Partition system resources such as network bandwidth, CPU power, and possibly even storage I/O bandwidth and real RAM in such a way as to give each user a reserved set of resources and allow all users to simultaneously maximize usage of their reserved resources without issue.
When working well, this should give similar results of benchmark tests runned anytime on given instances having the same resource limits.
For bexar, we aim at CPU partitioning only. Later all exhaustible resources should be partitioned well.
This doesn't seem to be going anywhere at the moment. I'm marking this as obsolete for now. Please let me know if there is any work actually still going on with this. Perhaps the majority of this is handled by the distributed scheduler additions? --vish
i added myself to assignee role, but i will need some help. please contact me if you like this idea.