|
2018-01-11
ยง
|
| 14:25 |
<zeljkof> |
EU SWAT finished |
[production] |
| 14:17 |
<jynus> |
upgrade and restart db2029 |
[production] |
| 14:16 |
<zfilipin@tin> |
Synchronized wmf-config/InitialiseSettings.php: SWAT: [[gerrit:403584|Create extendedconfirmed for kowiki (T184675)]] (duration: 01m 23s) |
[production] |
| 14:13 |
<akosiaris> |
set migration_downtime to 2000ms for seaborgium |
[production] |
| 14:01 |
<moritzm> |
reboot hafnium for kernel security update |
[production] |
| 14:00 |
<moritzm> |
reboot tungsten for kernel security update |
[production] |
| 13:58 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Increase db1099:3318 weight (duration: 01m 15s) |
[production] |
| 13:56 |
<jynus> |
perform master switchover of s7 codfw |
[production] |
| 13:42 |
<moritzm> |
rebooting ores2* for kernel security update |
[production] |
| 13:34 |
<jynus> |
upgrade and restart db2077 |
[production] |
| 13:34 |
<moritzm> |
rebooting bast2001 for kernel security update |
[production] |
| 13:31 |
<moritzm> |
migrating instances off ganeti1001 for subsequent reboot for kernel security update |
[production] |
| 13:27 |
<moritzm> |
failover the ganeti master in eqiad to ganeti1004 |
[production] |
| 12:39 |
<volans> |
Icinga failover back to einsteinium completed - T170353 |
[production] |
| 12:38 |
<moritzm> |
rearmed keyholder on naos |
[production] |
| 12:36 |
<moritzm> |
migrating instances off ganeti1007 for subsequent reboot for kernel security update |
[production] |
| 12:34 |
<moritzm> |
rebooting naos for kernel security update |
[production] |
| 12:28 |
<volans> |
Start Icinga failover back to einsteinium - T170353 |
[production] |
| 12:15 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Repool db1099:3318 with low weight (duration: 01m 44s) |
[production] |
| 12:07 |
<marostegui> |
Stop replication in sync db1089 db1099:3311 - T162807 |
[production] |
| 12:03 |
<moritzm> |
migrating instances off ganeti1006 for subsequent reboot for kernel security update |
[production] |
| 11:33 |
<moritzm> |
migrating instances off ganeti1005 for subsequent reboot for kernel security update |
[production] |
| 11:14 |
<moritzm> |
migrating instances off ganeti1004 for subsequent reboot for kernel security update |
[production] |
| 11:07 |
<moritzm> |
reboot remaining job runners in eqiad for kernel security update (along with update to HHVM 3.18.6) |
[production] |
| 11:02 |
<akosiaris> |
upload cg3_1.0.0~r12254-1+wmf1_amd64 to apt.wikimedia.org/jessie-wikimedia/main |
[production] |
| 11:02 |
<moritzm> |
migrating instances off ganeti1003 for subsequent reboot for kernel security update |
[production] |
| 10:56 |
<akosiaris> |
upload apertium_3.4.2~r68466-3+wmf1_amd64to apt.wikimedia.org/jessie-wikimedia/main T181464 |
[production] |
| 10:54 |
<akosiaris> |
set kvm:migration_downtime to 30ms for both eqiad/codfw ganeti clusters. Then set migration_downtime 30000 for nitrogen/nihal |
[production] |
| 10:52 |
<moritzm> |
rearmed keyholder on tin |
[production] |
| 10:47 |
<moritzm> |
rebooting tin for kernel security update |
[production] |
| 10:43 |
<marostegui> |
Upgrade and restart db1099:3311 and db1099:3318 |
[production] |
| 10:41 |
<jynus> |
upgrade and restart db2068 |
[production] |
| 10:31 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Restore db1110 original weight (duration: 01m 04s) |
[production] |
| 10:27 |
<moritzm> |
rolling reboot of sca/zotero clusters for kernel security update |
[production] |
| 10:23 |
<jynus> |
upgrade and restart db2061 |
[production] |
| 10:20 |
<akosiaris> |
upload hfst_3.13.0~r3461-1+wmf1_amd64 to apt.wikimedia.org/jessie-wikimedia/main T181463 |
[production] |
| 10:14 |
<moritzm> |
migrating instances off ganeti1002 for subsequent reboot for kernel security update |
[production] |
| 10:07 |
<jynus> |
upgrade and restart db2054 |
[production] |
| 10:06 |
<moritzm> |
rebooting rhenium for kernel security update |
[production] |
| 10:00 |
<elukey> |
reboot analytics1059-61 for kernel updates |
[production] |
| 10:00 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Increase db1110 weight (duration: 01m 06s) |
[production] |
| 09:41 |
<moritzm> |
reboot bast4002 for kernel security update |
[production] |
| 09:34 |
<elukey> |
reboot analytics1055->1058 for kernel updates |
[production] |
| 09:32 |
<godog> |
cleanup ores metrics older than 30d - T169969 |
[production] |
| 09:31 |
<marostegui@tin> |
Synchronized wmf-config/db-eqiad.php: Repool db1110 with low weight - T174569 (duration: 01m 08s) |
[production] |
| 09:24 |
<gehel> |
relforge reboot completed |
[production] |
| 09:08 |
<gehel> |
reboot of relforge* for kernel upgrade |
[production] |
| 09:04 |
<elukey> |
reboot analytics1051->1054 for kernel updates |
[production] |
| 09:00 |
<gehel> |
logstash rolling restart completed |
[production] |
| 08:57 |
<moritzm> |
reboot remaining mediawiki app servers in eqiad for kernel security update (along with update to HHVM 3.18.6) |
[production] |