|
2016-01-04
§
|
| 20:50 |
<mutante> |
ms-be1011 - powercycled, was frozen |
[production] |
| 20:43 |
<mutante> |
ms-be2007 - System halted!Error: Integrated RAID |
[production] |
| 20:42 |
<mutante> |
ms-be2007 - powercycle (was status: on but all frozen) (i assume xfs like be2006 appears in SAL recently) |
[production] |
| 20:36 |
<mutante> |
mw2019 - puppet run (icinga claimed it failed but just here) |
[production] |
| 20:19 |
<mutante> |
rutherfordium - attempt to restart with gnt-instance |
[production] |
| 20:12 |
<mutante> |
rutherfordium (people.wm) was down for days per icinga - then magically fixes itself when i connect to console but before even loggin in (ganeti VM) |
[production] |
| 20:00 |
<mutante> |
mw1123 - start HHVM (was 503 and service stopped) |
[production] |
| 19:28 |
<mutante> |
elastic1006 - out of disk - gzip eqiad_index_search_slowlog.log files |
[production] |
| 17:37 |
<yurik@tin> |
yurik@tin Synchronized php-1.27.0-wmf.9/extensions/Graph/: Deployed Graph ext - gerrit 262357 (duration: 00m 33s) |
[production] |
| 02:32 |
<l10nupdate@tin> |
l10nupdate@tin ResourceLoader cache refresh completed at Mon Jan 4 02:32:10 UTC 2016 (duration 6m 53s) |
[production] |
| 02:25 |
<mwdeploy@tin> |
mwdeploy@tin sync-l10n completed (1.27.0-wmf.9) (duration: 10m 05s) |
[production] |
|
2015-12-30
§
|
| 15:05 |
<andrewbogott> |
restarting puppet on seaborgium; openldap will restart but config should not change |
[production] |
| 14:57 |
<andrewbogott> |
restarting puppet on serpens; openldap will restart but config should not change |
[production] |
| 13:14 |
<mark> |
labstore1001: apt-get install irqbalance |
[production] |
| 08:01 |
<jynus> |
setting dbstore1001 to read_only, converting ruwiki.recentchanges back to InnoDB |
[production] |
| 02:32 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Wed Dec 30 02:32:15 UTC 2015 (duration 6m 55s) |
[production] |
| 02:26 |
<gwicke> |
restbase: finished full deploy of 7db8e216 (small bug fix & a security fix) to production cluster |
[production] |
| 02:25 |
<mwdeploy@tin> |
sync-l10n completed (1.27.0-wmf.9) (duration: 09m 50s) |
[production] |
| 02:17 |
<gwicke> |
restbase: starting full deploy of 7db8e216 (small bug fix & a security fix) to production cluster |
[production] |
| 02:14 |
<gwicke> |
restbase: canary deploy of 7db8e216 (small bug fix & a security fix) to restbase1001 |
[production] |
| 00:08 |
<andrewbogott> |
restarting nova-compute on labvirt1002 |
[production] |
|
2015-12-29
§
|
| 23:56 |
<andrewbogott> |
restarting nodepool on labnodepool1001 |
[production] |
| 22:13 |
<andrewbogott> |
restarting slapd on seaborgium and serpens |
[production] |
| 22:11 |
<andrewbogott> |
disabling puppet on seaborgium and serpens |
[production] |
| 16:47 |
<ebernhardson@tin> |
Synchronized wmf-config/InitialiseSettings.php: Turn off AB test for search lang detect via accept-language (duration: 00m 29s) |
[production] |
| 16:04 |
<thcipriani@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: Disable cross-wiki upload A/B test [[gerrit:261371]] (duration: 00m 31s) |
[production] |
| 15:06 |
<apergos> |
labs salt instances salt update in progress. It's slow and tedious and automated. A few hundred instances already done, the rest are going one at a time. Only instances that use the labcontrol salt master will be affected. |
[production] |
| 13:29 |
<apergos> |
salt wm2 packages now installed on all production hosts except for: mw1041.eqiad.wmnet, technetium.eqiad.wmnet, mw1228.eqiad.wmnet, ms-be1011.eqiad.wmnet |
[production] |
| 13:08 |
<apergos> |
labcontrol*, neodymium and palladium updated to latest salt packages (wm2), rest of prod to follow |
[production] |