|
2021-06-09
§
|
| 05:17 |
<marostegui@cumin1001> |
dbctl commit (dc=all): 'db1135 (re)pooling @ 75%: Repool db1135 after dropping an index', diff saved to https://phabricator.wikimedia.org/P16333 and previous config saved to /var/cache/conftool/dbconfig/20210609-051710-root.json |
[production] |
| 05:02 |
<marostegui@cumin1001> |
dbctl commit (dc=all): 'db1135 (re)pooling @ 50%: Repool db1135 after dropping an index', diff saved to https://phabricator.wikimedia.org/P16332 and previous config saved to /var/cache/conftool/dbconfig/20210609-050206-root.json |
[production] |
| 04:47 |
<marostegui@cumin1001> |
dbctl commit (dc=all): 'db1135 (re)pooling @ 25%: Repool db1135 after dropping an index', diff saved to https://phabricator.wikimedia.org/P16331 and previous config saved to /var/cache/conftool/dbconfig/20210609-044703-root.json |
[production] |
| 04:44 |
<marostegui@cumin1001> |
dbctl commit (dc=all): 'Depool db1135 to remove rev_page_id index T163532', diff saved to https://phabricator.wikimedia.org/P16330 and previous config saved to /var/cache/conftool/dbconfig/20210609-044428-marostegui.json |
[production] |
| 04:27 |
<ryankemper@cumin1001> |
END (PASS) - Cookbook sre.wdqs.data-transfer (exit_code=0) |
[production] |
| 03:30 |
<eileen> |
civicrm revision changed from eac772e9c9 to 31d07115a0, config revision is 931a941a5e |
[production] |
| 03:01 |
<Amir1> |
mwscript extensions/Cognate/maintenance/populateCognateSites.php --wiki=aawiktionary --site-group wiktionary (T284444) |
[production] |
| 02:58 |
<ryankemper@cumin1001> |
START - Cookbook sre.wdqs.data-transfer |
[production] |
| 02:56 |
<Amir1> |
clean up of the rest of mbox files (except arbcom) (T282303) |
[production] |
| 02:55 |
<ryankemper@cumin1001> |
END (ERROR) - Cookbook sre.wdqs.data-transfer (exit_code=97) |
[production] |
| 02:49 |
<ryankemper> |
T280382 `sudo -i cookbook sre.wdqs.data-transfer --source wdqs1010.eqiad.wmnet --dest wdqs1009.eqiad.wmnet --reason "xfer categories following reimage" --blazegraph_instance categories --without-lvs` on `ryankemper@cumin1001` tmux session `wdqs_1009` |
[production] |
| 02:49 |
<ryankemper@cumin1001> |
START - Cookbook sre.wdqs.data-transfer |
[production] |
| 02:39 |
<ryankemper> |
T280382 Re-enabled puppet on `wdqs1010` |
[production] |
| 01:20 |
<ryankemper@cumin1001> |
END (FAIL) - Cookbook sre.wdqs.data-transfer (exit_code=99) |
[production] |
| 00:37 |
<catrope@deploy1002> |
Synchronized wmf-config/InitialiseSettings.php: Config: [[gerrit:698654|Enable Wikisource OCR on select Wikisources (T283898)]] (duration: 01m 31s) |
[production] |
| 00:00 |
<ryankemper> |
T280382 `sudo -i cookbook sre.wdqs.data-transfer --source wdqs1010.eqiad.wmnet --dest wdqs1009.eqiad.wmnet --reason "transferring skolemized wikidata.jnl so we can reimage wdqs1009" --blazegraph_instance blazegraph --without-lvs` on `ryankemper@cumin1001` tmux session `wdqs_1009` |
[production] |
| 00:00 |
<ryankemper@cumin1001> |
START - Cookbook sre.wdqs.data-transfer |
[production] |
|
2021-06-08
§
|
| 22:36 |
<krinkle@deploy1002> |
Finished deploy [integration/docroot@d4c9e08]: (no justification provided) (duration: 00m 08s) |
[production] |
| 22:36 |
<krinkle@deploy1002> |
Started deploy [integration/docroot@d4c9e08]: (no justification provided) |
[production] |
| 22:21 |
<ryankemper> |
T284479 Block put back in place. We're back to expected traffic levels. We'll need a more granular mitigation in place before we can lift this block going forward. |
[production] |
| 22:15 |
<ryankemper> |
T284479 Successful puppet run on `cp3052`, proceeding to rest of `A:cp-text`: `sudo cumin -b 19 'A:cp-text' 'run-puppet-agent -q'` |
[production] |
| 22:14 |
<ryankemper> |
T284479 Merged https://gerrit.wikimedia.org/r/c/operations/puppet/+/698850, running puppet on `cp3052.esams.wmnet` |
[production] |
| 22:10 |
<ryankemper> |
T284479 Yup more than enough evidence of a strong upward spike now. Proceeding to revert |
[production] |
| 22:10 |
<ryankemper> |
