xmrig-auto-pause: fix

services/monero/xmrig-auto-pause.py

@@ -35,6 +35,11 @@ CPU_THRESHOLD = float(os.environ.get("CPU_THRESHOLD", "5"))
 # RandomX dataset initialization complete (~4s on the target hardware)
 # without retriggering a stop.
 STARTUP_COOLDOWN = float(os.environ.get("STARTUP_COOLDOWN", "10"))
+# Directory for persisting pause state across script restarts.  Without
+# this, a restart while xmrig is paused loses the paused_by_us flag and
+# xmrig stays stopped permanently.
+STATE_DIR = os.environ.get("STATE_DIR", "")
+_PAUSE_FILE = os.path.join(STATE_DIR, "paused") if STATE_DIR else ""
 
 
 def log(msg):
@@ -78,13 +83,36 @@ def systemctl(action, unit):
     return result.returncode == 0
 
 
+def _save_paused(paused):
+    """Persist pause flag so a script restart can resume where we left off."""
+    if not _PAUSE_FILE:
+        return
+    try:
+        if paused:
+            open(_PAUSE_FILE, "w").close()
+        else:
+            os.remove(_PAUSE_FILE)
+    except OSError:
+        pass
+
+
+def _load_paused():
+    """Check if a previous instance left xmrig paused."""
+    if not _PAUSE_FILE:
+        return False
+    return os.path.isfile(_PAUSE_FILE)
+
+
 def main():
-    paused_by_us = False
+    paused_by_us = _load_paused()
     idle_since = None
     started_at = None  # monotonic time when we last started xmrig
     prev_total = None
     prev_work = None
 
+    if paused_by_us:
+        log("Recovered pause state from previous instance")
+
     log(
         f"Starting: poll={POLL_INTERVAL}s grace={GRACE_PERIOD}s "
         f"threshold={CPU_THRESHOLD}% cooldown={STARTUP_COOLDOWN}s"
@@ -116,6 +144,14 @@ def main():
             if time.monotonic() - started_at < STARTUP_COOLDOWN:
                 time.sleep(POLL_INTERVAL)
                 continue
+            # Cooldown expired — verify xmrig survived startup.  If it
+            # crashed during init (hugepage failure, pool unreachable, etc.),
+            # re-enter the pause/retry cycle rather than silently leaving
+            # xmrig dead.
+            if not is_active("xmrig.service"):
+                log("xmrig died during startup cooldown — will retry")
+                paused_by_us = True
+                _save_paused(True)
             started_at = None
 
         busy = real_work_pct > CPU_THRESHOLD
@@ -128,6 +164,7 @@ def main():
                 # manage it again.
                 log("xmrig was restarted externally while paused — reclaiming")
                 paused_by_us = False
+                _save_paused(False)
             if not paused_by_us:
                 # Only claim ownership if xmrig is actually running.
                 # If something else stopped it (e.g. UPS battery hook),
@@ -136,6 +173,7 @@ def main():
                     log(f"Real workload detected ({real_work_pct:.1f}% CPU) — stopping xmrig")
                     if systemctl("stop", "xmrig.service"):
                         paused_by_us = True
+                        _save_paused(True)
         else:
             if paused_by_us:
                 if idle_since is None:
@@ -144,6 +182,7 @@ def main():
                     log(f"Workload ended ({real_work_pct:.1f}% CPU) past grace period — starting xmrig")
                     if systemctl("start", "xmrig.service"):
                         paused_by_us = False
+                        _save_paused(False)
                         started_at = time.monotonic()
                     idle_since = None