Data-aware workload scheduling and execution in heterogeneous environments

• US 9,715,408 B2
• Filed: 10/13/2016
• Issued: 07/25/2017
• Est. Priority Date: 09/18/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Dube, Parijat, Zhang, Li
• Primary Examiner(s): RONI, SYED A
• Application Number:
  US15/292,269
• Publication Number:
  US 20170031712A1
• Time in Patent Office: 285 Days
• Field of Search: None
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5005 to service a request
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals

Abstract

In an approach for scheduling the execution of a workload in a computing environment, a computer receives a request for scheduling execution of a computing job, wherein the computing job includes a plurality of computing tasks to be executed in a sequence, and wherein at least one computing task requires access to a set of data. The computer identifies information related to the computing environment, wherein the information comprises at least processors available to execute each computing task of the plurality of computing tasks and storage device proximity to the processors. The computer determines an execution configuration for the computing job based, at least in part, on the received request, the information related to the computing environment, and current utilization of the processors'"'"' resources. The computer schedules execution of the execution configuration for the computing job.

Claims

1. A method for scheduling and executing a computing job in a computing environment, the method comprising:

receiving, by a computer, a request for scheduling execution of a computing job, wherein the computing job includes a plurality of computing tasks to be executed in a sequence, and wherein at least one computing task requires access to a set of data;

identifying, by the computer, information related to the computing environment, wherein the information comprises at least;

processors available to execute each computing task of the plurality of computing tasks;

storage device proximity to the processors; and

a monetary cost associated with utilizing components of the computing environment;

generating, by the computer, one or more execution mappings for the computing job based, at least in part, on the received request, the information related to the computing environment, and current utilization of the processors'"'"' resources;

selecting, by the computer, an execution mapping from the one or more execution mappings based, at least in part, on an expected amount of time to execute the computing job and an expected cost associated with executing the computing job; and

executing, by the computer, the computing job according to the selected execution mapping.

2. The method of claim 1, wherein the processors comprise a plurality of types of processors;

and

wherein determining an execution mapping for the computing job is further based on capabilities of the plurality of types of processors to execute each task.

3. The method of claim 1, wherein the execution mapping for the computing job comprises an assignment of each computing task of the plurality of computing tasks to a processor of the processors and a selection of a storage device to provide the set of data required by the at least one computing task.

4. The method of claim 1, wherein each processor of the processors resources is selected from the group consisting of a central processing unit (CPU), a field programmable gate array (FPGA), a graphics processing unit (GPU), and an application-specific integrated circuit (ASIC).

5. The method of claim 1, wherein the selection of an execution mapping comprises solving an optimization problem, wherein the optimization problem comprises performance and cost evaluation for an execution mapping.

6. A computer program product for scheduling and executing a computing job in a computing environment, the computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising;

program instructions to receive a request for scheduling execution of a computing job, wherein the computing job includes a plurality of computing tasks to be executed in a sequence, and wherein at least one computing task requires access to a set of data;

program instructions to identify information related to the computing environment, wherein the information comprises at least;

processors available to execute each computing task of the plurality of computing tasks;

storage device proximity to the processors; and

a monetary cost associated with utilizing components of the computing environment;

program instructions to generate one or more execution mappings for the computing job based, at least in part, on the received request, the information related to the computing environment, and current utilization of the processors'"'"' resources;

program instructions to select an execution mapping from one or more execution mappings based, at least in part, on an expected amount of time to execute the computing job and an expected cost associated with executing the computing job; and

program instructions to execute the computing job according to the selected execution mapping.

7. The computer program product of claim 6, wherein the processors comprise a plurality of types of processors;

and

wherein program instructions to determine an execution mapping for the computing job are further based on capabilities of the plurality of types of processors to execute each task.

8. The computer program product of claim 6, wherein the execution mapping for the computing job comprises an assignment of each computing task of the plurality of computing tasks to a processor of the processors and a selection of a storage device to provide the set of data required by the at least one computing task.

9. The computer program product of claim 6, wherein each processor of the processors resources is selected from the group consisting of a central processing unit (CPU), a field programmable gate array (FPGA), a graphics processing unit (GPU), and an application-specific integrated circuit (ASIC).

10. The computer program product of claim 6, wherein program instructions to select an execution mapping comprise program instructions to solve an optimization problem, wherein the optimization problem comprises performance and cost evaluation for an execution mapping.

11. A computer system for scheduling and executing a computing job in a computing environment, the computer system comprising:

one or more computer processors, one or more computer readable storage media, and program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to receive a request for scheduling execution of a computing job, wherein the computing job includes a plurality of computing tasks to be executed in a sequence, and wherein at least one computing task requires access to a set of data;

program instructions to identify information related to the computing environment, wherein the information comprises at least;

processors available to execute each computing task of the plurality of computing tasks;

storage device proximity to the processors; and

a monetary cost associated with utilizing components of the computing environment;

program instructions to generate one or more execution mappings for the computing job based, at least in part, on the received request, the information related to the computing environment, and current utilization of the processors'"'"' resources;

program instructions to select an execution mapping from one or more execution mappings based, at least in part, on an expected amount of time to execute the computing job and an expected cost associated with executing the computing job; and

program instructions to execute the computing job according to the selected execution mapping.

12. The computer system of claim 11, wherein the processors comprise a plurality of types of processors;

and

wherein program instructions to determine an execution mapping for the computing job are further based on capabilities of the plurality of types of processors to execute each task.