fix(broker): cap outage backoff overflow and expand worker matrix coverage

Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>

trex_core/application/balance_health.py

@@ -1,6 +1,7 @@
 """Broker-balance worker health tracking with bounded backoff."""
 from __future__ import annotations
 
+import math
 from dataclasses import dataclass
 from datetime import UTC, datetime, timedelta
 from threading import Lock
@@ -64,6 +65,11 @@ class BalanceHealthTracker:
         self._max_backoff_sec = max(self._base_backoff_sec, float(max_backoff_sec))
         self._lock = Lock()
         self._states: dict[str, BalanceWorkerHealth] = {}
+        if self._base_backoff_sec >= self._max_backoff_sec:
+            self._max_backoff_exponent = 0
+        else:
+            ratio = self._max_backoff_sec / self._base_backoff_sec
+            self._max_backoff_exponent = int(math.floor(math.log2(ratio)))
 
     def _now(self) -> datetime:
         return self._clock()
@@ -101,10 +107,14 @@ class BalanceHealthTracker:
             prev = self._get(worker)
             now = self._now()
             failures = prev.consecutive_failures + 1
-            backoff = min(
-                self._base_backoff_sec * (2 ** max(0, failures - 1)),
-                self._max_backoff_sec,
-            )
+            exponent = max(0, failures - 1)
+            if exponent > self._max_backoff_exponent:
+                backoff = self._max_backoff_sec
+            else:
+                backoff = min(
+                    self._base_backoff_sec * (2.0 ** exponent),
+                    self._max_backoff_sec,
+                )
             self._states[worker] = BalanceWorkerHealth(
                 worker=worker,
                 last_success_at=prev.last_success_at,