ADAPTIVE SCHEDULING AND ORCHESTRATION IN A NETWORKED ENVIRONMENT

• US 20170078442A1
• Filed: 09/11/2015
• Published: 03/16/2017
• Est. Priority Date: 09/11/2015
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: Pacella, Dante J., Tadayon, Mani, Ahmad, Syed A., Rau, Lawrence Richard
• Granted Patent: US 10,015,278 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/62 Establishing a time schedule for servicing the requests

Abstract

A method, a device, and a non-transitory storage medium to receive a job request to schedule an execution of a process in a networked environment; generate a schedule for the execution of the process based on one or more current schedules directed to concurrent execution of one or more other processes; obtain resource utilization data indicating resource usage stemming from the concurrent execution of the process and the one or more other processes; analyze the resource utilization data; determine whether a resource inefficiency occurred during the concurrent execution based on an analysis of the resource utilization data; generate resource inefficiency data in response to a determination that the resource inefficiency occurred; and generate an adapted schedule for at least one of the process or the one or more other processes in response to a determination that the resource inefficiency occurred.

Claims

1. A method comprising:

receiving, by a networked device and from a user device, a job request to schedule an execution of a process in a networked environment;

generating, by the networked device, a schedule for the execution of the process in response to the receiving;

concurrently executing, by another networked device, the process according to the schedule and one or more other processes according to one or more current schedules;

obtaining, by the networked device, resource utilization data indicating resource usage stemming from the concurrently executing;

analyzing, by the networked device, the resource utilization data;

determining, by the networked device, whether a resource inefficiency occurred during the concurrently executing based on the analyzing;

generating, by the networked device, resource inefficiency data in response to determining that the resource inefficiency occurred during the concurrently executing; and

generating, by the networked device, an adapted schedule for at least one of the process or the one or more other processes in response to determining that the resource inefficiency occurred.

2. The method of claim 1, further comprising:

generating execution statistics data based on the analyzing of the resource utilization data; and

wherein the generating the resource inefficiency data further comprises;

generating the resource inefficiency data based on an analysis of the at least one of the execution statistics data or the resource utilization data, and wherein when the concurrently executing includes at least one of a transmission of data from the other networked device or a reception of data by the other networked device, the resource utilization data pertains to the other networked device and one or more links of the networked environment via which the transmission of the data or the reception of the data occurred.

3. The method of claim 1, wherein determining whether the resource inefficiency occurred further comprises:

comparing resource utilization data values to operational threshold values; and

determining whether the resource inefficiency occurred based on a result of the comparing.

4. The method of claim 3, further comprising:

calculating difference values between the resource utilization data values and the operational threshold values;

comparing the difference values to difference threshold values; and

determining whether to generate the adapted schedule based on the comparing of the difference values to the difference threshold values.

5. The method of claim 1, wherein generating the adapted schedule further comprises:

calculating one or more time offsets pertaining to at least one of the process or the one or more other processes, wherein each of the one or more time offsets indicates a time shift relative to a time instance of execution according to at least one of the one or more current schedules or the schedule; and

generating the adapted schedule based on the one or more time offsets.

6. The method of claim 5, further comprising:

determining an execution signature pattern pertaining to the at least one of the process or the one or more other processes; and

calculating the one or more time offsets based on the determining of the execution signature pattern.

7. The method of claim 1, wherein generating the adapted schedule further comprises:

determining which of at least one of the process or the one or more other processes to move to a target networked device different from the other networked device;

tearing down the at least one of the process or the one or more other processes in response to determining which of the at least one of the process or the one or more other processes to move; and

setting up, at the target networked device, the at least one of the process or the one or more other processes in response to the tearing down, and wherein the generating further comprises;

generating the adapted schedule based on the tearing down and the setting up.

8. The method of claim 1, further comprising:

publishing the adapted schedule; and

concurrently executing the at least one of the process or the one or more other processes based on the adapted schedule.

9. A networked device comprising:

a communication interface;

a memory, wherein the memory stores instructions; and

a processor, wherein the processor executes the instructions to;

receive, via the communication interface, from a user device, a job request to schedule an execution of a process in a networked environment;

generate a schedule for the execution of the process in response a receipt of the job request, wherein the schedule is generated based on one or more current schedules directed to concurrent execution of one or more other processes;

obtain resource utilization data indicating resource usage stemming from the concurrent execution of the process and the one or more other processes;

analyze the resource utilization data;

determine whether a resource inefficiency occurred during the concurrent execution based on an analysis of the resource utilization data;

generate resource inefficiency data in response to a determination that the resource inefficiency occurred during the concurrent execution; and

generate an adapted schedule for at least one of the process or the one or more other processes in response to a determination that the resource inefficiency occurred.

