[08:42:45] <elukey>	 morning folks
[08:43:08] <elukey>	 with a bit of delay, if everybody agrees I am going to deploy cp-jobqueue with the new docker image (node18+etc..)
[08:43:11] <elukey>	 https://gerrit.wikimedia.org/r/c/operations/deployment-charts/+/971114
[08:43:26] <elukey>	 only in eqiad, as done for cp as well
[08:43:43] <elukey>	 there will be an increase in cpu usage as we expect, but so far cp-eqiad worked fine
[08:48:27] <_joe_>	 +1
[08:48:45] <_joe_>	 elukey: cp-jobqueue though won't really matter much in eqiad
[08:48:47] <_joe_>	 :)
[08:48:57] <_joe_>	 oh well no, we do still generate some jobs there
[09:36:36] <wikibugs>	 10serviceops, 10Prod-Kubernetes, 10Kubernetes, 10User-jijiki: Deploy kube-state-metrics - https://phabricator.wikimedia.org/T264625 (10fgiunchedi) >>! In T264625#9327330, @kamila wrote: > With @JMeybohm's suggestion (T264625#9324445) we are at around **60k timeseries**.  Looks good to me, let's give it a t...
[09:39:50] <kostajh>	 could someone confirm please if the timezone for Kubernetes CronJobs defaults to Etc/UTC?For context, see https://gerrit.wikimedia.org/r/c/operations/deployment-charts/+/973867/6/helmfile.d/services/ipoid/values.yaml#32
[09:44:22] <jayme>	 kostajh: the nodes use UTC (like all hosts in prod do I guess). Which means k8s CronJobs will be UTC by default. Changing the TZ is not possible currently with our k8s version IITC
[09:44:24] <jayme>	 *IIRC
[09:44:33] <kostajh>	 ack, thanks.
[10:43:08] <wikibugs>	 10serviceops, 10SRE: Rebuild PHP 7.4 packages for Bullseye - https://phabricator.wikimedia.org/T350767 (10MoritzMuehlenhoff)
[11:04:19] <elukey>	 cp-jobqueue deployed, there was as expected a bump in cpu usage
[11:04:40] <elukey>	 there was already some cpu throttling going on (~1ms), now it is around ~3ms
[11:04:46] <elukey>	 in line with the cpu increase
[12:56:48] <wikibugs>	 10serviceops, 10SRE: Rebuild PHP 7.4 packages for Bullseye - https://phabricator.wikimedia.org/T350767 (10MoritzMuehlenhoff)
[13:18:54] <elukey>	 I am also going to merge https://gerrit.wikimedia.org/r/c/operations/deployment-charts/+/971225 to remove the extra threads caused by master/worker in cp
[13:46:07] <elukey>	 staging done, will wait a bit and then proceed in eqiad
[13:46:33] <elukey>	 (as expected, I see less threads)
[16:30:01] <wikibugs>	 10serviceops, 10DC-Ops, 10SRE, 10ops-codfw: Q2:rack/setup/install 4 parsoid hosts - https://phabricator.wikimedia.org/T349873 (10Jhancock.wm) We received the servers and need racking details please. @Clement_Goubert  or @Joe Thank you!
[17:02:27] <elukey>	 the reduction in num_workers has been deployed in all cp instances
[17:43:48] <wikibugs>	 10serviceops, 10Platform Team Initiatives (API Gateway): Update API gateway to newer version of Envoy - https://phabricator.wikimedia.org/T324130 (10hnowlan) 05Open→03Resolved
[17:43:59] <wikibugs>	 10serviceops, 10SRE, 10Traffic, 10envoy, 10Patch-For-Review: Upgrade Envoy to supported version - https://phabricator.wikimedia.org/T300324 (10hnowlan)
[17:48:48] <wikibugs>	 10serviceops, 10Platform Team Initiatives (API Gateway): Update API gateway to newer version of Envoy - https://phabricator.wikimedia.org/T324130 (10hnowlan) 05Resolved→03Open
[17:48:56] <wikibugs>	 10serviceops, 10SRE, 10Traffic, 10envoy, 10Patch-For-Review: Upgrade Envoy to supported version - https://phabricator.wikimedia.org/T300324 (10hnowlan)