diff options
Diffstat (limited to 'dashboards/smart.json')
| -rw-r--r-- | dashboards/smart.json | 3844 |
1 files changed, 3844 insertions, 0 deletions
diff --git a/dashboards/smart.json b/dashboards/smart.json new file mode 100644 index 0000000..ed48cd1 --- /dev/null +++ b/dashboards/smart.json @@ -0,0 +1,3844 @@ +{ + "title": "Drive Health (SMART)", + "uid": "drive-health-smart", + "description": "Per-drive SMART health in the style of CrystalDiskInfo: a Good/Caution/Bad verdict, full raw attribute tables for SATA, SCSI error counters for SAS, and self-test history.", + "tags": [ + "smart", + "storage", + "hardware" + ], + "timezone": "browser", + "schemaVersion": 41, + "version": 1, + "editable": true, + "graphTooltip": 1, + "refresh": "1m", + "time": { + "from": "now-24h", + "to": "now" + }, + "templating": { + "list": [ + { + "name": "ata_device", + "label": "SATA drive", + "type": "query", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "query": { + "qryType": 1, + "query": "label_values(smartctl:row{bus=\"ata\"}, row)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "refresh": 1, + "includeAll": true, + "multi": true, + "options": [], + "sort": 1, + "hide": 0, + "regex": "/^(?<text>(?<value>\\S+)\\s.*)$/", + "allValue": ".*", + "current": { + "text": [ + "All" + ], + "value": [ + "$__all" + ] + } + }, + { + "name": "sas_device", + "label": "SAS drive", + "type": "query", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "query": { + "qryType": 1, + "query": "label_values(smartctl:row{bus=\"sas\"}, row)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "refresh": 1, + "includeAll": true, + "multi": true, + "options": [], + "sort": 1, + "hide": 0, + "regex": "/^(?<text>(?<value>\\S+)\\s.*)$/", + "allValue": ".*", + "current": { + "text": [ + "All" + ], + "value": [ + "$__all" + ] + } + } + ] + }, + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "datasource", + "uid": "grafana" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "panels": [ + { + "type": "row", + "title": "Fleet Overview", + "id": 1, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "collapsed": false, + "panels": [] + }, + { + "type": "stat", + "title": "Healthy", + "description": "Drives with no failing attribute, no SCSI uncorrected errors and a passing SMART self-assessment.", + "id": 2, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 0, + "y": 1 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "count(smartctl:health_code == 0) or vector(0)", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "drives" + } + ] + }, + { + "type": "stat", + "title": "Caution", + "description": "Reallocated / pending / uncorrectable sectors on SATA, or a non-empty grown defect list on SAS. Not failing yet \u2014 worth watching the trend.", + "id": 3, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 4, + "y": 1 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "count(smartctl:health_code == 1) or vector(0)", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "drives" + } + ] + }, + { + "type": "stat", + "title": "Failing", + "description": "SMART self-assessment failed, an attribute is at or below its threshold, or the drive reported errors it could not correct. Replace these.", + "id": 4, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 8, + "y": 1 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "count(smartctl:health_code == 2) or vector(0)", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "drives" + } + ] + }, + { + "type": "stat", + "title": "Drives", + "description": "", + "id": 5, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 12, + "y": 1 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "count(smartctl_device_smart_status)", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "total" + } + ] + }, + { + "type": "stat", + "title": "Hottest Drive", + "description": "", + "id": 6, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 16, + "y": 1 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "yellow", + "value": 45 + }, + { + "color": "red", + "value": 55 + } + ] + }, + "unit": "celsius" + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max(smartctl_device_temperature{temperature_type=\"current\"})", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "max" + } + ] + }, + { + "type": "stat", + "title": "Longest Powered On", + "description": "", + "id": 7, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 20, + "y": 1 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max(max by (device) (smartctl_device_power_on_seconds or (smart_selftest_last_lifetime_hours * 3600)))", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "max" + } + ] + }, + { + "type": "table", + "title": "All Drives", + "description": "Every drive, worst first. Health is computed by rules/smartctl.yml.", + "id": 8, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 10, + "w": 16, + "x": 0, + "y": 5 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false, + "filterable": true + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Health" + }, + "properties": [ + { + "id": "mappings", + "value": [ + { + "type": "value", + "options": { + "0": { + "text": "GOOD", + "color": "green", + "index": 0 + }, + "1": { + "text": "CAUTION", + "color": "orange", + "index": 1 + }, + "2": { + "text": "BAD", + "color": "red", + "index": 2 + } + } + } + ] + }, + { + "id": "thresholds", + "value": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2 + } + ] + } + }, + { + "id": "custom.cellOptions", + "value": { + "type": "color-background", + "mode": "basic" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Temp" + }, + "properties": [ + { + "id": "unit", + "value": "celsius" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Powered On" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Capacity" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + } + ] + }, + "options": { + "showHeader": true, + "cellHeight": "sm", + "footer": { + "show": false, + "reducer": [ + "sum" + ], + "countRows": false, + "fields": "" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl:health_code * on(device) group_left(model_name, serial_number, protocol) smartctl_device", + "refId": "A", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_temperature{temperature_type=\"current\"})", + "refId": "B", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_power_on_seconds or (smart_selftest_last_lifetime_hours * 3600))", + "refId": "C", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_capacity_bytes)", + "refId": "D", + "instant": true, + "range": false, + "format": "table" + } + ], + "transformations": [ + { + "id": "filterFieldsByName", + "options": { + "include": { + "pattern": "device|model_name|serial_number|protocol|Value.*" + } + } + }, + { + "id": "joinByField", + "options": { + "byField": "device", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": {}, + "indexByName": { + "device": 0, + "model_name": 1, + "serial_number": 2, + "protocol": 3, + "Value #A": 4, + "Value #B": 5, + "Value #C": 6, + "Value #D": 7 + }, + "renameByName": { + "device": "Device", + "model_name": "Model", + "serial_number": "Serial", + "protocol": "Bus", + "Value #A": "Health", + "Value #B": "Temp", + "Value #C": "Powered On", + "Value #D": "Capacity" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": {}, + "sort": [ + { + "field": "Health", + "desc": true + } + ] + } + } + ] + }, + { + "type": "timeseries", + "title": "Temperatures", + "description": "Sustained operation above ~45C measurably shortens drive life.", + "id": 9, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 10, + "w": 8, + "x": 16, + "y": 5 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 1, + "fillOpacity": 15, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "celsius" + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_temperature{temperature_type=\"current\"}", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}}" + } + ] + }, + { + "type": "row", + "title": "${ata_device:text}", + "id": 10, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 15 + }, + "collapsed": false, + "panels": [], + "repeat": "ata_device", + "repeatDirection": "h" + }, + { + "type": "stat", + "title": "Health", + "description": "", + "id": 11, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 0, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "type": "value", + "options": { + "0": { + "text": "GOOD", + "color": "green", + "index": 0 + }, + "1": { + "text": "CAUTION", + "color": "orange", + "index": 1 + }, + "2": { + "text": "BAD", + "color": "red", + "index": 2 + } + } + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl:health_code{device=~\"$ata_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "{{device}}" + } + ] + }, + { + "type": "stat", + "title": "Temperature", + "description": "", + "id": 12, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 6, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "yellow", + "value": 45 + }, + { + "color": "red", + "value": 55 + } + ] + }, + "unit": "celsius" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_temperature{device=~\"$ata_device\", temperature_type=\"current\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "temp" + } + ] + }, + { + "type": "stat", + "title": "Powered On", + "description": "", + "id": 13, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 9, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_power_on_seconds{device=~\"$ata_device\"} or (smart_selftest_last_lifetime_hours{device=~\"$ata_device\"} * 3600))", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "hours" + } + ] + }, + { + "type": "stat", + "title": "Capacity", + "description": "", + "id": 14, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 12, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_capacity_bytes{device=~\"$ata_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "bytes" + } + ] + }, + { + "type": "stat", + "title": "Power Cycles", + "description": "", + "id": 15, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 15, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_power_cycle_count{device=~\"$ata_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "cycles" + } + ] + }, + { + "type": "stat", + "title": "Reallocated Sectors", + "description": "Attribute 5 raw. Sectors the drive has already retired. Any growth here is the single most predictive sign of impending failure.", + "id": 16, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 18, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_attribute{device=~\"$ata_device\", attribute_id=\"5\", attribute_value_type=\"raw\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "sectors" + } + ] + }, + { + "type": "stat", + "title": "Pending Sectors", + "description": "Attribute 197 raw. Sectors that failed to read and are waiting to be reallocated on next write. Often precedes reallocations.", + "id": 17, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 21, + "y": 16 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_attribute{device=~\"$ata_device\", attribute_id=\"197\", attribute_value_type=\"raw\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "sectors" + } + ] + }, + { + "type": "table", + "title": "Drive \u2014 $ata_device", + "description": "Identity of this drive. RPM shows SSD when the drive reports no rotation rate.", + "id": 18, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 24, + "x": 0, + "y": 20 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false, + "filterable": true + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Capacity" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "RPM" + }, + "properties": [ + { + "id": "unit", + "value": "rotrpm" + }, + { + "id": "noValue", + "value": "SSD" + } + ] + } + ] + }, + "options": { + "showHeader": true, + "cellHeight": "sm", + "footer": { + "show": false, + "reducer": [ + "sum" + ], + "countRows": false, + "fields": "" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device{device=~\"$ata_device\"}", + "refId": "A", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_rotation_rate{device=~\"$ata_device\"})", + "refId": "B", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_capacity_bytes{device=~\"$ata_device\"})", + "refId": "C", + "instant": true, + "range": false, + "format": "table" + } + ], + "transformations": [ + { + "id": "filterFieldsByName", + "options": { + "include": { + "pattern": "device|model_family|model_name|serial_number|firmware_version|interface|sata_version|form_factor|Value.*" + } + } + }, + { + "id": "joinByField", + "options": { + "byField": "device", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Value #A": true + }, + "indexByName": { + "device": 0, + "model_family": 1, + "model_name": 2, + "serial_number": 3, + "firmware_version": 4, + "interface": 5, + "sata_version": 6, + "form_factor": 7, + "Value #B": 8, + "Value #C": 9 + }, + "renameByName": { + "device": "Device", + "Value #B": "RPM", + "Value #C": "Capacity", + "model_family": "Family", + "model_name": "Model", + "serial_number": "Serial", + "firmware_version": "Firmware", + "interface": "Interface", + "sata_version": "SATA", + "form_factor": "Form" + } + } + } + ] + }, + { + "type": "table", + "title": "SMART Attributes \u2014 $ata_device", + "description": "Every attribute the drive reports, with its raw value. Current/Worst are normalised 0-253 scores (higher is better); Threshold is where the vendor declares failure; Margin is Current minus Threshold. ID sorts as text, so the table is ordered by attribute name.", + "id": 19, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 12, + "w": 24, + "x": 0, + "y": 24 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false, + "filterable": true + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Margin" + }, + "properties": [ + { + "id": "thresholds", + "value": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "yellow", + "value": 10 + }, + { + "color": "green", + "value": 25 + } + ] + } + }, + { + "id": "custom.cellOptions", + "value": { + "type": "color-background", + "mode": "basic" + } + } + ] + } + ] + }, + "options": { + "showHeader": true, + "cellHeight": "sm", + "footer": { + "show": false, + "reducer": [ + "sum" + ], + "countRows": false, + "fields": "" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_attribute{device=~\"$ata_device\", attribute_value_type=\"value\"}", + "refId": "A", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (attribute_id) (smartctl_device_attribute{device=~\"$ata_device\", attribute_value_type=\"worst\"})", + "refId": "B", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (attribute_id) (smartctl_device_attribute{device=~\"$ata_device\", attribute_value_type=\"thresh\"})", + "refId": "C", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (attribute_id) (smartctl_device_attribute{device=~\"$ata_device\", attribute_value_type=\"raw\"})", + "refId": "D", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (attribute_id) (smartctl_device_attribute{device=~\"$ata_device\", attribute_value_type=\"value\"} - on(device, attribute_id) smartctl_device_attribute{device=~\"$ata_device\", attribute_value_type=\"thresh\"})", + "refId": "E", + "instant": true, + "range": false, + "format": "table" + } + ], + "transformations": [ + { + "id": "filterFieldsByName", + "options": { + "include": { + "pattern": "attribute_id|attribute_name|Value.