Wait for the server's tailnet peer before connecting at app startup

mac/Sources/Byre/API.swift

@@ -144,7 +144,7 @@ func parseOrigin(_ text: String) -> URL? {
     }
     var origin = URLComponents()
     origin.scheme = "https"
-    origin.host = host.lowercased()
+    origin.host = (host.hasSuffix(".") ? String(host.dropLast()) : host).lowercased()
     origin.port = c.port
     return origin.url
 }

mac/Sources/Byre/Remote.swift

@@ -115,7 +115,7 @@ final class Remote {
                 case .success:
                     self.receive(task)
                 case .failure(let error):
-                    log.notice("client connection closed:\(errorText(error), privacy: .public)")
+                    log.notice("client connection closed:\(errorText(error), privacy: .public); \(tailnetNode.peerState(self.api.origin.host()!), privacy: .public)")
                     self.ws = nil
                     try? await Task.sleep(for: retryAfter)
                     self.start()

mac/Sources/Byre/Startup.swift

@@ -198,7 +198,7 @@ final class Connection {
 
     private func start() async {
         let old = store
-        while !stopped, !Tailnet.shared.running {
+        while !stopped, !Tailnet.shared.reachable(origin) {
             try? await Task.sleep(for: .milliseconds(500))
         }
         while !stopped, !(await attempt(old)) {
@@ -252,6 +252,7 @@ final class Connection {
             Notifier.shared.deliver()
             return true
         } catch {
+            log.notice("connect \(self.origin.absoluteString, privacy: .public) failed: \(errorText(error), privacy: .public); \(tailnetNode.peerState(self.origin.host()!), privacy: .public)")
             await store.stop()
             if !stopped {
                 phase = .failed(explain(error, origin))

mac/Sources/Byre/Tailnet.swift

@@ -40,6 +40,7 @@ final class TailnetNode: Sendable {
         Self.check(sd, "set hostname", unsafe tailscale_set_hostname(sd, hostname))
         Self.check(sd, "set dir", unsafe tailscale_set_dir(sd, dir.path))
         Self.check(sd, "set ephemeral", tailscale_set_ephemeral(sd, 0))
+        Self.check(sd, "set logfd", tailscale_set_logfd(sd, Self.logPipe()))
         Self.check(sd, "start", tailscale_start(sd))
         var addr = [CChar](repeating: 0, count: 64)
         var proxyCred = [CChar](repeating: 0, count: 33)
@@ -60,6 +61,49 @@ final class TailnetNode: Sendable {
         }
     }
 
+    private static let logs = Pipe()
+
+    private static func logPipe() -> Int32 {
+        let lines = LineBuffer()
+        logs.fileHandleForReading.readabilityHandler = { handle in
+            for line in lines.add(handle.availableData) {
+                log.notice("tsnet: \(line, privacy: .public)")
+            }
+        }
+        return dup(logs.fileHandleForWriting.fileDescriptor)
+    }
+
+    func peerState(_ host: String) -> String {
+        var out: UnsafeMutablePointer<CChar>?
+        guard unsafe tailscale_status_json(sd, &out) == 0, let out = unsafe out else {
+            return "no status: \(Self.errorMessage(sd))"
+        }
+        defer {
+            unsafe free(out)
+        }
+        struct Peer: Decodable {
+            let DNSName: String
+            let Online: Bool
+            let InNetworkMap: Bool
+            let InMagicSock: Bool
+            let InEngine: Bool
+            let LastHandshake: String
+            let CurAddr: String
+            let Relay: String
+        }
+        struct Status: Decodable {
+            let BackendState: String
+            let Peer: [String: Peer]?
+        }
+        guard let status = try? JSONDecoder().decode(Status.self, from: unsafe Data(bytes: out, count: strlen(out))) else {
+            return "undecodable status"
+        }
+        guard let p = (status.Peer ?? [:]).values.first(where: { $0.DNSName == host + "." || $0.DNSName == host }) else {
+            return "state=\(status.BackendState) peer \(host) not in status"
+        }
+        return "state=\(status.BackendState) online=\(p.Online) netmap=\(p.InNetworkMap) magicsock=\(p.InMagicSock) engine=\(p.InEngine) handshake=\(p.LastHandshake) addr=\(p.CurAddr) relay=\(p.Relay)"
+    }
+
     static func errorMessage(_ sd: tailscale) -> String {
         var buf = [CChar](repeating: 0, count: 1024)
         _ = unsafe tailscale_errmsg(sd, &buf, buf.count)
@@ -72,7 +116,7 @@ final class TailnetNode: Sendable {
         return proxy
     }
 
