8201-8250 of 10000 results (83ms)
2020-02-28 §
14:17 <gehel> rolling restart of elasticsearch/eqiad for JVM upgrade completed [production]
14:16 <gehel@cumin1001> END (PASS) - Cookbook sre.elasticsearch.rolling-restart (exit_code=0) [production]
14:15 <elukey@deploy1001> Finished deploy [analytics/refinery@2db36f4]: Fix refinery-drop-older-than script (duration: 14m 01s) [production]
14:10 <marostegui@cumin1001> dbctl commit (dc=all): 'Increase weight from 100 to 300', diff saved to https://phabricator.wikimedia.org/P10558 and previous config saved to /var/cache/conftool/dbconfig/20200228-141035-marostegui.json [production]
14:01 <elukey@deploy1001> Started deploy [analytics/refinery@2db36f4]: Fix refinery-drop-older-than script [production]
13:58 <gehel@cumin1001> START - Cookbook sre.elasticsearch.rolling-restart [production]
13:32 <marostegui> Reset idrac from db1114 [production]
12:11 <akosiaris@deploy1001> helmfile [EQIAD] Ran 'sync' command on namespace 'kube-system' for release 'calico-policy-controller' . [production]
12:06 <akosiaris@deploy1001> helmfile [CODFW] Ran 'sync' command on namespace 'kube-system' for release 'calico-policy-controller' . [production]
11:57 <akosiaris@deploy1001> helmfile [STAGING] Ran 'sync' command on namespace 'kube-system' for release 'calico-policy-controller' . [production]
11:04 <gehel@cumin1001> END (ERROR) - Cookbook sre.elasticsearch.rolling-restart (exit_code=97) [production]
10:53 <jynus> labsdb1009-12 prometheus metrics restored after 90 minutes of unscheduled unavailability [production]
10:27 <gehel@cumin1001> START - Cookbook sre.elasticsearch.rolling-restart [production]
10:15 <gehel@cumin1001> END (FAIL) - Cookbook sre.elasticsearch.rolling-restart (exit_code=99) [production]
10:13 <gehel@cumin1001> START - Cookbook sre.elasticsearch.rolling-restart [production]
10:01 <gehel@cumin1001> END (FAIL) - Cookbook sre.elasticsearch.rolling-restart (exit_code=99) [production]
09:59 <gehel@cumin1001> START - Cookbook sre.elasticsearch.rolling-restart [production]
09:59 <gehel> starting rolling restart of elasticsearch/eqiad for JVM upgrade [production]
09:36 <marostegui@cumin1001> dbctl commit (dc=all): 'Remove db1101:3318 from vslow,dump', diff saved to https://phabricator.wikimedia.org/P10555 and previous config saved to /var/cache/conftool/dbconfig/20200228-093653-marostegui.json [production]
09:26 <marostegui@cumin1001> dbctl commit (dc=all): 'Repool db1087 into vslow,dump as it was there originally', diff saved to https://phabricator.wikimedia.org/P10554 and previous config saved to /var/cache/conftool/dbconfig/20200228-092631-marostegui.json [production]
09:24 <marostegui@cumin1001> dbctl commit (dc=all): 'Repool db1087 after moving labs hosts back under it', diff saved to https://phabricator.wikimedia.org/P10553 and previous config saved to /var/cache/conftool/dbconfig/20200228-092453-marostegui.json [production]
09:21 <jynus> removed leftover labs prometheus target files from ops at prometheus1003, prometheus1004 [production]
08:44 <moritzm> installing openssh updates from buster point release [production]
08:44 <addshore> END warming wikidata term cache on db1126 for Q6-8 million T219123 (pass2 today) [production]
08:30 <moritzm> installing mariadb-10.3 update from buster point release (just client-side libs and tools, no mysqlds) [production]
08:24 <moritzm> installing cups updates from buster point release [production]
08:22 <marostegui> Stop db1087 and db2079 in sync [production]
08:22 <marostegui@cumin1001> dbctl commit (dc=all): 'Depool db1087 to move labs hosts back under it', diff saved to https://phabricator.wikimedia.org/P10551 and previous config saved to /var/cache/conftool/dbconfig/20200228-082213-marostegui.json [production]
08:12 <addshore> START warming wikidata term cache on db1126 for Q6-8 million T219123 (pass2 today) (pass1 just finished) [production]
08:05 <moritzm> installing systemd bugfix update from Buster point release [production]
07:38 <addshore> START warming wikidata term cache on db1126 for Q6-8 million T219123 (pass1 today) [production]
07:31 <moritzm> installing gnutls28 bugfix update from Buster point release [production]
06:40 <marostegui@cumin1001> dbctl commit (dc=all): 'Fully repool db1084 - T245621', diff saved to https://phabricator.wikimedia.org/P10550 and previous config saved to /var/cache/conftool/dbconfig/20200228-064037-marostegui.json [production]
06:25 <marostegui@cumin1001> dbctl commit (dc=all): '75% of original weight to db1084 - T245621', diff saved to https://phabricator.wikimedia.org/P10549 and previous config saved to /var/cache/conftool/dbconfig/20200228-062536-marostegui.json [production]
06:04 <mutante> rsyncing APT repo and firmware data from install1002 to apt2001 [production]
05:58 <mutante> apt2001 - signed puppet cert, initial run after OS install, rsyncing repo data, not in use yet [production]
01:25 <jforrester@deploy1001> Synchronized wmf-config/InitialiseSettings.php: Bonus sync for cache clearance (duration: 00m 56s) [production]
01:19 <jforrester@deploy1001> Synchronized wmf-config/InitialiseSettings.php: T196466 [wikitech] Remove the 'shell' user right from assignment and rights lists (duration: 00m 58s) [production]
01:15 <dzahn@cumin1001> END (PASS) - Cookbook sre.ganeti.makevm (exit_code=0) [production]
01:05 <James_F> Running mwscript emptyUserGroup.php --wiki=labswiki shell for T196466 [production]
2020-02-27 §
23:53 <dzahn@cumin1001> START - Cookbook sre.ganeti.makevm [production]
23:10 <jforrester@deploy1001> Synchronized wmf-config/CommonSettings.php: Stop setting wgLogos['wordmark'] based on wgMinervaCustomLogos, never set (duration: 00m 56s) [production]
23:07 <jforrester@deploy1001> Synchronized wmf-config/InitialiseSettings.php: Bonus sync for cache clearance (duration: 00m 56s) [production]
23:04 <jforrester@deploy1001> Synchronized wmf-config/InitialiseSettings.php: Merge wgMinervaCustomLogos into wgLogos, take 2 (duration: 00m 56s) [production]
23:01 <jforrester@deploy1001> Synchronized wmf-config/CommonSettings.php: Only try to set wgLogos['wordmark'] if not already done (duration: 00m 58s) [production]
22:49 <James_F> Manually `scap pull`ed on mw1349 and mw1351 as they were emitting odd errors. [production]
22:06 <milimetric@deploy1001> Finished deploy [analytics/aqs/deploy@5a67e6e]: AQS: Minor fix take 3 (duration: 07m 24s) [production]
21:59 <milimetric@deploy1001> Started deploy [analytics/aqs/deploy@5a67e6e]: AQS: Minor fix take 3 [production]
21:53 <effie> depool mw1262, suspecting it might have overloaded logstash [production]
21:51 <milimetric@deploy1001> Finished deploy [analytics/aqs/deploy@c70b338]: AQS: Minor fix take 2 (duration: 02m 59s) [production]