xmrig-auto-pause: fix

tests/xmrig-auto-pause.nix

@@ -44,6 +44,7 @@ pkgs.testers.runNixOSTest {
     GRACE_PERIOD = "5"
     CPU_THRESHOLD = "10"
     STARTUP_COOLDOWN = "4"
+    STATE_DIR = "/tmp/xap-state"
 
     def start_cpu_load(name):
         """Start a non-nice CPU burn as a transient systemd unit."""
@@ -55,22 +56,28 @@ pkgs.testers.runNixOSTest {
     def stop_cpu_load(name):
         machine.succeed(f"systemctl stop {name}")
 
-    start_all()
-    machine.wait_for_unit("multi-user.target")
-    machine.wait_for_unit("xmrig.service")
-
-    with subtest("Start auto-pause monitor"):
+    def start_monitor(unit_name):
+        """Start the auto-pause monitor as a transient unit."""
         machine.succeed(
-            f"systemd-run --unit=xmrig-auto-pause "
+            f"systemd-run --unit={unit_name} "
             f"--setenv=POLL_INTERVAL={POLL_INTERVAL} "
             f"--setenv=GRACE_PERIOD={GRACE_PERIOD} "
             f"--setenv=CPU_THRESHOLD={CPU_THRESHOLD} "
             f"--setenv=STARTUP_COOLDOWN={STARTUP_COOLDOWN} "
+            f"--setenv=STATE_DIR={STATE_DIR} "
             f"{PYTHON} {SCRIPT}"
         )
         # Monitor needs two consecutive polls to compute a CPU delta.
         time.sleep(3)
 
+    start_all()
+    machine.wait_for_unit("multi-user.target")
+    machine.wait_for_unit("xmrig.service")
+    machine.succeed(f"mkdir -p {STATE_DIR}")
+
+    with subtest("Start auto-pause monitor"):
+        start_monitor("xmrig-auto-pause")
+
     with subtest("xmrig stays running while system is idle"):
         machine.succeed("systemctl is-active xmrig")
 
@@ -134,5 +141,61 @@ pkgs.testers.runNixOSTest {
 
         stop_cpu_load("cpu-load-4")
         machine.wait_until_succeeds("systemctl is-active xmrig", timeout=20)
+
+    # --- State persistence and crash recovery ---
+    machine.succeed("systemctl stop xmrig-auto-pause")
+
+    with subtest("xmrig recovers after crash during startup cooldown"):
+        machine.succeed(f"rm -rf {STATE_DIR} && mkdir -p {STATE_DIR}")
+        start_monitor("xmrig-auto-pause-crash")
+
+        # Load -> xmrig stops
+        start_cpu_load("cpu-crash")
+        machine.wait_until_fails("systemctl is-active xmrig", timeout=20)
+
+        # End load -> xmrig restarts after grace period
+        stop_cpu_load("cpu-crash")
+        machine.wait_until_succeeds("systemctl is-active xmrig", timeout=30)
+
+        # Kill xmrig immediately — simulates crash during startup cooldown.
+        # The script should detect the failure when cooldown expires and
+        # re-enter the retry cycle.
+        machine.succeed("systemctl kill --signal=KILL xmrig")
+        machine.wait_until_fails("systemctl is-active xmrig", timeout=5)
+
+        # After cooldown + grace period + restart, xmrig should be back.
+        machine.wait_until_succeeds("systemctl is-active xmrig", timeout=30)
+
+        machine.succeed("systemctl stop xmrig-auto-pause-crash")
+        machine.succeed("systemctl reset-failed xmrig.service || true")
+        machine.succeed("systemctl start xmrig")
+        machine.wait_for_unit("xmrig.service")
+
+    with subtest("Script restart preserves pause state"):
+        machine.succeed(f"rm -rf {STATE_DIR} && mkdir -p {STATE_DIR}")
+        start_monitor("xmrig-auto-pause-persist")
+
+        # Load -> xmrig stops
+        start_cpu_load("cpu-persist")
+        machine.wait_until_fails("systemctl is-active xmrig", timeout=20)
+
+        # Kill the monitor while xmrig is paused (simulates script crash)
+        machine.succeed("systemctl stop xmrig-auto-pause-persist")
+
+        # State file must exist — the monitor persisted the pause flag
+        machine.succeed(f"test -f {STATE_DIR}/paused")
+
+        # Start a fresh monitor instance (reads state file on startup)
+        start_monitor("xmrig-auto-pause-persist2")
+
+        # End load — the new monitor should pick up the paused state
+        # and restart xmrig after the grace period
+        stop_cpu_load("cpu-persist")
+        machine.wait_until_succeeds("systemctl is-active xmrig", timeout=30)
+
+        # State file should be cleaned up after successful restart
+        machine.fail(f"test -f {STATE_DIR}/paused")
+
+        machine.succeed("systemctl stop xmrig-auto-pause-persist2")
   '';
 }