Temporarily scale up aws instances

Author: klieret

aws/setup/batch/environment.json

@@ -13,10 +13,10 @@
     "type": "EC2",
     "allocationStrategy": "BEST_FIT_PROGRESSIVE",
     "minvCpus": 0,
-    "maxvCpus": 200,
-    "desiredvCpus": 0,
+    "maxvCpus": 1000,
+    "desiredvCpus": 400,
     "instanceTypes": [
-      "m5.xlarge"
+      "m5.4xlarge"
     ],
     "subnets": [
       "subnet-02f03254ff2613e05",

aws/setup/batch/job_definition.json

@@ -17,11 +17,11 @@
     "ulimits": [],
     "resourceRequirements": [
       {
-        "value": "4",
+        "value": "16",
         "type": "VCPU"
       },
       {
-        "value": "14000",
+        "value": "60000",
         "type": "MEMORY"
       }
     ],

codeclash/games/robotrumble/robotrumble.py

@@ -4,8 +4,6 @@
 from collections import Counter
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
-from tqdm.auto import tqdm
-
 from codeclash.agents.player import Player
 from codeclash.constants import RESULT_TIE
 from codeclash.games.game import CodeGame, RoundStats
@@ -64,16 +62,19 @@ def execute_round(self, agents: list[Player]):
         cmd = f"{self.run_cmd_round} {shlex.join(args)}"
         self.logger.info(f"Running game: {cmd}")
 
-        with ThreadPoolExecutor(5) as executor:
+        with ThreadPoolExecutor(8) as executor:
             # Submit all simulations to the thread pool
             futures = [
                 executor.submit(self._run_single_simulation, agents, idx, cmd)
                 for idx in range(self.game_config.get("sims_per_round", 100))
             ]
 
             # Collect results as they complete
-            for future in tqdm(as_completed(futures), total=len(futures)):
+            i_completed = 0
+            for future in as_completed(futures):
                 future.result()
+                i_completed += 1
+                self.logger.info(f"Completed {i_completed} of {len(futures)} simulations")
 
     def _get_winner_txt(self, output_file: str, agents: list[Player]) -> str:
         try: