|
2017-11-10
§
|
| 14:57 |
<urandom> |
Decommissioning Cassandra, restbase2006-a.codfw.wmnet (T179422) |
[production] |
| 14:17 |
<moritzm> |
rebooting image scalers in codfw to 4.9.51 (and to pick up OpenSSL updates) |
[production] |
| 13:10 |
<marostegui> |
truncate /var/log/nginx/error.log.1 on install1002 as it is filling up |
[production] |
| 13:09 |
<moritzm> |
powercycling mw2118, stuck after reboot |
[production] |
| 13:05 |
<ema> |
cp4021: restart varnish-be due to mbox lag |
[production] |
| 12:48 |
<moritzm> |
rebooting video scalers in codfw to 4.9.51 (and to pick up OpenSSL updates) |
[production] |
| 11:46 |
<_joe_> |
restarted all services and repooled scb1001 |
[production] |
| 11:38 |
<moritzm> |
rebooting mw2163-2199 to 4.9.51 (and to pick up OpenSSL updates) |
[production] |
| 11:32 |
<_joe_> |
stopping mobileapps as well on scb1001 |
[production] |
| 11:27 |
<moritzm> |
rebooting wtp1025 to 4.9.51 |
[production] |
| 11:22 |
<_joe_> |
stopping changeprop, celery-ores, cpjobqueue on scb1001 |
[production] |
| 11:21 |
<addshore@tin> |
Synchronized wmf-config/InitialiseSettings-labs.php: [[gerrit:390392|Disable AdvancedSearch on deployment.beta]] BETA ONLY T180201 (duration: 00m 46s) |
[production] |
| 11:15 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Remove old comment about db1080 (duration: 00m 46s) |
[production] |
| 11:06 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Restore db1055 original weight - T178359 (duration: 00m 46s) |
[production] |
| 10:59 |
<jmm@puppetmaster1001> |
conftool action : set/pooled=inactive; selector: wtp2017.codfw.wmnet |
[production] |
| 10:55 |
<_joe_> |
depooling scb1001 from all services while it becomes healthy again |
[production] |
| 10:52 |
<_joe_> |
restarting ores on scb1001, causing memory exhaustion |
[production] |
| 10:51 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Increase db1055 weight - T178359 (duration: 00m 47s) |
[production] |
| 10:49 |
<moritzm> |
powercycling wtp2017, stuck after reboot |
[production] |
| 10:24 |
<marostegui> |
Deploy schema change on db2089 - T179106 |
[production] |
| 10:11 |
<moritzm> |
rebooting Parsoid servers in codfw to 4.9.51 (and to pick up OpenSSL updates) |
[production] |
| 10:03 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Increase db1055 weight - T178359 (duration: 00m 58s) |
[production] |
| 09:54 |
<marostegui> |
Compress enwiki on db1105.s1 - T178359 |
[production] |
| 09:45 |
<moritzm> |
powercycling mw2108, stuck after reboot |
[production] |
| 09:30 |
<hashar> |
Upgrading operations-puppet-tests-docker jenkins job to stop passing docker --tty and thus have signals forwarded from 'docker run' - T176747 |
[production] |
| 09:23 |
<moritzm> |
rebooting mw2097-mw2117 to 4.9.51 (and to pick up OpenSSL updates) |
[production] |
| 09:17 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Repool db1055 with low weight - T178359 (duration: 00m 47s) |
[production] |
| 09:13 |
<moritzm> |
powercycling mw2213, stuck after reboot |
[production] |
| 08:43 |
<moritzm> |
rebooting mw2200-mw2223 to 4.9.51 (and to pick up OpenSSL updates) |
[production] |
| 07:50 |
<smalyshev@tin> |
Finished deploy [wdqs/wdqs@213f864]: (no justification provided) (duration: 00m 33s) |
[production] |
| 07:49 |
<smalyshev@tin> |
Started deploy [wdqs/wdqs@213f864]: (no justification provided) |
[production] |
| 07:27 |
<_joe_> |
restarting apache on phab1001 |
[production] |
| 07:17 |
<marostegui> |
Deploy alter table on s3.codfw master (db2018) with replication, this will generate lag on codfw - T174569 |
[production] |
| 06:50 |
<marostegui> |
Deploy alter table on s5 eqiad master (db1063) - T172207 |
[production] |
| 06:41 |
<marostegui> |
Stop MySQL on db1055 to copy its content to db1105 - T178359 |
[production] |
| 06:40 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Depool db1055 - T178359 (duration: 00m 49s) |
[production] |
| 06:39 |
<marostegui> |
Force a BBU relearn on db1046 - T166141 |
[production] |
| 01:21 |
<aaron@tin> |
Synchronized php-1.31.0-wmf.7/includes/db: Use the main stash for LBFactory "memStash" parameter (duration: 00m 47s) |
[production] |
| 01:18 |
<demon@tin> |
Synchronized docroot/search.wikimedia.org/index.php: minor cleanups, less 500s (duration: 00m 47s) |
[production] |
|
2017-11-09
§
|
| 22:28 |
<urandom> |
Decommissioning Cassandra, restbase2004-c.codfw.wmnet (T179422) |
[production] |
| 20:28 |
<demon@tin> |
Synchronized php-1.31.0-wmf.7/includes/libs/objectcache/WANObjectCache.php: less spammy error logs (duration: 00m 47s) |
[production] |
| 20:09 |
<demon@tin> |
rebuilt wikiversions.php and synchronized wikiversions files: group2 to wmf.7 |
[production] |
| 19:06 |
<ebernhardson@tin> |
Synchronized php-1.31.0-wmf.7/extensions/WikimediaEvents/modules/all/ext.wikimediaEvents.searchSatisfaction.js: SWAT: Turn off DBN sizing AB test (duration: 00m 51s) |
[production] |
| 19:00 |
<bblack> |
cp3030 - end experimentation, puppetizing back to normal config |
[production] |
| 18:46 |
<bblack> |
cp3030 - round 2 of ssl_do_wait_shutdown test |
[production] |
| 18:41 |
<arlolra> |
Updated Parsoid to 2887b5ad (T178253, T173643, T176728, T180010, T171381, T179757) |
[production] |
| 18:28 |
<arlolra@tin> |
Finished deploy [parsoid/deploy@d1c7386]: Updating Parsoid to 2887b5ad (duration: 12m 20s) |
[production] |
| 18:22 |
<bblack> |
cp3030: puppet-disabled + manual nginx ssl_do_wait_shutdown config |
[production] |
| 18:16 |
<arlolra@tin> |
Started deploy [parsoid/deploy@d1c7386]: Updating Parsoid to 2887b5ad |
[production] |
| 18:14 |
<moritzm> |
not rebooting parsoid hosts due to Services deployment window, instead rolling restart of mw2120-mw2139 for kernel update to 4.9.51 |
[production] |