10. The networked device of claim 9, wherein the processor further executes the instructions to:

generate execution statistics data based on the analysis of the resource utilization data; and

wherein when generating the resource inefficiency data, the processor further executes the instructions to;

generate the resource inefficiency data based on an analysis of the at least one of the execution statistics data or the resource utilization data, and wherein when the concurrent execution includes at least one of a transmission of data from another networked device or a reception of data by the other networked device, the resource utilization data pertains to the other networked device and one or more links of the networked environment via which the transmission of the data or the reception of the data occurred.

11. The networked device of claim 9, wherein when determining whether the resource inefficiency occurred, the processor further executes the instructions to:

compare resource utilization data values to operational threshold values; and

omit to generate the resource inefficiency data based on a result of a comparison, wherein the result of the comparison indicates that the resource utilization data values satisfy the operational threshold values.

12. The networked device of claim 9, wherein the processor further executes the instructions to:

compare resource utilization data values to operational threshold values;

calculate difference values between the resource utilization data values and the operational threshold values; and

determine whether to generate the adapted schedule based on the difference values.

13. The networked device of claim 9, wherein the processor further executes the instructions to:

calculate one or more time offsets pertaining to at least one of the process or the one or more other processes, wherein each of the one or more time offsets indicates a time shift relative to a time instance of execution according to at least one of the one or more current schedules or the schedule; and

generate the adapted schedule based on the one or more time offsets.

14. The networked device of claim 13, wherein the processor further executes the instructions to:

determine an execution signature pattern pertaining to the at least one of the process or the one or more other processes; and

calculate the one or more time offsets based on a determination of the execution signature pattern.

15. The networked device of claim 9, wherein when generating the adapted schedule, the processor further executes the instructions to:

determine which of at least one of the process or the one or more other processes to move to a target networked device different from a source networked device on which the concurrent execution occurred;

tear down the at least one of the process or the one or more other processes in response to a determination which of the at least one of the process or the one or more other processes to move;

set up, at the target networked device, the at least one of the process or the one or more other processes in response to the tear down; and

generate the adapted schedule based on the tear down and the set up.

16. A non-transitory, computer-readable storage medium storing instructions executable by a processor of a computational device, which when executed cause the computational device to:

receive a job request to schedule an execution of a process in a networked environment;

generate a schedule for the execution of the process in response a receipt of the job request, wherein the schedule is generated based on one or more current schedules directed to concurrent execution of one or more other processes;

obtain resource utilization data indicating resource usage stemming from the concurrent execution of the process and the one or more other processes;

analyze the resource utilization data;

determine whether a resource inefficiency occurred during the concurrent execution based on an analysis of the resource utilization data;

generate resource inefficiency data in response to a determination that the resource inefficiency occurred during the concurrent execution; and

generate an adapted schedule for at least one of the process or the one or more other processes in response to a determination that the resource inefficiency occurred.

17. The non-transitory, computer-readable storage medium of claim 16, wherein the instructions further comprise instructions to:

compare resource utilization data values to operational threshold values; and

omit to generate the resource inefficiency data based on a result of a comparison, wherein the result of the comparison indicates that the resource utilization data values satisfy the operational threshold values.

18. The non-transitory, computer-readable storage medium of claim 16, wherein the instructions further comprise instructions to:

compare resource utilization data values to operational threshold values;

calculate difference values between the resource utilization data values and the operational threshold values when a result of a comparison indicates a difference between the resource utilization data values and the operational threshold values;

compare the difference values to difference threshold values; and

determine whether to generate the adapted schedule based on a comparison between the difference values and the difference threshold values.

19. The non-transitory, computer-readable storage medium of claim 16, wherein the instructions further comprise instructions to:

calculate one or more time offsets pertaining to at least one of the process or the one or more other processes, wherein each of the one or more time offsets indicates a time shift relative to a time instance of execution according to at least one of the one or more current schedules or the schedule; and

generate the adapted schedule based on the one or more time offsets.

20. The non-transitory, computer-readable storage medium of claim 16, wherein the instructions further comprise instructions to:

determine which of at least one of the process or the one or more other processes to move to a target networked device different from a source networked device on which the concurrent execution occurred;

tear down the at least one of the process or the one or more other processes in response to a determination which of the at least one of the process or the one or more other processes to move;

set up, at the target networked device, the at least one of the process or the one or more other processes in response to the tear down; and

generate the adapted schedule based on the tear down and the set up.