test-driver.py: delete VM state directory after test run

Keeping the VM state test across several run sometimes lead to subtle
and hard to spot errors in practice. We delete the VM state which
contains (among other things) the qcow volume.

We also introduce a -K (--keep-vm-state) flag making VM state to
persist after the test run. This flag makes test-driver.py to match
its previous behaviour.

3 files changed, 31 insertions, 4 deletions

diff --git a/nixos/doc/manual/development/running-nixos-tests-interactively.xml b/nixos/doc/manual/development/running-nixos-tests-interactively.xml
index 31216874c706..a11a9382764d 100644
--- a/nixos/doc/manual/development/running-nixos-tests-interactively.xml
+++ b/nixos/doc/manual/development/running-nixos-tests-interactively.xml
@@ -38,7 +38,12 @@ starting VDE switch for network 1
  </para>
 
  <para>
-  The machine state is kept across VM restarts in
-  <filename>/tmp/vm-state-</filename><varname>machinename</varname>.
+   You can re-use the VM states coming from a previous run
+   by setting the <command>--keep-vm-state</command> flag.
+<screen>
+<prompt>$ </prompt>./result/bin/nixos-run-vms --keep-vm-state
+</screen>
+  The machine state is stored in the
+  <filename>$TMPDIR/vm-state-</filename><varname>machinename</varname> directory.
  </para>
 </section>
diff --git a/nixos/doc/manual/release-notes/rl-2009.xml b/nixos/doc/manual/release-notes/rl-2009.xml
index a0a0b2cb40e4..627f1d08edd2 100644
--- a/nixos/doc/manual/release-notes/rl-2009.xml
+++ b/nixos/doc/manual/release-notes/rl-2009.xml
@@ -656,6 +656,12 @@ systemd.services.nginx.serviceConfig.ReadWritePaths = [ "/var/www" ];
      <package>nextcloud18</package> before upgrading to <package>nextcloud19</package>
      since Nextcloud doesn't support upgrades across multiple major versions.
     </para>
+     <para>
+       The <literal>nixos-run-vms</literal> script now deletes the
+       previous run machines states on test startup. You can use the
+       <literal>--keep-vm-state</literal> flag to match the previous
+       behaviour and keep the same VM state between different test runs.
+     </para>
    </listitem>
   </itemizedlist>
  </section>
diff --git a/nixos/lib/test-driver/test-driver.py b/nixos/lib/test-driver/test-driver.py
index e7b05968b079..f454b052dc31 100644
--- a/nixos/lib/test-driver/test-driver.py
+++ b/nixos/lib/test-driver/test-driver.py
@@ -4,6 +4,7 @@ from queue import Queue, Empty
 from typing import Tuple, Any, Callable, Dict, Iterator, Optional, List
 from xml.sax.saxutils import XMLGenerator
 import _thread
+import argparse
 import atexit
 import base64
 import codecs
@@ -751,6 +752,11 @@ class Machine:
 
         self.log("QEMU running (pid {})".format(self.pid))
 
+    def cleanup_statedir(self) -> None:
+        self.log("delete the VM state directory")
+        if os.path.isfile(self.state_dir):
+            shutil.rmtree(self.state_dir)
+
     def shutdown(self) -> None:
         if not self.booted:
             return
@@ -889,6 +895,15 @@ def subtest(name: str) -> Iterator[None]:
 
 
 if __name__ == "__main__":
+    arg_parser = argparse.ArgumentParser()
+    arg_parser.add_argument(
+        "-K",
+        "--keep-vm-state",
+        help="re-use a VM state coming from a previous run",
+        action="store_true",
+    )
+    (cli_args, vm_scripts) = arg_parser.parse_known_args()
+
     log = Logger()
 
     vlan_nrs = list(dict.fromkeys(os.environ.get("VLANS", "").split()))
@@ -896,8 +911,10 @@ if __name__ == "__main__":
     for nr, vde_socket, _, _ in vde_sockets:
         os.environ["QEMU_VDE_SOCKET_{}".format(nr)] = vde_socket
 
-    vm_scripts = sys.argv[1:]
     machines = [create_machine({"startCommand": s}) for s in vm_scripts]
+    for machine in machines:
+        if not cli_args.keep_vm_state:
+            machine.cleanup_statedir()
     machine_eval = [
         "{0} = machines[{1}]".format(m.name, idx) for idx, m in enumerate(machines)
     ]
@@ -911,7 +928,6 @@ if __name__ == "__main__":
                     continue
                 log.log("killing {} (pid {})".format(machine.name, machine.pid))
                 machine.process.kill()
-
             for _, _, process, _ in vde_sockets:
                 process.terminate()
         log.close()