Self-detecting storage bottleneck while handling sequential I/O operations

• US 9,063,669 B2
• Filed: 04/09/2013
• Issued: 06/23/2015
• Est. Priority Date: 04/09/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Shalev, Ori, Fischer-Toubol, Jonathan, Haklay, Omer, Milstein, Nir
• Primary Examiner(s): Sun, Michael
• Application Number:
  US13/859,108
• Publication Number:
  US 20140304428A1
• Time in Patent Office: 805 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0638 Organizing or formatting or addressing of data
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Delay commands are injected into sequential input/output (I/O) requests and the effects of the injected delay commands are measured for determining whether a storage system handling the sequential input/output (IO) requests is causing a bottleneck.

Claims

1. A method for self-detecting storage bottleneck by a processor device in a computing environment, the method comprising:

injecting delay commands into sequential input/output (I/O) requests and measuring effects of the injected delay commands for determining whether a storage system handling the sequential input/output (IO) requests is causing a bottleneck,

delaying a processing of the sequential I/O requests for a time period when injecting a delay command, and

delaying a response after processing the sequential I/O requests for a time period when injecting a delay command.

2. The method of claim 1, further including tracking the sequential I/O requests.

3. The method of claim 2, further including performing one of:

associating each I/O request with a specified one of the sequential I/O requests,

requesting a write operation at an end offset of a recently completed I/O request that is associated with the specified one of the sequential I/O requests, and

injecting delay commands into the sequential I/O requests when the sequential I/O requests that are being tracked are stable.

4. The method of claim 1, further including delaying patterns of the sequential I/O requests for a time period upon injecting the delay commands, wherein one of the patterns of the sequential I/O requests includes at least two consecutive sequential I/O requests.

5. The method of claim 1, further including performing one of:

injecting delayed patterns into an execution of the sequential I/O requests in the storage system, and

comparing the delayed pattern to a delayed effect pattern of the sequential I/O requests using a comparison module.

6. The method of claim 5, further including determining an output of the comparison module is positive if the delayed pattern is similar to the delayed effect pattern storage system, wherein the positive output of the comparison module indicates the storage system is a critical path causing the bottleneck.

7. The method of claim 6, further including using the positive output as a factor in determining a type of processing the storage system performs on data.

8. A system for self-detecting storage bottleneck in a computing environment, comprising:

a storage system;

a comparison module in association with the storage system; and

at least one processor device, in association with the storage system and the comparison module, operable in the computing environment, wherein processor device is adapted for;

injects delay commands into sequential input/output (I/O) requests and measuring effects of the injected delay commands for determining whether a storage system handling the sequential input/output (IO) requests is causing a bottleneck,

delaying a processing of the sequential I/O requests for a time period when injecting a delay command, and

delaying a response after processing the sequential I/O requests for a time period when injecting a delay command.

9. The system of claim 8, wherein the at least one processor device tracks the sequential I/O requests.

10. The system of claim 9, wherein the at least one processor device performs one of:

associating each I/O request with a specified one of the sequential I/O requests,

requesting a write operation at an end offset of a recently completed I/O request that is associated with the specified one of the sequential I/O requests, and

injecting delay commands into the sequential I/O requests when the sequential I/O requests that are being tracked are stable.

11. The system of claim 8, wherein the at least one processor device delays patterns of the sequential I/O requests for a time period upon injecting the delay commands, wherein one of the patterns of the sequential I/O requests includes at least two consecutive sequential I/O requests.

12. The system of claim 8, wherein the at least one processor device performs one of:

injecting delayed patterns into an execution of the sequential I/O requests in the storage system, and

comparing the delayed pattern to a delayed effect pattern of the sequential I/O requests using the comparison module.

13. The system of claim 12, wherein the at least one processor device determines an output of the comparison module is positive if the delayed pattern is similar to the delayed effect pattern storage system, wherein the positive output of the comparison module indicates the storage system is a critical path causing the bottleneck.

14. The system of claim 13, wherein the at least one processor device uses the positive output as a factor in determining a type of processing the storage system performs on data.

15. A computer program product for self-detecting storage bottleneck in a computing environment by a processor device, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion that injects delay commands into sequential input/output (I/O) requests and measuring effects of the injected delay commands for determining whether a storage system handling the sequential input/output (IO) requests is causing a bottleneck.

16. The computer program product of claim 15, further including a second executable portion that tracks the sequential I/O requests.

17. The computer program product of claim 16, further including a third executable portion that performs one of:

associating each I/O request with a specified one of the sequential I/O requests,

requesting a write operation at an end offset of a recently completed I/O request that is associated with the specified one of the sequential I/O requests, and

injecting delay commands into the sequential I/O requests when the sequential I/O requests that are being tracked are stable.

18. The computer program product of claim 15, further including a second executable portion that performs one of:

delaying a processing of the sequential I/O requests for a time period when injecting a delay command, and

delaying a response after processing the sequential I/O requests for a time period when injecting a delay command.

19. The computer program product of claim 15, further including a second executable portion that delays patterns of the sequential I/O requests for a time period upon injecting the delay commands, wherein one of the patterns of the sequential I/O requests includes at least two consecutive sequential I/O requests.

20. The computer program product of claim 15, further including a second executable portion that performs one of:

injecting delayed patterns into an execution of the sequential I/O requests in the storage system, and

comparing the delayed pattern to a delayed effect pattern of the sequential I/O requests using a comparison module.

21. The computer program product of claim 20, further including a third executable portion that determines an output of the comparison module is positive if the delayed pattern is similar to the delayed effect pattern storage system, wherein the positive output of the comparison module indicates the storage system is a critical path causing the bottleneck.

22. The computer program product of claim 21, further including a fourth executable portion that uses the positive output as a factor in determining a type of processing the storage system performs on data.