From 025390feec0af1a46a47fc78dd53ddf41b3d91cf Mon Sep 17 00:00:00 2001 From: gibsondan Date: Tue, 17 Sep 2024 13:33:53 -0500 Subject: [PATCH] Don't mention experimental resume run feature in every run monitoring failure message (#24541) Summary: Noticed this while testing something involving run monitoring. This feature is experimental and should only be refernced if the user has done something to enable it. Test Plan: BK ## Summary & Motivation ## How I Tested These Changes ## Changelog Insert changelog entry or "NOCHANGELOG" here. - [ ] `NEW` _(added new feature or capability)_ - [ ] `BUGFIX` _(fixed a bug)_ - [ ] `DOCS` _(added or updated documentation)_ --- .../dagster/dagster/_daemon/monitoring/run_monitoring.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/python_modules/dagster/dagster/_daemon/monitoring/run_monitoring.py b/python_modules/dagster/dagster/_daemon/monitoring/run_monitoring.py index 88302f5fd5ba4..7715420f8ead3 100644 --- a/python_modules/dagster/dagster/_daemon/monitoring/run_monitoring.py +++ b/python_modules/dagster/dagster/_daemon/monitoring/run_monitoring.py @@ -137,7 +137,10 @@ def monitor_started_run( # Return rather than immediately checking for a timeout, since we only just resumed return else: - if instance.run_launcher.supports_resume_run: + if ( + instance.run_launcher.supports_resume_run + and instance.run_monitoring_max_resume_run_attempts > 0 + ): msg = ( f"Detected run worker status {check_health_result}. Marking run" f" {run.run_id} as failed, because it has surpassed the configured maximum"