Determining an optimal maintenance time for a data storage system utilizing historical data

Patent metadata

Field	Value
Publication number	US-11194476-B2
Application number	US-201916559366-A
Country	US
Kind code	B2
Filing date	Sep 3, 2019
Priority date	Sep 3, 2019
Publication date	Dec 7, 2021
Grant date	Dec 7, 2021

Abstract

A computer-implemented method according to one embodiment includes receiving and storing historical data for historical data jobs performed within a data storage system; determining an optimal maintenance time for the data storage system, utilizing the stored historical data; determining a timing in which storage devices within the data storage system are taken offline, utilizing the optimal maintenance time and the stored historical data; and preparing the data storage system for one or more maintenance operations, utilizing the determined timing.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving and storing historical data for historical data jobs performed within a data storage system;
determining an optimal maintenance time for the data storage system, utilizing the stored historical data;
determining a timing in which storage devices within the data storage system are taken offline, utilizing the optimal maintenance time and the stored historical data; and
preparing the data storage system for one or more maintenance operations, utilizing the determined timing.

2. The computer-implemented method of claim 1 , wherein the data storage system includes a cluster of tape drives.

3. The computer-implemented method of claim 1 , wherein the data storage system includes a cluster of virtualized tape drives.

4. The computer-implemented method of claim 1 , wherein the historical data includes:
a size of data that was transferred between the data storage system and one or more client devices,
a source of a request for the data transfer,
a time needed to complete an historical data job, and
runtime environment data.

5. The computer-implemented method of claim 1 , wherein determining the optimal maintenance time includes generating a weighted curve based on the stored historical data.

6. The computer-implemented method of claim 1 , wherein the optimal maintenance time includes a time at which one or more maintenance operations are to be performed within the data storage system.

7. The computer-implemented method of claim 1 , wherein a data storage system drain-out process includes a process by which the storage devices within the data storage system are progressively taken offline.

8. The computer-implemented method of claim 1 , wherein a timing of a data storage system drain-out process is determined based on the optimal maintenance time.

9. The computer-implemented method of claim 1 , wherein before a start of a data storage system drain-out process, each storage device is compared to stored historical data for that storage device to determine a remaining job runtime for the storage device, and a storage device with a largest remaining job runtime is used to calculate a time at which the data storage system drain-out process begins.

10. The computer-implemented method of claim 1 , wherein during a data storage system drain-out process:
one or more incoming data jobs are received by the data storage system,
each of the incoming data jobs and current runtime environment data is compared against historical job runtimes and runtime environment data to determine a runtime for the incoming data jobs, and
each of the incoming data jobs is conditionally assigned to a storage device within the data storage system, based on the runtime for the incoming data jobs.

11. The computer-implemented method of claim 1 , wherein preparing the data storage system for one or more maintenance operations includes implementing a data storage system drain-out process at a calculated time.

12. The computer-implemented method of claim 1 , wherein preparing the data storage system for one or more maintenance operations includes conditionally assigning one or more incoming data jobs to one or more storage devices during a data storage system drain-out process.

13. The computer-implemented method of claim 1 , wherein one or more maintenance operations are performed within the data storage system after the data storage system has been prepared.

14. A computer program product comprising one or more non-transitory computer readable storage media, and program instructions collectively stored on the one or more non-transitory computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising:
receiving and storing, by the one or more processors, historical data for historical data jobs

performed within a data storage system;
determining, by the one or more processors, an optimal maintenance time for the data storage

system, utilizing the stored historical data;
determining, by the one or more processors, a timing in which storage devices within the data

storage system are taken offline, utilizing the optimal maintenance time and the stored historical data; and
preparing, by the one or more processors, the data storage system for one or more maintenance

operations, utilizing the determined timing.

15. The computer program product of claim 14 , wherein the data storage system includes a cluster of tape drives.

16. The computer program product of claim 14 , wherein the data storage system includes a cluster of virtualized tape drives.

17. The computer program product of claim 14 , wherein the historical data includes:
a size of data that was transferred between the data storage system and one or more client devices,
a source of a request for the data transfer,
a time needed to complete an historical data job, and
runtime environment data.

18. The computer program product of claim 14 , wherein determining the optimal maintenance time includes generating a weighted curve based on the stored historical data.

19. The computer program product of claim 14 , wherein the optimal maintenance time includes a time at which one or more maintenance operations are to be performed within the data storage system.

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:
receive and store historical data for historical data jobs performed within a data storage system;
determine an optimal maintenance time for the data storage system, utilizing the stored historical data;
determine a timing in which storage devices within the data storage system are taken offline, utilizing the optimal maintenance time and the stored historical data; and
prepare the data storage system for one or more maintenance operations, utilizing the determined timing.

Assignees

• IBM

Inventors

• Neff Stefan
• Krick Frank
• Rueger Erik

Classifications

• G06F3/0653

  Monitoring storage devices or systems · CPC title

• G06F3/0634

  by changing the state or mode of one or more devices · CPC title

• G06F11/3423

  where the assessed time is active or idle time · CPC title

• G06F3/0617 Primary

  in relation to availability · CPC title

• G11B27/36 Primary

  Monitoring, i.e. supervising the progress of recording or reproducing {(for digital recording G11B20/00 and s.gr.; for monitoring, testing or measuring of TV recorders of the type covered by H04N5/76 and subgroups, see H04N17/06)} · CPC title