Project

General

Profile

Edit History

Wiki » Planning » Jewel »

Rbd journal » History » Version 2

Jason Dillaman, 07/01/2015 07:59 PM

1 1 Josh Durgin 
h1. RBD journalling
2 





    3
    
    
    
*Summary*





    4
    
    
    
This is the next step towards disaster recovery for rbd. The idea is to record all writes (data and metadata changes) to a journal of rados objects, preserving a consistent point-in-time stream that can be mirrored to other sites.





    5
    
    
    





    6
    
    
    
*Owners*





    7
    
    
    
Jason Dillaman (Red Hat)





    8
    
    
    





    9
    
    
    
*Interested Parties*





    10
    
    
    
Josh Durgin (Red Hat)





    11
    
    
    





    12
    
    
    
*Current Status*





    13
    
    
    
A new feature bit is added for enabling journalling for an image, and a general journaling mechanism is almost ready.





    14
    
    
    





    15
    
    
    
*Detailed Description*





    16
    
    
    
See http://comments.gmane.org/gmane.comp.file-systems.ceph.devel/25331





    17
    2
    Jason Dillaman
    





    18
    
    
    
*Tracker*





    19
    
    
    
See http://tracker.ceph.com/issues/11286





    20
    1
    Josh Durgin
    





    21
    
    
    
Updates since then: active sets of objects are switched out wholesale once any current object becomes full, so that replay is bounded to an active set of objects as a maximum necessary amount of data to read at once.