*" + } + } + }, + { + "id": "joinByField", + "options": { + "byField": "attribute_id", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": {}, + "indexByName": { + "attribute_id": 0, + "attribute_name": 1, + "Value #A": 2, + "Value #B": 3, + "Value #C": 4, + "Value #D": 5, + "Value #E": 6 + }, + "renameByName": { + "attribute_id": "ID", + "attribute_name": "Attribute", + "Value #A": "Current", + "Value #B": "Worst", + "Value #C": "Threshold", + "Value #D": "Raw", + "Value #E": "Margin" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": {}, + "sort": [ + { + "field": "Attribute", + "desc": false + } + ] + } + } + ] + }, + { + "type": "row", + "title": "${sas_device:text}", + "id": 20, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 36 + }, + "collapsed": false, + "panels": [], + "repeat": "sas_device", + "repeatDirection": "h" + }, + { + "type": "stat", + "title": "Health", + "description": "", + "id": 21, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 0, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [ + { + "type": "value", + "options": { + "0": { + "text": "GOOD", + "color": "green", + "index": 0 + }, + "1": { + "text": "CAUTION", + "color": "orange", + "index": 1 + }, + "2": { + "text": "BAD", + "color": "red", + "index": 2 + } + } + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl:health_code{device=~\"$sas_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "{{device}}" + } + ] + }, + { + "type": "stat", + "title": "Temperature", + "description": "", + "id": 22, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 6, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "yellow", + "value": 45 + }, + { + "color": "red", + "value": 55 + } + ] + }, + "unit": "celsius" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_temperature{device=~\"$sas_device\", temperature_type=\"current\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "temp" + } + ] + }, + { + "type": "stat", + "title": "Powered On", + "description": "SAS drives have no ATA attribute 9, so smartctl reports power_on_time from the Background Scan Results log page \u2014 a counter the background-scan subsystem maintains, not the drive's lifetime meter, and one that commonly reads far too low. This tile takes the larger of that counter and the lifetime-hours stamp in the drive's own self-test log, which is why it can exceed what `smartctl -x` prints as 'Accumulated power on time'.", + "id": 23, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 9, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_power_on_seconds{device=~\"$sas_device\"} or (smart_selftest_last_lifetime_hours{device=~\"$sas_device\"} * 3600))", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "hours" + } + ] + }, + { + "type": "stat", + "title": "Capacity", + "description": "", + "id": 24, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 12, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_capacity_bytes{device=~\"$sas_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "bytes" + } + ] + }, + { + "type": "stat", + "title": "Link Speed", + "description": "Negotiated SAS link rate. A drive that has fallen back to a lower rate is worth investigating \u2014 usually a cable or expander.", + "id": 25, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 15, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bps" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_interface_speed{device=~\"$sas_device\", speed_type=\"current\"} * 1000", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "bps" + } + ] + }, + { + "type": "stat", + "title": "Grown Defects", + "description": "Sectors reallocated since the drive left the factory \u2014 the SAS equivalent of ATA attribute 5. A stable non-zero count is tolerable; growth is not.", + "id": 26, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 18, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_scsi_grown_defect_list{device=~\"$sas_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "defects" + } + ] + }, + { + "type": "stat", + "title": "Uncorrected Errors", + "description": "Errors the drive could not correct with ECC or retries, which means data was lost. Should be zero.", + "id": 27, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 3, + "x": 21, + "y": 37 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_read_total_uncorrected_errors{device=~\"$sas_device\"} + smartctl_write_total_uncorrected_errors{device=~\"$sas_device\"}", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "errors" + } + ] + }, + { + "type": "table", + "title": "Drive \u2014 $sas_device", + "description": "Identity of this drive. SAS drives leave firmware_version empty and report their revision in scsi_revision instead.", + "id": 28, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 4, + "w": 24, + "x": 0, + "y": 41 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false, + "filterable": true + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Capacity" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "RPM" + }, + "properties": [ + { + "id": "unit", + "value": "rotrpm" + }, + { + "id": "noValue", + "value": "SSD" + } + ] + } + ] + }, + "options": { + "showHeader": true, + "cellHeight": "sm", + "footer": { + "show": false, + "reducer": [ + "sum" + ], + "countRows": false, + "fields": "" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device{device=~\"$sas_device\"}", + "refId": "A", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_rotation_rate{device=~\"$sas_device\"})", + "refId": "B", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (device) (smartctl_device_capacity_bytes{device=~\"$sas_device\"})", + "refId": "C", + "instant": true, + "range": false, + "format": "table" + } + ], + "transformations": [ + { + "id": "filterFieldsByName", + "options": { + "include": { + "pattern": "device|scsi_vendor|model_name|serial_number|scsi_revision|scsi_version|protocol|form_factor|Value.*" + } + } + }, + { + "id": "joinByField", + "options": { + "byField": "device", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Value #A": true + }, + "indexByName": { + "device": 0, + "scsi_vendor": 1, + "model_name": 2, + "serial_number": 3, + "scsi_revision": 4, + "scsi_version": 5, + "protocol": 6, + "form_factor": 7, + "Value #B": 8, + "Value #C": 9 + }, + "renameByName": { + "device": "Device", + "Value #B": "RPM", + "Value #C": "Capacity", + "scsi_vendor": "Vendor", + "model_name": "Model", + "serial_number": "Serial", + "scsi_revision": "Revision", + "scsi_version": "SCSI", + "protocol": "Bus", + "form_factor": "Form" + } + } + } + ] + }, + { + "type": "timeseries", + "title": "Corrected Errors \u2014 $sas_device", + "description": "Errors the drive fixed on its own. ECC-fast corrections are routine and grow constantly. Delayed corrections and especially rewrites/retries climbing is the signal worth watching.", + "id": 29, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 45 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 1, + "fillOpacity": 15, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_read_errors_corrected_by_eccfast{device=~\"$sas_device\"}", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "read ECC fast" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_read_errors_corrected_by_eccdelayed{device=~\"$sas_device\"}", + "refId": "B", + "instant": false, + "range": true, + "legendFormat": "read ECC delayed" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_read_errors_corrected_by_rereads_rewrites{device=~\"$sas_device\"}", + "refId": "C", + "instant": false, + "range": true, + "legendFormat": "read retries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_write_errors_corrected_by_eccfast{device=~\"$sas_device\"}", + "refId": "D", + "instant": false, + "range": true, + "legendFormat": "write ECC fast" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_write_errors_corrected_by_eccdelayed{device=~\"$sas_device\"}", + "refId": "E", + "instant": false, + "range": true, + "legendFormat": "write ECC delayed" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_write_errors_corrected_by_rereads_rewrites{device=~\"$sas_device\"}", + "refId": "F", + "instant": false, + "range": true, + "legendFormat": "write retries" + } + ] + }, + { + "type": "timeseries", + "title": "Defects & Uncorrected \u2014 $sas_device", + "description": "Flat lines are good. Any upward step here is a real event.", + "id": 30, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 45 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 2, + "fillOpacity": 0, + "showPoints": "auto", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_scsi_grown_defect_list{device=~\"$sas_device\"}", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "grown defects" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_read_total_uncorrected_errors{device=~\"$sas_device\"}", + "refId": "B", + "instant": false, + "range": true, + "legendFormat": "read uncorrected" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_write_total_uncorrected_errors{device=~\"$sas_device\"}", + "refId": "C", + "instant": false, + "range": true, + "legendFormat": "write uncorrected" + } + ] + }, + { + "type": "row", + "title": "Self-Tests", + "id": 31, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 53 + }, + "collapsed": false, + "panels": [] + }, + { + "type": "stat", + "title": "Drives Never Tested", + "description": "Drives with no self-test log entries at all. smartd only runs tests if its config includes an -s schedule; merely enabling