User:Bhartshorne/swift tasks 2012-08-13
From Wikitech
< User:Bhartshorne(Difference between revisions)
Bhartshorne (Talk | contribs) |
Bhartshorne (Talk | contribs) |
||
| Line 6: | Line 6: | ||
** ms-be1003 and 1005 need re-installs, 1004 is waiting on a replacement SSD eta friday 8/17 | ** ms-be1003 and 1005 need re-installs, 1004 is waiting on a replacement SSD eta friday 8/17 | ||
* upgrade to 1.5.0 (with ganglia statsd stuff disabled) | * upgrade to 1.5.0 (with ganglia statsd stuff disabled) | ||
| − | ** test in labs | + | ** test in labs (lucid) |
| − | *** | + | *** done. tested fetching existent and nonexistent thumbs. tested with mismatched proxies and storage servers. |
| − | ** test on eqiad | + | ** test on eqiad (precise) |
* sync content | * sync content | ||
** test between eqiad-prod cluster and ??? (eiqad-test? labs? | ** test between eqiad-prod cluster and ??? (eiqad-test? labs? | ||
Revision as of 22:56, 13 August 2012
- move mediawiki reading originals to swift (aaron)
- updated squid and swift/rewrite.py to allow reads for originals (http://upload... but not thumbnails)
- squid change is acl work similar to how thumbnails got moved
- rewrite may or may not need changes to accept non-thumbnails and get to the right bucket
- finish building eqiad cluster
- ms-be1003 and 1005 need re-installs, 1004 is waiting on a replacement SSD eta friday 8/17
- upgrade to 1.5.0 (with ganglia statsd stuff disabled)
- test in labs (lucid)
- done. tested fetching existent and nonexistent thumbs. tested with mismatched proxies and storage servers.
- test on eqiad (precise)
- test in labs (lucid)
- sync content
- test between eqiad-prod cluster and ??? (eiqad-test? labs?
- enable 1.5 statsd ganglia stuff
- disable ganglia-logtailer
- disable local logging?
- update ganglia view for new metrics
- redo zones in pmtpa
- improve reaction-based documentation (instead of feature-based documentation)
- what to do when a host fails; what to do when a nagios alert triggers (for each nagios alert); etc.
- audit and replace disks across all backends
- improve dead disk detection methods, automate alerting and replacing
- document how to switch from pmtpa to eqiad
- container synchronization is an eventually consistent thing; how to synchronize the change?