fix: AlertWriter graceful flush (#15) + Rolling-Update Robustheit (#19) — v1.2.95

#15 waf/alerts.go: AlertWriter.Close() flusht gepufferte Alerts + stoppt die Goroutine (stop/done-Channels, sync.Once, atomic closed; Kanal wird NIE geschlossen → Send racet ohne Panic). Wiring in cmd/edgeguard-waf nach ListenAndServe (graceful shutdown). -race-Test alerts_test.go.
#19 handlers/cluster_rollingupdate.go: (a) RollingUpdateStatus mutiert State nicht mehr beim GET — terminale Zustände altern in readRollingUpdateState nach 10 min aus (kein verlorenes 'done' bei parallelen Pollern). (b) State-File via sync.Mutex + configgen.AtomicWrite (kein partieller Read / Race zwischen Handler & Goroutine). (c) Version-Flip wird gegen die VORHER erfasste Secondary-Baseline geprüft statt gegen die Primary-Version (verhindert sofort-/nie-Flip).
Bewusst belassen: geteilter upgrade.sh-Pfad ist deterministischer Inhalt + an exakte sudoers-Zeile gebunden → Überschreib-Race benign; MST-Timestamp-Parse locale (Server laufen C-Locale).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

internal/waf/alerts.go

@@ -3,6 +3,8 @@ package waf
 import (
 	"context"
 	"log/slog"
+	"sync"
+	"sync/atomic"
 	"time"
 
 	"github.com/jackc/pgx/v5/pgxpool"
@@ -26,8 +28,12 @@ type Alert struct {
 // AlertWriter accepts Alert values via a buffered channel and writes
 // them to PostgreSQL asynchronously so SPOE handling stays low-latency.
 type AlertWriter struct {
-	pool   *pgxpool.Pool
-	ch     chan Alert
+	pool      *pgxpool.Pool
+	ch        chan Alert
+	stop      chan struct{}
+	done      chan struct{}
+	closeOnce sync.Once
+	closed    atomic.Bool
 }
 
 // NewAlertWriter creates an AlertWriter and starts its background goroutine.
@@ -36,14 +42,19 @@ func NewAlertWriter(pool *pgxpool.Pool, bufSize int) *AlertWriter {
 	aw := &AlertWriter{
 		pool: pool,
 		ch:   make(chan Alert, bufSize),
+		stop: make(chan struct{}),
+		done: make(chan struct{}),
 	}
 	go aw.run()
 	return aw
 }
 
-// Send enqueues an alert. Drops silently if the channel is full to
-// avoid slowing down SPOE request handling.
+// Send enqueues an alert. Drops silently if the channel is full (or the
+// writer is closing) to avoid slowing down / panicking SPOE handling.
 func (aw *AlertWriter) Send(a Alert) {
+	if aw.closed.Load() {
+		return
+	}
 	select {
 	case aw.ch <- a:
 	default:
@@ -51,9 +62,34 @@ func (aw *AlertWriter) Send(a Alert) {
 	}
 }
 
+// Close stops the writer and flushes buffered alerts (best-effort).
+// Safe to call multiple times. The channel is never closed → Send never
+// panics even if it races with Close.
+func (aw *AlertWriter) Close() {
+	aw.closeOnce.Do(func() {
+		aw.closed.Store(true)
+		close(aw.stop)
+	})
+	<-aw.done
+}
+
 func (aw *AlertWriter) run() {
-	for a := range aw.ch {
-		aw.write(a)
+	defer close(aw.done)
+	for {
+		select {
+		case a := <-aw.ch:
+			aw.write(a)
+		case <-aw.stop:
+			// Restliche gepufferte Alerts noch wegschreiben, dann Ende.
+			for {
+				select {
+				case a := <-aw.ch:
+					aw.write(a)
+				default:
+					return
+				}
+			}
+		}
 	}
 }
 

internal/waf/alerts_test.go

@@ -0,0 +1,61 @@
+package waf
+
+import (
+	"context"
+	"os"
+	"sync"
+	"testing"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+)
+
+// Beweist Fix #15: AlertWriter.Close() flusht, ist idempotent, und Send/Close
+// racen ohne Panic (Kanal wird nie geschlossen). Guarded per EG_FWTEST_DSN.
+func TestAlertWriter_CloseFlush(t *testing.T) {
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the alert-writer test")
+	}
+	ctx := context.Background()
+	var mErr error
+	for i := 0; i < 3; i++ {
+		if mErr = database.Migrate(ctx, dsn); mErr == nil {
+			break
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	if mErr != nil {
+		t.Fatalf("migrate: %v", mErr)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	defer pool.Close()
+
+	aw := NewAlertWriter(pool, 64)
+	for i := 0; i < 20; i++ {
+		aw.Send(Alert{Hostname: "t.local", ClientIP: "203.0.113.1", Method: "GET", URI: "/", Action: "detected"})
+	}
+
+	// Send parallel zu Close → darf nicht paniken.
+	var wg sync.WaitGroup
+	for i := 0; i < 10; i++ {
+		wg.Add(1)
+		go func() { defer wg.Done(); aw.Send(Alert{Hostname: "t.local", Action: "detected"}) }()
+	}
+
+	done := make(chan struct{})
+	go func() { aw.Close(); close(done) }()
+	select {
+	case <-done:
+	case <-time.After(10 * time.Second):
+		t.Fatal("Close() did not return (flush hung)")
+	}
+	wg.Wait()
+
+	// Idempotent + Send nach Close ist No-op (kein Panic).
+	aw.Close()
+	aw.Send(Alert{Hostname: "after.local", Action: "detected"})
+}