2012-02-10
§
|
16:07 |
<mark> |
Rebalanced appserver load balancing by giving the new mw* pmtpa app servers weight 150 in the pybal server list |
[production] |
15:17 |
<mark> |
Turned on KeepAlive on apaches for better miss service times from eqiad |
[production] |
13:42 |
<mark> |
Configured cp1001 and cp1020 to contact backend servers directly instead of via pmtpa squids |
[production] |
12:02 |
<mark> |
Decommissioning sq38, sq46 and sq47 in squid configurator |
[production] |
11:50 |
<mark> |
Making cp1001-1005 API squids |
[production] |
05:08 |
<maplebed> |
deployed squid config to uploads to send 100% of thumbnail traffic to swift |
[production] |
02:49 |
<maplebed> |
deploying fix for & bug with swift (files with an & in the name wouldn't load properly) |
[production] |
02:18 |
<LocalisationUpdate> |
completed (1.18) at Fri Feb 10 02:18:37 UTC 2012 |
[production] |
00:22 |
<LeslieCarr> |
increased nagios max concurrent checks on spence and lowered the interval between processing them |
[production] |
00:20 |
<maplebed> |
deployed squid config to upload squids rolling thumbnails back to 75% handled by swift to test the & bug |
[production] |
2012-02-09
§
|
22:22 |
<Jeff_Green> |
adding community-analytics.wikimedia.org to DNS |
[production] |
21:36 |
<reedy> |
synchronized wmf-config/CommonSettings.php 'Increase wgCodeReviewMaxDiffPaths' |
[production] |
20:04 |
<binasher> |
started 1.19 schema migrations on seconadry db's (mwscript upgrade-1.19wmf1-1.php --secondary) |
[production] |
19:32 |
<reedy> |
synchronized wmf-config/CommonSettings.php 'Increase wgCodeReviewMaxDiffPaths' |
[production] |
17:31 |
<maplebed> |
deployed squid config to upload squids sending 100% of all thumbnail traffic to swift |
[production] |
16:31 |
<mark> |
Sending ALL non-european wikipedia traffic to eqiad text squids |
[production] |
16:17 |
<mark> |
Added Brazil traffic to eqiad text squids |
[production] |
15:49 |
<mark> |
Sending some Asian wikipedia traffic to wikipedia-lb.eqiad |
[production] |
15:13 |
<mark> |
Sending Canadian wikipedia traffic to wikipedia-lb.eqiad |
[production] |
14:27 |
<reedy> |
synchronized wmf-config/InitialiseSettings.php 'Bug 34183 - add alias redirection in ml wikisource' |
[production] |
14:23 |
<mark> |
Redirecting {wikiquote,wikisource,wikiversity,wiktionary}-lb.pmtpa traffic to .eqiad (geodns) |
[production] |
14:17 |
<reedy> |
synchronized wmf-config/InitialiseSettings.php 'Bug 34253 - Change site logo for lb.wiktionary' |
[production] |
14:11 |
<mark> |
Redirecting {foundation,wikibooks,wikinews}-lb.pmtpa traffic to .eqiad (geodns) |
[production] |
14:10 |
<hashar> |
synchronized docroot/mediawiki/xml 'update html pages for 0.1 and 0.2 schemes' |
[production] |
14:06 |
<hashar> |
synchronized docroot/mediawiki/xml/index.html 'Give a home page to our XML namespaces homepage' |
[production] |
13:52 |
<hashar> |
synchronized docroot/mediawiki/xml |
[production] |
13:45 |
<mark> |
Redirecting wikimedia-lb.pmtpa traffic to wikimedia-lb.eqiad (geodns) |
[production] |
13:28 |
<mark> |
Redirecting mediawiki-lb.pmtpa traffic to mediawiki-lb.eqiad (geodns) |
[production] |
12:49 |
<apergos> |
around 11:05 UTC, increased /proc/sys/vm/min_free_kbytes from 16259 to 262144 to check impact on network alloc issues, on dataset1001 |
[production] |
11:56 |
<mark_> |
Power cycled cp1017 |
[production] |
11:50 |
<mark_> |
Changed topology of eqiad text squids to request from pmtpa (similar to esams) |
[production] |
09:29 |
<mark_> |
Reactivated term selected-paths in policy-statement BGP_transit_in on cr2-eqiad, making path 14907 3257 1299 43821 active again |
[production] |
02:26 |
<LocalisationUpdate> |
completed (1.18) at Thu Feb 9 02:26:49 UTC 2012 |
[production] |
00:35 |
<asher> |
synchronized wmf-config/db.php 'returning db38 to s1 post schema migration testing' |
[production] |
2012-02-08
§
|
23:52 |
<asher> |
synchronized wmf-config/db.php 'returning db11' |
[production] |
23:49 |
<asher> |
synchronized wmf-config/db.php 'pulling db11' |
[production] |
22:01 |
<maplebed> |
deployed updated to upload squid.conf to send 75% of all thumbnail traffic to swift |
[production] |
17:37 |
<maplebed> |
deployed new squid config to upload to direct 50% of thumbnail traffic to swift |
[production] |
17:21 |
<apergos> |
reboot of dataset1001 for testing. |
[production] |
14:21 |
<mutante> |
srv189 - shut down again, PCI Express Error, -> RT 2413 created |
[production] |
14:15 |
<mutante> |
powercycling srv189 |
[production] |
13:09 |
<RoanKattouw> |
Batch-deleting 9,760 redirects on cswiktionary, requested by Danny B |
[production] |
02:26 |
<LocalisationUpdate> |
completed (1.18) at Wed Feb 8 02:26:55 UTC 2012 |
[production] |
2012-02-07
§
|
22:11 |
<maplebed> |
increasing traffic to swift from 12.5% to 25% |
[production] |
21:19 |
<apergos> |
reboot dataset1001, new kernel 2.6.38, should deal with kswap bug we just ran into under heavy i/o load, need to test |
[production] |
20:24 |
<mark> |
Uncommented sq63 in squid text-settings.php, please DO NOT COMMENT DOWN SQUIDS UNLESS DECOMMISSIONING THEM PERMANENTLY |
[production] |
20:19 |
<RobH> |
dns update for db59/60 mgmt |
[production] |
20:07 |
<mark> |
Added manutius's IP to the stats ACL in squid.conf |
[production] |
19:47 |
<Jeff_Green> |
email aliases adjusted for merchandise@, wikishop@ |
[production] |
19:09 |
<mark> |
Deployed torrus on server manutius, migrated DNS over |
[production] |