[09:31:52] <jbond>	 perl in python what could go wrong :P https://github.com/amad00r/perl-subroutine-wrapper/
[09:35:37] <volans>	 lol, run run run
[13:23:17] <TheresNoTime>	 bloody shellbox again?
[13:27:35] <cdanis>	 shellbox is not the issue
[13:31:07] <TheresNoTime>	 o.o
[13:39:22] <_joe_>	 shellbox is just a fallout of other issues
[16:52:34] <Krinkle>	 Amir1: marostegui: fyi - resourceloader's "write to core module_deps on GET requests" is now migrated to MainStash on all wikis. Added an increase to writes and reads at https://grafana.wikimedia.org/d/000000278/mysql-aggregated?orgId=1&var-site=eqiad&var-group=core&var-shard=x2&var-role=All&from=now-3h&to=now
[19:48:37] <RhinosF1>	 FYI; the status page is saying it's having issues getting some metrics
[20:28:09] <jynus>	 Krinkle: increases like https://grafana.wikimedia.org/goto/UEvtS_enz?orgId=1 ?
[20:29:49] <Krinkle>	 jynus: hm.. that's.. not good.
[20:29:59] <Krinkle>	 the db1152 eqiad replica seems unaffected.
[20:30:14] <Krinkle>	 do they have different replag modes? e.g. one rbr and one sbr?
[20:30:20] <Krinkle>	 I
[20:30:30] <Krinkle>	 I'm also seeing surprisingly reads and connections on the x2 replicas
[20:30:42] <jynus>	 my guess is the 3000 miles in between may have something to do with it...
[20:30:51] <Krinkle>	 whereas we only ever use the primary of x2, the replicas should are standby's only.
[20:31:27] <Krinkle>	 why would the latency cause more than a constant lag? afaik this would suggest it's taking more time for codfw to apply the changes than eqiad.
[20:31:31] <Krinkle>	 if it's going 10-20s lagging