feat(monitoring): add grafana, prometheus, node_exporter roles
- grafana: postgres backend, provisioning (prometheus datasource + node/NUT dashboards) - prometheus: native service, scrape config via host_vars, localhost bind - node_exporter: host metrics exporter (localhost:9100)
This commit is contained in:
Clément Désiles
@@ -0,0 +1,147 @@
|
||||
{
|
||||
"title": "Node Exporter - Host Overview",
|
||||
"uid": "node-exporter-overview",
|
||||
"tags": ["node-exporter", "linux", "system"],
|
||||
"schemaVersion": 39,
|
||||
"version": 1,
|
||||
"refresh": "1m",
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"timezone": "browser",
|
||||
"editable": true,
|
||||
"graphTooltip": 1,
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "instance",
|
||||
"label": "Host",
|
||||
"type": "query",
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"query": { "query": "label_values(node_uname_info, instance)", "refId": "A" },
|
||||
"refresh": 2,
|
||||
"multi": false,
|
||||
"includeAll": false,
|
||||
"sort": 1,
|
||||
"current": { "selected": false, "text": "", "value": "" }
|
||||
}
|
||||
]
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"type": "stat",
|
||||
"title": "Uptime",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "dtdurations", "color": { "mode": "thresholds" } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "none", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "node_time_seconds{instance=\"$instance\"} - node_boot_time_seconds{instance=\"$instance\"}" } ]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"type": "stat",
|
||||
"title": "CPU Cores",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short", "color": { "mode": "thresholds" } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "none", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "count(count by (cpu) (node_cpu_seconds_total{mode=\"idle\", instance=\"$instance\"}))" } ]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"type": "stat",
|
||||
"title": "Load 1m",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short", "color": { "mode": "thresholds" } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "none", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "node_load1{instance=\"$instance\"}" } ]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"type": "stat",
|
||||
"title": "Memory Used",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 75 }, { "color": "red", "value": 90 } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "100 * (1 - (node_memory_MemAvailable_bytes{instance=\"$instance\"} / node_memory_MemTotal_bytes{instance=\"$instance\"}))" } ]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"type": "timeseries",
|
||||
"title": "CPU Usage",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 20, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [ { "refId": "A", "expr": "100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\", instance=\"$instance\"}[$__rate_interval])) * 100)", "legendFormat": "CPU used" } ]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"type": "timeseries",
|
||||
"title": "System Load",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "short", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 10, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [
|
||||
{ "refId": "A", "expr": "node_load1{instance=\"$instance\"}", "legendFormat": "load1" },
|
||||
{ "refId": "B", "expr": "node_load5{instance=\"$instance\"}", "legendFormat": "load5" },
|
||||
{ "refId": "C", "expr": "node_load15{instance=\"$instance\"}", "legendFormat": "load15" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"type": "timeseries",
|
||||
"title": "Memory Usage %",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 20, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [ { "refId": "A", "expr": "100 * (1 - (node_memory_MemAvailable_bytes{instance=\"$instance\"} / node_memory_MemTotal_bytes{instance=\"$instance\"}))", "legendFormat": "Used %" } ]
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"type": "timeseries",
|
||||
"title": "Memory",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 20, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [
|
||||
{ "refId": "A", "expr": "node_memory_MemTotal_bytes{instance=\"$instance\"} - node_memory_MemAvailable_bytes{instance=\"$instance\"}", "legendFormat": "Used" },
|
||||
{ "refId": "B", "expr": "node_memory_Cached_bytes{instance=\"$instance\"} + node_memory_Buffers_bytes{instance=\"$instance\"}", "legendFormat": "Cached+Buffers" },
|
||||
{ "refId": "C", "expr": "node_memory_MemAvailable_bytes{instance=\"$instance\"}", "legendFormat": "Available" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"type": "timeseries",
|
||||
"title": "Filesystem Usage %",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 15, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [ { "refId": "A", "expr": "100 * (1 - (node_filesystem_avail_bytes{instance=\"$instance\", fstype!~\"tmpfs|overlay|squashfs|ramfs\"} / node_filesystem_size_bytes{instance=\"$instance\", fstype!~\"tmpfs|overlay|squashfs|ramfs\"}))", "legendFormat": "{{mountpoint}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"type": "timeseries",
|
||||
