server: a port that cannot be bound stops startup (closes #266)

The start hook now binds the listen port itself and serves on it in a
goroutine. A bind failure, such as a port already in use or a
privileged port without root, is returned to fx, which stops startup
and exits 1 with an error like "starting http server: listen tcp
:8080: bind: address already in use". Before, the bind happened inside
the goroutine and its error was only logged while the watcher kept
running without the dashboard, API or health check.

The http.Server is now built before that goroutine starts, so Shutdown
no longer reads a field another goroutine may still be writing.

TestPortInUseStopsStartup holds a port and checks that starting the
server on it fails with an error naming it.

Model: opus-5-5

README.md

@@ -423,7 +423,7 @@ following precedence (highest to lowest):
 
 | Variable                               | Description                                                                                                                           | Default               |
 | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | --------------------- |
-| `PORT`                                 | HTTP listen port                                                                                                                      | `8080`                |
+| `PORT`                                 | HTTP listen port; a port that cannot be bound, such as one already in use, stops startup                                              | `8080`                |
 | `DNSWATCHER_DEBUG`                     | Enable debug logging                                                                                                                  | `false`               |
 | `DNSWATCHER_DATA_DIR`                  | Directory for state file                                                                                                              | `/var/lib/dnswatcher` |
 | `DNSWATCHER_TARGETS`                   | Comma-separated DNS names (auto-classified via PSL)                                                                                   | `""`                  |
@@ -463,6 +463,16 @@ or empty variable (`DNSWATCHER_DNS_INTERVAL=`) means the default. If either is
 set to anything else, including a bare number or a zero or negative duration,
 dnswatcher refuses to start with an error naming the variable and the value.
 
+**`PORT` and `DNSWATCHER_TLS_EXPIRY_WARNING`** take a whole number: 1 to 65535
+for `PORT`, and a number of days, 1 or more, for
+`DNSWATCHER_TLS_EXPIRY_WARNING`. `DNSWATCHER_DEBUG`,
+`DNSWATCHER_MAINTENANCE_MODE` and `DNSWATCHER_SEND_TEST_NOTIFICATION` take
+`true` or `false`; `1`, `t`, `T`, `TRUE` and `True` also mean true, and `0`,
+`f`, `F`, `FALSE` and `False` also mean false. An unset or empty variable means
+the default. Any other value, such as `PORT=http`,
+`DNSWATCHER_TLS_EXPIRY_WARNING=7d` or `DNSWATCHER_DEBUG=yes`, makes dnswatcher
+refuse to start with an error naming the variable and the value.
+
 **`DNSWATCHER_SENTRY_DSN` reports crashes in HTTP requests to Sentry.** When it
 is set, a panic in an HTTP request handler is sent to Sentry, and the request
 still gets a `500 Internal Server Error` answer. Nothing else is sent to Sentry:

TODO.md

@@ -19,6 +19,10 @@ trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
 
 # Completed Steps
 
+- 2026-10-13: a `PORT` that cannot be bound stops startup with an error naming
+  the address, instead of running without the HTTP server (closes #266).
+- 2026-10-13: a bad `PORT`, `DNSWATCHER_TLS_EXPIRY_WARNING` or true/false
+  setting stops startup instead of being read as 0 or false (closes #269).
 - 2026-10-13: a check saving the state while the dashboard or `/api/v1/status`
   is read cannot crash the process (closes #261).
 - 2026-10-06: canonical files re-fetched from `sneak/prompts` at `dd4027b`; lint

internal/config/config.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"log/slog"
 	"slices"
+	"strconv"
 	"strings"
 	"time"
 
@@ -24,6 +25,9 @@ const (
 	defaultTLSExpiryWarning = 7
 )
 
+// maxPort is the highest TCP port number.
+const maxPort = 65535
+
 // ErrNoTargets is returned when no monitoring targets are configured.
 var ErrNoTargets = errors.New(
 	"no monitoring targets configured: set DNSWATCHER_TARGETS environment variable",
@@ -40,6 +44,23 @@ var ErrInvalidInterval = errors.New(
 // lists a name that is not in DNSWATCHER_TARGETS.
 var ErrNotInTargets = errors.New("name is not in DNSWATCHER_TARGETS")
 
