Changeset [d5eaabd11ce551685edc6ffb19bd9012e80cd0f2] by Ville Tuulos
August 15th, 2010 @ 01:54 AM
improved fault tolerance: jobs never fail due to data
(temporary) failures. Re-use failed replicas roughly in a
round-robin manner. Closes #170, #178, #176
http://github.com/tuulos/disco/commit/d5eaabd11ce551685edc6ffb19bd9...
Committed by Ville Tuulos
- M master/src/disco.hrl
- M master/src/fair_scheduler_job.erl
- M master/src/job_coordinator.erl
Create new ticket
Create your profile
Help contribute to this project by taking a few moments to create your personal profile. Create your profile ยป
Disco is an open-source implementation of the Map-Reduce framework for distributed computing. As the original framework, Disco supports parallel computations over large data sets on unreliable cluster of computers.