cfmcgrady commented on PR #2373:
URL: https://github.com/apache/celeborn/pull/2373#issuecomment-2051468165

   > a) If recomputation happens, we should fail the stage and not allow 
retries - this will prevent data loss.
   
   Totally agree! As @waitinfuture  mentioned 
[above](https://github.com/apache/celeborn/pull/2373#issuecomment-2041062688), 
and after discussing with @pan3793 offline, we can disable this feature and the 
use of `stage rerun` at the same time. I'll fix this later.
   
   > b) We should recommend enabling replication to leverage this feature - 
this minimizes the risk of data loss which would trigger recomputation.
   
   seem the replication mechanism is unable to mitigate the risk of data loss 
in this scenario?
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to