+// ErrInvalidPort is returned when PORT is set but is not a whole number
+// from 1 to 65535. An empty value counts as unset and means the default.
+var ErrInvalidPort = errors.New("port must be a whole number from 1 to 65535")
+
+// ErrInvalidTLSExpiryWarning is returned when DNSWATCHER_TLS_EXPIRY_WARNING
+// is set but is not a whole number, 1 or more. An empty value counts as unset
+// and means the default.
+var ErrInvalidTLSExpiryWarning = errors.New(
+	"TLS expiry warning must be a whole number of days, 1 or more",
+)
+
+// ErrInvalidBool is returned when DNSWATCHER_DEBUG,
+// DNSWATCHER_MAINTENANCE_MODE or DNSWATCHER_SEND_TEST_NOTIFICATION is set
+// but is not a value strconv.ParseBool accepts. An empty value counts as
+// unset and means the default.
+var ErrInvalidBool = errors.New("value must be true or false")
+
 // Params contains dependencies for Config.
 type Params struct {
 	fx.In
@@ -127,16 +148,9 @@ func buildConfig(
 	log *slog.Logger,
 	params *Params,
 ) (*Config, error) {
-	err := viper.ReadInConfig()
+	err := readConfigFile(log)
 	if err != nil {
-		var notFound viper.ConfigFileNotFoundError
+		return nil, err
-		if !errors.As(err, &notFound) {
-			log.Error("config file malformed", "error", err)
-
-			return nil, fmt.Errorf(
-				"config file malformed: %w", err,
-			)
-		}
 	}
 
 	dnsInterval, err := parseInterval("DNS_INTERVAL")
@@ -161,9 +175,34 @@ func buildConfig(
 		return nil, err
 	}
 
+	port, err := parsePort()
+	if err != nil {
+		return nil, err
+	}
+
+	tlsExpiryWarning, err := parseTLSExpiryWarning()
+	if err != nil {
+		return nil, err
+	}
+
+	debug, err := parseBool("DEBUG")
+	if err != nil {
+		return nil, err
+	}
+
+	maintenanceMode, err := parseBool("MAINTENANCE_MODE")
+	if err != nil {
+		return nil, err
+	}
+
+	sendTestNotification, err := parseBool("SEND_TEST_NOTIFICATION")
+	if err != nil {
+		return nil, err
+	}
+
 	cfg := &Config{
-		Port:                    viper.GetInt("PORT"),
+		Port:                    port,
-		Debug:                   viper.GetBool("DEBUG"),
+		Debug:                   debug,
 		DataDir:                 viper.GetString("DATA_DIR"),
 		Domains:                 domains,
 		Hostnames:               hostnames,
@@ -173,12 +212,12 @@ func buildConfig(
 		NtfyTopic:               viper.GetString("NTFY_TOPIC"),
 		DNSInterval:             dnsInterval,
 		TLSInterval:             tlsInterval,
-		TLSExpiryWarning:        viper.GetInt("TLS_EXPIRY_WARNING"),
+		TLSExpiryWarning:        tlsExpiryWarning,
 		SentryDSN:               viper.GetString("SENTRY_DSN"),
-		MaintenanceMode:         viper.GetBool("MAINTENANCE_MODE"),
+		MaintenanceMode:         maintenanceMode,
 		MetricsUsername:         viper.GetString("METRICS_USERNAME"),
 		MetricsPassword:         viper.GetString("METRICS_PASSWORD"),
-		SendTestNotification:    viper.GetBool("SEND_TEST_NOTIFICATION"),
+		SendTestNotification:    sendTestNotification,
 		params:                  params,
 		log:                     log,
 	}
@@ -186,6 +225,21 @@ func buildConfig(
 	return cfg, nil
 }
 
+// readConfigFile reads the config file, if there is one.
+func readConfigFile(log *slog.Logger) error {
+	err := viper.ReadInConfig()
+	if err != nil {
+		var notFound viper.ConfigFileNotFoundError
+		if !errors.As(err, &notFound) {
+			log.Error("config file malformed", "error", err)
+
+			return fmt.Errorf("config file malformed: %w", err)
+		}
+	}
+
+	return nil
+}
+
 // parseInterval reads the DNSWATCHER_-prefixed setting key as a duration. A
 // value that does not parse, or is zero or negative, is an error naming the
 // variable and the value; an unset variable has its default from setupViper.
@@ -202,6 +256,53 @@ func parseInterval(key string) (time.Duration, error) {
 	return interval, nil
 }
 
