_delay_p50" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Memory", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/heap_used" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/heap_utilization" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/heap_used_by_space" } }, { "x": 12, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/heap_limit" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "GC", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/gc_pause_p95" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/gc_rate_by_type" } } ] } } ], "variables": [ { "kind": "ListVariable", "spec": { "name": "instance", "display": { "name": "Instance" }, "allowAllValue": true, "allowMultiple": true, "customAllValue": ".*", "defaultValue": ".*", "plugin": { "kind": "PrometheusLabelValuesVariable", "spec": { "labelName": "instance" } } } } ], "duration": "1h", "refreshInterval": "30s", "datasources": {} } } ], "alert_rules": [ { "ref": "alert-high-http-error-rate", "name": "High HTTP 5xx error rate", "description": null, "query": "sum by (instance) (rate(http_server_request_duration_seconds_count{http_response_status_code=~\"5..\"}[5m])) / sum by (instance) (rate(http_server_request_duration_seconds_count[5m]))", "condition_op": "gt", "threshold": 0.05, "interval": "1m", "for": "5m", "severity": "critical", "message": "{{labels.instance}} is serving {{value | percent:1}} 5xx responses.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-high-http-latency-p95", "name": "High HTTP p95 latency", "description": null, "query": "histogram_quantile(0.95, sum by (instance, le) (rate(http_server_request_duration_seconds_bucket[5m])))", "condition_op": "gt", "threshold": 1, "interval": "1m", "for": "5m", "severity": "warning", "message": "{{labels.instance}} p95 request latency is {{value}}s.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-high-eventloop-utilization", "name": "Event-loop saturated", "description": null, "query": "max by (instance) (nodejs_eventloop_utilization_ratio)", "condition_op": "gt", "threshold": 0.9, "interval": "1m", "for": "5m", "severity": "critical", "message": "{{labels.instance}} event-loop utilization is {{value | percent:1}} — the event loop is starved.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-high-eventloop-delay", "name": "High event-loop delay", "description": null, "query": "max by (instance) (nodejs_eventloop_delay_p99_seconds)", "condition_op": "gt", "threshold": 0.1, "interval": "1m", "for": "5m", "severity": "warning", "message": "{{labels.instance}} p99 event-loop delay is {{value}}s — blocking work on the loop.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-heap-near-limit", "name": "V8 heap near limit", "description": null, "query": "sum by (instance) (min_over_time(v8js_memory_heap_used_bytes[10m])) / sum by (instance) (v8js_memory_heap_limit_bytes)", "condition_op": "gt", "threshold": 0.9, "interval": "1m", "for": "5m", "severity": "critical", "message": "{{labels.instance}} V8 heap stays above {{value | percent:1}} of pre-allocated size even after GC — risk of OOM/GC thrash.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-gc-pause-high", "name": "High GC pause duration", "description": null, "query": "histogram_quantile(0.95, sum by (instance, le) (rate(v8js_gc_duration_seconds_bucket[5m])))", "condition_op": "gt", "threshold": 0.1, "interval": "1m", "for": "10m", "severity": "warning", "message": "{{labels.instance}} p95 GC pause is {{value}}s — GC pressure.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-critical-http-latency-p99", "name": "Critical HTTP p99 latency", "description": null, "query": "histogram_quantile(0.99, sum by (instance, le) (rate(http_server_request_duration_seconds_bucket[5m])))", "condition_op": "gt", "threshold": 3, "interval": "1m", "for": "5m", "severity": "critical", "message": "{{labels.instance}} p99 request latency is {{value}}s.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-elevated-http-4xx", "name": "Elevated HTTP 4xx rate", "description": null, "query": "sum by (instance) (rate(http_server_request_duration_seconds_count{http_response_status_code=~\"4..\"}[5m])) / sum by (instance) (rate(http_server_request_duration_seconds_count[5m]))", "condition_op": "gt", "threshold": 0.3, "interval": "1m", "for": "10m", "severity": "warning", "message": "{{labels.instance}} 4xx ratio is {{value | percent:1}}.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-eventloop-utilization-warning", "name": "Elevated event-loop utilization", "description": null, "query": "max by (instance) (nodejs_eventloop_utilization_ratio)", "condition_op": "gt", "threshold": 0.7, "interval": "1m", "for": "10m", "severity": "warning", "message": "{{labels.instance}} event-loop utilization sustained at {{value | percent:1}}.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-heap-growth", "name": "Sustained heap growth", "description": null, "query": "sum by (instance) (v8js_memory_heap_used_bytes) - sum by (instance) (v8js_memory_heap_used_bytes offset 30m)", "condition_op": "gt", "threshold": 268435456, "interval": "1m", "for": "15m", "severity": "warning", "message": "{{labels.instance}} V8 heap grew by {{value | bytes}} over 30m — possible memory leak.", "notify_on_resolve": true, "paused": false, "channels": [] } ] } }