add SMART_INTERVAL env var with background smart data fetching

agent/agent.go

@@ -84,6 +84,7 @@ func NewAgent(dataDir ...string) (agent *Agent, err error) {
 			slog.Warn("Invalid DISK_USAGE_CACHE", "err", err)
 		}
 	}
+
 	// Set up slog with a log level determined by the LOG_LEVEL env var
 	if logLevelStr, exists := GetEnv("LOG_LEVEL"); exists {
 		switch strings.ToLower(logLevelStr) {
@@ -105,6 +106,16 @@ func NewAgent(dataDir ...string) (agent *Agent, err error) {
 	// initialize system info
 	agent.refreshSystemDetails()
 
+	// SMART_INTERVAL env var to update smart data at this interval
+	if smartIntervalEnv, exists := GetEnv("SMART_INTERVAL"); exists {
+		if duration, err := time.ParseDuration(smartIntervalEnv); err == nil && duration > 0 {
+			agent.systemDetails.SmartInterval = duration
+			slog.Info("SMART_INTERVAL", "duration", duration)
+		} else {
+			slog.Warn("Invalid SMART_INTERVAL", "err", err)
+		}
+	}
+
 	// initialize connection manager
 	agent.connectionManager = newConnectionManager(agent)
 

internal/entities/system/system.go

@@ -155,16 +155,17 @@ type Info struct {
 
 // Data that does not change during process lifetime and is not needed in All Systems table
 type Details struct {
-	Hostname    string `cbor:"0,keyasint"`
-	Kernel      string `cbor:"1,keyasint,omitempty"`
-	Cores       int    `cbor:"2,keyasint"`
-	Threads     int    `cbor:"3,keyasint"`
-	CpuModel    string `cbor:"4,keyasint"`
-	Os          Os     `cbor:"5,keyasint"`
-	OsName      string `cbor:"6,keyasint"`
-	Arch        string `cbor:"7,keyasint"`
-	Podman      bool   `cbor:"8,keyasint,omitempty"`
-	MemoryTotal uint64 `cbor:"9,keyasint"`
+	Hostname      string        `cbor:"0,keyasint"`
+	Kernel        string        `cbor:"1,keyasint,omitempty"`
+	Cores         int           `cbor:"2,keyasint"`
+	Threads       int           `cbor:"3,keyasint"`
+	CpuModel      string        `cbor:"4,keyasint"`
+	Os            Os            `cbor:"5,keyasint"`
+	OsName        string        `cbor:"6,keyasint"`
+	Arch          string        `cbor:"7,keyasint"`
+	Podman        bool          `cbor:"8,keyasint,omitempty"`
+	MemoryTotal   uint64        `cbor:"9,keyasint"`
+	SmartInterval time.Duration `cbor:"10,keyasint,omitempty"`
 }
 
 // Final data structure to return to the hub

internal/hub/systems/system.go

@@ -42,8 +42,9 @@ type System struct {
 	agentVersion   semver.Version       // Agent version
 	updateTicker   *time.Ticker         // Ticker for updating the system
 	detailsFetched atomic.Bool          // True if static system details have been fetched and saved
-	smartFetched   atomic.Bool          // True if SMART devices have been fetched and saved
 	smartFetching  atomic.Bool          // True if SMART devices are currently being fetched
+	smartInterval  time.Duration        // Interval for periodic SMART data updates
+	lastSmartFetch atomic.Int64         // Unix milliseconds of last SMART data fetch
 }
 
 func (sm *SystemManager) NewSystem(systemId string) *System {
@@ -132,14 +133,20 @@ func (sys *System) update() error {
 	// create system records
 	_, err = sys.createRecords(data)
 
-	// Fetch and save SMART devices when system first comes online
-	if backgroundSmartFetchEnabled() && !sys.smartFetched.Load() && sys.smartFetching.CompareAndSwap(false, true) {
-		go func() {
-			defer sys.smartFetching.Store(false)
-			if err := sys.FetchAndSaveSmartDevices(); err == nil {
-				sys.smartFetched.Store(true)
-			}
-		}()
+	// Fetch and save SMART devices when system first comes online or at intervals
+	if backgroundSmartFetchEnabled() {
+		if sys.smartInterval <= 0 {
+			sys.smartInterval = time.Hour
+		}
+		lastFetch := sys.lastSmartFetch.Load()
+		if time.Since(time.UnixMilli(lastFetch)) >= sys.smartInterval && sys.smartFetching.CompareAndSwap(false, true) {
+			go func() {
+				defer sys.smartFetching.Store(false)
+				// Throttle retries even on failure.
+				sys.lastSmartFetch.Store(time.Now().UnixMilli())
+				_ = sys.FetchAndSaveSmartDevices()
+			}()
+		}
 	}
 
 	return err
@@ -212,6 +219,10 @@ func (sys *System) createRecords(data *system.CombinedData) (*core.Record, error
 				return err
 			}
 			sys.detailsFetched.Store(true)
+			// update smart interval if it's set on the agent side
+			if data.Details.SmartInterval > 0 {
+				sys.smartInterval = data.Details.SmartInterval
+			}
 		}
 
 		// update system record (do this last because it triggers alerts and we need above records to be inserted first)