[06:11:21] <jinxer-wm>	 (ErrorBudgetBurn) firing: <no value>   - https://alerts.wikimedia.org/?q=alertname%3DErrorBudgetBurn
[08:42:40] <elukey>	 interesting! --^ 
[10:11:36] <jinxer-wm>	 (ErrorBudgetBurn) firing: <no value>   - https://alerts.wikimedia.org/?q=alertname%3DErrorBudgetBurn
[10:24:11] <isaranto>	 aha, so we do have alerts by default! seems like budget is burning for articlequality.
[10:25:13] <isaranto>	 it is the latency budget. I think we need to revisit these values per model based on the data that we have. lets talk about it on monday!
[11:41:12] <elukey>	 everything is still experimental, I wasn't aware of those alerts, we can probably don't bother for the moment..
[11:41:40] <elukey>	 the truth is that the 5 seconds latency SLO is not realistic for revscoring models
[11:41:46] <elukey>	 (with the current settings)
[11:58:11] <wikibugs>	 (03PS8) 10AikoChou: revert-risk: add batch_model.py and USE_BATCHER env var [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/977135 (https://phabricator.wikimedia.org/T348536)
[12:13:02] <wikibugs>	 (03PS9) 10AikoChou: revert-risk: add batch_model.py and USE_BATCHER env var [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/977135 (https://phabricator.wikimedia.org/T348536)
[12:15:57] <wikibugs>	 (03CR) 10AikoChou: [C: 03+2] "Thanks for the review :)" [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/977135 (https://phabricator.wikimedia.org/T348536) (owner: 10AikoChou)
[12:20:58] <wikibugs>	 (03Merged) 10jenkins-bot: revert-risk: add batch_model.py and USE_BATCHER env var [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/977135 (https://phabricator.wikimedia.org/T348536) (owner: 10AikoChou)
[14:11:36] <jinxer-wm>	 (ErrorBudgetBurn) firing: <no value>   - https://alerts.wikimedia.org/?q=alertname%3DErrorBudgetBurn
[18:01:21] <jinxer-wm>	 (ErrorBudgetBurn) resolved: <no value>   - https://alerts.wikimedia.org/?q=alertname%3DErrorBudgetBurn