Ceph

Feature #2226

Updated by Sage Weil about 12 years ago

- generate a pseudorandom sequence of operations that are non-idempotent 
   - collection_move 
   - long sequences of transactions that create object, modify it, and then move into place 
   - clone 
   etc. 
 - instrument a bunch of failure injection points in filestore.    these should include 
   - before and after any random op 
   - in the midst of the "interesting" ops that set a guard (e.g., collection_move) run sequence to completion, save result 
 - tester 
   - run a sequence again while injecting osd failures at various points, replay, confirm we get same result. 
   - inject a failure 
   - restart and replay journal 
   - compare state probably want to a parallel instance (another FileStore instance put specific error injection points in another directory) that runs sequence to same position but without a failure 
   - either continue to the next failure, or start over and repeat interesting operations (like collection_move) 

   

Back