+// parsePort reads PORT, which has no DNSWATCHER_ prefix, as a port number. A
+// value that is not a whole number from 1 to 65535 is an error naming the
+// variable and the value; an unset variable has its default from setupViper.
+func parsePort() (int, error) {
+	value := viper.GetString("PORT")
+
+	port, err := strconv.Atoi(value)
+	if err != nil || port < 1 || port > maxPort {
+		return 0, fmt.Errorf("invalid PORT %q: %w", value, ErrInvalidPort)
+	}
+
+	return port, nil
+}
+
+// parseTLSExpiryWarning reads DNSWATCHER_TLS_EXPIRY_WARNING as a number of
+// days. A value that is not a whole number, 1 or more, is an error naming the
+// variable and the value; an unset variable has its default from setupViper.
+func parseTLSExpiryWarning() (int, error) {
+	value := viper.GetString("TLS_EXPIRY_WARNING")
+
+	days, err := strconv.Atoi(value)
+	if err != nil || days < 1 {
+		return 0, fmt.Errorf(
+			"invalid DNSWATCHER_TLS_EXPIRY_WARNING %q: %w",
+			value, ErrInvalidTLSExpiryWarning,
+		)
+	}
+
+	return days, nil
+}
+
+// parseBool reads the DNSWATCHER_-prefixed setting key as true or false. A
+// value strconv.ParseBool does not accept is an error naming the variable and
+// the value; an unset variable has its default from setupViper.
+func parseBool(key string) (bool, error) {
+	value := viper.GetString(key)
+
+	result, err := strconv.ParseBool(value)
+	if err != nil {
+		return false, fmt.Errorf(
+			"invalid DNSWATCHER_%s %q: %w", key, value, ErrInvalidBool,
+		)
+	}
+
+	return result, nil
+}
+
 func parseAndValidateTargets() ([]string, []string, error) {
 	domains, hostnames, err := ClassifyTargets(
 		parseCSV(viper.GetString("TARGETS")),

internal/config/config_test.go

@@ -116,7 +116,7 @@ func TestNew_OnlyEmptyCSVSegments(t *testing.T) {
 }
 
 // TestNew_InvalidIntervalStopsStartup checks values that must stop startup;
-// TestNew_DefaultValues and TestNew_EmptyIntervalMeansDefault check that an
+// TestNew_DefaultValues and TestNew_EmptyValueMeansDefault check that an
 // unset or empty interval means the default.
 func TestNew_InvalidIntervalStopsStartup(t *testing.T) {
 	variables := []string{"DNSWATCHER_DNS_INTERVAL", "DNSWATCHER_TLS_INTERVAL"}
@@ -144,16 +144,107 @@ func TestNew_InvalidIntervalStopsStartup(t *testing.T) {
 	}
 }
 
-func TestNew_EmptyIntervalMeansDefault(t *testing.T) {
+func TestNew_EmptyValueMeansDefault(t *testing.T) {
 	viper.Reset()
 	t.Setenv("DNSWATCHER_TARGETS", "example.com")
 	t.Setenv("DNSWATCHER_DNS_INTERVAL", "")
 	t.Setenv("DNSWATCHER_TLS_INTERVAL", "")
+	t.Setenv("PORT", "")
+	t.Setenv("DNSWATCHER_TLS_EXPIRY_WARNING", "")
+	t.Setenv("DNSWATCHER_DEBUG", "")
+	t.Setenv("DNSWATCHER_MAINTENANCE_MODE", "")
+	t.Setenv("DNSWATCHER_SEND_TEST_NOTIFICATION", "")
 
