Erik Salter created ISPN-2431:
Summary: Default task failover policy enhancements
Issue Type: Feature Request
Components: Distributed Execution and Map/Reduce
Affects Versions: 5.2.0.Beta2
Reporter: Erik Salter
Assignee: Vladimir Blagojevic
The new failover policy enhancements behave differently than the 5.1 release. The default
is a random failover, which causes problems in my environment due to pessimistic locks
being acquired. The default policy should be "none"
Secondly, if a user specifies a key set, the failover policy should respect that. Using
pessimistic locks as an example, a valid optimization would be to submit on the local data
owner to avoid additional RPCs. A random node failover policy really doesn't fit in
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira