|
2016-08-31
ยง
|
| 22:02 |
<hashar> |
surge of since 31th 7:00 UTC : Retrying connection to search.svc.eqiad.wmnet |
[production] |
| 22:01 |
<urandom> |
T143226: Clearing repair status: restbase2004.codfw.wmnet |
[production] |
| 21:51 |
<urandom> |
T143226: Clearing repair status: restbase2003.codfw.wmnet |
[production] |
| 21:46 |
<urandom> |
T143226: Clearing repair status: restbase2007.codfw.wmnet |
[production] |
| 21:44 |
<urandom> |
T143226: Clearing repair status: restbase2002.codfw.wmnet |
[production] |
| 21:39 |
<urandom> |
T143226: Starting restbase2001-{b,c}.codfw.wmnet |
[production] |
| 21:38 |
<urandom> |
T143226: Stopping restbase2001-{a,b} to clear tables marked repaired |
[production] |
| 21:27 |
<urandom> |
T143226: Stopping restbase2001-a.codfw.wmnet to clear tables marked repaired |
[production] |
| 19:59 |
<hashar> |
group1 to 1.28.0-wmf.17 done. There is a couple explicit commit of implicit transactions for Wikidata T144433 T144434 not much of a worry |
[production] |
| 19:50 |
<apergos> |
restarted udp2log-mw on fluorine again after deployment of https://gerrit.wikimedia.org/r/#/c/307812/ |
[production] |
| 19:46 |
<hashar@tin> |
rebuilt wikiversions.php and synchronized wikiversions files: group1 wikis to 1.28.0-wmf.17 |
[production] |
| 19:15 |
<apergos> |
stopped/started udp2log-mw on fluorine |
[production] |
| 18:54 |
<gehel> |
shutting down elasticsearch on elastic1028 to prepare moving server - T143685 |
[production] |
| 18:52 |
<Pchelolo> |
RESTBase deploy fa1a5aab |
[production] |
| 18:47 |
<Pchelolo> |
RESTBase deploy fa1a5aab canary on restbase1007 |
[production] |
| 18:34 |
<Pchelolo> |
RESTBase deploy fa1a5aab to staging |
[production] |
| 18:22 |
<ebernhardson@tin> |
Synchronized php-1.28.0-wmf.16/extensions/WikimediaEvents/modules/ext.wikimediaEvents.searchSatisfaction.js: Enable CirrusSearch BM25 AB test (duration: 00m 47s) |
[production] |
| 18:17 |
<ebernhardson@tin> |
Synchronized php-1.28.0-wmf.17/extensions/WikimediaEvents/modules/ext.wikimediaEvents.searchSatisfaction.js: Enable CirrusSearch BM25 AB test (duration: 00m 50s) |
[production] |
| 17:41 |
<mobrovac> |
change-prop deploying bf221599c |
[production] |
| 14:49 |
<mobrovac> |
parsoid first scap3 deploy to wtp20xx |
[production] |
| 14:40 |
<godog> |
reenable puppet on wtf* post-merge of scap3 conversion |
[production] |
| 14:39 |
<elukey> |
the previous entry was related to apache2 |
[production] |
| 14:38 |
<elukey> |
upgrading the remaining codfw mw* to 2.4.10-10+deb8u6+wmf2 |
[production] |
| 14:38 |
<mobrovac> |
parsoid first scap3 deploy to wtp2001 only |
[production] |
| 14:25 |
<godog> |
stopping puppet on wtp* prior to merging https://gerrit.wikimedia.org/r/#/c/304470/ |
[production] |
| 14:19 |
<bblack> |
packages updates for cp* (new kernel, new nginx, misc updates) |
[production] |
| 13:59 |
<bblack> |
uploaded nginx 1.11.3-1+wmf2 for jessie-wikimedia to carbon (ssl curve variable support) |
[production] |
| 13:58 |
<jynus> |
running alter table on db1047 enwiki.categorylinks to mitigate lag issues |
[production] |
| 13:52 |
<elukey> |
upgrading the codfw jessie appservers to 2.4.10-10+deb8u6+wmf2 |
[production] |
| 13:40 |
<chasemp> |
restart rabbitmq on labcontrol1001 |
[production] |
| 13:36 |
<bblack> |
repooling ulsfo traffic |
[production] |
| 13:25 |
<moritzm> |
installing libarchive security updates on jessie |
[production] |
| 13:13 |
<moritzm> |
reimaging mw2212-mw2215 to jessie |
[production] |
| 11:39 |
<godog> |
swift eqiad-prod: set weight for ms-be1021 sd[h-n] to 0 - T139767 |
[production] |
| 11:10 |
<gehel> |
restarting elasticsearch104[456] to take new rack configuration into account - T143685 |
[production] |
| 10:32 |
<akosiaris> |
starting a gradual deployment of wikidiff2 across the mw* fleet. T140443 |
[production] |
| 09:53 |
<mobrovac> |
change-prop deploying e999f517 |
[production] |
| 09:51 |
<elukey> |
restarting cassandra on aqs100[123] to verify performances after daemon restart |
[production] |
| 09:42 |
<moritzm> |
reimaging mw2108-mw2111 to jessie |
[production] |
| 08:24 |
<akosiaris> |
drained ulsfo of traffic, it seems to be unstable currently |
[production] |
| 07:10 |
<moritzm> |
removed cached files on stat1001 (/var/www/limn-public-data/caching) after checking with joal, disk space on root partition was depleted |
[production] |
| 07:07 |
<jynus> |
removed db1027 from our dns |
[production] |
| 07:05 |
<moritzm> |
reimaging mw2104-mw2108 to jessie |
[production] |
| 04:28 |
<ejegg> |
updated civicrm from e1feb34ff688e230cced92c46e5c2a78e2b3cffa to d067c476da074afa70297c29e3d471743c110e3a |
[production] |
| 03:48 |
<ejegg> |
rolled back civicrm to e1feb34ff688e230cced92c46e5c2a78e2b3cffa |
[production] |
| 03:43 |
<ejegg> |
updated civicrm from e1feb34ff688e230cced92c46e5c2a78e2b3cffa to 8895f0e8ac9ad03cdf11b81542c17c5a39ca5cd8 |
[production] |
| 03:17 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Wed Aug 31 03:17:37 UTC 2016 (duration 7m 13s) |
[production] |
| 03:11 |
<krinkle@tin> |
Synchronized php-1.28.0-wmf.17/resources/src/mediawiki/mediawiki.js: Ie4e7464aa811 and I90eea4bfe (duration: 00m 47s) |
[production] |
| 03:10 |
<mwdeploy@tin> |
scap sync-l10n completed (1.28.0-wmf.17) (duration: 19m 02s) |
[production] |
| 02:57 |
<ejegg> |
rolled back civicrm to e1feb34ff688e230cced92c46e5c2a78e2b3cffa |
[production] |