Datacenter database generation using task fingerprint and allocated resources

1. A processor-implemented method to generate a task fingerprint and resource allocation database comprising:

receiving, by a processor, a plurality of tasks to be performed;

generating, by the processor, a task fingerprint for each received task to form a plurality of task fingerprints by performing at least one of:

sub-fingerprint masking a multiple number of subtasks within a received task and identifying unmasked subtasks of the task; or

performing a tree flow extraction on each received task;

allocating, by the processor, a resource set to each received task to define a plurality of allocated resource sets based at least in part on an identification of resource types, resource quantities, or resource combinations;

performing, by the processor, each received task using the resource set allocated by the processor;

gathering, by the processor, a performance metric for each performed task using the resource set allocated by the processor, wherein the performance metric comprises at least one of a task duration, a central processing unit (CPU) usage, a memory usage, a network usage, a storage volume usage, a storage volume access frequency, a state of change of memory use, or a network traffic change over time; and

relating, by the processor, each task fingerprint, allocated resource set, and performance metric for each performed task to generate the task fingerprint and resource allocation database.

2. The method of claim 1 , further comprising:

comparing at least a first and a second task fingerprint of the plurality of task fingerprints;

determining whether the first and the second task fingerprints substantially match; and

if the first and the second task fingerprints substantially match:

relating database entries for the first and the second task fingerprints as a common task fingerprint entry.

3. The method of claim 2 , wherein the first and the second task fingerprints match if, upon performing a matching algorithm, the results for the first and the second fingerprints are within a predetermined threshold.

4. The method of claim 1 , wherein the receiving, the generating, the allocating, the performing, the gathering, and the relating are all performed by a same resource.

5. The method of claim 1 , wherein at least one of the receiving, the generating, the allocating, the performing, the gathering, or the relating is performed by one resource, and at least another one of the receiving, the generating, the allocating, the performing, the gathering, or the relating is performed by another resource.

6. The method of claim 1 , wherein the receiving, the generating, the allocating, the performing, the gathering, and the relating are all performed by a same processor.

7. The method of claim 1 , wherein at least one of the receiving, the generating, the allocating, the performing, the gathering, or the relating is performed by one processor, and at least another one of the receiving, the generating, the allocating, the performing, the gathering, or the relating is performed by another processor.

8. A machine readable non-transitory medium having stored therein instructions that, when executed by at least one processor, result in generation of a task fingerprint and resource allocation database by causing the at least one processor to:

receive a plurality of tasks to be performed;

generate a task fingerprint for each received task to form a plurality of task fingerprints by causing the at least one processor to perform at least one of:

sub-fingerprint mask a multiple number of subtasks within a received task and identifying unmasked subtasks of the task; or

perform a tree flow extraction on each received task;

allocate a resource set to each received task to define a plurality of allocated resource sets based at least in part on an identification of resource types, resource quantities, or resource combinations;

perform each received task using the resource set allocated by the at least one processor;

gather a performance metric for each performed task using the resource set allocated by the at least one processor, wherein the performance metric comprises at least one of a task duration, a central processing unit (CPU) usage, a memory usage, a network usage, a storage volume usage, a storage volume access frequency, a state of change of memory use, or a network traffic change over time; and

relate each task fingerprint, allocated resource set, and performance metric for each performed task to generate the task fingerprint and resource allocation database.

9. The machine readable non-transitory medium of claim 8 having stored therein further instructions that, when executed, result in generation of a task fingerprint and resource allocation database by:

comparing at least a first and a second task fingerprint of the plurality of task fingerprints;

determining whether the first and the second task fingerprints substantially match; and

if the first and the second task fingerprints substantially match:

relating database entries for the first and the second task fingerprints as a common task fingerprint entry.

10. The machine readable non-transitory medium of claim 8 , wherein the receive, the generate, the allocate, the perform, the gather, and the relate are all performed by the at least one processor.

11. The machine readable non-transitory medium of claim 8 , wherein at least one of the receive, the generate, the allocate, the perform, the gather, or the relate are performed by the at least one processor, and at least another one of the receive, the generate, the allocate, the perform, the gather, or the relate are performed by at least one second processor.

12. The machine readable non-transitory medium of claim 8 , wherein the receive, the generate, the allocate, the perform, the gather, and the relate are all performed by at least one resource.

13. The machine readable non-transitory medium of claim 8 , wherein at least one of the receive, the generate, the allocate, the perform, the gather, or the relate are performed by the at least one resource, and at least another one of the receive, the generate, the allocate, the perform, the gather, or the relate are performed by at least one second resource.

14. A computing device comprising a processor configured to:

receive a plurality of tasks to be performed;

generate a task fingerprint for each received task to form a plurality of task fingerprints by causing the processor to perform at least one of:

sub-fingerprint mask a multiple number of subtasks within a received task and identifying unmasked subtasks of the task; or

perform a tree flow extraction on each received task;

allocate a resource set to each received task to define a plurality of allocated resource sets based at least in part on an identification of resource types, resource quantities, or resource combinations;

perform each received task using the resource set allocated by the processor;

gather a performance metric for each performed task using the resource set allocated by the processor, wherein the performance metric comprises at least one of a task duration, a central processing unit (CPU) usage, a memory usage, a network usage, a storage volume usage, a storage volume access frequency, a state of change of memory use, or a network traffic change over time; and

relate, in a database, each task fingerprint, allocated resource set, and performance metric for each performed task to generate the task fingerprint and resource allocation database.

15. The computing device of claim 14 , wherein the processor is further configured to:

compare at least a first and a second task fingerprint of the plurality of task fingerprints;

determine whether the first and the second task fingerprints substantially match; and

relate database entries for the first and the second task fingerprints as a common task fingerprint entry if the first and the second task fingerprints substantially match.