From 97eff6517e5eb77c21c4b9c24d9efc0bdca9aa1c Mon Sep 17 00:00:00 2001
From: evilight <evilight@163.com>
Date: Sat, 10 Oct 2026 16:06:55 +0800
Subject: [PATCH] login: probe the world port with a bind test instead of lsof

LoginServer.exec() -> checkServerHealth() -> isPortInUse() shelled out to
`lsof -i tcp:<port>` through /bin/bash and read the child's stdout until EOF.
There is no timeout and no waitFor(), so a child that blocks is fatal: in the
container lsof was observed stuck in uninterruptible I/O (D state) while it was
scanning the busy world server. The login server then never returned from its
startup path, the accept loop never started, and clients could open a TCP
connection to 6000 and wait forever for the 100 byte DH handshake, surfacing as
"Failed to open a server connection" after the client's own timeout. A container
restart was the only way out.

Replace the external probe with a bind probe: it cannot hang, needs no external
tool, and SO_REUSEADDR still does not allow stealing a port that is actively
listening, so a successful bind keeps meaning "free".
---
 src/engine/server/login/LoginServer.java | 47 +++++++++++++++---------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/src/engine/server/login/LoginServer.java b/src/engine/server/login/LoginServer.java
index e0ab95ee..4802652d 100644
--- a/src/engine/server/login/LoginServer.java
+++ b/src/engine/server/login/LoginServer.java
@@ -150,29 +150,42 @@ public class LoginServer {
 
     }
 
+    /**
+     * Returns true when something is already listening on the given TCP port.
+     *
+     * This used to shell out to `lsof -i tcp:<port>` through /bin/bash and read the
+     * child's output until EOF. With no timeout and no waitFor() a child that blocks
+     * is fatal: lsof has been observed stuck in uninterruptible I/O (D state) while
+     * scanning the busy world server inside the container, which left the login
+     * server permanently inside its startup path. LoginServer.exec() never returned
+     * from checkServerHealth(), the accept loop never started, and clients could open
+     * a TCP connection to the port and then wait forever for the 100 byte DH
+     * handshake - surfacing as "Failed to open a server connection" after the
+     * client's own timeout.
+     *
+     * A bind probe is equivalent for this purpose, needs no external tool and cannot
+     * hang. SO_REUSEADDR does not allow stealing a port that is actively listening,
+     * so a successful bind still means the port is free.
+     */
     public static boolean isPortInUse(int port) {
 
-        ProcessBuilder builder = new ProcessBuilder("/bin/bash", "-c", "lsof -i tcp:" + port + " | tail -n +2 | awk '{print $2}'");
-        builder.redirectErrorStream(true);
-        Process process = null;
-        String line = null;
-        boolean portInUse = false;
+        java.net.ServerSocket probe = null;
 
         try {
-            process = builder.start();
-
-            InputStream is = process.getInputStream();
-            BufferedReader reader = new BufferedReader(new InputStreamReader(is));
-
-            while ((line = reader.readLine()) != null) {
-                portInUse = true;
-            }
-
+            probe = new java.net.ServerSocket();
+            probe.setReuseAddress(true);
+            probe.bind(new java.net.InetSocketAddress(port));
+            return false;
         } catch (IOException e) {
-            e.printStackTrace();
+            return true;
+        } finally {
+            if (probe != null)
+                try {
+                    probe.close();
+                } catch (IOException e) {
+                    // the bind result is what matters; closing cannot change it
+                }
         }
-
-        return portInUse;
     }
 
     private void exec() {