|
2016-05-09
§
|
| 11:32 |
<moritzm> |
rolling restart of ocg for openssl update |
[production] |
| 11:27 |
<hashar> |
restarting Jenkins |
[production] |
| 11:17 |
<gehel> |
restarting elasticsearch server elastic1022.eqiad.wmnet (T110236), includes JDK upgrade |
[production] |
| 11:12 |
<moritzm> |
restarting archiva on titanium for java update |
[production] |
| 11:02 |
<moritzm> |
restarting gitblit for java update |
[production] |
| 10:54 |
<gehel> |
restarting elasticsearch server elastic1021.eqiad.wmnet (T110236), includes JDK upgrade |
[production] |
| 10:28 |
<jynus> |
general decommission of db1058 (puppet, salt, etc.) |
[production] |
| 10:21 |
<elukey> |
restarted eventlogging on eventlogging1001 for security upgrades |
[production] |
| 09:56 |
<elukey> |
memcached restarted on mc1009, now running with slab_reassign,maxconns_fast,hash_algorithm=murmur3,slab_automove,lru_crawler,lru_maintainer (T129963, performance experiment) |
[production] |
| 09:45 |
<jynus@tin> |
Synchronized wmf-config/db-eqiad.php: Increase db1070 weight after repooling (duration: 00m 38s) |
[production] |
| 09:27 |
<gehel> |
restarting elasticsearch server elastic1020.eqiad.wmnet (T110236), includes JDK upgrade |
[production] |
| 09:15 |
<godog> |
bootstrap restbase2007-a T132976 |
[production] |
| 08:18 |
<gehel> |
restarting elasticsearch server elastic1019.eqiad.wmnet (T110236) |
[production] |
| 08:16 |
<jynus@tin> |
Synchronized wmf-config/db-eqiad.php: Repool db1070 with low weight, weight increases, retire db1058 (duration: 00m 30s) |
[production] |
| 08:13 |
<jynus@tin> |
Synchronized wmf-config/db-codfw.php: Retire db1058 server (duration: 00m 39s) |
[production] |
| 07:38 |
<gehel> |
restarting elasticsearch server elastic1018.eqiad.wmnet (T110236) |
[production] |
| 06:48 |
<jynus> |
powercycling pc2006 (crashed) |
[production] |
| 06:11 |
<gehel> |
restarting elasticsearch server elastic1017.eqiad.wmnet (T110236) |
[production] |
| 02:51 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Mon May 9 02:51:58 UTC 2016 (duration 9m 18s) |
[production] |
| 02:42 |
<mwdeploy@tin> |
sync-l10n completed (1.27.0-wmf.23) (duration: 08m 40s) |
[production] |
| 02:24 |
<mwdeploy@tin> |
sync-l10n completed (1.27.0-wmf.22) (duration: 09m 53s) |
[production] |
|
2016-05-07
§
|
| 20:28 |
<SMalyshev> |
deploying updated Blazegraph version for WDQS to mitigate deadlock issue |
[production] |
| 20:13 |
<SMalyshev> |
restarted blazegraph on wdqs1001 and wdqs1002 |
[production] |
| 14:38 |
<jynus> |
inplace precise upgrade to trusty on db1069 before labs explodes |
[production] |
| 12:32 |
<hoo> |
Restarted blazegraph on wdqs1002 (Unresponsive, even locally: java.io.IOException: Too many open files) T134238 |
[production] |
| 11:55 |
<ori@tin> |
Synchronized php-1.27.0-wmf.22/includes/api/ApiStashEdit.php: If56084466: Make stashEditFromPreview() call setCacheTime() (duration: 00m 33s) |
[production] |
| 02:54 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Sat May 7 02:54:32 UTC 2016 (duration 9m 14s) |
[production] |
| 02:45 |
<mwdeploy@tin> |
sync-l10n completed (1.27.0-wmf.23) (duration: 05m 38s) |
[production] |
| 02:24 |
<mwdeploy@tin> |
sync-l10n completed (1.27.0-wmf.22) (duration: 09m 34s) |
[production] |
| 01:01 |
<ori@tin> |
Synchronized php-1.27.0-wmf.22/includes/api/ApiStashEdit.php: If56084466: Bump PRESUME_FRESH_TTL_SEC to improve hit rate and avoid link queries (duration: 00m 34s) |
[production] |
|
2016-05-06
§
|
| 22:37 |
<krenair@tin> |
Synchronized wmf-config/LabsServices.php: labs-only change: https://gerrit.wikimedia.org/r/#/c/287294/ (duration: 00m 33s) |
[production] |
| 22:37 |
<krenair@tin> |
Synchronized wmf-config/InitialiseSettings-labs.php: labs-only change: https://gerrit.wikimedia.org/r/#/c/287294/ (duration: 00m 45s) |
[production] |
| 19:56 |
<chasemp> |
launching some test query traffic against labs DNS to test new settings |
[production] |
| 14:56 |
<dcausse@tin> |
Synchronized wmf-config/LabsServices.php: Set analytics kafka broker info for labs deployment-prep (duration: 00m 33s) |
[production] |
| 14:46 |
<moritzm> |
restarting exim on MX servers to pick up openssl update |
[production] |
| 14:45 |
<gehel> |
restarting elasticsearch server elastic1014.eqiad.wmnet (T110236) |
[production] |
| 14:35 |
<demon@tin> |
Synchronized php-1.27.0-wmf.22/extensions/CentralAuth: Backporting T134246 (duration: 00m 38s) |
[production] |
| 13:53 |
<gehel> |
restarting elasticsearch server elastic1013.eqiad.wmnet (T110236) |
[production] |
| 13:26 |
<jynus> |
reimaging db1070 |
[production] |
| 13:06 |
<jynus@tin> |
Synchronized wmf-config/db-eqiad.php: Depool db1070 for maintenance (duration: 00m 29s) |
[production] |
| 12:40 |
<moritzm> |
restarted hhvm on mw1226 (hhvm-dump-debug output available) |
[production] |
| 12:28 |
<mobrovac> |
restbase rolling restart in eqiad for openssl update |
[production] |
| 11:52 |
<moritzm> |
rolling restart of restbase in codfw for openssl update |
[production] |
| 11:47 |
<elukey> |
restarting aqs on aqs100[123] for security upgrades. |
[production] |
| 11:15 |
<moritzm> |
restarting slapd on dubnium to pick up openssl update |
[production] |