Feature #1251
closed
rgw: consistent caching of bucket objects (acls)
Added by Sage Weil almost 13 years ago.
Updated over 6 years ago.
Description
use notify with payload on an object to sent out cache invalidation messages to all rgw instances
This is going to be implemented using watch/notify. Each node keeps its own cache but notifies other nodes about changes. Cache should have an LRU, memory size should be configurable. The cache information for each object should contain:
- object data
- xattrs
- negative lookup
- Translation missing: en.field_position set to 709
- Translation missing: en.field_position deleted (
718)
- Translation missing: en.field_position set to 719
- Translation missing: en.field_story_points set to 8
- Translation missing: en.field_position deleted (
719)
- Translation missing: en.field_position set to 719
- Assignee set to Yehuda Sadeh
This is done, using watch/notify to sync between the different daemons. However, we should probably make a few changes so that it is more scalable.
This should include a (stress?) test that gives us some confidence it is working properly. Something like:
- start up two radosgw instances
- for N iterations
- write A or B to one of M random objects on one rgw instance
- maybe to xattr only, data only, and/or updates to both
- read same object from other instance and verify we see the correct value
- Status changed from New to 7
- Status changed from 7 to Resolved
- Project changed from Ceph to rgw
- Category deleted (
22)
- Target version deleted (
v0.32)
Bulk reassign of radosgw category to RGW project.
Also available in: Atom
PDF