|
2016-08-15
§
|
| 19:39 |
<urandom> |
T140008: Starting major compaction (WP parsoid html, split output) on restbase1007-a.eqiad.wmnet |
[production] |
| 19:27 |
<urandom> |
T140008: Staring user-defined compaction (10 tables, highest droppable tombstones), restbase2001-b.codfw.wmnet |
[production] |
| 18:56 |
<awight> |
roll back paymentswiki from 75e4d2509a53910e5630ca3dca5950474b587a17 to 6b1f3c278308f831a149c986d2269342f94e2a16 |
[production] |
| 18:52 |
<awight> |
update paymentswiki from 6b1f3c278308f831a149c986d2269342f94e2a16 to 75e4d2509a53910e5630ca3dca5950474b587a17 |
[production] |
| 18:13 |
<ottomata> |
starting main-eqiad Kafka upgrade to confluent 0.9, will be stopping and starting brokers on kafka1001 and kafka1002 |
[production] |
| 17:03 |
<gehel> |
deploying latest wdqs on wdqs100[12].eqiad.wmnet |
[production] |
| 16:16 |
<mobrovac> |
restbase restarting in eqiad after cassandra restarts for the openjdk upgrade |
[production] |
| 16:07 |
<urandom> |
Restarting Cassandra to apply OpenJDK 8u102 upgrade, restbase1015.eqiad.wmnet |
[production] |
| 16:00 |
<urandom> |
Restarting Cassandra to apply OpenJDK 8u102 upgrade, restbase1014.eqiad.wmnet |
[production] |
| 15:52 |
<urandom> |
Restarting Cassandra to apply OpenJDK 8u102 upgrade, restbase1013.eqiad.wmnet |
[production] |
| 15:45 |
<urandom> |
Restarting Cassandra to apply OpenJDK 8u102 upgrade, restbase1012.eqiad.wmnet |
[production] |
| 15:38 |
<urandom> |
Restarting Cassandra to apply OpenJDK 8u102 upgrade, restbase1011.eqiad.wmnet |
[production] |
| 15:30 |
<urandom> |
Restarting Cassandra to apply OpenJDK 8u102 upgrade, restbase1010.eqiad.wmnet |
[production] |
| 15:03 |
<ostriches> |
gerrit: upgrading 2.12.2 -> 2.12.3. Quick restart will happen. |
[production] |
| 14:24 |
<moritzm> |
upgrading firejail on mw* to 0.9.40 |
[production] |
| 13:59 |
<moritzm> |
upgrading mw1293 to firejail 0.9.40 |
[production] |
| 11:08 |
<moritzm> |
rolling restart of cassandra on restbase1* to pick up openjdk security update |
[production] |
| 10:54 |
<moritzm> |
uploaded gerrit 2.12.3 to apt.wikimedia.org |
[production] |
| 10:49 |
<mobrovac> |
restbase restring RB in codfw following the jdk upgrade and cassandra restarts |
[production] |
| 10:06 |
<moritzm> |
rolling restart of cassandra on restbase2* to pick up openjdk security update |
[production] |
| 07:29 |
<moritzm> |
upgrading openjdk on maps clusters (along with cassandra restart) |
[production] |
| 02:30 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Mon Aug 15 02:30:30 UTC 2016 (duration 5m 51s) |
[production] |
| 02:24 |
<mwdeploy@tin> |
scap sync-l10n completed (1.28.0-wmf.14) (duration: 11m 21s) |
[production] |
|
2016-08-13
§
|
| 20:59 |
<Krenair> |
labtestcontrol2001: restarted mysql to unbreak labtesthorizon login again. we really need to figure out why this becomes necessary |
[production] |
| 11:38 |
<reedy@tin> |
Synchronized wmf-config/CommonSettings.php: wfLoadExtension all around (duration: 00m 49s) |
[production] |
| 10:57 |
<reedy@tin> |
Synchronized wmf-config/: Simplify WikimediaMessages loading, Remove Orphaned OpenStreetMapSlippyMap config (duration: 00m 50s) |
[production] |
| 10:45 |
<reedy@tin> |
Synchronized wmf-config/: Simplify WikimediaMessages loading, Remove Orphaned OpenStreetMapSlippyMap config (duration: 00m 52s) |
[production] |
| 10:33 |
<reedy@tin> |
Synchronized wmf-config/extension-list: Fix erroneous plural (duration: 00m 50s) |
[production] |
| 09:52 |
<reedy@tin> |
Synchronized wmf-config/extension-list: Fix path to FancyCaptcha extension.json in extension-list (duration: 00m 47s) |
[production] |
| 09:46 |
<reedy@tin> |
Synchronized wmf-config/extension-list: Many more to extension.json in extension-list (duration: 00m 50s) |
[production] |
| 09:13 |
<elukey> |
extended the maximum kafka topic partition size (350GiB) to upload as well (it was only text before) |
[production] |
| 08:57 |
<elukey> |
added temporary override to Kafka topic settings to free disk space: retention.bytes=375809638400 |
[production] |
| 08:41 |
<elukey> |
restarting cassandra on aqs100[456] (non live cluster) for jvm upgrades and new settings |
[production] |
| 08:22 |
<elukey> |
added temporary override to Kafka topic settings to free disk space: retention.bytes=429496729600 |
[production] |
| 08:14 |
<elukey> |
added temporary override to Kafka topic settings to free disk space: retention.bytes=483183820800 |
[production] |
| 07:31 |
<awight> |
Removed Ingenico audit processing post-build action to immediately start a thank-you mailing job. |
[production] |
| 02:33 |
<l10nupdate@tin> |
ResourceLoader cache refresh completed at Sat Aug 13 02:33:32 UTC 2016 (duration 6m 7s) |
[production] |
| 02:27 |
<mwdeploy@tin> |
scap sync-l10n completed (1.28.0-wmf.14) (duration: 11m 28s) |
[production] |
|
2016-08-12
§
|
| 20:12 |
<halfak> |
running FLUSHALL on oresrdb1001 T142857 |
[production] |
| 20:07 |
<Amir1> |
deploying ores 2ef24f2 to all nodes T142857 |
[production] |
| 20:03 |
<mattflaschen@tin> |
Synchronized wmf-config/CommonSettings-labs.php: T68699: Enable one-year login on Beta Cluster. Scheduled for prod on Tuesday. (duration: 00m 52s) |
[production] |
| 20:03 |
<Amir1> |
deploying ores 2ef24f2 to scb2001.codfw.wmnet (canary node) T142857 |
[production] |
| 16:34 |
<chasemp> |
reboot labstore1005 to test failure mode |
[production] |
| 15:36 |
<gehel> |
reset postgresql maps slave for maps1003 |
[production] |
| 15:18 |
<yurik> |
deployed tilerator to fix krtotherian restarts on maps100* |
[production] |
| 15:13 |
<moritzm> |
upgrading openjdk on restbase-test/xenon/praseodymium/cerium) (along with cassandra restart) |
[production] |
| 14:33 |
<mobrovac> |
zotero restarted, mem usage was at 11% |
[production] |