feat(zfs): add capacity metrics and Grafana dashboard
Deploy an hourly systemd timer that writes pool and dataset capacity to node_exporter's textfile collector, since --collector.zfs exposes only ARC/I-O/state. Add a provisioned 'ZFS - Pools & Datasets' dashboard with per-pool totals, per-dataset used/quota and daily growth panels.
This commit is contained in:
Clément Désiles
@@ -0,0 +1,148 @@
|
||||
{
|
||||
"title": "ZFS - Pools & Datasets",
|
||||
"uid": "zfs",
|
||||
"tags": ["zfs", "storage", "disks"],
|
||||
"schemaVersion": 39,
|
||||
"version": 1,
|
||||
"refresh": "30m",
|
||||
"time": { "from": "now-90d", "to": "now" },
|
||||
"timezone": "browser",
|
||||
"editable": true,
|
||||
"graphTooltip": 1,
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "pool",
|
||||
"label": "Pool",
|
||||
"type": "query",
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"query": { "query": "label_values(zfs_pool_size_bytes, pool)", "refId": "A" },
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"multi": true,
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": { "selected": true, "text": ["All"], "value": ["$__all"] }
|
||||
},
|
||||
{
|
||||
"name": "dataset",
|
||||
"label": "Dataset",
|
||||
"type": "query",
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"query": { "query": "label_values(zfs_dataset_used_bytes, dataset)", "refId": "A" },
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"multi": true,
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": { "selected": true, "text": ["All"], "value": ["$__all"] }
|
||||
}
|
||||
]
|
||||
},
|
||||
"panels": [
|
||||
{
|
||||
"id": 1,
|
||||
"type": "stat",
|
||||
"title": "Pool Size",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "none" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "value", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_pool_size_bytes{pool=~\"$pool\"}", "legendFormat": "{{pool}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"type": "stat",
|
||||
"title": "Pool Allocated",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "none" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "value", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_pool_alloc_bytes{pool=~\"$pool\"}", "legendFormat": "{{pool}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"type": "stat",
|
||||
"title": "Pool Free",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "none" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "value", "graphMode": "none", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_pool_free_bytes{pool=~\"$pool\"}", "legendFormat": "{{pool}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 4,
|
||||
"type": "stat",
|
||||
"title": "Pool Capacity",
|
||||
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "thresholds" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 80 }, { "color": "red", "value": 90 } ] } }, "overrides": [] },
|
||||
"options": { "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "colorMode": "background", "graphMode": "area", "textMode": "auto", "justifyMode": "auto", "orientation": "auto" },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_pool_capacity_percent{pool=~\"$pool\"}", "legendFormat": "{{pool}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"type": "timeseries",
|
||||
"title": "Pool usage over time",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 15, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } },
|
||||
"targets": [
|
||||
{ "refId": "A", "expr": "zfs_pool_size_bytes{pool=~\"$pool\"}", "legendFormat": "{{pool}} size" },
|
||||
{ "refId": "B", "expr": "zfs_pool_alloc_bytes{pool=~\"$pool\"}", "legendFormat": "{{pool}} alloc" },
|
||||
{ "refId": "C", "expr": "zfs_pool_free_bytes{pool=~\"$pool\"}", "legendFormat": "{{pool}} free" }
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": 6,
|
||||
"type": "timeseries",
|
||||
"title": "Pool capacity %",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "percent", "min": 0, "max": 100, "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 15, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 80 }, { "color": "red", "value": 90 } ] } }, "overrides": [] },
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_pool_capacity_percent{pool=~\"$pool\"}", "legendFormat": "{{pool}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"type": "timeseries",
|
||||
"title": "Dataset used bytes",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 15, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_dataset_used_bytes{dataset=~\"$dataset\"}", "legendFormat": "{{dataset}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 8,
|
||||
"type": "bargauge",
|
||||
"title": "Dataset used (current)",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "min": 0, "color": { "mode": "continuous-GrYlRd" } }, "overrides": [] },
|
||||
"options": { "displayMode": "gradient", "orientation": "horizontal", "reduceOptions": { "values": false, "calcs": ["lastNotNull"], "fields": "" }, "showUnfilled": true },
|
||||
"targets": [ { "refId": "A", "expr": "zfs_dataset_used_bytes{dataset=~\"$dataset\"}", "legendFormat": "{{dataset}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 9,
|
||||
"type": "timeseries",
|
||||
"title": "Daily growth - pool allocated (bytes/day)",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 15, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } },
|
||||
"targets": [ { "refId": "A", "expr": "deriv(zfs_pool_alloc_bytes{pool=~\"$pool\"}[1d]) * 86400", "legendFormat": "{{pool}}" } ]
|
||||
},
|
||||
{
|
||||
"id": 10,
|
||||
"type": "timeseries",
|
||||
"title": "Daily growth - datasets (bytes/day)",
|
||||
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 },
|
||||
"datasource": { "type": "prometheus", "uid": "prometheus" },
|
||||
"fieldConfig": { "defaults": { "unit": "bytes", "color": { "mode": "palette-classic" }, "custom": { "fillOpacity": 15, "lineWidth": 1, "drawStyle": "line", "showPoints": "never" } }, "overrides": [] },
|
||||
"options": { "legend": { "displayMode": "list", "placement": "bottom", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } },
|
||||
"targets": [ { "refId": "A", "expr": "deriv(zfs_dataset_used_bytes{dataset=~\"$dataset\"}[1d]) * 86400", "legendFormat": "{{dataset}}" } ]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -260,6 +260,15 @@
|
||||
- systemd-dashboard.json
|
||||
notify: Restart grafana
|
||||
|
||||
- name: Deploy ZFS dashboard
|
||||
ansible.builtin.copy:
|
||||
src: zfs-dashboard.json
|
||||
dest: "{{ grafana_provisioning_path }}/dashboards/zfs.json"
|
||||
owner: "{{ grafana_user }}"
|
||||
group: "{{ grafana_group }}"
|
||||
mode: "0644"
|
||||
notify: Restart grafana
|
||||
|
||||
# Service management
|
||||
- name: Enable and start Grafana service
|
||||
ansible.builtin.systemd:
|
||||
|
||||
Reference in New Issue
Block a user