Tuning utilization and heap memory size for real-time garbage collection

Patent metadata

Field	Value
Publication number	US-2016253103-A1
Application number	US-201514633295-A
Country	US
Kind code	A1
Filing date	Feb 27, 2015
Priority date	Feb 27, 2015
Publication date	Sep 1, 2016
Grant date	—

Abstract

According to an aspect, a user interface is provided for assisting a user with identifying parameters for starting an application that utilizes real-time garbage collection (GC). The parameters include a fixed heap size and a GC central processing unit (CPU) utilization. Responsive to receiving a request from the user, the user is provided with options for profiling the application. The profiling includes executing the application. The options include targeting the GC CPU utilization to meet real-time requirements, targeting the heap size to meet the real-time requirements, and targeting a balance between the GC CPU utilization and the heap size to meet the real-time requirements. Responsive to detecting a selection of an option by the user, the application is profiled according to the option selected. The user is presented with results of the profiling via the user interface. The results include values for the parameters.

First claim

What is claimed is:

1 . A method comprising:
providing a user interface to a user for assisting the user with identifying parameters for starting an application that utilizes real-time garbage collection (GC), the parameters including a fixed heap size and a GC central processing unit (CPU) utilization; responsive to receiving a request from the user, providing the user with options for profiling the application, the options including targeting the GC CPU utilization to meet real-time requirements, targeting the heap size to meet the real-time requirements, and targeting a balance between the GC CPU utilization and the heap size to meet the real-time requirements; responsive to detecting a selection of an option by the user, profiling the application according to the option selected, the profiling including executing the application; and presenting the user with results of the profiling, the presenting via the user interface and the results including values for the parameters.

2 . The method of claim 1 , wherein the real-time requirements include not exceeding a maximum heap usage percentage during execution of the application and preventing a synchronous GC during execution of the application.

3 . The method of claim 1 , wherein based on the user selecting the option for targeting the GC CPU utilization to meet real-time requirements, the profiling includes:
starting with a maximum potential heap size value and a minimum GC CPU utilization value; executing the application iteratively to identify a minimal GC CPU utilization value that meets the real-time requirements; and based on identifying the minimal GC CPU utilization value meeting the real-time requirements, executing the application iteratively to determine a minimum heap size value for the minimal GC CPU utilization value.

4 . The method of claim 1 , wherein based on the user selecting the option for targeting the heap size to meet real-time requirements, the profiling includes:
starting with a minimum potential heap size value and a maximum GC CPU utilization value; executing the application iteratively to identify a minimal heap size value that meets the real-time requirements; and based on identifying the minimal heap size value that meets the real-time requirements, executing the application iteratively to determine a minimum GC CPU utilization value for the minimum heap size value.

5 . The method of claim 1 , wherein based on the user selecting the option for targeting a balance between the GC CPU utilization and the heap size to meet real-time requirements, the profiling includes:
starting with a maximum potential heap size, a minimum GC CPU utilization, and an empty list of optimal heap size value and GC CPU utilization value pairs; iterating through potential heap size values in a stepwise fashion by decrementing the potential heap size value in each iteration, each iteration including executing the application to determine whether a corresponding minimal GC CPU utilization value exists; based on determining that a corresponding minimal GC CPU utilization value exists, adding a pairing of the heap size value and the minimal GC CPU utilization value to the list of optimal heap size and GC utilization value pairs; and based on determining that a corresponding minimal GC CPU utilization value does not exist, terminating the iterating.

6 . The method of claim 1 , further comprising setting the parameters to the values and executing the application based on the parameters.

7 . The method of claim 1 , wherein the application is a real-time Java application and the GC is performed over set intervals over a period of time.

8 . A computer program product comprising:
a tangible storage medium readable by a processor and storing instructions for execution by the processor to perform a method comprising: providing a user interface to a user for assisting the user with identifying parameters for starting an application that utilizes real-time garbage collection (GC), the parameters including a fixed heap size and a GC central processing unit (CPU) utilization; responsive to receiving a request from the user, providing the user with options for profiling the application, the options including targeting the GC CPU utilization to meet real-time requirements, targeting the heap size to meet the real-time requirements, and targeting a balance between the GC CPU utilization and the heap size to meet the real-time requirements; responsive to detecting a selection of an option by the user, profiling the application according to the option selected, the profiling including executing the application; and presenting the user with results of the profiling, the presenting via the user interface and the results including values for the parameters.

9 . The computer program product of claim 8 , wherein the real-time requirements include not exceeding a maximum heap usage percentage during execution of the application and preventing a synchronous GC during execution of the application.

10 . The computer program product of claim 8 , wherein based on the user selecting the option for targeting the GC CPU utilization to meet real-time requirements, the profiling includes:
starting with a maximum potential heap size value and a minimum GC CPU utilization value; executing the application iteratively to identify a minimal GC CPU utilization value that meets the real-time requirements; and based on identifying the minimal GC CPU utilization value meeting the real-time requirements, executing the application iteratively to determine a minimum heap size value for the minimal GC CPU utilization value.

11 . The computer program product of claim 8 , wherein based on the user selecting the option for targeting the heap size to meet real-time requirements, the profiling includes:
starting with a minimum potential heap size value and a maximum GC CPU utilization value; executing the application iteratively to identify a minimal heap size value that meets the real-time requirements; and based on identifying the minimal heap size value that meets the real-time requirements, executing the application iteratively to determine a minimum GC CPU utilization value for the minimum heap size value.

12 . The computer program product of claim 8 , wherein based on the user selecting the option for targeting a balance between the GC CPU utilization and the heap size to meet real-time requirements, the profiling includes:
starting with a maximum potential heap size, a minimum GC CPU utilization, and an empty list of optimal heap size value and GC CPU utilization value pairs; iterating through potential heap size values in a stepwise fashion by decrementing the potential heap size value in each iteration, each iteration including executing the application to determine whether a corresponding minimal GC CPU utilization value exists; based on determining that a corresponding minimal GC CPU utilization value exists, adding a pairing of the heap size value and the minimal GC CPU utilization value to the list of optimal heap size and GC utilization value pairs; and based on determining that a corresponding minimal GC CPU utilization value does not exist, terminating the iterating.

13 . The computer program product of claim 8 , wherein the method further comprises setting the parameters to the values and executing the application based on the parameters.

14 . The computer program product of claim 8 , wherein the application is a real-time Java application and the GC is performed over set intervals over a period of time.

15 . A system comprising:
a memo

Assignees

• IBM

Inventors

• Foley Sean C

Classifications

• G06F3/0608 Primary

  Saving storage space on storage systems · CPC title

• G06F3/0652

  Erasing, e.g. deleting, data cleaning, moving of data to a wastebasket · CPC title

• G06F3/0673

  Single storage device · CPC title

• G06F3/04847

  Interaction techniques to control parameter settings, e.g. interaction with sliders or dials · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title