801-850 of 10000 results (26ms)
2020-10-21 §
08:38 <root@cumin1001> START - Cookbook sre.ganeti.makevm [production]
08:38 <root@cumin1001> END (FAIL) - Cookbook sre.ganeti.makevm (exit_code=99) [production]
08:38 <root@cumin1001> START - Cookbook sre.ganeti.makevm [production]
08:33 <godog> swift codfw-prod: bump object weight for ms-be2057 - T261633 [production]
08:10 <XioNoX> Upgrade Routinator 3000 to 0.8.0 on rpki1001 - T266001 [production]
08:09 <XioNoX> add Routinator 3000 0.8.0 to apt - T266001 [production]
07:58 <elukey> update analytics-in4 filter on cr1/cr2-eqiad for https://gerrit.wikimedia.org/r/635319 [production]
04:35 <ryankemper> re-enabled icinga notifications on all wdqs hosts now that `wdqs-updater` is healthy [production]
2020-10-20 §
22:15 <James_F> Zuul: [mediawiki/extensions/MediaSearch] Install CI for this new prod repo T265939 [releng]
22:14 <James_F> Zuul: [mediawiki/extensions/IPInfo] Disable phan for now [releng]
22:10 <dwisehaupt> frmon2001 upgraded to buster with grafana 7.2.1 [production]
21:19 <razzi@cumin1001> END (PASS) - Cookbook sre.ganeti.makevm (exit_code=0) [production]
21:18 <cdanis> ✔️ cdanis@mw2252.codfw.wmnet ~ 🕠🍺 sudo depool [production]
20:59 <mforns> Deploying refinery with refinery-deploy-to-hdfs (for 0.0.137) [analytics]
20:57 <mforns@deploy1001> Finished deploy [analytics/refinery@e4d16f0] (thin): Regular analytics weekly train THIN [analytics/refinery@e4d16f08a96b6f65447fcdc6c9e8945724a89f54] (duration: 00m 08s) [production]
20:56 <mforns@deploy1001> Started deploy [analytics/refinery@e4d16f0] (thin): Regular analytics weekly train THIN [analytics/refinery@e4d16f08a96b6f65447fcdc6c9e8945724a89f54] [production]
20:39 <cdanis> doing some manual testing on mw2221, depooled and puppet disabled [production]
20:33 <mforns@deploy1001> Finished deploy [analytics/refinery@e4d16f0]: Regular analytics weekly train [analytics/refinery@e4d16f08a96b6f65447fcdc6c9e8945724a89f54] (duration: 08m 10s) [production]
20:31 <ryankemper> [Temporarily] disabled notifications for all wdqs hosts while we figure out how to unstick the updater process. Impact is that new updates will be delayed, but queries will still keep serving as normal, so fixing this is a priority but note that there's no availability outage [production]
20:29 <dzahn@cumin1001> END (PASS) - Cookbook sre.hosts.decommission (exit_code=0) [production]
20:25 <mforns@deploy1001> Started deploy [analytics/refinery@e4d16f0]: Regular analytics weekly train [analytics/refinery@e4d16f08a96b6f65447fcdc6c9e8945724a89f54] [production]
20:24 <mforns> Deploying refinery with scap for v0.0.137 [analytics]
20:19 <dzahn@cumin1001> START - Cookbook sre.hosts.decommission [production]
20:18 <dzahn@cumin1001> END (PASS) - Cookbook sre.hosts.decommission (exit_code=0) [production]
20:06 <dzahn@cumin1001> START - Cookbook sre.hosts.decommission [production]
20:00 <mforns> Deployed refinery-source v0.0.137 [analytics]
19:59 <dzahn@cumin1001> END (PASS) - Cookbook sre.hosts.decommission (exit_code=0) [production]
19:47 <dzahn@cumin1001> START - Cookbook sre.hosts.decommission [production]
19:47 <dzahn@cumin1001> END (FAIL) - Cookbook sre.hosts.decommission (exit_code=1) [production]
19:47 <dzahn@cumin1001> START - Cookbook sre.hosts.decommission [production]
19:45 <dzahn@cumin1001> conftool action : set/pooled=yes; selector: dc=codfw,cluster=parsoid,service=canary [production]
19:24 <razzi@cumin1001> START - Cookbook sre.ganeti.makevm [production]
18:58 <andrew@cumin1001> END (PASS) - Cookbook sre.hosts.downtime (exit_code=0) [production]
18:56 <andrew@cumin1001> START - Cookbook sre.hosts.downtime [production]
18:36 <bstorm> brought up mariadb and replication on clouddb1002 T263677 [clouddb-services]
17:48 <effie> depooling mw2328 - T266052 [production]
17:37 <andrew@cumin1001> END (PASS) - Cookbook sre.hosts.downtime (exit_code=0) [production]
17:35 <andrew@cumin1001> START - Cookbook sre.hosts.downtime [production]
17:14 <bstorm> shutting down clouddb1003 T263677 [clouddb-services]
17:13 <bstorm> stopping postgresql on clouddb1003 T263677 [clouddb-services]
17:08 <bstorm> poweroff clouddb1002 T263677 [clouddb-services]
17:08 <bstorm> stopping mariadb on clouddb1002 T263677 [clouddb-services]
17:07 <bstorm> shut down replication on clouddb1002 (now with task) T263677 [clouddb-services]
17:05 <bstorm> shut down replication on clouddb1002 [clouddb-services]
16:11 <bstorm> restarted mariadb on quarry-db-01 so it pointed to the right data directory [quarry]
16:00 <andrewbogott> rebooting quarry-web-01; lots of cruft in /tmp [quarry]
15:56 <andrewbogott> restarting nginx on quarry-web-01 [quarry]
15:54 <ebernhardson@deploy1001> Finished deploy [wikimedia/discovery/analytics@629e8bc]: search satisfaction: remove unused y/m/d cli args (duration: 01m 31s) [production]
15:52 <ebernhardson@deploy1001> Started deploy [wikimedia/discovery/analytics@629e8bc]: search satisfaction: remove unused y/m/d cli args [production]
15:47 <arturo> changing DNS recursor ACLs (https://gerrit.wikimedia.org/r/c/operations/puppet/+/635314) this can be reverted any time if it causes problems (T261724) [admin]