Instance name on process log lines and every metric (closes #91)

Process log lines carry instance, as request lines do; the instance name
is read before the other settings, so the line saying a setting is
invalid carries it too. Every metric, Go's and the process's included,
carries the label instance, set once on the registry. README.md says so,
and that Prometheus keeps it as exported_instance unless the scrape sets
honor_labels. An instance name that is not valid UTF-8 stops the start,
as the metrics library panics on such a label.

Tests that read metrics expect the label; one helper replaces the alert
tests' loops that wait for them.

Judgement call: the label is named instance, as in the log lines and
alerts, although Prometheus gives each target a label of that name.

Model: opus-5-5

internal/config/config.go

@@ -34,9 +34,10 @@ type Config struct {
 	ListenAddr string
 	// UpstreamURL is the app (SWWAF_UPSTREAM_URL).
 	UpstreamURL *url.URL
-	// InstanceName is the name each request log line gives as instance
-	// (SWWAF_INSTANCE_NAME), by default the host's name, which docker sets
-	// to the first 12 characters of the container's id.
+	// InstanceName is the name every log line and alert gives as instance,
+	// and every metric carries as its label instance (SWWAF_INSTANCE_NAME),
+	// by default the host's name, which docker sets to the first 12
+	// characters of the container's id.
 	InstanceName string
 	// Observe is true in observe mode, when SWWAF_MODE is observe rather
 	// than enforce: a request that SWWAF_DENY_NETS, a ban, the country
@@ -267,6 +268,7 @@ var (
 		"is not ban, permanent_ban, waf_block, anomaly, reputation_hit, " +
 			"source_failure or file_error")
 	errNotNumberOrOff = errors.New("is not a whole number above zero, such as 60, or off")
+	errNotUTF8        = errors.New("is not valid UTF-8")
 )
 
 // FromEnvironment reads the settings with lookupEnv, normally
@@ -276,11 +278,10 @@ var (
 // setting that is set but invalid is an error that names it.
 func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 	env := &environment{lookupEnv: lookupEnv}
-	hostname, _ := os.Hostname() // "" when the host has no name to give
 	cfg := &Config{
 		ListenAddr:           env.address("SWWAF_LISTEN_ADDR", defaultListenAddr),
 		UpstreamURL:          env.appURL("SWWAF_UPSTREAM_URL", defaultUpstreamURL),
-		InstanceName:         env.value("SWWAF_INSTANCE_NAME", hostname),
+		InstanceName:         env.instanceName(),
 		Observe:              env.observe("SWWAF_MODE", "enforce"),
 		TrustedProxies:       env.netblocks("SWWAF_TRUSTED_PROXIES", privateRanges),
 		ClientRequestTimeout: env.duration("SWWAF_CLIENT_REQUEST_TIMEOUT", "60s"),
@@ -373,6 +374,16 @@ func ListenAddrAndUpstreamURL(
 	return listenAddr, upstreamURL, nil
 }
 
+// InstanceName reads only SWWAF_INSTANCE_NAME, which may be given as a
+// file, as FromEnvironment does, so that the line saying a setting is
+// invalid carries it too. A file that cannot be read gives the default
+// here, and FromEnvironment then stops the start over it.
+func InstanceName(lookupEnv func(string) (string, bool)) string {
+	env := &environment{lookupEnv: lookupEnv}
+
+	return env.instanceName()
+}
+
 // privateRanges are the private address ranges, the default trusted
 // proxies.
 const privateRanges = "10.0.0.0/8,172.16.0.0/12,192.168.0.0/16"
@@ -660,6 +671,19 @@ func (e *environment) facility(name, defaultValue string) int {
 	return number
 }
 
+// instanceName reads SWWAF_INSTANCE_NAME, by default the host's name. It
+// must be valid UTF-8: the metrics library panics on a label that is not.
+func (e *environment) instanceName() string {
+	hostname, _ := os.Hostname() // "" when the host has no name to give
+
+	value := e.value("SWWAF_INSTANCE_NAME", hostname)
+	if !utf8.ValidString(value) {
+		e.check("SWWAF_INSTANCE_NAME", fmt.Errorf("%q %w", value, errNotUTF8))
+	}
+
+	return value
+}
+
 // appName reads the setting that is the APP-NAME of the records the log
 // lines are sent in, by default the instance name. Its value is checked
 // when it is set, and, while lines are sent, when it is the instance name.

internal/config/config_test.go

@@ -737,6 +737,25 @@ func TestInstanceNameWithAControlCharacterStopsTheStartOnlyWithNtfySet(t *testin
 	}
 }
 
+func TestInstanceNameNotUTF8StopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	// café saved in Latin-1.
+	const latin1 = "caf\xe9"
+
+	for name, env := range map[string]environment{
+		"set":       {instanceName: latin1},
+		"in a file": {instanceName + "_FILE": writeFile(t, latin1+"\n")},
+	} {
+		_, err := config.FromEnvironment(env.lookupEnv)
+
+		want := instanceName + `: "caf\xe9" is not valid UTF-8`
+		if err == nil || err.Error() != want {
+			t.Errorf("%s: error %v, want %s", name, err, want)
+		}
+	}
+}
+
 func TestCodeOnBothCountryListsStopsTheStart(t *testing.T) {
 	t.Parallel()