T284479 Already starting to see a large upward spike in requests. Doing a quick sanity check to make sure this is out of the ordinary but I'll likely be putting the block back in place shortly |
[production] |
| 22:09 |
<ryankemper> |
T284479 Puppet run complete across all of `cp-text`. Monitoring https://grafana.wikimedia.org/d/000000455/elasticsearch-percentiles?viewPanel=47&orgId=1&from=now-1h&to=now over the next few minutes to see if we see a large spike in `full_text` and `entity_full_text` queries |
[production] |
| 22:03 |
<ryankemper> |
T284479 Successful puppet run on `cp3052`, proceeding to rest of `A:cp-text`: `sudo cumin -b 15 'A:cp-text' 'run-puppet-agent -q'` |
[production] |
| 22:01 |
<ryankemper> |
T284479 Merged https://gerrit.wikimedia.org/r/c/operations/puppet/+/698849, running puppet on `cp3052.esams.wmnet` |
[production] |
| 21:59 |
<ryankemper> |
T284479 Prior context: We put a block on a range of Google App Engine IPs yesterday to protect Cirrussearch from a bad actor; now we're going to try lifting the block and seeing if we're still getting slammed with traffic |
[production] |
| 21:44 |
<ryankemper@cumin1001> |
END (PASS) - Cookbook sre.hosts.downtime (exit_code=0) for 2:00:00 on wdqs1009.eqiad.wmnet with reason: REIMAGE |
[production] |
| 21:42 |
<ryankemper@cumin1001> |
START - Cookbook sre.hosts.downtime for 2:00:00 on wdqs1009.eqiad.wmnet with reason: REIMAGE |
[production] |
| 21:29 |
<ryankemper> |
T280382 `sudo -i wmf-auto-reimage-host -p T280382 wdqs1009.eqiad.wmnet` on `ryankemper@cumin1001` tmux session `wdqs_1009` |
[production] |
| 21:27 |
<ryankemper> |
T280382 Disabled puppet on `wdqs1010` out of abundance of caution; will re-enable after wdqs1009 is reimaged and xfer back is complete |
[production] |
| 21:12 |
<ryankemper@cumin1001> |
END (PASS) - Cookbook sre.wdqs.data-transfer (exit_code=0) |
[production] |
| 20:38 |
<bblack> |
authdns1001: update gdnsd to 3.7.0-2~wmf1 |
[production] |
| 20:18 |
<bblack> |
authdns2001: update gdnsd to 3.7.0-2~wmf1 |
[production] |
| 19:55 |
<bblack> |
dns[1235]002: update gdnsd to 3.7.0-2~wmf1 |
[production] |
| 19:53 |
<jhuneidi@deploy1002> |
rebuilt and synchronized wikiversions files: group0 wikis to 1.37.0-wmf.9 refs T281150 |
[production] |
| 19:46 |
<bblack> |
dns[1235]001: update gdnsd to 3.7.0-2~wmf1 |
[production] |
| 19:43 |
<ryankemper@cumin1001> |
START - Cookbook sre.wdqs.data-transfer |
[production] |
| 19:36 |
<ryankemper@cumin1001> |
END (ERROR) - Cookbook sre.wdqs.data-transfer (exit_code=97) |
[production] |
| 19:36 |
<ryankemper> |
T280382 Cancelling the data-transfer run to restart it; realized that the cookbook will start up the `wdqs-updater` again so will locally hack the cookbook on `cumin1001` to prevent that |
[production] |
| 19:32 |
<ladsgroup@deploy1002> |
Synchronized php-1.37.0-wmf.9/extensions/Echo/modules/nojs/mw.echo.alert.monobook.less: Backport: [[gerrit:698848|Fix MonoBook orange banner hover styles (T284496)]] (duration: 01m 08s) |
[production] |
| 19:26 |
<bblack> |
dns400[12]: update gdnsd to 3.7.0-3~wmf1 |
[production] |
| 19:25 |
<bblack> |
apt: update gdnsd package to gdnsd-3.7.0-2~wmf1 (fix systemd reload issues) |
[production] |
| 19:20 |
<ryankemper> |
T280382 `sudo -i cookbook sre.wdqs.data-transfer --source wdqs1009.eqiad.wmnet --dest wdqs1010.eqiad.wmnet --reason "transferring skolemized wikidata.jnl so we can reimage wdqs1009" --blazegraph_instance blazegraph --without-lvs` on `ryankemper@cumin1001` tmux session `wdqs_1009` |
[production] |
| 19:20 |
<ryankemper@cumin1001> |
START - Cookbook sre.wdqs.data-transfer |
[production] |
| 19:19 |
<ryankemper@cumin1001> |
END (FAIL) - Cookbook sre.wdqs.data-transfer (exit_code=99) |
[production] |
| 19:19 |
<ryankemper@cumin1001> |
START - Cookbook sre.wdqs.data-transfer |
[production] |
| 19:18 |
<ryankemper> |
T280382 `sudo systemctl stop wdqs-updater wdqs-blazegraph` on `wdqs1010` in preparation for transfer |
[production] |
| 19:08 |
<ryankemper> |
[WDQS] `ryankemper@wdqs1005:~$ sudo pool` (all caught up on lag) |
[production] |