From 215fd4da668c7856f436d012b358e87f62d21001 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Yuan-Ting=20Hsieh=20=28=E8=AC=9D=E6=B2=85=E5=BB=B7=29?= Date: Thu, 23 Jan 2025 15:17:51 -0800 Subject: [PATCH] [2.5] Remove hardcode heartbeat_timeout 0 (#3176) ### Description The original hardcode 0 has a problem, if the external user code has an exception and the program will never return. Our FL client job process (running LauncherExecutor) will never ends. By using the default heartbeat_timeout value, if the FL client job process does not receive the heartbeat from the user process for heartbeat_timeout seconds, then we will consider it dead. ### Types of changes - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Quick tests passed locally by running `./runtest.sh`. - [ ] In-line docstrings updated. - [ ] Documentation updated. --- nvflare/job_config/script_runner.py | 1 - 1 file changed, 1 deletion(-) diff --git a/nvflare/job_config/script_runner.py b/nvflare/job_config/script_runner.py index 5fa79e3fb0..0fdd0d7a84 100644 --- a/nvflare/job_config/script_runner.py +++ b/nvflare/job_config/script_runner.py @@ -186,7 +186,6 @@ def add_to_fed_job(self, job: FedJob, ctx, **kwargs): launcher_id=launcher_id, params_exchange_format=self._params_exchange_format, params_transfer_type=self._params_transfer_type, - heartbeat_timeout=0, ) ) job.add_executor(executor, tasks=tasks, ctx=ctx)