-    func status() -> (state: String, authURL: URL?, servers: [URL])? {
+    func status() -> (state: String, authURL: URL?, servers: [URL], peers: Set<String>)? {
         var out: UnsafeMutablePointer<CChar>?
         guard unsafe tailscale_status_json(sd, &out) == 0, let out = unsafe out else {
             return nil
@@ -99,15 +143,18 @@ final class TailnetNode: Sendable {
         guard let status = try? JSONDecoder().decode(Status.self, from: unsafe Data(bytes: out, count: strlen(out))) else {
             return nil
         }
-        let servers = (status.Peer ?? [:]).values.compactMap { peer -> URL? in
-            let host = peer.DNSName.hasSuffix(".") ? String(peer.DNSName.dropLast()) : peer.DNSName
-            let name = host.split(separator: ".").first ?? ""
+        let peers = (status.Peer ?? [:]).values
+        let host = { (peer: Node) in
+            (peer.DNSName.hasSuffix(".") ? String(peer.DNSName.dropLast()) : peer.DNSName).lowercased()
+        }
+        let servers = peers.compactMap { peer -> URL? in
+            let name = host(peer).split(separator: ".").first ?? ""
             guard peer.Online, peer.UserID == status.me?.UserID, name.hasPrefix("byre-"), !name.hasPrefix("byre-app-") else {
                 return nil
             }
-            return parseOrigin("https://\(host)")
+            return parseOrigin("https://\(host(peer))")
         }
-        return (status.BackendState, URL(string: status.AuthURL), servers)
+        return (status.BackendState, URL(string: status.AuthURL), servers, Set(peers.map(host)))
     }
 
     // Blocks until the connection is made or fails.
@@ -120,6 +167,20 @@ final class TailnetNode: Sendable {
     }
 }
 
+private final class LineBuffer: @unchecked Sendable {
+    private var pending = Data()
+
+    func add(_ data: Data) -> [String] {
+        pending.append(data)
+        var lines: [String] = []
+        while let nl = pending.firstIndex(of: 0x0A) {
+            lines.append(String(decoding: pending[pending.startIndex..<nl], as: UTF8.self))
+            pending.removeSubrange(pending.startIndex...nl)
+        }
+        return lines
+    }
+}
+
 let tailnetNode = TailnetNode()
 
 @MainActor
@@ -131,12 +192,18 @@ final class Tailnet {
     private(set) var authURL: URL?
     private(set) var service: TailnetInfo?
     private(set) var searched = false
+    private(set) var peers: Set<String> = []
     @ObservationIgnored private var servers: [URL] = []
 
     var running: Bool {
         state == "Running"
     }
 
+    // A node starting from its cached netmap reports Running before it knows any peer, and dials made then fail.
+    func reachable(_ origin: URL) -> Bool {
+        running && peers.contains(origin.host()!.lowercased())
+    }
+
     var needsLogin: Bool {
         state == "NeedsLogin" || state == "NeedsMachineAuth" || service?.state == "NeedsLogin"
     }
@@ -148,6 +215,9 @@ final class Tailnet {
                     state = status.state
                     authURL = status.authURL
                     servers = status.servers
+                    if peers != status.peers {
+                        peers = status.peers
+                    }
                 }
                 try? await Task.sleep(for: .seconds(1))
             }