[04:58:25] <marostegui>	 legoktm: gotcha, thanks
[04:58:46] <marostegui>	 legoktm: do you want to close the above task or leave it open?
[04:58:58] <legoktm>	 I think we need to leave it open 
[04:59:37] <legoktm>	 The current spicerack in the Git repo is broken, I just live hacked cumin1001
[04:59:58] <marostegui>	 sounds good :)
[05:00:10] <marostegui>	 not the repo breakage, but leaving the task open
[05:00:32] <legoktm>	 :p
[05:00:44] <marostegui>	 Going to give the buffer pools another go just now
[05:01:40] <legoktm>	 Cool, I was going to ask if there's any other pre-switchover steps we need to check 
[05:03:20] <marostegui>	 I am going to double check replication between codfw -> eqiad again (although stevie did a check a few days ago, it doesn't hurt!)
[08:35:01] <kormat>	 legoktm: note that while right now x2 is the exception, eventually all "core" dbs will have the same behaviour (when multi-dc finally happens, any day now, ™)
[15:06:35] <marostegui>	 removed old s5 backup sources from orchestrator as they are no longer there
[19:18:08] <wikibugs>	 10DBA, 10SRE, 10Datacenter-Switchover: When switching DCs, update pc hosts in tendril - https://phabricator.wikimedia.org/T266723 (10Legoktm) I've documented this as a manual step going forward: https://wikitech.wikimedia.org/w/index.php?title=Switch_Datacenter&type=revision&diff=1917204&oldid=1917111
[19:45:03] <wikibugs>	 10DBA, 10SRE, 10Datacenter-Switchover: switchdc should automatically downtime "Read only" checks on DB masters being switched - https://phabricator.wikimedia.org/T285803 (10Legoktm)
[20:22:09] <wikibugs>	 10DBA, 10observability, 10Datacenter-Switchover: "User 'prometheus' has exceeded the 'max_user_connections' resource" during DC switchover - https://phabricator.wikimedia.org/T285807 (10Legoktm)
[20:38:32] <wikibugs>	 10DBA, 10observability, 10Datacenter-Switchover: "User 'prometheus' has exceeded the 'max_user_connections' resource" during DC switchover - https://phabricator.wikimedia.org/T285807 (10Marostegui) 05Open→03Invalid That timestamp isn't from the DC switch, that's from two weeks ago when the host got overl...
[20:44:23] <wikibugs>	 10DBA, 10observability, 10Datacenter-Switchover: "User 'prometheus' has exceeded the 'max_user_connections' resource" during DC switchover - https://phabricator.wikimedia.org/T285807 (10Legoktm) ...I should've looked more closely, my bad. Also no idea why it ended up in the etherpad :p