Systems and methods for controlling process priority for efficient resource allocation

Patent metadata

Field	Value
Publication number	US-2018109469-A1
Application number	US-201615295470-A
Country	US
Kind code	A1
Filing date	Oct 17, 2016
Priority date	Oct 17, 2016
Publication date	Apr 19, 2018
Grant date	—

Abstract

Methods and systems for controlling process priority for one or more work units having one or more processes. The method includes monitoring a combination of a throughput value and a response time value for each work unit, detecting a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit, and reallocating one or more resources to the work unit when the priority level exceeds a predetermined threshold value.

First claim

1 . A method for controlling process priority for one or more work units having one or more processes, the method comprising:
monitoring a combination of a throughput value and a response time value for each work unit; detecting a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit; and reallocating one or more resources to the work unit when the priority level exceeds a predetermined threshold value.

2 . The method of claim 1 , wherein the work unit is a container having at least one application, the at least one application including at least one process.

3 . The method of claim 1 , wherein the work unit is a virtual machine, the virtual machine including at least one process.

4 . The method of claim 1 , wherein reallocating the one or more resources includes reallocating memory to the work unit.

5 . The method of claim 4 , further comprising increasing the priority level associated with the work unit when the throughput value and the response time value are increased such that swappiness of the memory is decreased for the work unit.

6 . The method of claim 4 , further comprising decreasing the priority level associated with the work unit when the throughput value and the response time value are decreased such that swappiness of the memory is increased for the work unit.

7 . The method of claim 1 , further comprising maintaining the priority level associated with the work unit when one of the throughput value and the response time value is increased.

8 . The method of claim 1 , further comprising maintaining the priority level associated with the work unit when one of the throughput value and the response time value is decreased.

9 . A non-transitory computer readable storage medium comprising a computer readable program for controlling process priority for one or more work units having one or more processes, wherein the computer readable program when executed on a computer causes the computer to execute:
monitoring a combination of a throughput value and a response time value for each work unit; detecting a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit; and reallocating one or more resources to the work unit when the priority level exceeds a predetermined threshold value.

10 . The non-transitory computer readable storage medium of claim 9 , wherein the work unit is a container having at least one application, the at least one application including at least one process.

11 . The non-transitory computer readable storage medium of claim 9 , wherein the work unit is a virtual machine, the virtual machine including a plurality of processes.

12 . The non-transitory computer readable storage medium of claim 9 , wherein reallocating the one or more resources includes reallocating memory to the work unit.

13 . The non-transitory computer readable storage medium of claim 12 , further comprising increasing the priority level associated with the work unit when the throughput value and the response time value are increased such that swappiness of the memory is decreased for the work unit.

14 . The non-transitory computer readable storage medium of claim 12 , further comprising decreasing the priority level associated with the work unit when the throughput value and the response time value are decreased such that swappiness of the memory is increased for the work unit.

15 . The non-transitory computer readable storage medium of claim 9 , further comprising maintaining the priority level associated with the work unit when one of the throughput value and the response time value is increased.

16 . The non-transitory computer readable storage medium of claim 9 , further comprising maintaining the priority level associated with the work unit when one of the throughput value and the response time value is decreased.

17 . A system, comprising:
a memory; and a hardware processor configured to:
monitor a combination of a throughput value and a response time value for each work unit from one or more work units, the one or more work units having one or more processes;
detect a change in load level for each work unit based on a correlation between the throughput value and the response time value to adjust a priority level associated with the work unit; and
reallocate one or more resources to the work unit when the priority level exceeds a predetermined threshold value.

18 . The system of claim 17 , wherein the one or more resources includes memory.

19 . The system of claim 18 , wherein the hardware processor is further configured to increase the priority level associated with the work unit when the throughput value and the response time value are increased such that swappiness of the memory is decreased for the work unit.

20 . The system of claim 18 , wherein the hardware processor is further configured to decrease the priority level associated with the work unit when the throughput value and the response time value are decreased such that swappiness of the memory is increased for the work unit.

Assignees

• IBM

Inventors

• Nakazawa Rina
• Ogata Kazunori
• Seelam Seetharami R

Classifications

• G06F9/5061

  Partitioning or combining of resources · CPC title

• H04L43/0888

  Throughput · CPC title

• H04L47/822

  Collecting or measuring resource availability data · CPC title

• H04L47/821 Primary

  Prioritising resource allocation or reservation requests · CPC title

• G06F9/5083

  Techniques for rebalancing the load in a distributed system · CPC title