the service does not.", + "id": 32, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 0, + "y": 54 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "count(smartctl_device_smart_status) - count(count by (device) (smart_selftest_last_lifetime_hours)) or count(smartctl_device_smart_status)", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "drives" + } + ] + }, + { + "type": "stat", + "title": "Failed Self-Tests", + "description": "", + "id": 33, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 4, + "y": 54 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 1 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "count(smart_selftest_last_passed == 0) or vector(0)", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "tests" + } + ] + }, + { + "type": "stat", + "title": "Oldest Long Test", + "description": "Powered-on hours since the least recently tested drive last completed an extended (long) self-test. Shows 'never run' when no drive has ever completed one \u2014 which is the default state, since smartd schedules no tests unless its config carries an -s directive.", + "id": 34, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 8, + "y": 54 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "yellow", + "value": 336 + }, + { + "color": "red", + "value": 1080 + } + ] + }, + "unit": "h", + "noValue": "never run" + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "textMode": "auto", + "wideLayout": true, + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max(max by (device) (smartctl_device_power_on_seconds or (smart_selftest_last_lifetime_hours * 3600)) / 3600 - on(device) group_right() smart_selftest_last_lifetime_hours{test_type=\"extended\"})", + "refId": "A", + "instant": true, + "range": false, + "legendFormat": "hours ago" + } + ] + }, + { + "type": "table", + "title": "Self-Test History", + "description": "Short and extended self-test results per drive, from collectors/smart-selftest.py. 'At Hours' is the drive's powered-on hour count when the test ran, straight from the log. 'Hours Ago' subtracts it from the drive's current powered-on hours; on SAS that figure already falls back to this log, so 0 means the newest log entry is also the highest hour count the drive has ever reported \u2014 not that the test ran just now.", + "id": 35, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 54 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false, + "filterable": true + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Last Result" + }, + "properties": [ + { + "id": "mappings", + "value": [ + { + "type": "value", + "options": { + "0": { + "text": "FAILED", + "color": "red", + "index": 0 + }, + "1": { + "text": "passed", + "color": "green", + "index": 1 + } + } + } + ] + }, + { + "id": "custom.cellOptions", + "value": { + "type": "color-background", + "mode": "basic" + } + } + ] + } + ] + }, + "options": { + "showHeader": true, + "cellHeight": "sm", + "footer": { + "show": false, + "reducer": [ + "sum" + ], + "countRows": false, + "fields": "" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "label_join(smart_selftest_last_passed, \"drive_test\", \"/\", \"device\", \"test_type\")", + "refId": "A", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (drive_test) (label_join(smart_selftest_last_lifetime_hours, \"drive_test\", \"/\", \"device\", \"test_type\"))", + "refId": "B", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (drive_test) (label_join(smart_selftest_count, \"drive_test\", \"/\", \"device\", \"test_type\"))", + "refId": "C", + "instant": true, + "range": false, + "format": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "max by (drive_test) (label_join(max by (device) (smartctl_device_power_on_seconds or (smart_selftest_last_lifetime_hours * 3600)) / 3600 - on(device) group_right() smart_selftest_last_lifetime_hours, \"drive_test\", \"/\", \"device\", \"test_type\"))", + "refId": "D", + "instant": true, + "range": false, + "format": "table" + } + ], + "transformations": [ + { + "id": "filterFieldsByName", + "options": { + "include": { + "pattern": "drive_test|device|test_type|Value.*" + } + } + }, + { + "id": "joinByField", + "options": { + "byField": "drive_test", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "drive_test": true + }, + "indexByName": { + "device": 0, + "test_type": 1, + "Value #A": 2, + "Value #B": 3, + "Value #C": 4, + "Value #D": 5 + }, + "renameByName": { + "device": "Device", + "test_type": "Test", + "Value #A": "Last Result", + "Value #B": "At Hours", + "Value #C": "Logged", + "Value #D": "Hours Ago" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": {}, + "sort": [ + { + "field": "Device", + "desc": false + } + ] + } + } + ] + }, + { + "type": "row", + "title": "Attribute Trends", + "id": 41, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 64 + }, + "collapsed": true, + "panels": [ + { + "type": "timeseries", + "title": "Reallocated Sectors (all SATA drives)", + "description": "", + "id": 36, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 65 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 2, + "fillOpacity": 0, + "showPoints": "auto", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_attribute{attribute_id=\"5\", attribute_value_type=\"raw\"}", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}}" + } + ] + }, + { + "type": "timeseries", + "title": "Pending & Uncorrectable Sectors", + "description": "", + "id": 37, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 65 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 2, + "fillOpacity": 0, + "showPoints": "auto", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_attribute{attribute_id=~\"197|198\", attribute_value_type=\"raw\"}", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}} {{attribute_name}}" + } + ] + }, + { + "type": "timeseries", + "title": "CRC Errors (cabling)", + "description": "Attribute 199 counts errors on the SATA link rather than the platters. Growth here usually means a cable or backplane, not a dying disk.", + "id": 38, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 65 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 2, + "fillOpacity": 0, + "showPoints": "auto", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_attribute{attribute_id=\"199\", attribute_value_type=\"raw\"}", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}}" + } + ] + }, + { + "type": "timeseries", + "title": "Data Written / Read (SAS)", + "description": "", + "id": 39, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 72 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 1, + "fillOpacity": 15, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes", + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_bytes_written", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}} written" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_bytes_read", + "refId": "B", + "instant": false, + "range": true, + "legendFormat": "{{device}} read" + } + ] + }, + { + "type": "timeseries", + "title": "Health Code History", + "description": "", + "id": 40, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 72 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "stepAfter", + "lineWidth": 2, + "fillOpacity": 0, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [ + { + "type": "value", + "options": { + "0": { + "text": "GOOD", + "color": "green", + "index": 0 + }, + "1": { + "text": "CAUTION", + "color": "orange", + "index": 1 + }, + "2": { + "text": "BAD", + "color": "red", + "index": 2 + } + } + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0, + "max": 2 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl:health_code", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}}" + } + ] + } + ] + }, + { + "type": "row", + "title": "Collector Health", + "id": 45, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 65 + }, + "collapsed": true, + "panels": [ + { + "type": "timeseries", + "title": "smartctl Exit Status", + "description": "Non-zero means smartctl itself had trouble reading the device. Bit 0 is a command-line problem, bit 1 a device-open failure, bit 3 a failing drive.", + "id": 42, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 66 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 1, + "fillOpacity": 15, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_device_smartctl_exit_status", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "{{device}}" + } + ] + }, + { + "type": "timeseries", + "title": "Self-Test Collector Duration", + "description": "", + "id": 43, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 66 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 1, + "fillOpacity": 15, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s", + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smart_selftest_collection_duration_seconds", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "collection" + } + ] + }, + { + "type": "timeseries", + "title": "Devices Seen", + "description": "These should agree. A divergence means one of the two cannot see some drives.", + "id": 44, + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 66 + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "drawStyle": "line", + "lineInterpolation": "linear", + "lineWidth": 1, + "fillOpacity": 15, + "showPoints": "never", + "spanNulls": true, + "axisBorderShow": false, + "axisCenteredZero": false, + "gradientMode": "none", + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "min": 0 + }, + "overrides": [] + }, + "options": { + "legend": { + "calcs": [ + "lastNotNull", + "max" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smartctl_devices", + "refId": "A", + "instant": false, + "range": true, + "legendFormat": "exporter" + }, + { + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "editorMode": "code", + "expr": "smart_selftest_devices", + "refId": "B", + "instant": false, + "range": true, + "legendFormat": "self-test collector" + } + ] + } + ] + } + ] +} |