|
2016-09-19
§
|
| 14:40 |
<chasemp> |
testing nfs export performance on labstore1004/1005 cluster |
[production] |
| 14:35 |
<yurik> |
depl graphoid https://gerrit.wikimedia.org/r/#/c/311374/ |
[production] |
| 14:28 |
<moritzm> |
uploaded apache 2.4.10-10+deb8u7+wmf1 for jessie-wikimedia to carbon |
[production] |
| 14:21 |
<elukey> |
adding aqs1004 to live traffic - aqs.svc.eqiad.wmnet - T144497 |
[production] |
| 14:10 |
<moritzm> |
reimaging mw1246-mw1248 to jessie |
[production] |
| 14:10 |
<hashar> |
European SWAT is complete. |
[production] |
| 14:05 |
<zeljkof> |
EU SWAT finished |
[production] |
| 14:05 |
<zfilipin@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: [[gerrit:311327|Add WT namespace alias to NS_PROJECT in mywiktionary (T140998)]] (duration: 00m 47s) |
[production] |
| 14:01 |
<hashar@tin> |
Synchronized php-1.28.0-wmf.19/extensions/Graph: Fixed wikiraw: protocol bug T146010 (duration: 00m 47s) |
[production] |
| 14:00 |
<hashar@tin> |
Synchronized php-1.28.0-wmf.18/extensions/Graph: Fixed wikiraw: protocol bug T146010 (duration: 00m 48s) |
[production] |
| 13:58 |
<zfilipin@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: [[gerrit:309823|Enable WikidataPageBanner on itwikiwoyage (T145328)]] (duration: 00m 48s) |
[production] |
| 13:55 |
<hashar> |
Europe SWAT extended as we still have some patches to process |
[production] |
| 13:47 |
<zfilipin@tin> |
Synchronized wmf-config/throttle.php: SWAT: [[gerrit:311086|Throttling rule for RCL (T145838)]] [[gerrit:311087|[throttle] Allow the same number accounts]] [[gerrit:311088|Throttle for RCL]] (duration: 00m 47s) |
[production] |
| 13:18 |
<hashar@tin> |
Synchronized php-1.28.0-wmf.19/includes/api/ApiQueryBacklinksprop.php: API: Force straight join for prop=linkshere|transcludedin|fileusage T145079 (duration: 00m 47s) |
[production] |
| 13:18 |
<hashar@tin> |
Synchronized php-1.28.0-wmf.18/includes/api/ApiQueryBacklinksprop.php: API: Force straight join for prop=linkshere|transcludedin|fileusage T145079 (duration: 00m 50s) |
[production] |
| 12:59 |
<moritzm> |
installing wget updates from jessie 8.6 point update |
[production] |
| 12:51 |
<elukey> |
adding mw1191 back to serving traffic after reimage |
[production] |
| 11:43 |
<mobrovac> |
restbase cassandra truncating local_group_wikipedia_T_feed_aggregated.data |
[production] |
| 11:32 |
<jynus> |
rebooting again db1061 for upgrade |
[production] |
| 11:13 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Temporarily depool db1062 and repool db1034, in order to be able to ALTER a large table. T141951 (duration: 00m 48s) |
[production] |
| 10:49 |
<moritzm> |
reimaging mw1249, mw1250, mw1258 to jessie |
[production] |
| 10:23 |
<jynus> |
powercycle db1061, unresponsive since ~1am |
[production] |
| 09:20 |
<moritzm> |
invalidated squid cache on carbon |
[production] |
| 08:49 |
<akosiaris> |
increase /var/lib/puppet to 50GB on puppetmaster1002, puppetmaster2001, puppetmaster2002 |
[production] |
| 08:48 |
<addshore@tin> |
Synchronized wmf-config/CommonSettings.php: {{gerrit|311118}} NOOP Some inline comments added (duration: 00m 58s) |
[production] |
| 08:04 |
<marostegui> |
renaming tables in S1, S4 and S4 in eqiad before dropping them T54924 |
[production] |
| 07:50 |
<elukey> |
reimaging mw1191.eqiad.wmnet to jessie |
[production] |
| 07:49 |
<moritzm> |
installing updates for file/libmagic from jessie 8.6 point update |
[production] |
| 07:42 |
<moritzm> |
reimaging mw1255-mw1257 to jessie |
[production] |
| 02:28 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Mon Sep 19 02:28:46 UTC 2016 (duration 5m 4s) |
[production] |
| 02:23 |
<mwdeploy@tin> |
scap sync-l10n completed (1.28.0-wmf.18) (duration: 10m 39s) |
[production] |
|
2016-09-18
§
|
| 20:37 |
<bblack> |
restart upload backend: cp3036 |
[production] |
| 20:22 |
<bblack> |
restart upload backend: cp3039 |
[production] |
| 19:58 |
<bblack> |
restart upload backend: cp1074 (stats indicate LRU_Fail imminent) |
[production] |
| 19:28 |
<bblack> |
restart upload backend: cp1064 (already in LRU_Fail, caught early) |
[production] |
| 19:28 |
<bblack> |
restart up |
[production] |
| 18:06 |
<bblack> |
restart upload varnish backend: cp1050 (already in LRU_Fail) |
[production] |
| 17:58 |
<bblack> |
restart upload varnish backend: cp2008 |
[production] |
| 17:42 |
<bblack> |
restart upload varnish backend: cp1071 |
[production] |
| 17:32 |
<bblack> |
restart upload varnish backend: cp2020 |
[production] |
| 17:06 |
<bblack> |
restart upload varnish backend: cp2026 |
[production] |
| 16:35 |
<bblack> |
restarting upload varnish backend: cp2011 |
[production] |
| 15:43 |
<bblack> |
restarting upload varnish backend: cp2017 |
[production] |
| 15:13 |
<bblack> |
restarting upload varnish backend: cp2005 |
[production] |
| 14:52 |
<bblack> |
restarting upload varnish backend: cp1049 |
[production] |
| 14:42 |
<bblack> |
restarting upload varnish backend: cp2022 |
[production] |
| 14:17 |
<bblack> |
restarting varnish backend on cp1073 (503 LRU_Fail pattern, has been up a few days...) |
[production] |
| 13:29 |
<bblack> |
disabling puppet on cp1074, to experiment with vhtcpd regex filter |
[production] |
| 11:17 |
<ema> |
repooling varnish-be in codfw |
[production] |
| 10:59 |
<ema> |
varnish-backend restart on cp3037 |
[production] |