 	cfg, err := config.New(nil, newTestParams(t))
 	require.NoError(t, err)
 	assert.Equal(t, time.Hour, cfg.DNSInterval)
 	assert.Equal(t, 12*time.Hour, cfg.TLSInterval)
+	assert.Equal(t, 8080, cfg.Port)
+	assert.Equal(t, 7, cfg.TLSExpiryWarning)
+	assert.False(t, cfg.Debug)
+	assert.False(t, cfg.MaintenanceMode)
+	assert.False(t, cfg.SendTestNotification)
+}
+
+// TestNew_InvalidNumberOrBoolStopsStartup checks values that must stop
+// startup; TestNew_EnvironmentOverrides, the two tests after this one and
+// TestNew_EmptyValueMeansDefault check values that must not.
+func TestNew_InvalidNumberOrBoolStopsStartup(t *testing.T) {
+	notBools := []string{"yes", "on", "2", "tRUE"}
+	tests := []struct {
+		variable string
+		values   []string
+		want     error
+	}{
+		{
+			variable: "PORT",
+			values:   []string{"notaport", "0", "-1", "65536", "8080.5"},
+			want:     config.ErrInvalidPort,
+		},
+		{
+			variable: "DNSWATCHER_TLS_EXPIRY_WARNING",
+			values:   []string{"abc", "7d", "0", "-5"},
+			want:     config.ErrInvalidTLSExpiryWarning,
+		},
+		{
+			variable: "DNSWATCHER_DEBUG",
+			values:   notBools,
+			want:     config.ErrInvalidBool,
+		},
+		{
+			variable: "DNSWATCHER_MAINTENANCE_MODE",
+			values:   notBools,
+			want:     config.ErrInvalidBool,
+		},
+		{
+			variable: "DNSWATCHER_SEND_TEST_NOTIFICATION",
+			values:   notBools,
+			want:     config.ErrInvalidBool,
+		},
+	}
+
+	for _, tt := range tests {
+		for _, value := range tt.values {
+			t.Run(tt.variable+"="+value, func(t *testing.T) {
+				viper.Reset()
+				t.Setenv("DNSWATCHER_TARGETS", "example.com")
+				t.Setenv(tt.variable, value)
+
+				_, err := config.New(nil, newTestParams(t))
+				require.ErrorIs(t, err, tt.want)
+				require.ErrorContains(t, err, tt.variable)
+				require.ErrorContains(t, err, strconv.Quote(value))
+			})
+		}
+	}
+}
+
+func TestNew_LowestNumbersAndOtherSpellingsOfTrue(t *testing.T) {
+	viper.Reset()
+	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+	t.Setenv("PORT", "1")
+	t.Setenv("DNSWATCHER_TLS_EXPIRY_WARNING", "1")
+	t.Setenv("DNSWATCHER_DEBUG", "1")
+	t.Setenv("DNSWATCHER_MAINTENANCE_MODE", "T")
+	t.Setenv("DNSWATCHER_SEND_TEST_NOTIFICATION", "True")
+
+	cfg, err := config.New(nil, newTestParams(t))
+	require.NoError(t, err)
+	assert.Equal(t, 1, cfg.Port)
+	assert.Equal(t, 1, cfg.TLSExpiryWarning)
+	assert.True(t, cfg.Debug)
+	assert.True(t, cfg.MaintenanceMode)
+	assert.True(t, cfg.SendTestNotification)
+}
+
+func TestNew_HighestPort(t *testing.T) {
+	viper.Reset()
+	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+	t.Setenv("PORT", "65535")
+
+	cfg, err := config.New(nil, newTestParams(t))
+	require.NoError(t, err)
+	assert.Equal(t, 65535, cfg.Port)
 }
 
 func TestNew_DebugEnablesDebugLogging(t *testing.T) {

internal/server/export_test.go

@@ -13,8 +13,8 @@ import (
 const RequestTimeout time.Duration = requestTimeout
 
 // SetListenPort overrides the port Run binds. A test uses it to hand
-// Run an unbindable port so ListenAndServe fails immediately and Run
+// Run an unbindable port, so that Run stores its http.Server and then
-// returns after storing its http.Server.
+// returns an error without listening.
 func SetListenPort(s *Server, port int) {
 	s.port = port
 }

internal/server/server.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"log/slog"
+	"net"
 	"net/http"
 	"time"
 
@@ -112,7 +113,7 @@ func New(
 	}
 
 	lifecycle.Append(fx.Hook{
-		OnStart: func(_ context.Context) error {
+		OnStart: func(ctx context.Context) error {
 			srv.startupTime = time.Now()
 
 			err := srv.enableSentry()
@@ -120,9 +121,7 @@ func New(
 				return err
 			}
 
-			go srv.Run()
+			return srv.Run(ctx)
-
-			return nil
 		},
 		OnStop: func(ctx context.Context) error {
 			return srv.Shutdown(ctx)
@@ -149,8 +148,10 @@ func newHTTPServer(
 	}
 }
 
