{ "leansignal_demand_export": "1.0", "exported_at": "2026-07-17T00:00:00Z", "source_tenant": "leansignal-catalog", "catalog": { "slug": "host-metrics-node-exporter-otel-demand-standard", "integration": "host-metrics-node-exporter", "variant": "standard", "title": "Host Metrics (node_exporter) — Standard", "category": "Infrastructure", "dashboards": 1, "panels": 7, "alerts": 6, "docs_url": "https://docs.leansignal.io/integrations/host-metrics-node-exporter/" }, "demand": { "ref": "demand", "name": "Host Metrics (node_exporter) — Standard (OpenTelemetry)", "description": "A well-rounded host overview: adds per-state memory, disk I/O, and network errors, with paired warning/critical alerting. The recommended default for most fleets.", "dashboards": [ { "ref": "dash-host-metrics-node-exporter", "name": "Host Metrics (node_exporter) — Standard", "description": "Host metrics from Prometheus node_exporter — CPU, memory, disk, and network, plus the hardware sensors — temperatures, fan speeds, power draw, and ECC memory errors (standard variant).", "data": { "display": { "name": "Host Metrics (node_exporter) — Standard" }, "panels": { "load_average": { "kind": "Panel", "spec": { "display": { "name": "Load average", "description": "Runnable tasks averaged over 1/5/15 minutes — sustained load above the cores line means saturation." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decimal" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_load1{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · 1m" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_load5{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · 5m" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_load15{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · 15m" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "count by (instance) (node_cpu_seconds_total{instance=~\"$instance\",mode=\"idle\"})", "seriesNameFormat": "{{instance}} · cores" } } } } ] } }, "memory_utilization": { "kind": "Panel", "spec": { "display": { "name": "Memory utilization", "description": "Fraction of physical memory in use per host (1 − MemAvailable/MemTotal)." }, "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": "1 - (max by (instance) (node_memory_MemAvailable_bytes{instance=~\"$instance\"}) / max by (instance) (node_memory_MemTotal_bytes{instance=~\"$instance\"}))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "memory_by_state": { "kind": "Panel", "spec": { "display": { "name": "Memory usage by state", "description": "Used vs cached vs buffered vs free, per host." }, "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": "max by (instance) (node_memory_MemTotal_bytes{instance=~\"$instance\"} - node_memory_MemFree_bytes{instance=~\"$instance\"} - node_memory_Buffers_bytes{instance=~\"$instance\"} - node_memory_Cached_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · used" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_memory_Cached_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · cached" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_memory_Buffers_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · buffers" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_memory_MemFree_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · free" } } } } ] } }, "filesystem_utilization": { "kind": "Panel", "spec": { "display": { "name": "Filesystem utilization", "description": "Fill level per mount point (RAM-backed filesystems excluded)." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "percent-decimal" }, "min": 0, "max": 1 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance, mountpoint) (1 - node_filesystem_avail_bytes{instance=~\"$instance\",fstype!~\"tmpfs|ramfs\"} / node_filesystem_size_bytes{instance=~\"$instance\",fstype!~\"tmpfs|ramfs\"})", "seriesNameFormat": "{{instance}} · {{mountpoint}}" } } } } ] } }, "disk_io": { "kind": "Panel", "spec": { "display": { "name": "Disk I/O", "description": "Read/write throughput per device." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decbytes/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_disk_read_bytes_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} read" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_disk_written_bytes_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} write" } } } } ] } }, "network_io": { "kind": "Panel", "spec": { "display": { "name": "Network I/O", "description": "Receive/transmit throughput per interface (loopback excluded)." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decbytes/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_receive_bytes_total{instance=~\"$instance\",device!=\"lo\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} rx" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_transmit_bytes_total{instance=~\"$instance\",device!=\"lo\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} tx" } } } } ] } }, "network_errors": { "kind": "Panel", "spec": { "display": { "name": "Network errors", "description": "Interface errors — zero on a healthy link." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "packets/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_receive_errs_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} rx" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_transmit_errs_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} tx" } } } } ] } } }, "layouts": [ { "kind": "Grid", "spec": { "display": { "title": "CPU", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/load_average" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Memory", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/memory_utilization" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/memory_by_state" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Filesystem", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/filesystem_utilization" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Disk", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/disk_io" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Network", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/network_io" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/network_errors" } } ] } } ], "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-host-down", "name": "Host down or unreachable", "description": null, "query": "min by (instance) (up{job=\"node\"})", "condition_op": "lt", "threshold": 1, "interval": "1m", "for": "5m", "severity": "critical", "message": "node_exporter on {{labels.instance}} has stopped answering scrapes — host down, exporter down, or unreachable.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-load-critical", "name": "Host load high (critical)", "description": null, "query": "max by (instance) (node_load5) / count by (instance) (node_cpu_seconds_total{mode=\"idle\"})", "condition_op": "gt", "threshold": 3, "interval": "1m", "for": "10m", "severity": "critical", "message": "5m load on {{labels.instance}} is {{value}}× its core count — the host is heavily saturated.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-load-warning", "name": "Host load high (warning)", "description": null, "query": "max by (instance) (node_load5) / count by (instance) (node_cpu_seconds_total{mode=\"idle\"})", "condition_op": "gt", "threshold": 1.5, "interval": "1m", "for": "15m", "severity": "warning", "message": "5m load on {{labels.instance}} is {{value}}× its core count — runnable tasks exceed the cores.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-memory-critical", "name": "Host memory usage high (critical)", "description": null, "query": "1 - (max by (instance) (node_memory_MemAvailable_bytes) / max by (instance) (node_memory_MemTotal_bytes))", "condition_op": "gt", "threshold": 0.9, "interval": "1m", "for": "5m", "severity": "critical", "message": "Memory utilization on {{labels.instance}} is above 90% ({{value}}).", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-filesystem-critical", "name": "Host filesystem usage high (critical)", "description": null, "query": "max by (instance, mountpoint) (1 - node_filesystem_avail_bytes{fstype!~\"tmpfs|ramfs\"} / node_filesystem_size_bytes{fstype!~\"tmpfs|ramfs\"})", "condition_op": "gt", "threshold": 0.9, "interval": "1m", "for": "10m", "severity": "critical", "message": "Filesystem {{labels.mountpoint}} on {{labels.instance}} is above 90% full ({{value}}).", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-filesystem-warning", "name": "Host filesystem usage high (warning)", "description": null, "query": "max by (instance, mountpoint) (1 - node_filesystem_avail_bytes{fstype!~\"tmpfs|ramfs\"} / node_filesystem_size_bytes{fstype!~\"tmpfs|ramfs\"})", "condition_op": "gt", "threshold": 0.8, "interval": "1m", "for": "15m", "severity": "warning", "message": "Filesystem {{labels.mountpoint}} on {{labels.instance}} is above 80% full ({{value}}).", "notify_on_resolve": true, "paused": false, "channels": [] } ] } }