2012-05-17
§
|
20:34 |
<maplebed> |
deployed change to swift and mediawiki for MW to write thumbnails to swift instead of rewrite.py with aaron |
[production] |
20:32 |
<maplebed> |
deployed parallel thumbnail purging for test, test2, and mediawiki with aaron |
[production] |
20:25 |
<aaron> |
synchronized wmf-config/swift.php 'Enabled thumb copy hook for testwikis and mw.org' |
[production] |
20:14 |
<binasher> |
completed securepoll_votes.vote_ip and all ipv6 schema migration |
[production] |
20:10 |
<aaron> |
synchronized wmf-config/CommonSettings.php |
[production] |
20:09 |
<aaron> |
synchronized wmf-config/swift.php |
[production] |
20:03 |
<aaron> |
synchronized wmf-config/swift.php 'Enabling new purge hook on testwikis again.' |
[production] |
20:03 |
<binasher> |
running securepoll_votes.vote_ip schema migration on s1 |
[production] |
20:01 |
<binasher> |
running securepoll_votes.vote_ip schema migration on all s2 dbs |
[production] |
19:19 |
<binasher> |
running securepoll_votes.vote_ip schema migration on all s4 + s3 dbs |
[production] |
19:17 |
<binasher> |
running securepoll_votes.vote_ip schema migration on all s5 dbs |
[production] |
19:16 |
<binasher> |
running securepoll_votes.vote_ip schema migration on all s6 dbs |
[production] |
19:02 |
<binasher> |
running securepoll_votes.vote_ip schema migration on all s7 dbs |
[production] |
18:49 |
<binasher> |
syncing cluster23 tables from es1002 to es1004 |
[production] |
18:46 |
<binasher> |
stopped replication on es1002 |
[production] |
18:44 |
<notpeter> |
restarting puppet on brewster |
[production] |
18:39 |
<catrope> |
synchronizing Wikimedia installation... : ArticleFeedbackv5 updates |
[production] |
18:13 |
<aaron> |
synchronized wmf-config/swift.php |
[production] |
18:08 |
<aaron> |
synchronized php-1.20wmf3/includes/filerepo 'deployed 103efda39dd57bc22898bd0e69932982c1cfd588' |
[production] |
18:00 |
<Jeff_Green> |
shutting down grosley for disk and RAM upgrades |
[production] |
17:42 |
<notpeter> |
temporarily turning off puppet on brewster for preseed hackz |
[production] |
17:20 |
<maplebed> |
flushing the mobile cache post-deploy |
[production] |
17:17 |
<maplebed> |
deploying config change to mobile - more zero IP addresses. gerrit [[rev:7867|r7867]] |
[production] |
15:31 |
<dzahn> |
synchronized php/cache/interwiki.cdb 'Updating interwiki cache' |
[production] |
15:30 |
<mutante> |
sync-common-file interwiki.cdb |
[production] |
15:30 |
<mutante> |
creating fresh interwiki.cdb from dumpInterwiki.php |
[production] |
15:30 |
<Jeff_Green> |
adding DNS records to wikimedia.org for RT #2960 |
[production] |
14:22 |
<mutante> |
adding gerrit project analytics/udplog parent analytics |
[production] |
13:44 |
<cmjohnson1> |
shutting down bellin for troubleshooting |
[production] |
09:04 |
<hashar> |
Site outage was due to our custom wfLogXFF() which uses wfErrorLog(). $wmfUdp2logDest not being global there, caused exception to be shown. |
[production] |
08:59 |
<hashar> |
Broken the cluster by having an invalid global set |
[production] |
08:58 |
<hashar> |
synchronized wmf-config/CommonSettings.php |
[production] |
08:47 |
<hashar> |
synchronizing Wikimedia installation... : |
[production] |
08:44 |
<hashar> |
running scap to apply https://gerrit.wikimedia.org/r/7702 |
[production] |
08:41 |
<hashar> |
Deploying https://gerrit.wikimedia.org/r/7702 which abstract out the udp2log destination |
[production] |
08:15 |
<hashar> |
WMFLabs seems to have recovered now |
[production] |
06:50 |
<hashar> |
WMFLabs dieing out, I/O latency raised constantly over the last 2 hours and eventually lead to situation where system (via ssh) is not usable anymore |
[production] |
03:41 |
<asher> |
synchronized wmf-config/db.php 'returning db12 and db46' |
[production] |
02:48 |
<LocalisationUpdate> |
completed (1.20wmf2) at Thu May 17 02:48:02 UTC 2012 |
[production] |
02:22 |
<LocalisationUpdate> |
completed (1.20wmf3) at Thu May 17 02:22:02 UTC 2012 |
[production] |
02:18 |
<reedy> |
synchronized wmf-config/CommonSettings.php 'Enable SpecialCite everywhere' |
[production] |
01:40 |
<Tim> |
on cp1004: reverted after TIME_WAIT client connections reached 38k with no sign of a plateau |
[production] |
01:37 |
<Tim> |
on cp1004: trying tcp_tw_reuse=1 instead of tcp_tw_recycle |
[production] |
01:00 |
<Tim> |
reverted after client-side TIME_WAIT connections rose rapidly from 367 to 9000 |
[production] |
00:59 |
<Tim> |
experimentally setting net.ipv4.tcp_tw_recycle=0 on cp1004 |
[production] |