Enabled DNS by default

README.md

@@ -199,7 +199,7 @@ belongs to, which `--help` shows as two sections:
 
 * **System** — what the agent itself does: how it reaches peers (`--reach`),
   the one overlay interface it owns (`--interface`, `--mtu`, `--no-tun`), the
-  address range (`--ipv4-range`), and the local resolver (`--dns`).
+  address range (`--ipv4-range`), and the local resolver (`--no-dns` to disable).
 * **Transport** — which protocols carry packets (`--protocol`, a list) and
   their own settings (`-o key=value`, or `-o protocol:key=value`).
 
@@ -228,20 +228,19 @@ session with no agreed protocol.
 
 ## Names
 
-`--dns` serves a local DNS zone for **every network this device is in**,
+DNS is enabled by default and serves a local zone for **every network this device is in**,
 each named after the network, so members can be reached by name instead of
 by address:
 
 ```bash
-tsunagi up --dns          # or `tsunagi dns on` against a running agent
+tsunagi up               # DNS is already enabled
 dig @127.0.0.1 -p 5354 music.lab
 ```
 
-It is remembered with the device rather than with the command line: once on
+An explicit choice is remembered across restarts. `--no-dns` or `tsunagi dns off`
-it stays on across restarts, and `tsunagi dns off` is what turns it off. A
+disables it; `--dns` or `tsunagi dns on` enables it again. Existing saved opt-outs
-resolver that quietly disappears because a flag was not retyped is worse
+remain respected. The `dns on` and `dns off` commands also take effect immediately
-than none, because the names simply stop working. `tsunagi dns on` also
+on a running agent. `--dns` and `--no-dns` cannot be combined.
-turns it on for an agent that is already running, without restarting it.
 
 The zone of a network is its name — `--dns-zone` is gone, because with
 several networks there is no single zone to name. A network name may contain

crates/tsunagi-cli/src/main.rs

@@ -422,7 +422,7 @@ struct UpArgs {
     #[arg(long, value_name = "CIDR", help_heading = "System")]
     ipv4_range: Option<String>,
 
-    /// Serve a local DNS zone for every network this device is in.
+    /// Enable local DNS for every network (on by default).
     ///
     /// Each network becomes a zone named after it, and its members resolve
     /// as `<hostname>.<network>` from signed state, so a member that is
@@ -430,10 +430,16 @@ struct UpArgs {
     /// addresses; questions are taken on loopback of both families, over
     /// UDP and TCP.
     ///
-    /// Remembered: once on it stays on, and `tsunagi dns off` turns it off.
+    /// Overrides a remembered opt-out. Use --no-dns or `tsunagi dns off` to disable.
-    #[arg(long, help_heading = "System")]
+    #[arg(long, conflicts_with = "no_dns", help_heading = "System")]
     dns: bool,
 
+    /// Disable local DNS and remember this choice for future starts.
+    ///
+    /// Use --dns or `tsunagi dns on` to enable it again.
+    #[arg(long, conflicts_with = "dns", help_heading = "System")]
+    no_dns: bool,
+
     /// Port for the local DNS server, on loopback of both families.
     ///
     /// Remembered with the setting, so it needs giving only when changing.
@@ -505,7 +511,7 @@ struct DnsSetting {
 impl Default for DnsSetting {
     fn default() -> Self {
         Self {
-            enabled: false,
+            enabled: true,
             port: DEFAULT_DNS_PORT,
         }
     }
@@ -517,9 +523,9 @@ fn dns_setting(paths: &StoragePaths) -> DnsSetting {
         return DnsSetting::default();
     };
     DnsSetting {
-        enabled: matches!(
+        enabled: !matches!(
             store.get_setting(DNS_ENABLED).ok().flatten().as_deref(),
-            Some("1")
+            Some("0")
         ),
         port: store
             .get_setting(DNS_PORT)
@@ -3256,11 +3262,10 @@ async fn up(args: UpArgs) -> Result<(), Box<dyn std::error::Error>> {
     let ipv4_range = resolve_ipv4_range(args.ipv4_range.as_ref())?;
 
     // The resolver is a property of the device, not of this command line.
-    // `--dns` turns it on and it stays on; `tsunagi dns off` is what turns
+    // Enabled unless deliberately disabled. Explicit flags override the
-    // it off. Anything else means names work today and are gone tomorrow
+    // remembered choice, which otherwise survives subsequent restarts.
-    // because a flag was not retyped.
     let stored_dns = dns_setting(&paths);
-    let serve_dns = args.dns || stored_dns.enabled;
+    let serve_dns = !args.no_dns && (args.dns || stored_dns.enabled);
     let dns_port = args.dns_port.unwrap_or(stored_dns.port);
     if serve_dns != stored_dns.enabled || dns_port != stored_dns.port {
         // Written before the agent takes the directory, which it is about

crates/tsunagi-cli/tests/dns_service.rs

@@ -22,6 +22,7 @@ const PORT_REBIND: u16 = 15362;
 const PORT_REFUSE: u16 = 15363;
 const PORT_TWO_ZONES: u16 = 15364;
 const PORT_SWITCH: u16 = 15365;
+const PORT_FLAGS: u16 = 15366;
 
