| 
      
        2019-10-30
      
      §
     | 
  
    
  | 11:13 | 
  <Urbanecm> | 
  EU SWAT done | 
  [production] | 
            
  | 11:12 | 
  <Urbanecm> | 
  Synchronized wmf-config/InitialiseSettings.php: SWAT: 61cb77c: Re-apply: MCR: Set testwiki to use the new MCR-only schema (T198558) (duration: 00m 59s) | 
  [production] | 
            
  | 10:07 | 
  <jynus> | 
  restarting bacula-dir, bacula-sd on backup1001 T236406 | 
  [production] | 
            
  | 09:46 | 
  <vgutierrez> | 
  Switch from nginx to ats-tls on cp4029 - T231627 | 
  [production] | 
            
  | 09:34 | 
  <vgutierrez> | 
  Switch from nginx to ats-tls on cp4028 - T231627 | 
  [production] | 
            
  | 09:25 | 
  <gehel@cumin1001> | 
  END (FAIL) - Cookbook sre.wdqs.data-reload (exit_code=99) | 
  [production] | 
            
  | 08:51 | 
  <gehel@cumin1001> | 
  START - Cookbook sre.wdqs.data-reload | 
  [production] | 
            
  | 08:45 | 
  <gehel@cumin2001> | 
  START - Cookbook sre.elasticsearch.rolling-upgrade | 
  [production] | 
            
  | 08:25 | 
  <moritzm> | 
  installing php7.0 security updates | 
  [production] | 
            
  | 07:58 | 
  <oblivian@deploy1001> | 
  helmfile [CODFW] Ran 'apply' command on namespace 'blubberoid' for release 'production' . | 
  [production] | 
            
  | 07:57 | 
  <oblivian@deploy1001> | 
  helmfile [EQIAD] Ran 'apply' command on namespace 'blubberoid' for release 'production' . | 
  [production] | 
            
  | 05:58 | 
  <vgutierrez> | 
  Rolling restart of ats-tls to get rid of leaked sockets and benefit from the lower inactivity timeout - T236458 | 
  [production] | 
            
  | 04:24 | 
  <vgutierrez> | 
  restarting ats-tls on cp4027 with half open disabled - T236458 | 
  [production] | 
            
  | 03:09 | 
  <vgutierrez> | 
  Rolling restart of prometheus-exporter-trafficserver-tls - T236458 | 
  [production] | 
            
  | 02:40 | 
  <vgutierrez> | 
  restarting ats-tls on cp3050 with half open disabled - T236458 | 
  [production] | 
            
  | 00:54 | 
  <dzahn@cumin1001> | 
  conftool action : set/pooled=yes; selector: name=wtp1025.eqiad.wmnet,service=parsoid-php | 
  [production] | 
            
  
    | 
      
        2019-10-29
      
      §
     | 
  
    
  | 23:42 | 
  <dzahn@cumin1001> | 
  conftool action : set/pooled=no; selector: name=wtp1025.eqiad.wmnet,service=parsoid-php | 
  [production] | 
            
  | 23:09 | 
  <mutante> | 
  ganeti1003 - gnt-instance remove ununpentium.wikimedia.org (T236748) | 
  [production] | 
            
  | 23:05 | 
  <Urbanecm> | 
  Evening SWAT done | 
  [production] | 
            
  | 23:05 | 
  <Urbanecm> | 
  Purge https://en.wikipedia.org/static/images/project-logos/atjwiki* (T236777) | 
  [production] | 
            
  | 23:04 | 
  <urbanecm@deploy1001> | 
  Synchronized static/images/project-logos/: SWAT: f7b9972: Revert "Milestone lobo for atjwiki" (T236777) (duration: 01m 01s) | 
  [production] | 
            
  | 22:26 | 
  <dzahn@cumin1001> | 
  END (FAIL) - Cookbook sre.hosts.decommission (exit_code=1) | 
  [production] | 
            
  | 22:24 | 
  <dzahn@cumin1001> | 
  START - Cookbook sre.hosts.decommission | 
  [production] | 
            
  | 22:17 | 
  <mutante> | 
  ununpentium - shutdown Ganeti VM - running decom script, schedule icinga downtime (T236748) | 
  [production] | 
            
  | 22:14 | 
  <mutante> | 
  rsynced data dump and config from ununpentium to moscovium in /srv/ before shutting down the old server (T180641) | 
  [production] | 
            
  | 20:43 | 
  <papaul> | 
  rebooting cp3056 for HW check | 
  [production] | 
            
  | 20:19 | 
  <Trey314159> | 
  reindexing Slovak wikis on elastic@eqiad and elastic@codfw complete (T235654) | 
  [production] | 
            
