Реализация device-control-service: gRPC + MQTT + Device Shadow в Redis

Добавлен gRPC-контракт proto/device_control (TurnOn/TurnOff/SetLevel), общий Go-модуль proto/ для переиспользования сгенерированного кода. device-control-service принимает команды по gRPC, обновляет desired_state в Redis и публикует их в MQTT; слушает devices/+/telemetry и devices/+/ack для отметки живости устройства и обновления reported_state; горутина health-check переводит устройство в offline по таймауту и публикует событие в RabbitMQ (device.status_changed) для будущего notification-service. Проверено сквозным тестом через docker compose: grpcurl TurnOn/SetLevel меняет desired_state и уходит в MQTT, mosquitto_pub с ack обновляет reported_state и статус, health-check автоматически переводит устройство в offline по истечении таймаута.
2026-07-26 18:40:36 +05:00
parent 28ca67f42c
commit 3eb84aae6c
23 changed files with 1885 additions and 9 deletions
@@ -0,0 +1,171 @@
+// Command device-control-service exposes a gRPC API for issuing device
+// commands, dispatches them over MQTT, maintains the Device Shadow in
+// Redis, and runs a health-check loop that flips stale devices offline.
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"log/slog"
+	"net"
+	"os"
+	"os/signal"
+	"strings"
+	"syscall"
+	"time"
+
+	"google.golang.org/grpc"
+
+	devicecontrol "git.cactoz.su/cacto/home_automatization/proto/device_control"
+	"git.cactoz.su/cacto/home_automatization/services/device-control-service/internal/config"
+	"git.cactoz.su/cacto/home_automatization/services/device-control-service/internal/healthcheck"
+	"git.cactoz.su/cacto/home_automatization/services/device-control-service/internal/mqttclient"
+	"git.cactoz.su/cacto/home_automatization/services/device-control-service/internal/rabbitmq"
+	"git.cactoz.su/cacto/home_automatization/services/device-control-service/internal/server"
+	"git.cactoz.su/cacto/home_automatization/services/device-control-service/internal/shadow"
+)
+
+func main() {
+	logger := slog.New(slog.NewJSONHandler(os.Stdout, nil))
+
+	if err := run(logger); err != nil {
+		logger.Error("device-control-service exited with error", "error", err)
+		os.Exit(1)
+	}
+}
+
+func run(logger *slog.Logger) error {
+	cfg, err := config.Load()
+	if err != nil {
+		return err
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	shadowStore, err := shadow.Connect(ctx, cfg.RedisAddr, cfg.RedisPassword, cfg.RedisDB)
+	cancel()
+	if err != nil {
+		return err
+	}
+	defer shadowStore.Close()
+
+	publisher, err := rabbitmq.Connect(cfg.RabbitMQURL)
+	if err != nil {
+		return err
+	}
+	defer publisher.Close()
+
+	mqttClient, err := mqttclient.Connect(mqttclient.Config{
+		BrokerURL: cfg.MQTTBrokerURL,
+		ClientID:  cfg.MQTTClientID,
+	}, logger)
+	if err != nil {
+		return err
+	}
+	defer mqttClient.Close()
+
+	if err := mqttClient.Subscribe("devices/+/telemetry", 1, telemetryHandler(shadowStore, publisher, logger)); err != nil {
+		return fmt.Errorf("subscribe telemetry: %w", err)
+	}
+	if err := mqttClient.Subscribe("devices/+/ack", 1, ackHandler(shadowStore, publisher, logger)); err != nil {
+		return fmt.Errorf("subscribe ack: %w", err)
+	}
+
+	checker := healthcheck.New(shadowStore, cfg.HealthCheckTimeout, cfg.HealthCheckInterval, func(deviceID string) {
+		pubCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+		defer cancel()
+		if err := publisher.PublishStatusChanged(pubCtx, deviceID, shadow.StatusOffline); err != nil {
+			logger.Error("publish offline event failed", "device_id", deviceID, "error", err)
+		}
+	}, logger)
+	checker.Start()
+	defer checker.Stop()
+
+	lis, err := net.Listen("tcp", fmt.Sprintf(":%d", cfg.GRPCPort))
+	if err != nil {
+		return fmt.Errorf("listen on grpc port %d: %w", cfg.GRPCPort, err)
+	}
+	grpcServer := grpc.NewServer()
+	devicecontrol.RegisterDeviceControlServer(grpcServer, server.New(shadowStore, mqttClient, logger))
+
+	go func() {
+		logger.Info("device-control-service started", "grpc_port", cfg.GRPCPort)
+		if err := grpcServer.Serve(lis); err != nil {
+			logger.Error("grpc server stopped", "error", err)
+		}
+	}()
+
+	stop := make(chan os.Signal, 1)
+	signal.Notify(stop, syscall.SIGINT, syscall.SIGTERM)
+	<-stop
+
+	logger.Info("shutting down")
+	grpcServer.GracefulStop()
+
+	return nil
+}
+
+// deviceIDFromTopic extracts {device_id} from "devices/{device_id}/<suffix>".
+func deviceIDFromTopic(topic string) (string, bool) {
+	parts := strings.Split(topic, "/")
+	if len(parts) != 3 || parts[0] != "devices" || parts[1] == "" {
+		return "", false
+	}
+	return parts[1], true
+}
+
+// telemetryHandler only tracks liveness: ingest-service owns storing and
+// interpreting telemetry, this service just needs to know the device is alive.
+func telemetryHandler(store *shadow.Store, publisher *rabbitmq.Publisher, logger *slog.Logger) mqttclient.Handler {
+	return func(topic string, _ []byte, _ time.Time) {
+		deviceID, ok := deviceIDFromTopic(topic)
+		if !ok {
+			logger.Warn("dropping telemetry from unparseable topic", "topic", topic)
+			return
+		}
+		touch(context.Background(), store, publisher, deviceID, logger)
+	}
+}
+
+type ackPayload struct {
+	State map[string]any `json:"state"`
+}
+
+func ackHandler(store *shadow.Store, publisher *rabbitmq.Publisher, logger *slog.Logger) mqttclient.Handler {
+	return func(topic string, payload []byte, _ time.Time) {
+		deviceID, ok := deviceIDFromTopic(topic)
+		if !ok {
+			logger.Warn("dropping ack from unparseable topic", "topic", topic)
+			return
+		}
+
+		var ack ackPayload
+		if err := json.Unmarshal(payload, &ack); err != nil {
+			logger.Warn("dropping invalid ack payload", "device_id", deviceID, "error", err)
+			return
+		}
+
+		ctx := context.Background()
+		if len(ack.State) > 0 {
+			if err := store.PatchReportedState(ctx, deviceID, ack.State); err != nil {
+				logger.Error("patch reported state failed", "device_id", deviceID, "error", err)
+			}
+		}
+		touch(ctx, store, publisher, deviceID, logger)
+	}
+}
+
+func touch(ctx context.Context, store *shadow.Store, publisher *rabbitmq.Publisher, deviceID string, logger *slog.Logger) {
+	becameOnline, err := store.Touch(ctx, deviceID)
+	if err != nil {
+		logger.Error("touch device failed", "device_id", deviceID, "error", err)
+		return
+	}
+	if becameOnline {
+		pubCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
+		defer cancel()
+		if err := publisher.PublishStatusChanged(pubCtx, deviceID, shadow.StatusOnline); err != nil {
+			logger.Error("publish online event failed", "device_id", deviceID, "error", err)
+		}
+	}
+}