|
2016-04-30
§
|
| 13:41 |
<elukey> |
disabled puppet on analytics1047 and scheduled downtime for the host, IO errors in the dmesg for /dev/sdd. Stopped also Hadoop daemons to remove it from the cluster temporarily (not sure how to do it properly, will write docs). |
[production] |
| 10:45 |
<volans> |
Reset slave on sanitarium:3311 due to corrupted relay log after skipping query for duplicate key T132416 |
[production] |
| 10:19 |
<volans> |
restarted slave on dbstore1001 skipping missing database T132837 |
[production] |
| 08:28 |
<gehel> |
restarting elasticsearch server elastic1031.eqiad.wmnet (T110236) |
[production] |
| 07:15 |
<gehel> |
restarting elasticsearch server elastic1030.eqiad.wmnet (T110236) |
[production] |
| 06:32 |
<gehel> |
restarting elasticsearch server elastic1029.eqiad.wmnet (T110236) |
[production] |
| 06:16 |
<gehel> |
restarting elasticsearch server elastic1028.eqiad.wmnet (T110236) |
[production] |
| 01:15 |
<aude> |
applied Ibd302e1 to terbium for debugging broken wikidata rdf dumps |
[production] |
|
2016-04-29
§
|
| 22:57 |
<mutante> |
DNS - forced authdns-gen-zones etc from https://phabricator.wikimedia.org/T97051#1994679 on ns0/ns1/ns2 to get new language added |
[production] |
| 20:59 |
<gehel> |
restarting elasticsearch server elastic1027.eqiad.wmnet (T110236) |
[production] |
| 19:56 |
<urandom> |
(Re)starting cleanup on restbase1009-{a,b}.eqiad.wmnet |
[production] |
| 19:56 |
<catrope@tin> |
Synchronized php-1.27.0-wmf.22/extensions/CentralNotice/: T133971 (duration: 00m 41s) |
[production] |
| 19:29 |
<gehel> |
restarting elasticsearch server elastic1026.eqiad.wmnet (T110236) |
[production] |
| 19:07 |
<gehel> |
restarting elasticsearch server elastic1025.eqiad.wmnet (T110236) |
[production] |
| 18:21 |
<jzerebecki@tin> |
Synchronized php-1.27.0-wmf.22/extensions/Wikidata/extensions/Wikibase/repo/includes/Hooks/OutputPageBeforeHTMLHookHandler.php: wmf.22 fc20c54f7915b94ec0d15ef17e207c116910623d 2 of 2 T132645 (duration: 00m 28s) |
[production] |
| 18:20 |
<jzerebecki@tin> |
Synchronized php-1.27.0-wmf.22/extensions/Wikidata/extensions/Wikibase/repo/includes/Dumpers/DumpGenerator.php: wmf.22 fc20c54f7915b94ec0d15ef17e207c116910623d 1 of 2 T133924 (duration: 00m 29s) |
[production] |
| 18:14 |
<jzerebecki@tin> |
Synchronized php-1.27.0-wmf.22/extensions/Wikidata/extensions/Wikibase/repo/includes/Hooks/OutputPageBeforeHTMLHookHandler.php: wmf.22 fc20c54f7915b94ec0d15ef17e207c116910623d 2 of 2 T132645 (duration: 00m 34s) |
[production] |
| 18:14 |
<robh> |
started all slaves via dbstore2001 this time. |
[production] |
| 18:12 |
<jzerebecki@tin> |
Synchronized php-1.27.0-wmf.22/extensions/Wikidata/extensions/Wikibase/repo/includes/Dumpers/DumpGenerator.php: wmf.22 fc20c54f7915b94ec0d15ef17e207c116910623d 1 of 2 T133924 (duration: 00m 44s) |
[production] |
| 18:07 |
<robh> |
started all slaves via dbstore2002 per jaime's request |
[production] |
| 17:45 |
<gehel> |
restarting elasticsearch server elastic1024.eqiad.wmnet (T110236) |
[production] |
| 16:56 |
<gehel> |
restarting elasticsearch server elastic1023.eqiad.wmnet (T110236) |
[production] |
| 16:22 |
<gehel> |