  | 19:42 | 
  <andrew@deploy1001> | 
  Finished deploy [horizon/deploy@dbe892e]: (no justification provided) (duration: 03m 59s) | 
  [production] | 
            
  | 19:38 | 
  <andrew@deploy1001> | 
  Started deploy [horizon/deploy@dbe892e]: (no justification provided) | 
  [production] | 
            
  | 19:32 | 
  <jynus> | 
  restarting bacula-fd on install1002 T236406 | 
  [production] | 
            
  | 19:31 | 
  <andrew@deploy1001> | 
  Finished deploy [horizon/deploy@bab5d37]: (no justification provided) (duration: 01m 35s) | 
  [production] | 
            
  | 19:30 | 
  <andrew@deploy1001> | 
  Started deploy [horizon/deploy@bab5d37]: (no justification provided) | 
  [production] | 
            
  | 19:25 | 
  <brennen@deploy1001> | 
  rebuilt and synchronized wikiversions files: group0 to 1.35.0-wmf.4 | 
  [production] | 
            
  | 19:14 | 
  <brennen@deploy1001> | 
  Finished scap: testwiki to php-1.35.0-wmf.4 and rebuild l10n cache (duration: 21m 11s) | 
  [production] | 
            
  | 18:54 | 
  <jynus@cumin1001> | 
  dbctl commit (dc=all): 'Revert state to before overload+maintenance', diff saved to https://phabricator.wikimedia.org/P9501 and previous config saved to /var/cache/conftool/dbconfig/20191029-185438-jynus.json | 
  [production] | 
            
  | 18:53 | 
  <brennen@deploy1001> | 
  Started scap: testwiki to php-1.35.0-wmf.4 and rebuild l10n cache | 
  [production] | 
            
  | 18:53 | 
  <Trey314159> | 
  reindexing Slovak wikis on elastic@eqiad and elastic@codfw (T235654) | 
  [production] | 
            
  | 18:50 | 
  <brennen@deploy1001> | 
  Pruned MediaWiki: 1.35.0-wmf.1 (duration: 08m 09s) | 
  [production] | 
            
  | 18:21 | 
  <ppchelko@deploy1001> | 
  Finished deploy [restbase/deploy@cf80130]: Mirror 10% of /page/html/ traffic to Parsoid/PHP T235902 (duration: 14m 13s) | 
  [production] | 
            
  | 18:07 | 
  <ppchelko@deploy1001> | 
  Started deploy [restbase/deploy@cf80130]: Mirror 10% of /page/html/ traffic to Parsoid/PHP T235902 | 
  [production] | 
            
  | 17:42 | 
  <brennen> | 
  cutting branch for 1.35.0-wmf.4 | 
  [production] | 
            
  | 17:38 | 
  <mutante> | 
  phab1001 - upgrading php7.3 packages | 
  [production] | 
            
  | 17:34 | 
  <mutante> | 
  phab2001 - upgrading PHP packages | 
  [production] | 
            
  | 17:06 | 
  <jynus@cumin1001> | 
  dbctl commit (dc=all): 'repool db1099 both instances fully to increase redundancy', diff saved to https://phabricator.wikimedia.org/P9499 and previous config saved to /var/cache/conftool/dbconfig/20191029-170648-jynus.json | 
  [production] | 
            
  | 16:56 | 
  <jynus@cumin1001> | 
  dbctl commit (dc=all): 'depool fully db1105:3311, stability/lag issues', diff saved to https://phabricator.wikimedia.org/P9498 and previous config saved to /var/cache/conftool/dbconfig/20191029-165633-jynus.json | 
  [production] | 
            
  | 16:52 | 
  <ssastry@deploy1001> | 
  Finished deploy [parsoid/deploy@aa59ce3]: Update parsoid to 089bf28d (duration: 09m 35s) | 
  [production] | 
            
  | 16:46 | 
  <jynus@cumin1001> | 
  dbctl commit (dc=all): 'pool db1106 into s1 rcs', diff saved to https://phabricator.wikimedia.org/P9497 and previous config saved to /var/cache/conftool/dbconfig/20191029-164640-jynus.json | 
  [production] | 
            
  | 16:43 | 
  <ssastry@deploy1001> | 
  Started deploy [parsoid/deploy@aa59ce3]: Update parsoid to 089bf28d | 
  [production] | 
            
  | 16:39 | 
  <gehel@cumin2001> | 
  END (ERROR) - Cookbook sre.elasticsearch.rolling-upgrade (exit_code=97) | 
  [production] | 
            
  | 16:31 | 
  <dzahn@cumin1001> | 
  conftool action : set/pooled=yes; selector: name=wtp2002.codfw.wmnet,service=parsoid-php | 
  [production] |