Method and apparatus for providing traffic re-aware slot placement
A method and apparatus of providing an RE-aware technique for placing slots based on redundancy across and within slot communication pairs. In particular, the RE-aware placement strategy takes into account the redundancy in data transfers for slot-to-slot communications and place slots to exploit redundancy in data transfers while minimizing the overall inter-rack (or inter-data center) bandwidth usage.
1. An apparatus for providing slot placement, the apparatus comprising:
a data storage; and
a processor communicatively connected to the data storage, the processor being configured to:
determine a plurality of slots to be placed within a plurality of containers;
determine a plurality of redundancy parameters based on communication redundancy between at least a portion of the plurality of slots;
determine a placement of the plurality of slots in the plurality of containers based on the plurality of redundancy parameters; and
exchange a first placed slot and a second placed slot based on a determination that inter-container-bandwidth-usage will be improved and that the exchange meets one or more inter-container bandwidth constraints.
2. The apparatus of claim 1 , wherein a plurality of the plurality of slots are virtual machines.
3. The apparatus of claim 1 , wherein a plurality of the plurality of containers are racks in a data center.
4. The apparatus of claim 1 , wherein the redundancy parameters are based on intra-comm-redundancy and inter-comm-redundancy of at least a portion of the plurality of slots.
5. The apparatus of claim 4 , wherein the redundancy parameters are based on communication patterns of at least a portion of the plurality of slots.
6. The apparatus of claim 1 , wherein the determination of the placement of the plurality of slots comprises configuring the processor to:
determine a plurality of clusters;
assign each of at least a portion of the plurality of slots to at least one of the plurality of clusters; and
assign each of at least a portion of the plurality of clusters to the at least one of the plurality of containers.
7. The apparatus of claim 6 , wherein the assignment of the portion of the plurality of slots is based on a required slot bandwidth after redundancy elimination.
8. The apparatus of claim 7 , wherein the assignment of the portion of the plurality of slots is further based on one or more slot placement constraints.
9. The apparatus of claim 6 , wherein the assignment of the portion of the plurality of clusters is based on an effective-inter-container-bandwidth-usage.
10. A system for providing slot placement, the system comprising:
a placement controller;
a plurality of agents communicatively connected to the placement controller, each of the plurality of agents configured to:
collect a plurality of redundancy measurements based on communication redundancy between at least a portion of the plurality of slots; and
send the plurality of redundancy measurements to the placement controller; and
the placement controller configured to:
receive the plurality of redundancy measurements;
determine a plurality of slots to be placed within a plurality of containers;
determine a plurality of redundancy parameters based on the plurality of redundancy measurements;
determine a placement of the plurality of slots in the plurality of containers based on the plurality of redundancy parameters; and
exchange a first placed slot and a second placed slot based on a determination that inter-container-bandwidth-usage will be improved and that the exchange meets one or more inter-container bandwidth constraints.
11. The system of claim 10 , wherein the determination of the placement of the plurality of slots comprises configuring the placement controller to:
determine a plurality of clusters;
assign each of at least a portion of the plurality of slots to at least one of the plurality of clusters; and
assign each of at least a portion of the plurality of clusters to the at least one of the plurality of containers.
12. The system of claim 11 , wherein the assignment of the portion of the plurality of slots is based on a required slot bandwidth after redundancy elimination.
13. The system of claim 12 , wherein the assignment of the portion of the plurality of slots is further based on one or more slot placement constraints.
14. The system of claim 11 , wherein the assignment of the portion of the plurality of clusters is based on an effective-inter-container-bandwidth-usage.
15. A method for providing slot placement, the method comprising:
at a processor communicatively connected to a data storage, determining a plurality of slots to be placed within a plurality of containers;
determining, by the processor in cooperation with the data storage, a plurality of redundancy parameters based on communication redundancy between at least a portion of the plurality of slots;
determining, by the processor in cooperation with the data storage, a placement of the plurality of slots in the plurality of containers based on the plurality of redundancy parameters; and
exchanging, by the processor in cooperation with the data storage, a first placed slot and a second placed slot based on a determination that inter-container-bandwidth-usage will be improved and that the exchange meets one or more inter-container bandwidth constraints.
16. The method of claim 15 , wherein the step of determining the placement of the plurality of slots comprises:
determining, by the processor in cooperation with the data storage, a plurality of clusters;
assigning, by the processor in cooperation with the data storage, each of at least a portion of the plurality of slots to at least one of the plurality of clusters; and
assigning, by the processor in cooperation with the data storage, each of at least a portion of the plurality of clusters to the at least one of the plurality of containers.
17. The method of claim 16 , wherein the step of assigning the portion of the plurality of slots is based on a required slot bandwidth after redundancy elimination.