System and method of providing a self-optimizing reservation in space of compute resources
View Patent ↗A system and method of dynamically controlling a reservation of compute resources within a compute environment is disclosed. The method aspect of the invention comprises receiving a request from a requestor for a reservation of resources within the compute environment, reserving a first group of resources, evaluating resources within the compute environment to determine if a more efficient use of the compute environment is available and if a more efficient use of the compute environment is available, then canceling the reservation for the first group of resources and reserving a second group of resources of the compute environment according to the evaluation.
1. A method comprising:
reserving a first group of compute resources within a compute environment based on a request for the compute resources to yield a reservation of the first group of compute resources, the first group of compute resources having a first value that is used to determine a threshold value;
evaluating the compute environment to determine a second value for a second group of compute resources within the compute environment;
comparing the second value of the second group of compute resources with the threshold value to yield a determination;
if the determination indicates that the second value of the second group of compute resources is an improvement over the threshold value, then modifying the reservation from the first group of compute resources to the second group of compute resources of the compute environment; and
allocating the second group of compute resources according to the reservation, wherein the improvement is an improved resource allocation gained from meeting at least one preferred criterion.
2. The method of claim 1 , wherein the compute environment is one of an enterprise compute farm, a cluster and a grid.
3. The method of claim 1 , wherein the request further comprises the at least one preferred criterion and at least one required criterion.
4. The method of claim 3 , wherein the evaluating further comprises identifying compute resources that are available and meet explicit or implicit preferred criteria of the reservation.
5. The method of claim 4 , wherein available compute resources comprise compute resources in an up state with no partial or complete failure.
6. The method of claim 3 , wherein the reservation of the first group of compute resources meets a required criterion.
7. The method of claim 6 , wherein evaluating compute resources within the compute environment further comprises determining if at least one of the preferred criteria can be met by modifying the first group of compute resources allocated for the reservation.
8. The method of claim 7 , wherein the evaluating comprises a comparison of a cost of migrating the reservation from the first group of compute resources to the second group of compute resources with the improved resource allocation gained from meeting the at least one of the preferred criterion.
9. The method of claim 8 , wherein the reservation is not modified if the cost of modifying the reservation from the first group of compute resources to the second group of compute resources is equal to or higher than either the threshold value or the improved resource allocation of the compute environment gained by meeting the at least one of the preferred criteria.
10. The method of claim 8 , wherein the evaluating further uses a per-reservation policy.
11. The method of claim 10 , wherein the per-reservation policy is at least one of an administrator policy, a user-based policy, a policy of never taking an action, a policy of always taking an action and a cost-based policy.
12. The method of claim 1 , wherein modifying the reservation further comprises at least one of canceling the reservation and creating a new reservation, dynamically modifying attributes of an existing reservation, and dynamically modifying attributes of the first group of compute resources to better satisfy the reservation.
13. The method of claim 1 , wherein the reservation for the first group of compute resources and a second reservation for the second group of compute resources overlap.
14. The method of claim 1 , wherein the request is identified as a self-optimizing request.
15. The method of claim 14 , wherein a requestor of the request identifies the request as self-optimizing.
16. The method of claim 14 , wherein the request is identified as self-optimizing in space.
17. The method of claim 14 , wherein a requestor of the request is charged more for a self-optimizing request relative to a charge for a non-self-optimizing request.
18. A system comprising:
a processor; and
a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising:
reserving a first group of compute resources within a compute environment based on a request for the compute resources to yield a reservation, the first group of compute resources having a first value that is used to determine a threshold value;
evaluating the compute environment to determine a second value for a second group of compute resources within the compute environment;
comparing the second value of the second group of compute resources with the threshold value to yield a determination;
if the determination indicates that the second value of the second group of compute resources is an improvement over the threshold value, then modifying the reservation from the first group of compute resources to the second group of compute resources of the compute environment; and
allocating the second group of compute resources according to the reservation, wherein the improvement is an improved resource allocation gained from meeting at least one preferred criterion.
19. A non-transitory computer-readable medium storing instructions which, when executed by a computing device, cause the computing device to perform operations comprising:
reserving a first group of compute resources within a compute environment based on a request for the compute resources to yield a reservation, the first group of compute resources having a first value that is used to determine a threshold value;
evaluating the compute environment to determine a second value for a second group of compute resources within the compute environment;
comparing the second value of the second group of compute resources with the threshold value to yield a determination;
if the determination indicates that the second value of the second group of compute resources is an improvement over the threshold value, then modifying the reservation from the first group of compute resources to the second group of compute resources of the compute environment; and
allocating the second group of compute resources according to the reservation, wherein the improvement is an improved resource allocation gained from meeting at least one preferred criterion.