restarting elasticsearch server elastic1022.eqiad.wmnet (T110236) |
[production] |
| 15:29 |
<jynus@tin> |
Synchronized wmf-config/db-codfw.php: Repool db2047 and db2068. Depool db2008, db2009. Pool db2033 as the new x1 node. (duration: 00m 27s) |
[production] |
| 15:17 |
<gehel> |
restarting elasticsearch server elastic1021.eqiad.wmnet (T110236) |
[production] |
| 14:56 |
<oblivian@palladium> |
conftool action : set/pooled=yes; selector: name=mw1153.eqiad.wmnet |
[production] |
| 14:54 |
<jynus> |
moving topology of db2033 to be the new x1 master on codfw |
[production] |
| 14:40 |
<oblivian@palladium> |
conftool action : set/pooled=no; selector: name=mw1153.eqiad.wmnet |
[production] |
| 14:32 |
<gehel> |
restarting elasticsearch server elastic1020.eqiad.wmnet (T110236) |
[production] |
| 14:26 |
<hashar> |
Rebased tin:/srv/mediawiki-staging 31886c7..8e2670a . Bring in 3 changes that are solely for beta cluster. |
[production] |
| 13:54 |
<jynus> |
stopping mysql db2008 (cloning to db2033) |
[production] |
| 13:39 |
<jynus> |
reimaging db2033 |
[production] |
| 13:09 |
<gehel> |
restarting elasticsearch server elastic1019.eqiad.wmnet (T110236) |
[production] |
| 12:30 |
<gehel> |
restarting elasticsearch server elastic1018.eqiad.wmnet (T110236) |
[production] |
| 11:39 |
<elukey> |
soft reboot for mw1119 (not responsive to ssh, root login timed out on the console) |
[production] |
| 09:43 |
<gehel> |
restarting elasticsearch server elastic1017.eqiad.wmnet (T110236) |
[production] |
| 09:42 |
<gehel> |
restarting elasticsearch server elastic1016.eqiad.wmnet (T110236) |
[production] |
| 09:01 |
<jynus> |
changing live configuration of db1049 thread_pool_stall_limit to 10 to test impact on connection timout |
[production] |
| 08:20 |
<gehel> |
restarting elasticsearch server elastic1016.eqiad.wmnet (T110236) |
[production] |
| 07:57 |
<elukey> |
puppet disabled on new kafka codfw instances due to errors while starting Event Bus (hosts not in service) |
[production] |
| 07:54 |
<moritzm> |
enabled base::firewall on stat1002 |
[production] |
| 07:52 |
<gehel> |
restarting elasticsearch server elastic1015.eqiad.wmnet (T110236) |
[production] |
| 07:36 |
<godog> |
stop cleanups on restbase1014-b |
[production] |
| 06:46 |
<jynus@tin> |
Synchronized wmf-config/db-eqiad.php: Reduce normal traffic on s2 API servers (duration: 00m 27s) |
[production] |
| 06:33 |
<jynus@tin> |
Synchronized wmf-config/db-eqiad.php: Repool db1038, increase weight of new hardware slaves db107[4-8] (duration: 00m 33s) |
[production] |
| 05:42 |
<gehel> |
restarting elasticsearch server elastic1014.eqiad.wmnet (T110236) |
[production] |
| 05:41 |
<mutante> |
re: "02:29 Krenair: last deployment was slow because of snapshot1007 being offline" it's back, i don't know why, it was powered down and i just tried switching it on. that helped. the command is literally "power on" on HP |
[production] |
| 05:39 |
<mutante> |
snapshot1007 - was powered down, powering it on. (..connect to mgmt.. "damn it's a HP") |
[production] |
| 05:34 |
<mutante> |
snapshot1007 - not reachable, duration 10h |
[production] |
| 04:58 |
<gehel> |
restarting elasticsearch server elastic1013.eqiad.wmnet (T110236) |
[production] |