-
Notifications
You must be signed in to change notification settings - Fork 146
App and retraining never start #171
Comments
Issues go stale after 90d of inactivity. If this issue is safe to close now please do so with /lifecycle stale |
1 similar comment
Issues go stale after 90d of inactivity. If this issue is safe to close now please do so with /lifecycle stale |
Stale issues rot after 30d of inactivity. If this issue is safe to close now please do so with /lifecycle rotten |
Rotten issues close after 30d of inactivity. /close |
@sesheta: Closing this issue. In response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository. |
Hi all,
I attempted to use the prometheus anomaly detector to detect anomalies in my metrics. I set it up to track just one metric (quite a few targets though). However both times I ran the program it seemed to train just fine, but it seems to hang after finishing the initial training run. I don't get the message "Initializing Tornado Web App", nor the "Will retrain model every x minutes". Nothing happens after the retraining period passes, and no metrics ever get exposed on :8080/metrics.
Running the program, but on just one instance of the metrics (which concludes in ~3 minutes), works without issue, and none of the above mentioned problems/symptoms occur. One theory I have is that the training took longer than the retraining interval, but I do not know why that would be an issue.
I have attached a copy of the logs (without the direct training data, but I can upload that if necessary).
obfus.log
The text was updated successfully, but these errors were encountered: