fix(test): do not use absolute path to true when opening ssh connection

In #4955 the executable to check the ssh connection liveliness was
changed from `true` to `/usr/bin/true`, but that is not its path in all
rootfs, causing failures in the `test-populat-containers` suite.

Also, since the error is retried but the control socket is not cleaned
up, subsequent retries would fail for the assertion.

This change fixes both issues by using the binary name `true` and
cleaning up the control socket on error before the next retry.

Fixes: 3b2c2d4 ("test: use single SSH connection for lifetime of microvm")
Signed-off-by: Riccardo Mancini <mancio@amazon.com>

tests/host_tools/network.py

@@ -129,14 +129,20 @@ def _init_connection(self):
             "ControlPersist=yes",
             *self.options,
             self.user_host,
-            "/usr/bin/true",
+            "true",
         ]
 
-        # don't set a low timeout here, because otherwise we might get into a race condition
-        # where ssh already forked off the persisted connection daemon, but gets killed here
-        # before exiting itself. In that case, self._control_path will exist, and the retry
-        # will hit the assert at the start of this function.
-        self._exec(establish_cmd, check=True)
+        try:
+            # don't set a low timeout here, because otherwise we might get into a race condition
+            # where ssh already forked off the persisted connection daemon, but gets killed here
+            # before exiting itself. In that case, self._control_path will exist, and the retry
+            # will hit the assert at the start of this function.
+            self._exec(establish_cmd, check=True)
+        except Exception:
+            # cleanup the control socket to allow for retries
+            if self._control_path.exists():
+                self._control_path.unlink()
+            raise
 
     def _check_liveness(self) -> int:
         """Checks whether the ControlPersist connection is still alive"""