Some alerts got received of lag on enwiki:
[11:33] <icinga-wm> PROBLEM - MariaDB sustained replica lag on db1106 is CRITICAL: 2.4 ge 2 https://wikitech.wikimedia.org/wiki/MariaDB/troubleshooting%23Replication_lag https://grafana.wikimedia.org/d/000000273/mysql?orgId=1&var-server=db1106&var-port=9104
Lag issue seems to have started at around 11:20, with that host and some others lagging behing several seconds.
While I am not yet 100% sure of the cause, tendril gave us the top offender in long running queries in the last hour:
Hits Tmax Tavg Tsum Hosts Users Schemas 73 72 40 2,947 db1105:3311, db1144:3314, db1146:3314 <mw user> commonswiki, enwiki SELECT /* ClearUserWatchlistJob::run */ wl_id AS `value` FROM `watchlist` WHERE wl_user = <id> AND (wl_id <= <id2>) ORDER BY wl_id ASC LIMIT 100 /* <hash> db1146:3314 commonswiki 41s */
@Joe told me those were (possibly) jobs generated by newly deployed feature "watchlist expiry"
This means that several dozens of long running queries are probably running in the last hour, until they are killed by the query killer.