[management] fix offline statuses for public proxy clusters (#6133)

management/server/store/sql_store.go

@@ -8,6 +8,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"net/url"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -2794,12 +2795,27 @@ func NewSqliteStore(ctx context.Context, dataDir string, metrics telemetry.AppMe
 		connStr = filepath.Join(dataDir, filePath)
 	}
 
-	// Append query parameters: user-provided take precedence, otherwise default to cache=shared on non-Windows
-	if hasQuery {
-		connStr += "?" + query
-	} else if runtime.GOOS != "windows" {
+	// Compose query parameters. User-provided ?_busy_timeout (or its mattn alias
+	// ?_timeout) overrides our default; otherwise inject 30s so SQLite waits at
+	// most that long on a lock instead of blocking the only Go-side connection.
+	// mattn/go-sqlite3 applies PRAGMA from the DSN on every fresh connection, so
+	// the value survives ConnMaxIdleTime/ConnMaxLifetime recycling. cache=shared
+	// stays the default on non-Windows for the same reason as before.
+	parsed, _ := url.ParseQuery(query)
+	var defaults []string
+	if parsed.Get("_busy_timeout") == "" && parsed.Get("_timeout") == "" {
+		defaults = append(defaults, "_busy_timeout=30000")
+	}
+	if !hasQuery && runtime.GOOS != "windows" {
 		// To avoid `The process cannot access the file because it is being used by another process` on Windows
-		connStr += "?cache=shared"
+		defaults = append(defaults, "cache=shared")
+	}
+	parts := defaults
+	if hasQuery {
+		parts = append(parts, query)
+	}
+	if len(parts) > 0 {
+		connStr += "?" + strings.Join(parts, "&")
 	}
 
 	db, err := gorm.Open(sqlite.Open(connStr), getGormConfig())
@@ -3402,7 +3418,7 @@ func (s *SqlStore) IncrementNetworkSerial(ctx context.Context, accountId string)
 }
 
 func (s *SqlStore) ExecuteInTransaction(ctx context.Context, operation func(store Store) error) error {
-	timeoutCtx, cancel := context.WithTimeout(context.Background(), s.transactionTimeout)
+	timeoutCtx, cancel := context.WithTimeout(ctx, s.transactionTimeout)
 	defer cancel()
 
 	startTime := time.Now()

management/server/store/sql_store_test.go

@@ -4592,3 +4592,55 @@ func TestSqlStore_DeleteZoneDNSRecords(t *testing.T) {
 	require.NoError(t, err)
 	assert.Equal(t, 0, len(remainingRecords))
 }
+
+// TestNewSqliteStore_BusyTimeoutApplied opens a fresh SQLite store and verifies
+// that the _busy_timeout DSN parameter took effect at the driver level. Without
+// this, lock contention on the single SQLite connection waits indefinitely on
+// the Go side and can be hidden behind the 5-minute transactionTimeout.
+func TestNewSqliteStore_BusyTimeoutApplied(t *testing.T) {
+	dir := t.TempDir()
+	store, err := NewSqliteStore(context.Background(), dir, nil, true)
+	require.NoError(t, err)
+	t.Cleanup(func() {
+		_ = store.Close(context.Background())
+	})
+
+	sqlDB, err := store.db.DB()
+	require.NoError(t, err)
+	row := sqlDB.QueryRow("PRAGMA busy_timeout")
+	var busyTimeout int
+	require.NoError(t, row.Scan(&busyTimeout))
+	assert.Equal(t, 30000, busyTimeout, "SQLite busy_timeout must be set via DSN so it survives connection recycling")
+}
+
+// TestNewSqliteStore_BusyTimeoutRespectsUserOverride confirms that an operator
+// passing _busy_timeout or its mattn alias _timeout via NB_STORE_ENGINE_SQLITE_FILE
+// wins over our 30s default. This guards the DSN merge logic in NewSqliteStore.
+func TestNewSqliteStore_BusyTimeoutRespectsUserOverride(t *testing.T) {
+	cases := []struct {
+		name     string
+		envFile  string
+		expected int
+	}{
+		{name: "explicit _busy_timeout wins", envFile: "store.db?_busy_timeout=5000", expected: 5000},
+		{name: "alias _timeout wins", envFile: "store.db?_timeout=7000", expected: 7000},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv("NB_STORE_ENGINE_SQLITE_FILE", tc.envFile)
+			dir := t.TempDir()
+			store, err := NewSqliteStore(context.Background(), dir, nil, true)
+			require.NoError(t, err)
+			t.Cleanup(func() {
+				_ = store.Close(context.Background())
+			})
+
+			sqlDB, err := store.db.DB()
+			require.NoError(t, err)
+			row := sqlDB.QueryRow("PRAGMA busy_timeout")
+			var busyTimeout int
+			require.NoError(t, row.Scan(&busyTimeout))
+			assert.Equal(t, tc.expected, busyTimeout)
+		})
+	}
+}