Enhanced application request based scheduling on heterogeneous elements of information technology infrastructure
A method includes receiving an application request comprising specifications for a given application workload, selecting a given hardware configuration for the given application workload using one or more hardware configuration templates and information identifying a plurality of heterogeneous elements of the information technology infrastructure, modifying the application request to generate an enhanced application request specifying the given hardware configuration, and providing the enhanced application request to a scheduler, the enhanced application request being utilizable by the scheduler to select from the plurality of heterogeneous elements of the information technology infrastructure to schedule the given application workload.
1. A method comprising:
receiving an application request comprising specifications for a given application workload, the specifications comprising hardware-agnostic service level objective expressions not specifying particular types of hardware to be used for the given application workload;
identifying a plurality of heterogeneous elements of an information technology infrastructure, the plurality of heterogeneous elements comprising at least two different types of hardware providing compute, storage and network resources;
selecting a given hardware configuration for the given application workload that specifies particular types of hardware providing compute, storage and network resources by mapping the hardware-agnostic service level objective expressions of the application request to one or more application classes and one or more workload types of one or more hardware configuration templates of a local repository of hardware configuration templates, the local repository comprising hardware configuration templates specifying particular types of hardware providing compute, storage and network resources that may be fulfilled utilizing the identified plurality of heterogeneous elements of the information technology infrastructure;
modifying the application request to generate an enhanced application request specifying the given hardware configuration; and
providing the enhanced application request to a scheduler, the enhanced application request being utilizable by the scheduler to select from the plurality of heterogeneous elements of the information technology infrastructure to schedule the given application workload; and
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The method of claim 1 wherein modifying the application request to generate the enhanced application request is responsive to determining that the information technology infrastructure has sufficient available capacity to fulfill the application request at a given time using the given hardware configuration.
3. The method of claim 1 , further comprising:
determining that the information technology infrastructure has sufficient overall capacity to fulfill the application request but insufficient available capacity at a given time to fulfill the application request; and
responsive to determining that the information technology infrastructure has sufficient overall capacity to fulfill the application request but insufficient available capacity at a given time to fulfill the application request, at least one of:
waiting until the information technology infrastructure has sufficient available capacity to fulfill the application request using the given hardware configuration before providing the enhanced application request to the scheduler; and
modifying the given hardware configuration by reducing one or more specifications of the given application workload such that the information technology infrastructure has sufficient available capacity at the given time to fulfill the application request using the modified hardware configuration.
4. The method of claim 1 , further comprising:
determining that the information technology infrastructure has insufficient overall capacity to fulfill the application request; and
responsive to determining that the information technology infrastructure has insufficient overall capacity to fulfill the application request, at least one of:
modifying the given configuration by reducing one or more specifications of the given application workload such that the information technology infrastructure has sufficient overall capacity to fulfill the application request using the modified hardware configuration; and
generating a recommendation for upgrading the information technology infrastructure such that the information technology infrastructure would have sufficient overall capacity to fulfill the application request using the given hardware configuration.
5. The method of claim 1 wherein the local repository of hardware configuration templates is obtained by filtering a global repository comprising one or more previously used hardware configurations and learned hardware configurations using a local platform catalog representing capabilities of the identified plurality of heterogeneous elements of the information technology infrastructure.
6. The method of claim 1 wherein the plurality of heterogeneous elements comprise two or more different types of processors, and wherein the hardware-agnostic service level objective expressions do not specify a given type of processor to be used for the given application workload.
7. The method of claim 6 wherein the two or more different types of processors comprise one or more of: central processing unit architectures, instruction set architectures, system-on-chip integrated circuits, graphics processing units and general purpose graphics processing units.
8. The method of claim 1 wherein the plurality of heterogeneous elements comprise two or more different types of storage, and wherein the hardware-agnostic service level objective expressions do not specify a given type of storage to be used for the given application workload.
9. The method of claim 8 wherein the two or more different types of storage comprise one or more of: flash memory, hard disk drives and network attached storage.
10. The method of claim 1 wherein the plurality of heterogeneous elements comprises two or more different fabric topologies, and wherein the hardware-agnostic service level objective expressions do not specify a given type of fabric topology to be used for the given application workload.