 /// Asks, and returns the raw reply. Raw because a parsed packet borrows
 /// from the bytes it came out of.
@@ -73,6 +74,33 @@ struct Running {
 }
 
 impl Running {
+    fn wait_ready(&mut self) {
+        let runtime = tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .unwrap();
+        let socket = tsunagi::ipc::control_socket_path(&self.dir.path().join("state"));
+        let deadline = Instant::now() + Duration::from_secs(20);
+        while !runtime.block_on(tsunagi::ipc::is_serving(&socket)) {
+            assert!(
+                self.child.try_wait().unwrap().is_none(),
+                "the agent exited before becoming ready"
+            );
+            assert!(
+                Instant::now() < deadline,
+                "the control socket never became ready"
+            );
+            std::thread::sleep(Duration::from_millis(25));
+        }
+    }
+
+    fn restart(&mut self, dns_flag: Option<&str>) {
+        self.child.kill().unwrap();
+        self.child.wait().unwrap();
+        self.child = spawn_child(&self.dir, None, dns_flag);
+        self.wait_ready();
+    }
+
     /// Runs another `tsunagi` command against this agent's directory.
     fn run(&self, args: &[&str]) -> std::process::Output {
         std::process::Command::new(env!("CARGO_BIN_EXE_tsunagi"))
@@ -135,6 +163,17 @@ fn start_without_dns(network: &str) -> Running {
 /// The agent alone: `up` runs it, and what it belongs to is decided after.
 fn start_without_dns_at(_network: &str, dns_port: Option<u16>) -> Running {
     let dir = TempDir::new().unwrap();
+    let child = spawn_child(&dir, dns_port, dns_port.is_none().then_some("--no-dns"));
+    let mut agent = Running { child, dir };
+    agent.wait_ready();
+    agent
+}
+
+fn spawn_child(
+    dir: &TempDir,
+    dns_port: Option<u16>,
+    dns_flag: Option<&str>,
+) -> std::process::Child {
     let mut command = std::process::Command::new(env!("CARGO_BIN_EXE_tsunagi"));
     command
         .arg("up")
@@ -145,21 +184,21 @@ fn start_without_dns_at(_network: &str, dns_port: Option<u16>) -> Running {
         // No real interface and no internet: this is about the wiring.
         .args(["--reach", "local", "--no-tun"]);
     if let Some(port) = dns_port {
-        command.arg("--dns").args(["--dns-port", &port.to_string()]);
+        command.args(["--dns-port", &port.to_string()]);
     }
-    let child = command
+    if let Some(flag) = dns_flag {
+        command.arg(flag);
+    }
+    command
         .args(["--log", "error", "--status-interval", "0"])
         .stdout(std::process::Stdio::null())
         .stderr(std::process::Stdio::null())
         .spawn()
-        .expect("the agent binary starts");
+        .expect("the agent binary starts")
-    // Long enough for the control socket to be there to talk to.
-    std::thread::sleep(Duration::from_secs(2));
-    Running { child, dir }
 }
 
 #[test]
-fn the_resolver_comes_up_even_with_no_overlay_interface_to_put_it_on() {
+fn the_resolver_is_on_by_default_even_without_an_overlay_interface() {
     // The promise is that the port is served whatever else fails: with
     // `--no-tun` there is no interface to attach a resolver setting to,
     // and the zone is answered on loopback all the same. Getting this
@@ -247,15 +286,11 @@ fn every_network_gets_a_zone_of_its_own() {
 
 #[test]
 fn the_resolver_can_be_switched_on_and_off_while_the_agent_runs() {
-    // Forgetting `--dns` on a command line should not be a decision that
+    // An intentional --no-dns can be reversed at runtime without restarting.
-    // lasts until the next restart, and it is not: the setting belongs to
-    // the device, and turning it on takes effect at once.
     let agent = start_without_dns("switch.internal");
     let server: SocketAddr = format!("127.0.0.1:{PORT_SWITCH}").parse().unwrap();
     let host = hostname();
 
-    // Give the agent time to be up before asking it anything.
-    std::thread::sleep(Duration::from_secs(1));
     assert!(
         query(server, &format!("{host}.switch.internal"), TYPE::A).is_none(),
         "nothing should be answering yet"
@@ -280,3 +315,33 @@ fn the_resolver_can_be_switched_on_and_off_while_the_agent_runs() {
         std::thread::sleep(Duration::from_millis(200));
     }
 }
+
+#[test]
+fn explicit_dns_choices_override_the_saved_setting_and_survive_restart() {
+    let mut agent = start("flags.internal", PORT_FLAGS);
+    let server = format!("127.0.0.1:{PORT_FLAGS}").parse().unwrap();
+    let name = format!("{}.flags.internal", hostname());
+    wait_for_answer(server, &name);
+
+    for flag in [Some("--no-dns"), None] {
+        agent.restart(flag);
+        let state = agent.run(&["dns"]);
+        assert!(state.status.success());
+        assert!(String::from_utf8_lossy(&state.stdout).contains("not serving"));
+        assert!(query(server, &name, TYPE::A).is_none());
+    }
+    agent.restart(Some("--dns"));
+    wait_for_answer(server, &name);
+    agent.restart(None);
+    wait_for_answer(server, &name);
+}
+
+#[test]
+fn opposing_dns_flags_are_rejected() {
+    let result = std::process::Command::new(env!("CARGO_BIN_EXE_tsunagi"))
+        .args(["up", "--dns", "--no-dns"])
+        .output()
+        .unwrap();
+    assert!(!result.status.success());
+    assert!(String::from_utf8_lossy(&result.stderr).contains("cannot be used with"));
+}

crates/tsunagi-cli/tests/network_cli.rs

@@ -46,7 +46,7 @@ fn start_bare(port: u16) -> Running {
         .arg(dir.path().join("state"))
         .arg("--cache-dir")
         .arg(dir.path().join("cache"))
-        .args(["--reach", "local", "--no-tun"])
+        .args(["--reach", "local", "--no-tun", "--no-dns"])
         .arg("--bind")
         .arg(format!("127.0.0.1:{port}"))
         .args(["--log", "error", "--status-interval", "0"])