|
2016-03-02
§
|
| 21:12 |
<urandom> |
forcing a major compaction on {local_group_wikipedia_T_parsoid_dataW4ULtxs1oMqJ,local_group_wikipedia_T_parsoid_html}.data, xenon.eqiad.wmnet : T125906 |
[production] |
| 20:53 |
<bblack> |
repooling cp1048, seems unlikely to recrash (rare kernel bug) |
[production] |
| 20:45 |
<bblack> |
cp1048: depooled in confd, too |
[production] |
| 20:45 |
<bblack> |
cp1048: unresponsive console, powercycled |
[production] |
| 20:35 |
<gehel> |
elastic1011.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 20:11 |
<demon@tin> |
Finished scap: group1 to wmf.15 (duration: 08m 41s) |
[production] |
| 20:02 |
<demon@tin> |
Started scap: group1 to wmf.15 |
[production] |
| 19:21 |
<mobrovac> |
restbase rolling restart for https://gerrit.wikimedia.org/r/274456 T127387 |
[production] |
| 19:07 |
<volans> |
Data transfer completed, started MySQL and replica on es2014,es2016,es2018 [ T127330 ] |
[production] |
| 18:58 |
<gehel> |
elastic1010.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 18:44 |
<apergos> |
rolled back all changes for dataset1001, running with same old precise OS, grrrrr |
[production] |
| 18:06 |
<apergos> |
still slugging away at pxe book with these broadcom netxtreme II nics (dataset1001) |
[production] |
| 17:55 |
<volans@tin> |
Synchronized wmf-config/db-codfw.php: Repooling external storage DBs in codfw after data was copied: T127330 (duration: 01m 06s) |
[production] |
| 17:44 |
<godog> |
bounce statsdlb on graphite1001 to add 3x statsite instances T105679 |
[production] |
| 17:35 |
<jynus> |
disabling puppet on db1009 (m5-master) to test heartbeat changes |
[production] |
| 17:20 |
<gehel> |
elastic1009.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 16:54 |
<thcipriani@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: Enabling ShortURL for bnwikisource [[gerrit:273936]] (duration: 01m 04s) |
[production] |
| 16:39 |
<mobrovac> |
restbase deploy end of fb66dbf |
[production] |
| 16:34 |
<gehel> |
elastic1008.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 16:31 |
<mobrovac> |
restbase deploy continue of fb66dbf for the rest of the nodes |
[production] |
| 16:30 |
<thcipriani@tin> |
Synchronized php-1.27.0-wmf.15/extensions/ContentTranslation/includes/TranslationStorageManager.php: SWAT: Use correct timestamp for updates [[gerrit:274363]] (duration: 00m 59s) |
[production] |
| 16:28 |
<urandom> |
starting post-bootstrap (1009-b) cleanup on restbase100{5,6,9-a}.eqiad.wmnet : T95253 |
[production] |
| 16:25 |
<thcipriani@tin> |
Synchronized php-1.27.0-wmf.15/extensions/ContentTranslation/modules/widgets/translator/ext.cx.translator.js: SWAT: Translator widget: Fix js error if translator does not have recent contributions [[gerrit:274340]] (duration: 01m 05s) |
[production] |
| 16:07 |
<thcipriani@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: Do not send Referer from private wikis [[gerrit:274414]] (duration: 01m 18s) |
[production] |
| 15:53 |
<apergos> |
extending maintenance window for dataset1001 by one hour to 5 pm UTC |
[production] |
| 15:53 |
<mobrovac> |
restbase deploy start of fb66dbf on restbase1001 |
[production] |
| 15:44 |
<apergos> |
may extend the maintenance window for dataset1001 upgrade if headway can be made on PXE boot issues... 15 minutes left to decide |
[production] |
| 15:16 |
<andrewbogott> |
rebooting californium just to make sure dist-upgrade didn’t mess up grub |
[production] |
| 15:15 |
<gehel> |
elastic1007.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 15:06 |
<andrewbogott> |
running apt-get dist upgrade to upgrade californium packages to openstack Liberty |
[production] |
| 15:02 |
<mobrovac> |
restbase reverting to fa1207e95, problems spotted in logstash |
[production] |
| 14:58 |
<mobrovac> |
restbase deploy start of 5def2f8 on restbase1001 |
[production] |
| 14:32 |
<gehel> |
elastic1006.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 14:06 |
<godog> |
bootstrap restbase1010-a T128107 |
[production] |
| 14:03 |
<apergos> |
web service for dumps.wikimedia.org and download.wikimedia.org is now unavailable (upgrade of server to jessie) |
[production] |
| 13:32 |
<apergos> |
nfs service for dataset1001 disabled (impacts users of stat100{2,3} in prep for jessie upgrade |
[production] |
| 13:23 |
<gehel> |
elastic1005.eqiad.wmnet: upgrading to 1.7.5, shipping logs to logstash (T122697, T109101) |
[production] |
| 13:13 |
<_joe_> |
re-enabled puppet on scb1002, repooled scb1001 for mobileapps |
[production] |
| 13:10 |
<mobrovac> |
mobileapps re-deploying d384f1ba for T113542 |
[production] |
| 12:33 |
<bblack> |
restarted logstash on logstash1002 |
[production] |
| 12:32 |
<mobrovac> |
mobileapps stopping (again) the service on scb1001 for debugging, T113542 |
[production] |
| 12:29 |
<bblack> |
restarted logstash on logstash1001 |
[production] |
| 12:27 |
<_joe_> |
puppet disabled on both scb1001/2, depooled scb1001 for moborovac to test and config manually patched on scb1002 so that it runs with the old code correctly |
[production] |
| 12:25 |
<mobrovac> |
mobileapps rolling back to 68e38ec7, problems found in the latest deploy for T113542 |
[production] |
| 12:00 |
<mobrovac> |
mobileapps stopping the service on scb1001 for debug purposes, T113542 |
[production] |
| 11:56 |
<_joe_> |
stopped puppet on scb1002, depooled scb1001 from mobileapps |
[production] |
| 11:36 |
<mobrovac> |
mobileapps deploying d384f1ba |
[production] |
| 11:09 |
<jynus> |
profiling db1023 and db1061 for 24 hours- 1/20th of the queries slightly slower |
[production] |
| 10:42 |
<moritzm> |
restarting graphite-web on graphite1001 (for django security update) |
[production] |
| 10:42 |
<hashar> |
Zuul should no more be caught in death loop due to Depends-On on an event-schemas change. Hole filled with https://gerrit.wikimedia.org/r/#/c/274356/ T128569 |
[production] |