11. The method of claim 1 wherein:
receiving the application request comprises parsing and interpreting the hardware-agnostic service level objective expressions to generate an application workload specification template in a format compatible with entries in the local repository comprising the one or more hardware configuration templates;
selecting the given hardware configuration for the application request comprises aligning the application workload specification template with a given entry in the local repository corresponding to the given hardware configuration; and
modifying the application request to generate the enhanced application request comprises combining the hardware-agnostic service level objective expressions with the given hardware configuration to generate a job request statement.
12. The method of claim 1 further comprising monitoring performance of the given application workload and one or more other application workloads to at least one of:
generate one or more recommendations for upgrading hardware elements of the information technology infrastructure;
generate one or more new hardware configuration templates; and
generate a modified hardware configuration recommendation for use in fulfilling the application request.
13. The method of claim 1 wherein selecting the given hardware configuration for the given application workload is based on performance requirements associated with the given application workload.
14. The method of claim 1 wherein selecting the given hardware configuration for the given application workload is based on performance requirements associated with the given application workload and one or more other application workloads utilizing the information technology infrastructure.
15. The method of claim 1 wherein selecting the given hardware configuration for the given application workload is based at least in part on one or more attributes of the given application workload, the one or more attributes comprising at least one of a size of the given application workload and a lifespan of the given application workload.
16. The method of claim 1 wherein each of the hardware configurations in the local repository is associated with a topology of hardware providing compute, storage and network resources of designated types for a particular types of application classes and workload types.
17. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device cause the at least one processing device:
to receive an application request comprising specifications for a given application workload, the specifications comprising hardware-agnostic service level objective expressions not specifying particular types of hardware to be used for the given application workload;
to identify a plurality of heterogeneous elements of an information technology infrastructure, the plurality of heterogeneous elements comprising at least two different types of hardware providing compute, storage and network resources;
to select a given hardware configuration for the given application workload that specifies particular types of hardware providing compute, storage and network resources by mapping the hardware-agnostic service level objective expressions of the application request to one or more application classes and one or more workload types of one or more hardware configuration templates of a local repository of hardware configuration templates, the local repository comprising hardware configuration templates specifying particular types of hardware providing compute, storage and network resources that may be fulfilled utilizing the identified a plurality of heterogeneous elements of the information technology infrastructure;
to modify the application request to generate an enhanced application request specifying the given hardware configuration; and
to provide the enhanced application request to a scheduler, the enhanced application request being utilizable by the scheduler to select from the plurality of heterogeneous elements of the information technology infrastructure to schedule the given application workload.
18. The computer program product of claim 17 wherein the program code when executed by the at least one processing device further causes the at least one processing device:
to receive the application request by parsing and interpreting the hardware-agnostic service level objective expressions to generate an application workload specification template in a format compatible with entries in the local repository comprising the one or more hardware configuration templates;
to select the given hardware configuration for the application request by aligning the application workload specification template with a given entry in the local repository corresponding to the given hardware configuration; and
to modify the application request to generate the enhanced application request by combining the hardware-agnostic service level objective expressions with the given hardware configuration to generate a job request statement.
19. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to receive an application request comprising specifications for a given application workload, the specifications comprising hardware-agnostic service level objective expressions not specifying particular types of hardware to be used for the given application workload;
to identify a plurality of heterogeneous elements of an information technology infrastructure, the plurality of heterogeneous elements comprising at least two different types of hardware providing compute, storage and network resources;
to select a given hardware configuration for the given application workload that specifies particular types of hardware providing compute, storage and network resources by mapping the hardware-agnostic service level objective expressions of the application request to one or more application classes and one or more workload types of one or more hardware configuration templates of a local repository of hardware configuration templates, the local repository comprising hardware configuration templates specifying particular types of hardware providing compute, storage and network resources that may be fulfilled utilizing the identified plurality of heterogeneous elements of the information technology infrastructure;
to modify the application request to generate an enhanced application request specifying the given hardware configuration; and
to provide the enhanced application request to a scheduler, the enhanced application request being utilizable by the scheduler to select from the plurality of heterogeneous elements of the information technology infrastructure to schedule the given application workload.
20. The apparatus of claim 19 wherein the at least one processing device is further configured:
to receive the application request by parsing and interpreting the hardware-agnostic service level objective expressions to generate an application workload specification template in a format compatible with entries in the local repository comprising the one or more hardware configuration templates;
to select the given hardware configuration for the application request by aligning the application workload specification template with a given entry in the local repository corresponding to the given hardware configuration; and
to modify the application request to generate the enhanced application request by combining the hardware-agnostic service level objective expressions with the given hardware configuration to generate a job request statement.