-// Run starts the HTTP server.
+// Run binds the listen port, then serves HTTP on it in a new goroutine
-func (s *Server) Run() {
+// and returns. A port that cannot be bound is returned as an error, so
+// that startup stops instead of running without the HTTP server.
+func (s *Server) Run(ctx context.Context) error {
 	s.SetupRoutes()
 
 	listenAddr := fmt.Sprintf(":%d", s.port)
@@ -158,10 +159,21 @@ func (s *Server) Run() {
 
 	s.log.Info("http server starting", "addr", listenAddr)
 
-	err := s.httpServer.ListenAndServe()
+	lc := &net.ListenConfig{}
-	if err != nil && !errors.Is(err, http.ErrServerClosed) {
+
-		s.log.Error("http server error", "error", err)
+	listener, err := lc.Listen(ctx, "tcp", listenAddr)
+	if err != nil {
+		return fmt.Errorf("starting http server: %w", err)
 	}
+
+	go func() {
+		err := s.httpServer.Serve(listener)
+		if err != nil && !errors.Is(err, http.ErrServerClosed) {
+			s.log.Error("http server error", "error", err)
+		}
+	}()
+
+	return nil
 }
 
 // Shutdown gracefully shuts down the server, then sends the error

internal/server/server_test.go

@@ -1,6 +1,8 @@
 package server_test
 
 import (
+	"net"
+	"strings"
 	"testing"
 
 	"github.com/spf13/viper"
@@ -58,15 +60,13 @@ func buildServer(t *testing.T) *server.Server {
 }
 
 // TestRunWiresSocketTimeouts pins that the http.Server the running
-// server actually serves — the one Run builds and hands to
+// server actually serves — the one Run builds and serves on the port
-// ListenAndServe — carries every socket-level timeout, plus the two
+// it binds — carries every socket-level timeout, plus the two
 // relationships the values must satisfy.
 //
-// Run is driven to completion with an unbindable port: it builds and
+// Run is given an unbindable port: it builds and stores s.httpServer,
-// stores s.httpServer, then ListenAndServe fails at once and Run
+// then the bind fails and Run returns the error without ever
-// returns without ever listening. The assertions run in the same
+// listening. Nothing here measures elapsed time.
-// goroutine after Run returns, so reading s.httpServer is free of any
-// data race. Nothing here measures elapsed time.
 //
 // ReadTimeout must be at least ReadHeaderTimeout. net/http reads the
 // headers under ReadHeaderTimeout, then sets the read deadline for the
@@ -84,7 +84,10 @@ func TestRunWiresSocketTimeouts(t *testing.T) {
 	srv := buildServer(t)
 	server.SetListenPort(srv, -1)
 
-	srv.Run()
+	err := srv.Run(t.Context())
+	if err == nil {
+		t.Fatal("Run bound port -1")
+	}
 
 	hs := server.HTTPServerOf(srv)
 	if hs == nil {
@@ -133,3 +136,38 @@ func TestRunWiresSocketTimeouts(t *testing.T) {
 		)
 	}
 }
+
+func TestPortInUseStopsStartup(t *testing.T) {
+	// Bound on every address, as Run binds, so that Run's bind fails.
+	lc := &net.ListenConfig{}
+
+	taken, err := lc.Listen(t.Context(), "tcp", ":0")
+	if err != nil {
+		t.Fatalf("binding a port for the test: %v", err)
+	}
+
+	defer func() { _ = taken.Close() }()
+
+	_, port, err := net.SplitHostPort(taken.Addr().String())
+	if err != nil {
+		t.Fatalf("reading the bound port: %v", err)
+	}
+
+	viper.Reset()
+	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+	t.Setenv("DNSWATCHER_DATA_DIR", t.TempDir())
+	t.Setenv("PORT", port)
+
+	app := newServerApp(fx.Invoke(func(*server.Server) {}))
+
+	err = app.Start(t.Context())
+	if err == nil {
+		_ = app.Stop(t.Context())
+
+		t.Fatal("startup succeeded on a port that is already bound")
+	}
+
+	if !strings.Contains(err.Error(), ":"+port) {
+		t.Errorf("startup error does not name port %s: %v", port, err)
+	}
+}