PTFE-1196 Make it easier to identify events related to missed webhooks (

#497) Adding a log statement to indicate when a new runner needs to be created for a runner group due to a high time to start, and including the name of the deleted idle runner in the log statement for the healthcheck function.
scality · Dec 11, 2023 · 323c169 · 323c169
1 parent 6c1196a
commit 323c169
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/runner_manager/jobs/workflow_job.py b/runner_manager/jobs/workflow_job.py
@@ -71,7 +71,9 @@ def in_progress(webhook: WorkflowJobInProgress) -> str | None:
     # in the case we have missed a webhook, we still have a runner
     # available for the jobs that are requesting it.
     if tts > settings.timeout_runner and runner_group.is_full is False:
-        log.info(f"Runner group {runner_group.name} needs a new runner")
+        log.info(
+            f"Time to start too high ({tts}), creating runner for {runner_group.name}"
+        )
         github: GitHub = get_github()
         runner_group.create_runner(github)
     return runner.pk

diff --git a/runner_manager/models/runner_group.py b/runner_manager/models/runner_group.py
@@ -323,7 +323,7 @@ def healthcheck(
         while len(idle_runners) > self.min:
             runner = idle_runners.pop()
             self.delete_runner(runner, github)
-            log.info(f"Runner {runner.name} deleted")
+            log.info(f"Deleted idle {runner}")
 
     def reset(self, github: GitHub):
         """Reset runner group."""