{ "leansignal_demand_export": "1.0", "exported_at": "2026-07-17T00:00:00Z", "source_tenant": "leansignal-catalog", "catalog": { "slug": "host-metrics-node-exporter-otel-demand-extended", "integration": "host-metrics-node-exporter", "variant": "extended", "title": "Host Metrics (node_exporter) — Extended", "category": "Infrastructure", "dashboards": 2, "panels": 18, "alerts": 14, "docs_url": "https://docs.leansignal.io/integrations/host-metrics-node-exporter/" }, "demand": { "ref": "demand", "name": "Host Metrics (node_exporter) — Extended (OpenTelemetry)", "description": "Deep host and hardware visibility: CPU utilization and by-mode breakdown, swap, inodes, disk operations and busy time, and dropped packets — plus a separate Hardware health dashboard with the sensors the hostmetrics receiver cannot read: temperatures, fan speeds, CPU package power, and ECC memory errors.", "dashboards": [ { "ref": "dash-host-metrics-node-exporter-overview", "name": "Host Metrics (node_exporter) — Host overview — Extended", "description": "Host golden signals from node_exporter — load, memory, filesystem, disk, and network.", "data": { "display": { "name": "Host Metrics (node_exporter) — Host overview — Extended" }, "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" } } } } ] } }, "cpu_utilization": { "kind": "Panel", "spec": { "display": { "name": "CPU utilization", "description": "Busy (non-idle) CPU fraction per host, averaged over 5m windows. Volatile by nature — read it for diagnosis; alerting rides on load per core." }, "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 - avg by (instance) (rate(node_cpu_seconds_total{instance=~\"$instance\",mode=\"idle\"}[5m]))", "seriesNameFormat": "{{instance}}" } } } } ] } }, "cpu_by_mode": { "kind": "Panel", "spec": { "display": { "name": "CPU by mode", "description": "Where CPU time goes — user, system, iowait, and friends." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "percent-decimal" }, "min": 0, "max": 1 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "avg by (instance, mode) (rate(node_cpu_seconds_total{instance=~\"$instance\",mode!=\"idle\"}[5m]))", "seriesNameFormat": "{{instance}} · {{mode}}" } } } } ] } }, "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=~\"$instance\"})", "seriesNameFormat": "{{instance}} · free" } } } } ] } }, "swap_usage": { "kind": "Panel", "spec": { "display": { "name": "Swap usage", "description": "Sustained swap use signals memory pressure. Empty on hosts with no swap configured." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "bytes" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_memory_SwapTotal_bytes{instance=~\"$instance\"} - node_memory_SwapFree_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · used" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance) (node_memory_SwapTotal_bytes{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · total" } } } } ] } }, "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}}" } } } } ] } }, "filesystem_inodes": { "kind": "Panel", "spec": { "display": { "name": "Inode utilization", "description": "Inodes used per mount — a full inode table blocks writes even with disk space left." }, "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_files_free{instance=~\"$instance\",fstype!~\"tmpfs|ramfs\"} / node_filesystem_files{instance=~\"$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" } } } } ] } }, "disk_operations": { "kind": "Panel", "spec": { "display": { "name": "Disk operations", "description": "IOPS per device, split by read/write." }, "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, device) (rate(node_disk_reads_completed_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} read" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_disk_writes_completed_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} write" } } } } ] } }, "disk_busy": { "kind": "Panel", "spec": { "display": { "name": "Disk busy time", "description": "Fraction of time each device spends servicing I/O — pinned near 100% means the device is the bottleneck." }, "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, device) (rate(node_disk_io_time_seconds_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}}" } } } } ] } }, "network_io": { "kind": "Panel", "spec": { "display": { "name": "Network I/O", "description": "Receive/transmit throughput per interface (loopback excluded)." