|
2014-10-13
§
|
| 22:17 |
<akosiaris> |
ran update-rc.d -f puppetmaster remove on palladium/strontium |
[production] |
| 21:47 |
<akosiaris> |
restarting apache on palladium, strontium |
[production] |
| 20:20 |
<_joe_> |
load test done. HHVM is awesome |
[production] |
| 19:51 |
<_joe_> |
load test on HHVM starting |
[production] |
| 19:13 |
<oblivian> |
Synchronized wmf-config/CommonSettings.php: Serving 5% of anons with HHVM (duration: 00m 12s) |
[production] |
| 17:12 |
<oblivian> |
Synchronized wmf-config/CommonSettings.php: Serving 2% of anons with HHVM (duration: 00m 06s) |
[production] |
| 16:19 |
<_joe_> |
restarting gitlbit, stuck in GC probably |
[production] |
| 14:30 |
<_joe_> |
rolling restart of the ocg cluster |
[production] |
| 13:10 |
<godog> |
enable container sync on wikibooks originals as test |
[production] |
| 11:01 |
<hoo> |
Synchronized wmf-config/InitialiseSettings.php: Add edh-www.adw.uni-heidelberg.de to the wgCopyUploadsDomains whitelist (duration: 00m 08s) |
[production] |
| 10:30 |
<godog> |
enable container sync as a test on wiktionary*-local-public |
[production] |
| 09:49 |
<godog> |
test enable container sync on wikibooks-it-local-thumb |
[production] |
| 08:24 |
<godog> |
stopping swift on ms-be1013, out of disk space on / |
[production] |
| 03:33 |
<LocalisationUpdate> |
ResourceLoader cache refresh completed at Mon Oct 13 03:33:51 UTC 2014 (duration 33m 50s) |
[production] |
| 02:37 |
<springle> |
Synchronized wmf-config/db-eqiad.php: s1 api traffic prefer db1065 and db1066 (duration: 00m 07s) |
[production] |
| 02:28 |
<LocalisationUpdate> |
completed (1.25wmf3) at 2014-10-13 02:28:12+00:00 |
[production] |
| 02:16 |
<LocalisationUpdate> |
completed (1.25wmf2) at 2014-10-13 02:16:03+00:00 |
[production] |
| 02:10 |
<springle> |
Synchronized wmf-config/db-eqiad.php: repool db1062, warm up (duration: 00m 07s) |
[production] |
| 01:59 |
<springle> |
Synchronized wmf-config/db-eqiad.php: s4 api traffic prefer db1059 (duration: 00m 08s) |
[production] |
|
2014-10-11
§
|
| 23:39 |
<Reedy> |
killed both logstash events on logstash100[23]. Started logstash again after |
[production] |
| 23:33 |
<Reedy> |
killed both logstash events on logstash1001. Started logstash again after |
[production] |
| 23:23 |
<Reedy> |
Started logstash on logstash1001 |
[production] |
| 23:21 |
<bd808> |
logstash not showing any udp2log events after 2014-10-10T01:42:22.000Z |
[production] |
| 16:09 |
<hoo> |
Synchronized php-1.25wmf3/extensions/CentralAuth/: Deploying forgotten backport from Thursday: SpecialCentralAutoLogin: Fix getting files after file layout change (duration: 00m 08s) |
[production] |
| 06:01 |
<bblack> |
put ms-fe.svc.codfw.wmnet into downtime for the next two days, because I'm tired of getting paged about it :p |
[production] |
| 03:35 |
<LocalisationUpdate> |
ResourceLoader cache refresh completed at Sat Oct 11 03:35:00 UTC 2014 (duration 34m 59s) |
[production] |
| 02:29 |
<LocalisationUpdate> |
completed (1.25wmf3) at 2014-10-11 02:29:32+00:00 |
[production] |
| 02:17 |
<LocalisationUpdate> |
completed (1.25wmf2) at 2014-10-11 02:17:18+00:00 |
[production] |
|
2014-10-10
§
|
| 19:41 |
<Coren> |
mw1026 rebuild complete (now with HHVM goodness in every bite!) |
[production] |
| 18:02 |
<Coren> |
begin reimaging of mw1026 |
[production] |
| 17:32 |
<ejegg> |
updated civicrm from c684b07805ad75f10796fd4dbb82ece4818a7aa3 to 05e5388df34059c651223d53fb2986ac1c39a2d9 |
[production] |
| 17:17 |
<Coren> |
mw1027 rebuild complete (now with HHVM goodness in every bite!) |
[production] |
| 16:18 |
<paravoid> |
stopping swift on ms-be1013, debugging |
[production] |
| 14:07 |
<hashar> |
Disconnecting / reconnecting Jenkins/Zuul gearman as per https://bugzilla.wikimedia.org/show_bug.cgi?id=63760#c12 |
[production] |
| 13:29 |
<manybubbles> |
Synchronized wmf-config/CirrusSearch-common.php: Add configuration so cirrus can build an index to speed up regex searches (duration: 00m 04s) |
[production] |
| 11:22 |
<godog> |
rolling restart of container-server on ms-be1* |
[production] |
| 11:13 |
<godog> |
rolling restart of container-server on ms-be2* |
[production] |
| 07:12 |
<legoktm> |
running migratePass0 across all wikis |
[production] |
| 06:49 |
<_joe_> |
load testing done |
[production] |
| 06:22 |
<_joe_> |
doing some load testing on HHVM (api) |
[production] |
| 04:38 |
<LocalisationUpdate> |
ResourceLoader cache refresh completed at Fri Oct 10 04:38:38 UTC 2014 (duration 38m 37s) |
[production] |
| 04:22 |
<^d> |
elasticsearch upgrade from 1.3.2 -> 1.3.4 complete for all 18 nodes. Sporadic icinga warnings about health should go away now |
[production] |
| 04:19 |
<springle> |
upgrade db1046 mariadb 10 |
[production] |