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.
This commit is contained in:
2026-07-26 18:40:36 +05:00
parent 28ca67f42c
commit 3eb84aae6c
23 changed files with 1885 additions and 9 deletions
@@ -0,0 +1,156 @@
// Package shadow implements the Device Shadow pattern on top of Redis:
// desired_state (what the user wants) vs reported_state (what the device
// confirmed), plus status and last_seen for liveness tracking.
package shadow
import (
"context"
"encoding/json"
"fmt"
"strconv"
"time"
"github.com/redis/go-redis/v9"
)
// knownDevicesKey backs a lightweight device registry: health-check needs to
// know which device IDs to scan, and this service has no PostgreSQL access
// (device registration lives in Laravel), so every device we hear from gets
// added to this set.
const knownDevicesKey = "devices:known"
func desiredKey(deviceID string) string { return "device:" + deviceID + ":desired_state" }
func reportedKey(deviceID string) string { return "device:" + deviceID + ":reported_state" }
func statusKey(deviceID string) string { return "device:" + deviceID + ":status" }
func lastSeenKey(deviceID string) string { return "device:" + deviceID + ":last_seen" }
const (
StatusOnline = "online"
StatusOffline = "offline"
)
type Store struct {
rdb *redis.Client
}
func New(rdb *redis.Client) *Store {
return &Store{rdb: rdb}
}
func Connect(ctx context.Context, addr, password string, db int) (*Store, error) {
rdb := redis.NewClient(&redis.Options{Addr: addr, Password: password, DB: db})
if err := rdb.Ping(ctx).Err(); err != nil {
return nil, fmt.Errorf("ping redis: %w", err)
}
return New(rdb), nil
}
func (s *Store) Close() error {
return s.rdb.Close()
}
// PatchDesiredState merges patch into the device's desired_state JSON object.
func (s *Store) PatchDesiredState(ctx context.Context, deviceID string, patch map[string]any) error {
return s.patchJSON(ctx, desiredKey(deviceID), patch)
}
// PatchReportedState merges patch into the device's reported_state JSON object.
func (s *Store) PatchReportedState(ctx context.Context, deviceID string, patch map[string]any) error {
return s.patchJSON(ctx, reportedKey(deviceID), patch)
}
func (s *Store) patchJSON(ctx context.Context, key string, patch map[string]any) error {
existing := map[string]any{}
raw, err := s.rdb.Get(ctx, key).Result()
switch {
case err == redis.Nil:
// no existing state yet, start from an empty object
case err != nil:
return fmt.Errorf("get %s: %w", key, err)
default:
if err := json.Unmarshal([]byte(raw), &existing); err != nil {
return fmt.Errorf("unmarshal existing %s: %w", key, err)
}
}
for k, v := range patch {
existing[k] = v
}
merged, err := json.Marshal(existing)
if err != nil {
return fmt.Errorf("marshal %s: %w", key, err)
}
if err := s.rdb.Set(ctx, key, merged, 0).Err(); err != nil {
return fmt.Errorf("set %s: %w", key, err)
}
return nil
}
// Touch registers deviceID as known, bumps last_seen to now, and — if the
// device wasn't already marked online — flips status to online. It reports
// whether that online transition happened, so the caller can decide whether
// a "device back online" event is worth emitting.
func (s *Store) Touch(ctx context.Context, deviceID string) (becameOnline bool, err error) {
if err := s.rdb.SAdd(ctx, knownDevicesKey, deviceID).Err(); err != nil {
return false, fmt.Errorf("register known device %s: %w", deviceID, err)
}
if err := s.rdb.Set(ctx, lastSeenKey(deviceID), time.Now().Unix(), 0).Err(); err != nil {
return false, fmt.Errorf("set last_seen for %s: %w", deviceID, err)
}
status, err := s.rdb.Get(ctx, statusKey(deviceID)).Result()
if err != nil && err != redis.Nil {
return false, fmt.Errorf("get status for %s: %w", deviceID, err)
}
if status == StatusOnline {
return false, nil
}
if err := s.rdb.Set(ctx, statusKey(deviceID), StatusOnline, 0).Err(); err != nil {
return false, fmt.Errorf("set status online for %s: %w", deviceID, err)
}
return true, nil
}
// MarkOfflineIfStale flips deviceID to offline if it is currently online and
// its last_seen is older than timeout. It reports whether a change was made.
