swarm-controller: let each test nats-server bind its own port

TestNats picked a port by binding 127.0.0.1:0, dropping the listener
and handing the number to nats-server. Until that server bound it, the
port was free for a concurrent test's bind(0) to return again. Both
servers were then started on it (with the same store dir, since that was
keyed by pid and port); the loser exited silently and both tests'
clients reached the winner. term_stream's tests all use the stream
term-main-iris, and one of them creates it with max_message_size 4096,
so a test sharing its server got "stream name already in use with a
different configuration" (10058) from open_or_create's
get-then-create.

The server now binds a port of its choice (-p -1) and announces it in a
ports file, and each server has its own tempdir for the store and that
file, so a test can only reach the server it started.

Fixes #5261

swarm-controller/src/test_nats.rs

@@ -5,19 +5,26 @@
 //! `nix/devshell.nix` export. A test that needs it panics when it is unset
 //! rather than skipping, so it never shows green without having run.
 
-use std::path::PathBuf;
+use std::path::Path;
 use std::process::{Child, Command, Stdio};
 use std::time::Duration;
 
 /// The variable naming the `nats-server` binary.
 pub(crate) const NATS_SERVER_ENV: &str = "HIVE_NATS_SERVER";
 
-/// A running server on a loopback port, with its store in a fresh directory.
-/// Dropping it kills the server and removes the store.
+/// The subdirectory holding nothing but the server's ports file.
+const PORTS_DIR: &str = "ports";
+
+/// A running server on a loopback port it bound itself, with its store and
+/// ports file under a directory of its own. Dropping it kills the server and
+/// removes the directory.
+///
+/// The port is the server's choice, read back from its ports file: a port
+/// picked here and handed over would be free for a concurrent test to pick
+/// too, and both tests would then talk to whichever server won the bind.
 pub(crate) struct TestNats {
     child: Child,
-    store: PathBuf,
-    url: String,
+    dir: tempfile::TempDir,
 }
 
 impl TestNats {
@@ -25,42 +32,69 @@ impl TestNats {
         let bin = std::env::var(NATS_SERVER_ENV).unwrap_or_else(|_| {
             panic!("{NATS_SERVER_ENV} is exported by nix/checks.nix and nix/devshell.nix")
         });
-        // Bound and released to learn a free port; the server binds it next.
-        let port = std::net::TcpListener::bind("127.0.0.1:0")
-            .and_then(|l| l.local_addr())
-            .expect("a free loopback port")
-            .port();
-        let store = std::env::temp_dir().join(format!("test-nats-{}-{port}", std::process::id()));
+        let dir = tempfile::Builder::new()
+            .prefix("test-nats-")
+            .tempdir()
+            .expect("a fresh directory for the server");
+        std::fs::create_dir(dir.path().join(PORTS_DIR)).expect("the ports file directory");
         let child = Command::new(&bin)
-            .args(["-a", "127.0.0.1", "-p", &port.to_string(), "-js", "-sd"])
-            .arg(&store)
+            .args(["-a", "127.0.0.1", "-p", "-1", "-js", "-sd"])
+            .arg(dir.path().join("store"))
+            .arg("--ports_file_dir")
+            .arg(dir.path().join(PORTS_DIR))
             .stdout(Stdio::null())
             .stderr(Stdio::null())
             .spawn()
             .unwrap_or_else(|e| panic!("starting {bin}: {e}"));
-        Self {
-            child,
-            store,
-            url: format!("nats://127.0.0.1:{port}"),
-        }
+        Self { child, dir }
     }
 
     /// A client connected to the server, once it accepts connections.
     pub(crate) async fn client(&self) -> async_nats::Client {
         for _ in 0..100 {
-            if let Ok(client) = async_nats::connect(&self.url).await {
+            if let Some(url) = announced_url(&self.dir.path().join(PORTS_DIR))
+                && let Ok(client) = async_nats::connect(&url).await
+            {
                 return client;
             }
             tokio::time::sleep(Duration::from_millis(100)).await;
         }
-        panic!("nats-server at {} never accepted a connection", self.url);
+        panic!(
+            "nats-server in {} never accepted a connection",
+            self.dir.path().display()
+        );
     }
 }
 
+/// The client URL in the `<exe>_<pid>.ports` file, the one file the server
+/// writes into `dir` once it listens, or `None` while there is none to read.
+fn announced_url(dir: &Path) -> Option<String> {
+    let ports = std::fs::read_dir(dir).ok()?.next()?.ok()?;
+    let ports: serde_json::Value =
+        serde_json::from_slice(&std::fs::read(ports.path()).ok()?).ok()?;
+    ports["nats"][0].as_str().map(str::to_owned)
+}
+
 impl Drop for TestNats {
     fn drop(&mut self) {
         let _ = self.child.kill();
         let _ = self.child.wait();
-        let _ = std::fs::remove_dir_all(&self.store);
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::TestNats;
+
+    /// Servers started back to back are each their own, so no test reaches
+    /// another test's streams.
+    #[tokio::test]
+    async fn each_test_nats_is_its_own_server() {
+        let servers: Vec<TestNats> = (0..4).map(|_| TestNats::start()).collect();
+        let mut ids = std::collections::BTreeSet::new();
+        for nats in &servers {
+            ids.insert(nats.client().await.server_info().server_id);
+        }
+        assert_eq!(ids.len(), servers.len(), "server ids: {ids:?}");
     }
 }