[Agent] feat: parse ATA device statistics for temperature and future metrics (#1689)

* feat: add ATA Device Statistics parsing and fall back for SMART temp reading

* simplify ata device statistics structs and fix smartctl args tests

* simplify ata device statistics lookup to use page number only

---------

Co-authored-by: henrygd <hank@henrygd.me>

agent/smart.go

@@ -515,10 +515,12 @@ func (sm *SmartManager) CollectSmart(deviceInfo *DeviceInfo) error {
 // smartctlArgs returns the arguments for the smartctl command
 // based on the device type and whether to include standby mode
 func (sm *SmartManager) smartctlArgs(deviceInfo *DeviceInfo, includeStandby bool) []string {
-	args := make([]string, 0, 7)
+	args := make([]string, 0, 9)
+	var deviceType, parserType string
 
 	if deviceInfo != nil {
-		deviceType := strings.ToLower(deviceInfo.Type)
+		deviceType = strings.ToLower(deviceInfo.Type)
+		parserType = strings.ToLower(deviceInfo.parserType)
 		// types sometimes misidentified in scan; see github.com/henrygd/beszel/issues/1345
 		if deviceType != "" && deviceType != "scsi" && deviceType != "ata" {
 			args = append(args, "-d", deviceInfo.Type)
@@ -526,6 +528,13 @@ func (sm *SmartManager) smartctlArgs(deviceInfo *DeviceInfo, includeStandby bool
 	}
 
 	args = append(args, "-a", "--json=c")
+	effectiveType := parserType
+	if effectiveType == "" {
+		effectiveType = deviceType
+	}
+	if effectiveType == "sat" || effectiveType == "ata" {
+		args = append(args, "-l", "devstat")
+	}
 
 	if includeStandby {
 		args = append(args, "-n", "standby")
@@ -829,6 +838,11 @@ func (sm *SmartManager) parseSmartForSata(output []byte) (bool, int) {
 	smartData.FirmwareVersion = data.FirmwareVersion
 	smartData.Capacity = data.UserCapacity.Bytes
 	smartData.Temperature = data.Temperature.Current
+	if smartData.Temperature == 0 {
+		if temp, ok := temperatureFromAtaDeviceStatistics(data.AtaDeviceStatistics); ok {
+			smartData.Temperature = temp
+		}
+	}
 	smartData.SmartStatus = getSmartStatus(smartData.Temperature, data.SmartStatus.Passed)
 	smartData.DiskName = data.Device.Name
 	smartData.DiskType = data.Device.Type
@@ -867,6 +881,36 @@ func getSmartStatus(temperature uint8, passed bool) string {
 	}
 }
 
+func temperatureFromAtaDeviceStatistics(stats smart.AtaDeviceStatistics) (uint8, bool) {
+	entry := findAtaDeviceStatisticsEntry(stats, 5, "Current Temperature")
+	if entry == nil || entry.Value == nil {
+		return 0, false
+	}
+	if *entry.Value > 255 {
+		return 0, false
+	}
+	return uint8(*entry.Value), true
+}
+
+// findAtaDeviceStatisticsEntry centralizes ATA devstat lookups so additional
+// metrics can be pulled from the same structure in the future.
+func findAtaDeviceStatisticsEntry(stats smart.AtaDeviceStatistics, pageNumber uint8, entryName string) *smart.AtaDeviceStatisticsEntry {
+	for pageIdx := range stats.Pages {
+		page := &stats.Pages[pageIdx]
+		if page.Number != pageNumber {
+			continue
+		}
+		for entryIdx := range page.Table {
+			entry := &page.Table[entryIdx]
+			if !strings.EqualFold(entry.Name, entryName) {
+				continue
+			}
+			return entry
+		}
+	}
+	return nil
+}
+
 func (sm *SmartManager) parseSmartForScsi(output []byte) (bool, int) {
 	var data smart.SmartInfoForScsi
 