func (s *Store) MarkOfflineIfStale(ctx context.Context, deviceID string, timeout time.Duration) (changed bool, err error) {
status, err := s.rdb.Get(ctx, statusKey(deviceID)).Result()
if err == redis.Nil || status != StatusOnline {
return false, nil
}
if err != nil {
return false, fmt.Errorf("get status for %s: %w", deviceID, err)
}
lastSeenRaw, err := s.rdb.Get(ctx, lastSeenKey(deviceID)).Result()
if err != nil && err != redis.Nil {
return false, fmt.Errorf("get last_seen for %s: %w", deviceID, err)
}
var lastSeen time.Time
if lastSeenRaw != "" {
sec, err := strconv.ParseInt(lastSeenRaw, 10, 64)
if err != nil {
return false, fmt.Errorf("parse last_seen for %s: %w", deviceID, err)
}
lastSeen = time.Unix(sec, 0)
}
if time.Since(lastSeen) <= timeout {
return false, nil
}
if err := s.rdb.Set(ctx, statusKey(deviceID), StatusOffline, 0).Err(); err != nil {
return false, fmt.Errorf("set status offline for %s: %w", deviceID, err)
}
return true, nil
}
// KnownDevices lists every device ID this instance has ever heard from.
func (s *Store) KnownDevices(ctx context.Context) ([]string, error) {
ids, err := s.rdb.SMembers(ctx, knownDevicesKey).Result()
if err != nil {
return nil, fmt.Errorf("list known devices: %w", err)
}
return ids, nil
}
@@ -0,0 +1,119 @@
package shadow
import (
"context"
"encoding/json"
"testing"
"time"
"github.com/alicebob/miniredis/v2"
"github.com/redis/go-redis/v9"
)
func newTestStore(t *testing.T) *Store {
t.Helper()
mr := miniredis.RunT(t)
rdb := redis.NewClient(&redis.Options{Addr: mr.Addr()})
t.Cleanup(func() { rdb.Close() })
return New(rdb)
}
func TestPatchDesiredState_MergesFields(t *testing.T) {
ctx := context.Background()
s := newTestStore(t)
if err := s.PatchDesiredState(ctx, "d1", map[string]any{"power": "on"}); err != nil {
t.Fatalf("first patch: %v", err)
}
if err := s.PatchDesiredState(ctx, "d1", map[string]any{"level": 42.0}); err != nil {
t.Fatalf("second patch: %v", err)
}
raw, err := s.rdb.Get(ctx, desiredKey("d1")).Result()
if err != nil {
t.Fatalf("get: %v", err)
}
var got map[string]any
if err := json.Unmarshal([]byte(raw), &got); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if got["power"] != "on" || got["level"] != 42.0 {
t.Fatalf("got %+v, want power=on and level=42", got)
}
}
func TestTouch_FirstCallReportsOnlineTransition(t *testing.T) {
ctx := context.Background()
s := newTestStore(t)
becameOnline, err := s.Touch(ctx, "d1")
if err != nil {
t.Fatalf("touch: %v", err)
}
if !becameOnline {
t.Fatal("expected first touch to report an online transition")
}
becameOnline, err = s.Touch(ctx, "d1")
if err != nil {
t.Fatalf("second touch: %v", err)
}
if becameOnline {
t.Fatal("expected second touch (already online) to report no transition")
}
ids, err := s.KnownDevices(ctx)
if err != nil {
t.Fatalf("known devices: %v", err)
}
if len(ids) != 1 || ids[0] != "d1" {
t.Fatalf("got known devices %+v, want [d1]", ids)
}
}
func TestMarkOfflineIfStale(t *testing.T) {
ctx := context.Background()
s := newTestStore(t)
if _, err := s.Touch(ctx, "d1"); err != nil {
t.Fatalf("touch: %v", err)
}
changed, err := s.MarkOfflineIfStale(ctx, "d1", time.Hour)
if err != nil {
t.Fatalf("mark offline (not stale): %v", err)
}
if changed {
t.Fatal("device just touched should not be considered stale")
}
changed, err = s.MarkOfflineIfStale(ctx, "d1", -time.Second) // any age counts as stale
if err != nil {
t.Fatalf("mark offline (stale): %v", err)
}
if !changed {
t.Fatal("expected status to flip to offline")
}
// Already offline: a second call should report no further change.
changed, err = s.MarkOfflineIfStale(ctx, "d1", -time.Second)
if err != nil {
t.Fatalf("mark offline (already offline): %v", err)
}
if changed {
t.Fatal("expected no change once already offline")
}
}
func TestMarkOfflineIfStale_UnknownDeviceIsNoop(t *testing.T) {
ctx := context.Background()
s := newTestStore(t)
changed, err := s.MarkOfflineIfStale(ctx, "ghost", time.Second)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
if changed {
t.Fatal("unknown device should never be reported as changed")
}
}