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decbytes/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_receive_bytes_total{instance=~\"$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=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} tx" } } } } ] } }, "network_dropped": { "kind": "Panel", "spec": { "display": { "name": "Network dropped packets", "description": "Drops per interface — buffer or driver pressure." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "packets/sec" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_receive_drop_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · {{device}} rx" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance, device) (rate(node_network_transmit_drop_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" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/cpu_utilization" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/cpu_by_mode" } } ] } }, { "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" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/swap_usage" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Filesystem", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/filesystem_utilization" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/filesystem_inodes" } } ] } }, { "kind": "Grid", "spec": { "display": { "title": "Disk", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/disk_io" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/disk_operations" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/disk_busy" } } ] } }, { "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" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/network_dropped" } } ] } } ], "variables": [ { "kind": "ListVariable", "spec": { "name": "instance", "display": { "name": "Instance" }, "allowAllValue": true, "allowMultiple": true, "customAllValue": ".*", "defaultValue": ".*", "plugin": { "kind": "PrometheusLabelValuesVariable", "spec": { "labelName": "instance" } } } } ], "duration": "1h", "refreshInterval": "30s", "datasources": {} } }, { "ref": "dash-host-metrics-node-exporter-hardware", "name": "Host Metrics (node_exporter) — Hardware health — Extended", "description": "Physical-machine health from the kernel sensors — temperatures, fan speeds, CPU package power, and ECC memory errors. Bare metal only; empty on VMs.", "data": { "display": { "name": "Host Metrics (node_exporter) — Hardware health — Extended" }, "panels": { "hw_temperatures": { "kind": "Panel", "spec": { "display": { "name": "Temperatures (°C)", "description": "Every hwmon temperature sensor plus kernel thermal zones — CPU package, NVMe composite, chipset. Bare metal only; empty on most VMs." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decimal" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance, chip, sensor) (node_hwmon_temp_celsius{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · {{chip}} {{sensor}}" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance, zone, type) (node_thermal_zone_temp{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · zone {{type}}" } } } } ] } }, "hw_fan_speeds": { "kind": "Panel", "spec": { "display": { "name": "Fan speeds (RPM)", "description": "hwmon fan tachometers — a fan at 0 RPM under thermal load is a failure." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decimal" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "max by (instance, chip, sensor) (node_hwmon_fan_rpm{instance=~\"$instance\"})", "seriesNameFormat": "{{instance}} · {{chip}} {{sensor}}" } } } } ] } }, "hw_package_power": { "kind": "Panel", "spec": { "display": { "name": "CPU package power (W)", "description": "Average power draw per CPU package from RAPL energy counters. Needs a powercap-capable CPU; absent on most VMs." }, "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": "sum by (instance, index) (rate(node_rapl_package_joules_total{instance=~\"$instance\"}[5m]))", "seriesNameFormat": "{{instance}} · package {{index}}" } } } } ] } }, "hw_ecc_errors": { "kind": "Panel", "spec": { "display": { "name": "ECC memory errors", "description": "ECC errors caught by the memory controller over the last hour — a rising correctable count is a DIMM starting to die. Needs ECC memory (EDAC)." }, "plugin": { "kind": "TimeSeriesChart", "spec": { "legend": { "position": "bottom", "mode": "table", "values": [ "last-number", "mean", "max" ] }, "yAxis": { "format": { "unit": "decimal" }, "min": 0 } } }, "queries": [ { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (increase(node_edac_correctable_errors_total{instance=~\"$instance\"}[1h]))", "seriesNameFormat": "{{instance}} · correctable (1h)" } } } }, { "kind": "TimeSeriesQuery", "spec": { "plugin": { "kind": "PrometheusTimeSeriesQuery", "spec": { "query": "sum by (instance) (increase(node_edac_uncorrectable_errors_total{instance=~\"$instance\"}[1h]))", "seriesNameFormat": "{{instance}} · uncorrectable (1h)" } } } } ] } } }, "layouts": [ { "kind": "Grid", "spec": { "display": { "title": "Hardware", "collapse": { "open": true } }, "items": [ { "x": 0, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/hw_temperatures" } }, { "x": 12, "y": 0, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/hw_fan_speeds" } }, { "x": 0, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/hw_package_power" } }, { "x": 12, "y": 8, "width": 12, "height": 8, "content": { "$ref": "#/spec/panels/hw_ecc_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-memory-warning", "name": "Host memory usage high (warning)", "description": null, "query": "1 - (max by (instance) (node_memory_MemAvailable_bytes) / max by (instance) (node_memory_MemTotal_bytes))", "condition_op": "gt", "threshold": 0.8, "interval": "1m", "for": "15m", "severity": "warning", "message": "Memory utilization on {{labels.instance}} is above 80% ({{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": [] }, { "ref": "alert-inodes-high", "name": "Host filesystem inodes high", "description": null, "query": "max by (instance, mountpoint) (1 - node_filesystem_files_free{fstype!~\"tmpfs|ramfs\"} / node_filesystem_files{fstype!~\"tmpfs|ramfs\"})", "condition_op": "gt", "threshold": 0.85, "interval": "1m", "for": "15m", "severity": "warning", "message": "Inode usage on {{labels.mountpoint}} ({{labels.instance}}) is above 85% ({{value}}).", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-swap-high", "name": "Host swap usage high", "description": null, "query": "max by (instance) ((node_memory_SwapTotal_bytes - node_memory_SwapFree_bytes) / node_memory_SwapTotal_bytes)", "condition_op": "gt", "threshold": 0.5, "interval": "1m", "for": "15m", "severity": "warning", "message": "Swap utilization on {{labels.instance}} is above 50% ({{value}}).", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-network-errors-high", "name": "Host network errors high", "description": null, "query": "sum by (instance) (rate(node_network_receive_errs_total[5m])) + sum by (instance) (rate(node_network_transmit_errs_total[5m]))", "condition_op": "gt", "threshold": 10, "interval": "1m", "for": "5m", "severity": "warning", "message": "Network error rate on {{labels.instance}} is {{value}}/s.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-temperature-warning", "name": "Host temperature high (warning)", "description": null, "query": "max by (instance, chip, sensor) (node_hwmon_temp_celsius)", "condition_op": "gt", "threshold": 85, "interval": "1m", "for": "15m", "severity": "warning", "message": "Sensor {{labels.sensor}} ({{labels.chip}}) on {{labels.instance}} has read above 85°C for 15 minutes ({{value}}°C).", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-temperature-critical", "name": "Host temperature high (critical)", "description": null, "query": "max by (instance, chip, sensor) (node_hwmon_temp_celsius)", "condition_op": "gt", "threshold": 95, "interval": "1m", "for": "5m", "severity": "critical", "message": "Sensor {{labels.sensor}} ({{labels.chip}}) on {{labels.instance}} reads {{value}}°C — thermal throttling or shutdown imminent.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-ecc-correctable", "name": "Host ECC memory errors (correctable)", "description": null, "query": "sum by (instance) (increase(node_edac_correctable_errors_total[1h]))", "condition_op": "gt", "threshold": 0, "interval": "1m", "for": "5m", "severity": "warning", "message": "{{labels.instance}} corrected {{value}} ECC memory errors in the last hour — a DIMM may be degrading.", "notify_on_resolve": true, "paused": false, "channels": [] }, { "ref": "alert-ecc-uncorrectable", "name": "Host ECC memory errors (uncorrectable)", "description": null, "query": "sum by (instance) (increase(node_edac_uncorrectable_errors_total[1h]))", "condition_op": "gt", "threshold": 0, "interval": "1m", "for": "5m", "severity": "critical", "message": "{{labels.instance}} hit {{value}} uncorrectable ECC memory errors in the last hour — corrupted data was served; replace the DIMM.", "notify_on_resolve": true, "paused": false, "channels": [] } ] } }