Stage 12: observability & performance (OTel/OTLP, domain metrics, guest GC)
- pkg/telemetry: shared OTel provider bootstrap (none/stdout/otlp + W3C
propagators + Go runtime metrics); backend/internal/telemetry becomes a thin
facade keeping its gin middleware.
- Telemetry parity: gateway and the Telegram connector gain telemetry runtimes
and config (GATEWAY_/TELEGRAM_ SERVICE_NAME + OTEL_*); otelgrpc instruments the
backend push server, the gateway's backend+connector clients and the connector
server. Default exporter stays none (collector/dashboards are Stage 14).
- Operational metrics (variant attribute on game-scoped ones): game_replay_duration,
game_move_validate_duration, games_started_total, games_abandoned_total,
game_cache_active, chat_messages_total{kind}, gateway edge_request_duration.
Wired via the SetMetrics setter pattern (default no-op meter).
- TODO-3: account.GuestReaper deletes guests with no game seat past
BACKEND_GUEST_RETENTION (default 30d, swept every BACKEND_GUEST_REAP_INTERVAL).
- Tests: pkg/telemetry exporter selection; game/social/edge metric recording via
a manual reader; config (otlp accepted, guest knobs); inttest guest reaper.
- Docs: PLAN.md re-scopes Stage 12 and adds Stage 13 (alphabet-on-wire) + Stage 14
(CI/deploy) with the agreed dictionary-versioning resolution; ARCHITECTURE 11/13,
TESTING, the three READMEs and FUNCTIONAL(+ru) updated.
This commit is contained in:
@@ -80,6 +80,9 @@ func run(ctx context.Context, cfg config.Config, logger *zap.Logger) error {
|
||||
logger.Warn("telemetry shutdown", zap.Error(err))
|
||||
}
|
||||
}()
|
||||
if err := tel.StartRuntimeMetrics(); err != nil {
|
||||
logger.Warn("telemetry: start runtime metrics", zap.Error(err))
|
||||
}
|
||||
|
||||
db, err := postgres.Open(ctx, cfg.Postgres,
|
||||
postgres.WithTracerProvider(tel.TracerProvider()),
|
||||
@@ -131,10 +134,19 @@ func run(ctx context.Context, cfg config.Config, logger *zap.Logger) error {
|
||||
accounts := account.NewStore(db)
|
||||
games := game.NewService(game.NewStore(db), accounts, registry, cfg.Game, logger)
|
||||
games.SetNotifier(hub)
|
||||
games.SetMetrics(tel.MeterProvider().Meter("scrabble/backend/game"))
|
||||
go games.RunSweeper(ctx, cfg.Game.TimeoutSweepInterval)
|
||||
logger.Info("game turn-timeout sweeper started",
|
||||
zap.Duration("interval", cfg.Game.TimeoutSweepInterval))
|
||||
|
||||
// Stage 12 TODO-3: reap abandoned guest accounts (no game seat, account age past
|
||||
// the retention window). Dependent rows fall away via ON DELETE CASCADE.
|
||||
guestReaper := account.NewGuestReaper(accounts, cfg.GuestRetention, logger)
|
||||
go guestReaper.Run(ctx, cfg.GuestReapInterval)
|
||||
logger.Info("guest reaper started",
|
||||
zap.Duration("interval", cfg.GuestReapInterval),
|
||||
zap.Duration("retention", cfg.GuestRetention))
|
||||
|
||||
// Stage 4 lobby & social domains. Their REST and stream surface is added with
|
||||
// the gateway in Stage 6, so they are handed to the server (like the route
|
||||
// groups) for the handlers to come.
|
||||
@@ -145,6 +157,7 @@ func run(ctx context.Context, cfg config.Config, logger *zap.Logger) error {
|
||||
links := link.NewService(emails, accounts, accountmerge.NewMerger(db), sessions)
|
||||
socialSvc := social.NewService(social.NewStore(db), accounts, games)
|
||||
socialSvc.SetNotifier(hub)
|
||||
socialSvc.SetMetrics(tel.MeterProvider().Meter("scrabble/backend/social"))
|
||||
|
||||
// Stage 5 robot opponent: provision its durable account pool (a hard startup
|
||||
// dependency, like the dictionaries) and start its move driver. The matchmaker
|
||||
|
||||
Reference in New Issue
Block a user