Storage system performance models based on empirical component utilization

Patent metadata

Field	Value
Publication number	US-11144427-B2
Application number	US-201916596390-A
Country	US
Kind code	B2
Filing date	Oct 8, 2019
Priority date	May 12, 2017
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

A computer-implemented method according to one embodiment includes identifying aggregated customer performance data for a system resource, creating a first system map for the system resource, utilizing the aggregated customer performance data, comparing the first system map to a second system map created for the system resource utilizing calibration data, and adjusting the second system map, based on the comparing.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
identifying aggregated customer performance data for a system resource;
filtering the aggregated customer performance data to create a filtered portion of the aggregated customer performance data;
estimating one or more customer performance service time overheads for the system resource, utilizing the filtered portion of the aggregated customer performance data;
creating a first system map for the system resource, utilizing the one or more customer performance service time overheads;
comparing the first system map to a second system map created for the system resource utilizing calibration data; and
adjusting the second system map, based on the comparing.

2. The computer-implemented method of claim 1 , wherein the system resource includes a redundant array of independent disks (RAID) array.

3. The computer-implemented method of claim 1 , wherein the aggregated customer performance data includes a performance of the system resource in response to usage of the system resource by a plurality of different customers of a storage system.

4. The computer-implemented method of claim 1 , wherein filtering the aggregated customer performance data includes determining a subset of the aggregated customer performance data that shares one or more predetermined characteristics with the calibration data.

5. The computer-implemented method of claim 1 , wherein the calibration data includes a set of laboratory measurements used to calibrate one or more assumptions within a performance and capacity sizing model for a storage system.

6. The computer-implemented method of claim 1 , wherein the first system map and the second system map each include a mapped curve representing an interaction between different aspects of performance data for the system resource.

7. The computer-implemented method of claim 1 , wherein the first system map is determined by performing dynamic monitoring of utilization within a storage system to calculate utilization of the system resource based on customer usage.

8. The computer-implemented method of claim 1 , wherein the calibration data is generated by running a set of synthetic benchmarks against a storage system and measuring a response in a laboratory setting.

9. The computer-implemented method of claim 1 , wherein comparing the first system map to the second system map includes determining one or more differences between the first system map and the second system map.

10. The computer-implemented method of claim 9 , wherein the second system map is adjusted to eliminate or reduce the one or more differences between the first system map and the second system map.

11. A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising:
identifying aggregated customer performance data for a system resource, utilizing the one or more processors;
filtering the aggregated customer performance data to create a filtered portion of the aggregated customer performance data, utilizing the one or more processors;
estimating, utilizing the one or more processors, one or more customer performance service time overheads for the system resource, utilizing the filtered portion of the aggregated customer performance data;
creating, utilizing the one or more processors, a first system map for the system resource, utilizing the one or more customer performance service time overheads;
comparing, utilizing the one or more processors, the first system map to a second system map created for the system resource utilizing calibration data; and
adjusting the second system map based on the comparing, utilizing the processor.

12. The computer program product of claim 11 , wherein the system resource includes a device adapter.

13. The computer program product of claim 11 , wherein the aggregated customer performance data includes a performance of the system resource in response to usage of the system resource by a plurality of different customers of a storage system.

14. The computer program product of claim 11 , wherein filtering the aggregated customer performance data includes determining a subset of the aggregated customer performance data that shares one or more predetermined characteristics with the calibration data, utilizing the one or more processors.

15. The computer program product of claim 11 , wherein the calibration data includes a set of laboratory measurements used to calibrate one or more assumptions within a performance and capacity sizing model for a storage system.

16. The computer program product of claim 11 , wherein the first system map and the second system map each include a mapped curve representing an interaction between different aspects of performance data for the system resource.

17. The computer program product of claim 11 , wherein the first system map is determined by performing dynamic monitoring of utilization within a storage system to calculate utilization of the system resource based on customer usage.

18. The computer program product of claim 11 , wherein the calibration data is generated by running a set of synthetic benchmarks against a storage system and measuring a response in a laboratory setting.

19. The computer program product of claim 11 , wherein comparing the first system map to the second system map includes determining one or more differences between the first system map and the second system map, utilizing the one or more processors.

20. A system, comprising:
a processor; and
logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to:
identify aggregated customer performance data for a system resource;
filter the aggregated customer performance data to create a filtered portion of the aggregated customer performance data;
estimate one or more customer performance service time overheads for the system resource, utilizing the filtered portion of the aggregated customer performance data;
create a first system map for the system resource, utilizing the one or more customer performance service time overheads;
compare the first system map to a second system map created for the system resource utilizing calibration data; and
adjust the second system map, based on the comparison.

Assignees

• IBM

Inventors

• Peiro Eduardo Campos
• Martin Joshua D
• Mcnutt Bruce
• Miller Vernon W

Classifications

• G06F11/3447 Primary

  Performance evaluation by modeling · CPC title

• G06F11/3414

  Workload generation, e.g. scripts, playback · CPC title

• G06F2201/88

  Monitoring involving counting · CPC title

• G06F7/24

  Sorting, i.e. extracting data from one or more carriers, rearranging the data in numerical or other ordered sequence, and rerecording the sorted data on the original carrier or on a different carrier or set of carriers {sorting methods in general}(G06F7/36 takes precedence) · CPC title

• G06F11/3485

  for I/O devices · CPC title