agent/smart_test.go

@@ -89,6 +89,39 @@ func TestParseSmartForSata(t *testing.T) {
 	}
 }
 
+func TestParseSmartForSataDeviceStatisticsTemperature(t *testing.T) {
+	jsonPayload := []byte(`{
+		"smartctl": {"exit_status": 0},
+		"device": {"name": "/dev/sdb", "type": "sat"},
+		"model_name": "SanDisk SSD U110 16GB",
+		"serial_number": "DEVSTAT123",
+		"firmware_version": "U21B001",
+		"user_capacity": {"bytes": 16013942784},
+		"smart_status": {"passed": true},
+		"ata_smart_attributes": {"table": []},
+		"ata_device_statistics": {
+			"pages": [
+				{
+					"number": 5,
+					"name": "Temperature Statistics",
+					"table": [
+						{"name": "Current Temperature", "value": 22, "flags": {"valid": true}}
+					]
+				}
+			]
+		}
+	}`)
+
+	sm := &SmartManager{SmartDataMap: make(map[string]*smart.SmartData)}
+	hasData, exitStatus := sm.parseSmartForSata(jsonPayload)
+	require.True(t, hasData)
+	assert.Equal(t, 0, exitStatus)
+
+	deviceData, ok := sm.SmartDataMap["DEVSTAT123"]
+	require.True(t, ok, "expected smart data entry for serial DEVSTAT123")
+	assert.Equal(t, uint8(22), deviceData.Temperature)
+}
+
 func TestParseSmartForSataParentheticalRawValue(t *testing.T) {
 	jsonPayload := []byte(`{
 		"smartctl": {"exit_status": 0},
@@ -267,15 +300,21 @@ func TestSmartctlArgs(t *testing.T) {
 
 	sataDevice := &DeviceInfo{Name: "/dev/sda", Type: "sat"}
 	assert.Equal(t,
-		[]string{"-d", "sat", "-a", "--json=c", "-n", "standby", "/dev/sda"},
+		[]string{"-d", "sat", "-a", "--json=c", "-l", "devstat", "-n", "standby", "/dev/sda"},
 		sm.smartctlArgs(sataDevice, true),
 	)
 
 	assert.Equal(t,
-		[]string{"-d", "sat", "-a", "--json=c", "/dev/sda"},
+		[]string{"-d", "sat", "-a", "--json=c", "-l", "devstat", "/dev/sda"},
 		sm.smartctlArgs(sataDevice, false),
 	)
 
+	nvmeDevice := &DeviceInfo{Name: "/dev/nvme0", Type: "nvme"}
+	assert.Equal(t,
+		[]string{"-d", "nvme", "-a", "--json=c", "-n", "standby", "/dev/nvme0"},
+		sm.smartctlArgs(nvmeDevice, true),
+	)
+
 	assert.Equal(t,
 		[]string{"-a", "--json=c", "-n", "standby"},
 		sm.smartctlArgs(nil, true),
@@ -516,18 +555,18 @@ func TestUpdateSmartDevicesPreservesRAIDDrives(t *testing.T) {
 		},
 		SmartDataMap: map[string]*smart.SmartData{
 			"serial-0": {
-				DiskName: "/dev/sda",
+				DiskName:     "/dev/sda",
-				DiskType: "megaraid,0",
+				DiskType:     "megaraid,0",
 				SerialNumber: "serial-0",
 			},
 			"serial-1": {
-				DiskName: "/dev/sda",
+				DiskName:     "/dev/sda",
-				DiskType: "megaraid,1",
+				DiskType:     "megaraid,1",
 				SerialNumber: "serial-1",
 			},
 			"serial-stale": {
-				DiskName: "/dev/sda",
+				DiskName:     "/dev/sda",
-				DiskType: "megaraid,2",
+				DiskType:     "megaraid,2",
 				SerialNumber: "serial-stale",
 			},
 		},

internal/entities/smart/smart.go

@@ -130,10 +130,23 @@ type SummaryInfo struct {
 }
 
 type AtaSmartAttributes struct {
-	// Revision int                 `json:"revision"`
 	Table []AtaSmartAttribute `json:"table"`
 }
 
+type AtaDeviceStatistics struct {
+	Pages []AtaDeviceStatisticsPage `json:"pages"`
+}
+
+type AtaDeviceStatisticsPage struct {
+	Number uint8                      `json:"number"`
+	Table  []AtaDeviceStatisticsEntry `json:"table"`
+}
+
+type AtaDeviceStatisticsEntry struct {
+	Name  string  `json:"name"`
+	Value *uint64 `json:"value,omitempty"`
+}
+
 type AtaSmartAttribute struct {
 	ID         uint16 `json:"id"`
 	Name       string `json:"name"`
@@ -343,7 +356,8 @@ type SmartInfoForSata struct {
 	SmartStatus SmartStatusInfo `json:"smart_status"`
 	// AtaSmartData                 AtaSmartData                 `json:"ata_smart_data"`
 	// AtaSctCapabilities           AtaSctCapabilities           `json:"ata_sct_capabilities"`
-	AtaSmartAttributes AtaSmartAttributes `json:"ata_smart_attributes"`
+	AtaSmartAttributes  AtaSmartAttributes  `json:"ata_smart_attributes"`
+	AtaDeviceStatistics AtaDeviceStatistics `json:"ata_device_statistics"`
 	// PowerOnTime                  PowerOnTimeInfo              `json:"power_on_time"`
 	// PowerCycleCount              uint16                       `json:"power_cycle_count"`
 	Temperature TemperatureInfo `json:"temperature"`