[02:11:44] FIRING: LiftWingServiceErrorRate: ... [02:11:44] LiftWing service has a high rate of non 2/3/400 error code responses - https://wikitech.wikimedia.org/wiki/Machine_Learning/LiftWing/Alerts#LiftWingServiceErrorRate - https://grafana.wikimedia.org/d/G7yj84Vnk/istio?orgId=1&refresh=30s&var-cluster=eqiad%20prometheus/k8s-mlserve&var-namespace=revscoring-editquality-damaging&var-backend=frwiki-damaging-predictor-default.%2A - https://alerts.wikimedia.org/?q=alertname%3DLiftWingServiceErrorRate [02:36:44] RESOLVED: LiftWingServiceErrorRate: ... [02:36:44] LiftWing service has a high rate of non 2/3/400 error code responses - https://wikitech.wikimedia.org/wiki/Machine_Learning/LiftWing/Alerts#LiftWingServiceErrorRate - https://grafana.wikimedia.org/d/G7yj84Vnk/istio?orgId=1&refresh=30s&var-cluster=eqiad%20prometheus/k8s-mlserve&var-namespace=revscoring-editquality-damaging&var-backend=frwiki-damaging-predictor-default.%2A - https://alerts.wikimedia.org/?q=alertname%3DLiftWingServiceErrorRate [07:25:48] Good morning ! [08:33:48] morning! [08:44:21] o/ Aiko! [08:58:11] 早上好人人! [08:58:41] as FYI I have reimaged one of the Dragonfly supernodes in codfw, now runs Bookworm [08:59:06] o/ grazie! [08:59:08] if you see anything weird during deployments lemme know (The host is part of the p2p network that we use to cache docker layers etc..) [08:59:41] 06Machine-Learning-Team, 10ORES, 07dark-mode, 10MW-1.43-notes (1.43.0-wmf.22; 2024-09-10), and 3 others: Damaging edits are not readable in contributions page in dark mode due to ORES highlight - https://phabricator.wikimedia.org/T368680#10129055 (10Ebrahim) https://gerrit.wikimedia.org/r/1050501 {F57... [09:49:23] I deployed articlequality to prod again, didnt face any issues! [09:51:25] elukey: were you trying to say "everyone"? we don't say 人人 (literally "people people"). we say 大家 (dà jiā, literally "big family") instead. I know it's confusing :D [10:01:48] aiko: I did yes! I thought 人人 was everyone! Of course 大家 [10:01:52] is better :) [10:02:01] I'll take notes :D [10:28:35] 06Machine-Learning-Team, 06Content-Transform-Team, 06Research, 13Patch-For-Review: Add Article Quality Model to LiftWing - https://phabricator.wikimedia.org/T360455#10129300 (10isarantopoulos) All changes are deployed and the model is ready for use: Simple request: ` % curl https://api.wikimedia.org/servi... [11:38:15] 06Machine-Learning-Team, 10ORES, 07dark-mode, 10MW-1.43-notes (1.43.0-wmf.22; 2024-09-10), and 3 others: Damaging edits are not readable in contributions page in dark mode due to ORES highlight - https://phabricator.wikimedia.org/T368680#10129501 (10Ebrahim) Recent comments weren't related to this issu... [11:39:02] * isaranto afk lunch! [13:31:43] running an errand be back in 30'! [14:12:55] back online! [14:26:10] 06Machine-Learning-Team, 13Patch-For-Review: Migrate the ownership of ML-Owned Docker images in production-images repo to mailing lists - https://phabricator.wikimedia.org/T374233#10130138 (10elukey) I'd also add the knative images: ` ls images/knative/serving/ activator autoscaler build controller domain... [14:27:52] 06Machine-Learning-Team, 13Patch-For-Review: Migrate the ownership of ML-Owned Docker images in production-images repo to mailing lists - https://phabricator.wikimedia.org/T374233#10130128 (10elukey) [14:37:07] 06Machine-Learning-Team, 13Patch-For-Review: Migrate the ownership of ML-Owned Docker images in production-images repo to mailing lists - https://phabricator.wikimedia.org/T374233#10130194 (10isarantopoulos) [14:47:00] 06Machine-Learning-Team, 13Patch-For-Review: Migrate the ownership of ML-Owned Docker images in production-images repo to mailing lists - https://phabricator.wikimedia.org/T374233#10130267 (10isarantopoulos) [15:22:46] Good morning all [15:23:32] Mooorning Chris o/ [15:45:50] o/ hi Chris [17:14:59] going afk folks, have a nice evening/rest of day [17:42:42] 10Lift-Wing, 06Machine-Learning-Team: Request to host the Reference Risk Model on LiftWing - https://phabricator.wikimedia.org/T372405#10131224 (10XiaoXiao-WMF) @AikoChou a side note - please make sure, when we integrate with Enterprise, we can record usage (User Agent String to the http Requests or something... [18:40:59] 06Machine-Learning-Team, 06Content-Transform-Team, 06Research, 13Patch-For-Review: Add Article Quality Model to LiftWing - https://phabricator.wikimedia.org/T360455#10131485 (10Isaac) many thanks @isarantopoulos! I think from my end, we can mark this as resolved. If anything comes up when Enterprise starts...