|
2018-07-25
§
|
| 09:55 |
<marostegui@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Repool db1121 (duration: 00m 47s) |
[production] |
| 09:53 |
<godog> |
bounce grafana on krypton |
[production] |
| 09:31 |
<ema> |
upload varnish 5.1.3-1wm9 to apt.w.o (fixing POST requests w/ separate VCL) T164609 |
[production] |
| 09:20 |
<gehel> |
restarting elasticsearch cluster restart on codfw - T156137 |
[production] |
| 08:41 |
<jynus> |
stop es1014 for reimage |
[production] |
| 08:14 |
<marostegui> |
Deploy schema change on db1121 with replication, this will generate lag on labsdb hosts for s4 T144010 T51190 T199368 |
[production] |
| 08:11 |
<marostegui@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Depool db1121 (duration: 00m 47s) |
[production] |
| 08:10 |
<Amir1> |
start of ladsgroup@mwmaint1001:~$ foreachwikiindblist s4 populateChangeTagDef.php --sleep 2 (T193873) |
[production] |
| 08:05 |
<marostegui@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Repool db1097:3314 db1091 (duration: 00m 47s) |
[production] |
| 08:02 |
<gehel> |
pausing elasticsearch cluster restart on codfw - T156137 |
[production] |
| 07:58 |
<jynus@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Depool es1014 (duration: 00m 48s) |
[production] |
| 07:35 |
<gehel> |
rolling restart of elasticsearch / cirrus / codfw to disable G1 - T156137 |
[production] |
| 07:12 |
<marostegui> |
Deploy schema change on db1091 T144010 T51190 T199368 |
[production] |
| 06:53 |
<gehel> |
resetting postgres data on maps1004 after failing replication - T200228 |
[production] |
| 06:38 |
<marostegui> |
Stop replication in sync on db1091 and db1097:3314 |
[production] |
| 06:38 |
<marostegui@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Depool db1097:3314 db1091 (duration: 00m 48s) |
[production] |
| 06:33 |
<jynus> |
finished es1014 -> es1017 switch T197073 |
[production] |
| 06:27 |
<jynus> |
enabling semi-sync master on es1017, disabling it as client |
[production] |
| 06:21 |
<jynus> |
deploy es3-master dns change |
[production] |
| 06:02 |
<jynus@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Switchover es3 master eqiad from es1014 to es1017 (duration: 00m 24s) |
[production] |
| 06:01 |
<jynus> |
switchover es3 eqiad master from es1014 to es1017 |
[production] |
| 04:35 |
<tstarling@deploy1001> |
Synchronized php-1.32.0-wmf.13/includes/api/ApiMain.php: record all API requests in statsd (duration: 00m 49s) |
[production] |
| 02:43 |
<l10nupdate@deploy1001> |
ResourceLoader cache refresh completed at Wed Jul 25 02:43:05 UTC 2018 (duration 10m 19s) |
[production] |
| 02:32 |
<l10nupdate@deploy1001> |
scap sync-l10n completed (1.32.0-wmf.13) (duration: 13m 28s) |
[production] |
|
2018-07-24
§
|
| 21:59 |
<XioNoX> |
re-pooling eqsin |
[production] |
| 21:15 |
<XioNoX> |
re1 is master routing engine on cr1-eqsin, triggering a re switch |
[production] |
| 21:10 |
<XioNoX> |
starting to see recoveries from cr1-eqsin upgrade |
[production] |
| 21:06 |
<XioNoX> |
Install done, cr1-eqsin re-rebooting |
[production] |
| 21:00 |
<XioNoX> |
restarting cr1-eqsin for software upgrade |
[production] |
| 20:32 |
<XioNoX> |
depooling eqsin for cr1-eqsin software upgrade |
[production] |
| 19:09 |
<gehel> |
resetting postgres data on maps1003 after failing replication - T200228 |
[production] |
| 18:34 |
<mobrovac@deploy1001> |
Finished deploy [eventstreams/deploy@690fdad]: Wait for the client to consume the meesage being sent before consuming the next one - T199813 (duration: 02m 18s) |
[production] |
| 18:32 |
<mobrovac@deploy1001> |
Started deploy [eventstreams/deploy@690fdad]: Wait for the client to consume the meesage being sent before consuming the next one - T199813 |
[production] |
| 17:40 |
<ema> |
re-enable puppet on all cache nodes with alternate domains disabled T164609 |
[production] |
| 17:33 |
<zfilipin@deploy1001> |
rebuilt and synchronized wikiversions files: all wikis to 1.32.0-wmf.13 |
[production] |
| 17:18 |
<thcipriani> |
train window running long, services deploy delayed |
[production] |
| 17:18 |
<ema> |
restart varnish-fe on cp1068 to clear "child restarted" alert T164609 |
[production] |
| 17:17 |
<elukey> |
restart eventstreams on scb2* nodes (hopefully last time before deploying the fix) to avoid mem leaks issues during the EU night |
[production] |
| 17:06 |
<ladsgroup@deploy1001> |
Synchronized php-1.32.0-wmf.14/includes/page/PageArchive.php: [[gerrit:447636|PageArchive: Pass correct overrides to newRevisionFromArchiveRow() (T200072)]] (duration: 01m 01s) |
[production] |
| 16:58 |
<jynus> |
finishing test on es3 hosts T199224 |
[production] |
| 16:42 |
<ladsgroup@deploy1001> |
Synchronized php-1.32.0-wmf.13/includes/page/PageArchive.php: [[gerrit:447636|PageArchive: Pass correct overrides to newRevisionFromArchiveRow() (T200072)]] (duration: 01m 03s) |
[production] |
| 16:07 |
<jynus> |
test switchover from es2018 to es2017 |
[production] |
| 16:02 |
<dcausse> |
T156137: unbanning elastic1031 |
[production] |
| 15:59 |
<dcausse> |
T156137: restarting elasticsearch on elastic1031 to disable G1GC |
[production] |
| 15:55 |
<jynus> |
test switchover from es2017 to es2018 |
[production] |
| 15:46 |
<marostegui@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Repool db1103:3314 (duration: 01m 02s) |
[production] |
| 15:38 |
<jynus> |
stopping puppet on es2017, es2018; changing mysql configuration for production testing |
[production] |
| 15:29 |
<gehel> |
restart postgres on maps1001 - T200228 |
[production] |
| 14:53 |
<marostegui@deploy1001> |
Synchronized wmf-config/db-eqiad.php: Repool db1084 (duration: 01m 02s) |
[production] |
| 14:47 |
<dcausse> |
T156137: banning elastic1031 due to high load (same "getEntryAfterMiss" symptoms) |
[production] |