Cognitive scheduler for Kubernetes
Embodiments are directed to deploying a workload on the best/highest performance node. Nodes configured to accommodate a request for a workload are selected. Information is collected on each of the selected nodes and the workload. Predicted response times expected for the workload running on each of the selected nodes are determined. The workload is deployed on a node of the selected nodes, the node having a corresponding predicted response time for the workload, the workload being deployed on the node based at least in part on the corresponding predicted response time.
1. A computer-implemented method comprising:
selecting nodes configured to accommodate a request for a workload;
collecting information on each of the selected nodes and the workload;
determining predicted response times expected for the workload running on each of the selected nodes;
deploying the workload on a node of the selected nodes, the node having a corresponding predicted response time for the workload;
determining that execution of the workload on the node exceeds a threshold related to the corresponding predicted response time; and
deploying the workload to another node of the selected nodes, the another node having another corresponding predicted time closest to the corresponding predicted response time.
2. The computer-implemented method of claim 1 , wherein the corresponding predicted response time comprises a lowest predicted response time of the predicted response times.
3. The computer-implemented method of claim 1 further comprising ranking the selected nodes based on the predicted response times.
4. The computer-implemented method of claim 1 further comprising selecting the node based on the corresponding predicted response time being a lowest of.
5. The computer-implemented method of claim 1 , wherein selecting the selected nodes configured to accommodate the request for the workload comprises determining that the selected nodes have available resources to run the workload.
6. The computer-implemented method of claim 1 , wherein the workload comprises a pod, the pod comprising a container.
7. A system comprising:
a memory having computer readable instructions; and
one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
selecting nodes configured to accommodate a request for a workload;
collecting information on each of the selected nodes and the workload;
determining predicted response times expected for the workload running on each of the selected nodes; and
deploying the workload on a node of the selected nodes, the node having a corresponding predicted response time for the workload;
determining that execution of the workload on the node exceeds a threshold related to the corresponding predicted response time; and
deploying the workload to another node of the selected nodes, the another node having another corresponding predicted time closest to the corresponding predicted response time.
8. The system of claim 7 , wherein the corresponding predicted response time comprises a lowest predicted response time of the predicted response times.
9. The system of claim 7 , wherein the one or more processors perform operations further comprising ranking the selected nodes based on the predicted response times.
10. The system of claim 7 , wherein the one or more processors perform operations further comprising selecting the node based on the corresponding predicted response time being a lowest of the predicted response times.
11. The system of claim 7 , wherein selecting the selected nodes configured to accommodate the request for the workload comprises determining that the selected nodes have available resources to run the workload.
12. The system of claim 7 , wherein the workload comprises a pod, the pod comprising a container.
13. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
selecting nodes configured to accommodate a request for a workload;
collecting information on each of the selected nodes and the workload;
determining predicted response times expected for the workload running on each of the selected nodes; and
deploying the workload on a node of the selected nodes, the node having a corresponding predicted response time for the workload;
determining that execution of the workload on the node exceeds a threshold related to the corresponding predicted response time; and
deploying the workload to another node of the selected nodes, the another node having another corresponding predicted time closest to the corresponding predicted response time.
14. The computer program product of claim 13 , wherein the corresponding predicted response time comprises a lowest predicted response time of the predicted response times.
15. The computer program product of claim 13 , wherein the one or more processors perform operations further comprising ranking the selected nodes based on the predicted response times.
16. The computer program product of claim 13 , wherein the one or more processors perform operations further comprising selecting the node based on the corresponding predicted response time being a lowest of the predicted response times.
17. The computer program product of claim 13 , wherein selecting the selected nodes configured to accommodate the request for the workload comprises determining that the selected nodes have available resources to run the workload.