Workload deployment with real-time consideration of global network congestion
View Patent ↗In one embodiment, a system includes a switch controller configured to communicate with a plurality of network devices in a network. The switch controller includes a processor and logic integrated with and/or executable by the processor. The logic is configured to determine a throughput associated with a workload in the network and select an optimum location for the workload in the network based on the throughput associated with the workload. In another embodiment, a computer program product includes a computer readable storage medium having program code embodied therewith. The embodied program code is readable/executable by a processor to cause the processor to determine a throughput associated a workload in a network. The embodied program code is also readable/executable by the processor to cause the processor to select an optimum location for the workload in the network based on the throughput associated with the workload.
1. A system, comprising:
a switch controller configured to communicate with a plurality of network devices in a network, the switch controller comprising a processor and logic integrated with and/or executable by the processor, the logic being configured to:
determine a throughput associated with a workload in the network; and
select an optimum location for the workload in the network based on the throughput associated with the workload and based on determining one or more most frequent communication partners for the workload in the network; and
instantiate the workload on the selected optimum location.
2. The system as recited in claim 1 , wherein the logic configured to determine the throughput associated with the workload in the network determines the throughput in response to a request to instantiate the workload.
3. The system as recited in claim 1 , wherein the logic configured to determine the throughput associated with the workload in the network determines the throughput in response to a request to move the workload in the network.
4. The system as recited in claim 1 , wherein the logic configured to select the optimum location for the workload in the network based on the throughput associated with the workload is configured to:
determine a plurality of possible locations for instantiation of the workload;
determine a plurality of possible paths between each possible instantiation location and the one or more most frequent communication partners; and
determine which of the plurality of possible paths are capable of handling the throughput associated with the workload.
5. The system as recited in claim 4 , wherein the logic is further configured to determine a latency associated with the workload, wherein the logic configured to determine which of the plurality of possible paths are capable of handling the throughput associated with the workload is further configured to determine which of the plurality of possible paths are capable of providing the latency associated with the workload, and wherein the logic configured to select the optimum location for the workload is further configured to select the optimum location based further on the latency associated with the workload in addition to the throughput associated with the workload and the one or more most frequent communication partners for the workload in the network.
6. The system as recited in claim 1 , wherein the logic configured to select the optimum location for the workload based on the throughput associated with the workload is further configured to:
determine a possible instantiation location which has one or more shortest paths from a plurality of possible paths that are capable of handling the throughput; and
select the possible instantiation location associated with the one or more shortest paths to be the optimum location.
7. The system as recited in claim 1 , wherein the logic is further configured to receive statistics from a plurality of ports in the network describing at least throughput associated with the plurality of ports in the network.
8. The system as recited in claim 7 , wherein the statistics further describe a latency of the plurality of ports in the network.
9. The system as recited in claim 7 , wherein the throughput is one of: a current throughput or an average throughput.
10. A computer program product comprising a computer readable storage device having program code embodied therewith, the embodied program code read/executed by a processor to cause the processor to:
determine a throughput associated a workload in a network;
select an optimum location for the workload in the network based on the throughput associated with the workload and based on determining one or more most frequent communication partners for the workload in the network; and
instantiate the workload on the selected optimum location.
11. The computer program product as recited in claim 10 , wherein the program code read/executed by the processor to select the optimum location for the workload in the network based on the throughput associated with the workload is further readable/executable by the processor to:
determine a plurality of possible locations for instantiation of the workload;
determine a plurality of possible paths between each possible instantiation location and the one or more most frequent communication partners; and
determine which of the plurality of possible paths are capable of handling the throughput associated with the workload.
12. The computer program product as recited in claim 11 , wherein the program code is further
read/executed by the processor to determine a latency associated with the workload, wherein the program code read/executed by the processor to determine which of the plurality of possible paths are capable of handling the throughput associated with the workload is further read/executed by the processor to determine which of the plurality of possible paths are capable of providing the latency associated with the workload, and wherein the program code read/executed by the processor to select the optimum location for the workload in the network comprises program code read/executed by the processor to select the optimum location based further on the latency associated with the workload in addition to the throughput associated with the workload and the determining one or more most frequent communication partners for the workload in the network.
13. The computer program product as recited in claim 10 , wherein the program code read/executed by the processor to select the optimum location for the workload based on the throughput associated with the workload is further
read/executed by the processor to:
determine a possible instantiation location which has one or more shortest paths from a plurality of possible paths that are capable of handling the throughput; and
select the possible instantiation location associated with the one or more shortest paths to be the optimum location.
14. The computer program product as recited in claim 10 , wherein the program code read/executed by the processor is further read/executed by the processor to receive statistics from a plurality of ports in the network describing at least throughput associated with the plurality of ports in the network.
15. The computer program product as recited in claim 14 , wherein the statistics further describe a latency of the plurality of ports in the network.
16. The computer program product as recited in claim 12 , wherein the throughput is one of: a current throughput or an average throughput.
17. A method comprising:
a switch controller determining a throughput associated with a workload in a network; and
selecting an optimum location for the workload in the network based on the throughput associated with workload and based on determining one or more most frequent communication partners for the workload in the network; and
instantiating the workload on the selected optimum location.
18. The method as recited in claim 17 , wherein the selecting the optimum location for the workload in the network based on the throughput associated with the workload comprises:
determining a possible instantiation location which has one or more shortest paths from a plurality of possible paths that are capable of handling the throughput; and
selecting the possible instantiation location associated with the one or more shortest paths to be the optimum location.
19. The method as recited in claim 17 , wherein the selecting the optimum location for the workload in the network based on the throughput associated with the workload comprises:
determining a plurality of possible locations for instantiation of the workload;
determining a plurality of possible paths between each possible instantiation location and the one or more most frequent communication partners; and
determining which of the plurality of possible paths are capable of handling the throughput associated with the workload.
20. The method as recited in claim 19 , further comprising determining a latency associated with the workload, wherein the determining which of the plurality of possible paths are capable of handling the throughput associated with the workload comprises determining which of the plurality of possible paths are capable of providing the latency associated with the workload, and wherein the selecting the optimum location for the workload is based further on the latency associated with the workload in addition to the throughput associated with the workload and the one or more most frequent communication partners for the workload in the network.
21. The method as recited in claim 17 , further comprising receiving statistics from a plurality of ports in the network describing at least throughput associated with the plurality of ports in the network.
22. The method as recited in claim 21 , wherein the statistics further describe a latency of the plurality of ports in the network, and wherein the throughput is one of: a current throughput or an average throughput.