succd: Add metrics for RP and RP operating time

Add counter metrics that count the total operating time for the roughing
pump and the diffusion pump.

succbone/succd/http.go

@@ -163,16 +163,68 @@ func (s *webServer) viewStream(w http.ResponseWriter, r *http.Request) {
 	}
 }
 
+func boolToFloat(b bool) float32 {
+	if b {
+		return 1.0
+	} else {
+		return 0.0
+	}
+}
+
 // httpMetrics serves minimalistic Prometheus-compatible metrics.
 func (s *webServer) viewMetrics(w http.ResponseWriter, r *http.Request) {
 	// TODO(q3k): also serve Go stuff using the actual Prometheus metrics client
 	// library.
 	// TODO(q3k): serve the rest of the data model
 	state := s.d.snapshot()
-	mbar := state.piraniMbar100.mbar
+
+	// sem_pressure_mbar is meant to represent the fused pressure value
+	// from all data sources once we have more vacuum sensors in the
+	// system.  sem_pirani_mbar is just the reading from the pirani gauge.
 	fmt.Fprintf(w, "# HELP sem_pressure_mbar Pressure in the SEM chamber, in millibar\n")
 	fmt.Fprintf(w, "# TYPE sem_pressure_mbar gauge\n")
-	fmt.Fprintf(w, "sem_pressure_mbar %f\n", mbar)
+	fmt.Fprintf(w, "sem_pressure_mbar %f\n", state.piraniMbar100.mbar)
+
+	fmt.Fprintf(w, "# HELP sem_pirani_mbar Pressure reading by the Pirani gauge, in millibar\n")
+	fmt.Fprintf(w, "# TYPE sem_pirani_mbar gauge\n")
+	fmt.Fprintf(w, "sem_pirani_mbar %f\n", state.piraniMbar100.mbar)
+
+	fmt.Fprintf(w, "# HELP sem_pirani_volts Voltage output from the Pirani gauge, in volts\n")
+	fmt.Fprintf(w, "# TYPE sem_pirani_volts gauge\n")
+	fmt.Fprintf(w, "sem_pirani_volts %f\n", state.piraniVolts100.avg)
+
+	fmt.Fprintf(w, "# HELP sem_pirani_failsafe_active Whether pirani gauge failsafe mode is active (boolean)\n")
+	fmt.Fprintf(w, "# TYPE sem_pirani_failsafe_active gauge\n")
+	fmt.Fprintf(w, "sem_pirani_failsafe_active %f\n", boolToFloat(state.safety.failsafe))
+
+	fmt.Fprintf(w, "# HELP sem_dp_lockout_active Whether diffusion pump lockout is active (boolean)\n")
+	fmt.Fprintf(w, "# TYPE sem_dp_lockout_active gauge\n")
+	fmt.Fprintf(w, "sem_dp_lockout_active %f\n", boolToFloat(state.safety.highPressure))
+
+	fmt.Fprintf(w, "# HELP sem_pump_diffusion_running Whether the diffusion pump is running (boolean)\n")
+	fmt.Fprintf(w, "# TYPE sem_pump_diffusion_running gauge\n")
+	fmt.Fprintf(w, "sem_pump_diffusion_running %f\n", boolToFloat(state.dpOn))
+
+	fmt.Fprintf(w, "# HELP sem_pump_roughing_running Whether the roughing pump is running (boolean)\n")
+	fmt.Fprintf(w, "# TYPE sem_pump_roughing_running gauge\n")
+	fmt.Fprintf(w, "sem_pump_roughing_running %f\n", boolToFloat(state.rpOn))
+
+	rough, high := state.vacuumStatus()
+	fmt.Fprintf(w, "# HELP sem_vacuum_rough_reached Whether a rough vacuum has been reached (boolean)\n")
+	fmt.Fprintf(w, "# TYPE sem_vacuum_rough_reached gauge\n")
+	fmt.Fprintf(w, "sem_vacuum_rough_reached %f\n", boolToFloat(rough))
+
+	fmt.Fprintf(w, "# HELP sem_vacuum_high_reached Whether a high vacuum has been reached (boolean)\n")
+	fmt.Fprintf(w, "# TYPE sem_vacuum_high_reached gauge\n")
+	fmt.Fprintf(w, "sem_vacuum_high_reached %f\n", boolToFloat(high))
+
+	fmt.Fprintf(w, "# HELP sem_rp_operating_seconds_total Operating time of the roughing pump, in seconds\n")
+	fmt.Fprintf(w, "# TYPE sem_rp_operating_seconds_total counter\n")
+	fmt.Fprintf(w, "sem_rp_operating_seconds_total %f\n", state.rpOperatingTime.Seconds())
+
+	fmt.Fprintf(w, "# HELP sem_dp_operating_seconds_total Operating time of the diffusion pump, in seconds\n")
+	fmt.Fprintf(w, "# TYPE sem_dp_operating_seconds_total counter\n")
+	fmt.Fprintf(w, "sem_dp_operating_seconds_total %f\n", state.dpOperatingTime.Seconds())
 }
 
 func (s *webServer) viewRoughingPumpEnable(w http.ResponseWriter, r *http.Request) {

succbone/succd/process.go

@@ -51,6 +51,9 @@ type daemonState struct {
 	rpOn bool
 	dpOn bool
 
+	rpOperatingTime time.Duration
+	dpOperatingTime time.Duration
+
 	vent       momentaryOutput
 	pumpdown   momentaryOutput
 	aboveRough thresholdOutput
@@ -77,11 +80,15 @@ func (d *daemon) process(ctx context.Context) {
 		select {
 		case <-ticker.C:
 			now := time.Now()
-			if elapsed := now.Sub(lastRun); !lastRun.IsZero() && elapsed > periodGrace {
-				klog.Warningf("Processing loop lag: took %s, want %s", elapsed, period)
+			var elapsed time.Duration = 0
+			if !lastRun.IsZero() {
+				elapsed = now.Sub(lastRun)
+				if elapsed > periodGrace {
+					klog.Warningf("Processing loop lag: took %s, want %s", elapsed, period)
+				}
 			}
 			lastRun = now
-			if err := d.processOnce(ctx); err != nil {
+			if err := d.processOnce(ctx, elapsed); err != nil {
 				if errors.Is(err, ctx.Err()) {
 					return
 				} else {
@@ -99,7 +106,7 @@ func (d *daemon) process(ctx context.Context) {
 }
 
 // processOnce runs the main loop step of succd.
-func (d *daemon) processOnce(_ context.Context) error {
+func (d *daemon) processOnce(_ context.Context, elapsed time.Duration) error {
 	v, err := d.adcPirani.Read()
 	if err != nil {
 		return fmt.Errorf("when reading ADC: %w", err)
@@ -190,5 +197,13 @@ func (d *daemon) processOnce(_ context.Context) error {
 		}
 	}
 
+	// Update operating time counters
+	if d.rpOn && elapsed > 0 {
+		d.rpOperatingTime += elapsed
+	}
+	if d.dpOn && elapsed > 0 {
+		d.dpOperatingTime += elapsed
+	}
+
 	return nil
 }