2017-08-01
§
|
16:17 |
<dcausse> |
restarting elastic on relforge100x servers to pick up new version of the plugins |
[production] |
15:54 |
<bblack> |
varnish backend restart on cp1072 (mailbox lag) |
[production] |
15:43 |
<bblack> |
rebooting lvs1002 |
[production] |
15:42 |
<marostegui> |
db1069: Migrate trwiktionary.page from TokuDB to InnoDB |
[production] |
15:40 |
<bblack> |
stopping pybal on lvs1002 for impending reboot |
[production] |
15:39 |
<bblack> |
stopping pybal on 1002 for impending reboot |
[production] |
15:33 |
<marostegui> |
Stop s3 on db1069 - replication stuck |
[production] |
15:17 |
<marostegui> |
Stop MySQL on db1055 for maintenance - https://phabricator.wikimedia.org/T148507 |
[production] |
14:56 |
<andrewbogott> |
rebooting labvirt1016 |
[production] |
14:46 |
<marostegui> |
Deploy InnoDB compression on s3 - db2074 for the following tables (revision, pagelinks and templatelinks) - T170662 |
[production] |
14:45 |
<ema> |
lvs1001-1003 (eqiad primaries): upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
14:28 |
<ema> |
lvs1004-1006 (eqiad secondaries): upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
14:27 |
<bblack> |
restart varnish backend on cp1049 (mailbox lag) |
[production] |
14:12 |
<bblack> |
restart varnish backend on cp1074 (mailbox lag) |
[production] |
13:53 |
<ema@neodymium> |
conftool action : set/pooled=yes; selector: name=achernar.wikimedia.org,service=pdns_recursor |
[production] |
13:26 |
<ema@neodymium> |
conftool action : set/pooled=no; selector: name=achernar.wikimedia.org,service=pdns_recursor |
[production] |
13:10 |
<hashar@tin> |
Synchronized wmf-config/InitialiseSettings.php: Enable OOjs UI EditPage on all wikis except Commons (duration: 00m 44s) |
[production] |
13:06 |
<marostegui> |
Compress s2 on db1102 - T172169 |
[production] |
12:49 |
<elukey> |
restart hive daemons on analytics1003 to pick up new jvm settings (bigger Xmx, JMX ports) |
[production] |
12:06 |
<dcausse> |
100% cpu spike on elastic1023 caused percentiles to jump for a short period of time (T169498) |
[production] |
12:04 |
<elukey> |
stop eventlogging_sync on analytics-slaves && rename all CookieBlock* tables (log db) to CookieBlock*_backup - T171883 |
[production] |
11:52 |
<marostegui> |
Stop MySQL on db2057 to copy its data to db2074 - T170662 |
[production] |
11:36 |
<marostegui@tin> |
Synchronized wmf-config/db-codfw.php: Depool db2057 - T170662 (duration: 00m 43s) |
[production] |
11:10 |
<marostegui@tin> |
Synchronized wmf-config/db-codfw.php: Repool db2065 - T170662 (duration: 00m 43s) |
[production] |
10:31 |
<hashar> |
Enabling Zuul/CI again and reenabling puppet on contint1001 |
[production] |
10:24 |
<hashar> |
contint1001 stopped puppet agent to prevent Zuul server to come back up |
[production] |
10:12 |
<hashar> |
Stopped Zuul / CI for mass mediawiki extension changes |
[production] |
08:55 |
<ema> |
lvs2001-2003 (codfw primaries): upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
08:32 |
<ema> |
lvs2004-2006 (codfw secondaries): upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
08:03 |
<ema> |
lvs3*: upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
07:40 |
<ema> |
lvs4001, lvs4002 (ulsfo primaries): upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
07:35 |
<ema> |
lvs4003, lvs4004 (ulsfo secondaries): upgrade to pybal 1.13.11 - one-packet-scheduling, instrumentation fixes. T104442, T103882 |
[production] |
07:33 |
<ema> |
pybal 1.13.11 uploaded to apt.w.o T103882 |
[production] |
06:20 |
<marostegui> |
Stop MySQL on db2065 to copy its data to db2073 - T170662 |
[production] |
06:13 |
<marostegui@tin> |
Synchronized wmf-config/db-codfw.php: Depool db2065 - T170662 (duration: 00m 43s) |
[production] |
05:21 |
<marostegui> |
Restart MySQL on labsdb1003 as it is totally stuck |
[production] |
03:50 |
<mobrovac@tin> |
Finished deploy [restbase/deploy@0d12138]: Add nl.wikinews - T171897 (duration: 07m 57s) |
[production] |
03:42 |
<mobrovac@tin> |
Started deploy [restbase/deploy@0d12138]: Add nl.wikinews - T171897 |
[production] |
02:32 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Tue Aug 1 02:32:17 UTC 2017 (duration 6m 36s) |
[production] |
02:25 |
<l10nupdate@tin> |
scap sync-l10n completed (1.30.0-wmf.11) (duration: 07m 46s) |
[production] |
2017-07-31
§
|
23:34 |
<thcipriani@tin> |
Synchronized dblists: SWAT: [[gerrit:368951|Revert "Make ptwikimedia a fishbowl wiki"]] T171501 (duration: 00m 42s) |
[production] |
23:32 |
<thcipriani@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: [[gerrit:368233|Path for enwikiquote logo]] T171810 (duration: 00m 43s) |
[production] |
23:17 |
<thcipriani@tin> |
Synchronized dblists: SWAT: [[gerrit:367892|Make ptwikimedia a fishbowl wiki]] T171501 (duration: 00m 43s) |
[production] |
23:11 |
<thcipriani@tin> |
Synchronized wmf-config/Wikibase-production.php: SWAT: [[gerrit:366488|Cleanup old BC config for JsonUnitStorage]] T171107 (duration: 00m 42s) |
[production] |
22:38 |
<mobrovac@tin> |
Finished deploy [citoid/deploy@7ad598d]: Do not wait for PubMed requests to complete - T162886 (duration: 05m 52s) |
[production] |
22:32 |
<mobrovac@tin> |
Started deploy [citoid/deploy@7ad598d]: Do not wait for PubMed requests to complete - T162886 |
[production] |
20:48 |
<mutante> |
restarting pdfrender service on sc1001 after icinga alert (T159922) |
[production] |
20:33 |
<cscott> |
Updated Parsoid to version 08114f35 (T43716, T154718, T166413) |
[production] |
20:32 |
<cscott@tin> |
Finished deploy [parsoid/deploy@c1cba48]: Updating Parsoid to 08114f35 (duration: 10m 50s) |
[production] |
20:22 |
<cscott@tin> |
Started deploy [parsoid/deploy@c1cba48]: Updating Parsoid to 08114f35 |
[production] |