"title": "Disk I/O",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "Bps", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 10, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [
|
||||
{ "refId": "A", "expr": "rate(node_disk_read_bytes_total{instance=\"$instance\", device!~\"ram.*|loop.*\"}[$__rate_interval])", "legendFormat": "{{device}} read" },
|
||||
{ "refId": "B", "expr": "-rate(node_disk_written_bytes_total{instance=\"$instance\", device!~\"ram.*|loop.*\"}[$__rate_interval])", "legendFormat": "{{device}} write" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 11,
|
||||
"type": "timeseries",
|
||||
"title": "Network Traffic",
|
||||
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 28 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "Bps", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 10, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [
|
||||
{ "refId": "A", "expr": "rate(node_network_receive_bytes_total{instance=\"$instance\", device!~\"lo|veth.*|cni.*|br-.*|docker.*\"}[$__rate_interval])", "legendFormat": "{{device}} in" },
|
||||
{ "refId": "B", "expr": "-rate(node_network_transmit_bytes_total{instance=\"$instance\", device!~\"lo|veth.*|cni.*|br-.*|docker.*\"}[$__rate_interval])", "legendFormat": "{{device}} out" }
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,102 @@
|
||||
{
|
||||
"title": "UPS - NUT Status",
|
||||
"uid": "nut-status",
|
||||
"tags": ["nut", "ups", "power"],
|
||||
"schemaVersion": 39,
|
||||
"version": 1,
|
||||
"refresh": "30s",
|
||||
"time": { "from": "now-24h", "to": "now" },
|
||||
"timezone": "browser",
|
||||
"editable": true,
|
||||
"graphTooltip": 1,
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "instance",
|
||||
"label": "UPS",
|
||||
"type": "query",
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"query": { "query": "label_values(network_ups_tools_device_info, instance)", "refId": "A" },
|
||||
"refresh": 2,
|
||||
"multi": false,
|
||||
"includeAll": false,
|
||||
"sort": 1,
|
||||
"current": { "selected": false, "text": "", "value": "" }
|
||||
}
|
||||
]
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"type": "stat",
|
||||
"title": "Battery Charge",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "orange", "value": 25 }, { "color": "green", "value": 50 } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "network_ups_tools_battery_charge{instance=\"$instance\"}" } ]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"type": "stat",
|
||||
"title": "UPS Load",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 70 }, { "color": "red", "value": 85 } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "network_ups_tools_ups_load{instance=\"$instance\"}" } ]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"type": "stat",
|
||||
"title": "On Battery",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] }, "mappings": [ { "type": "value", "options": { "0": { "text": "No", "color": "green" }, "1": { "text": "YES", "color": "red" } } } ] }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "network_ups_tools_ups_status{instance=\"$instance\", flag=\"OB\"}" } ]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"type": "stat",
|
||||
"title": "Low Battery",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] }, "mappings": [ { "type": "value", "options": { "0": { "text": "No", "color": "green" }, "1": { "text": "YES", "color": "red" } } } ] }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "network_ups_tools_ups_status{instance=\"$instance\", flag=\"LB\"}" } ]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"type": "timeseries",
|
||||
"title": "Battery Charge",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 20, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [ { "refId": "A", "expr": "network_ups_tools_battery_charge{instance=\"$instance\"}", "legendFormat": "charge" } ]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"type": "timeseries",
|
||||
"title": "UPS Load",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 20, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"targets": [ { "refId": "A", "expr": "network_ups_tools_ups_load{instance=\"$instance\"}", "legendFormat": "load" } ]
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"type": "timeseries",
|
||||
"title": "Status Flags",
|
||||
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "none", "min": 0, "max": 1, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 0, "lineWidth": 1, "drawStyle": "line", "showPoints": "never", "staircase": true } }, "overrides": [] },
|
||||
"targets": [
|
||||
{ "refId": "A", "expr": "network_ups_tools_ups_status{instance=\"$instance\", flag=\"OL\"}", "legendFormat": "On line" },
|
||||
{ "refId": "B", "expr": "network_ups_tools_ups_status{instance=\"$instance\", flag=\"OB\"}", "legendFormat": "On battery" },
|
||||
{ "refId": "C", "expr": "network_ups_tools_ups_status{instance=\"$instance\", flag=\"LB\"}", "legendFormat": "Low battery" },
|
||||
{ "refId": "D", "expr": "network_ups_tools_ups_status{instance=\"$instance\", flag=\"CHRG\"}", "legendFormat": "Charging" }
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
apiVersion: 1
|
||||
|
||||
datasources:
|
||||
- name: prometheus
|
||||
uid: prometheus
|
||||
type: prometheus
|
||||
access: proxy
|
||||
url: http://127.0.0.1:9090
|
||||
isDefault: true
|
||||
Reference in New Issue
Block a user