Variable drive health determination and data placement

• US 9,037,921 B1
• Filed: 03/29/2012
• Issued: 05/19/2015
• Est. Priority Date: 03/29/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Brooker, Marc J., Holgers, Tobias L., Parthasarathy, Madhuvanesh, Wei, Danny
• Primary Examiner(s): Bonzo, Bryce
• Assistant Examiner(s): Arcos, Jeison C
• Application Number:
  US13/433,730
• Time in Patent Office: 1,146 Days
• Field of Search: 714/8, 714/13, 714/42, 714/71, 714/723, 709/219, 709/224, 709/232, 709/233, 369/53.1
• US Class Current: 714/47.1
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 11/1458 Management of the backup or restore process
• CPC Class Codes: G06F 11/30 Monitoring
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 12/02 Addressing or allocation; Relocation program address sequencing G06F9/00; arrangements for selecting an address in a digital store G11C8/00
• CPC Class Codes: G06F 2201/815 Virtual
• CPC Class Codes: G06F 2201/86 Event-based monitoring
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0683 Plurality of storage devices

Abstract

The relative health of data storage drives may be determined based, at least in some aspects, on data access information and/or other drive operation information. In some examples, upon receiving the operation information from a computing device, a health level of a drive may be determined. The health level determination may be based at least in part on operating information received from a client entity. Additionally, a storage space allocation instruction or operation may be determined for execution. The allocation instruction or operation determined to be performed may be based at least in part on the determined health level.

Claims

1. A computer-implemented method for data storage management, comprising:

under control of one or more computer systems configured with executable instructions,

receiving, from a client computing device of the one or more computer systems, operating information associated with a first data storage device operationally attached to the client computing device, the operating information indicating an ability to perform data operations on data stored in the first data storage device;

determining, based at least in part on the operating information, a health level for the first data storage device attached to the client computing device, the determined health level from a plurality of possible health levels, where the plurality of possible health levels includes at least a healthy level, a suspect level, and an unhealthy level, the healthy level has a lower probability of failure than the suspect level and the unhealthy level, and the suspect level has a lower level of probability of failure than the unhealthy level;

receiving an operational parameter associated with first data stored in the first data storage device on behalf of the client computing device; and

when it is determined that the health level of the first data storage device is within the suspect level and the received operational parameter is above a predefined amount;

causing the first data to be stored in a second data storage device determined to be within the healthy level based at least in part on the received operational parameter; and

reallocating storage space of the first data storage device such that it is only available for reading or writing second data with a second operational parameter below the predefined amount based at least in part on the health level of the first data storage device.

2. The computer-implemented method of claim 1, further comprising:

when it is determined that the health level of the first data storage device is within the unhealthy level;

causing the first data to be stored in a second data storage device within the healthy level; and

causing one or more actions to be performed that disable reading or writing to storage space of the first data storage device.

3. The computer-implemented method of claim 1, wherein the operating information is based at least in part on a number of lost data packets during a client read or write operation of the first data storage device.

4. The computer-implemented method of claim 1, wherein the operational parameter is based at least in part on at least one of a desired reliability level, a desired performance level, a desired persistence level, or a desired security level.

20. The computer-implemented method of claim 1, wherein the computer-implemented method further includes:

determining that the health level of the first data storage device is within the suspect level; and

preventing new data from being written to the first data storage device.

21. The computer-implemented method of claim 1, wherein the computer-implemented method further includes:

determining that the health level of the first data storage device is within the suspect level; and

performing one or more diagnostics tests on the first data storage device.

5. A computer-implemented method for data storage management, comprising:

under control of one or more computer systems configured with executable instructions,

receiving, from a client entity of the one or more computer systems, an operating parameter associated with a first storage system operationally attached to the client entity;

determining, based at least in part on the received operating parameter, a health level of the first storage system, wherein the health level is based at least in part on a suspect level indicating that the first storage system has a higher probability of failure than a storage system with a healthy level health level; and

when it is determined that (i) the health level of the first storage fails a set of one or more criteria, and (ii) a data parameter, associated with first data stored in the first storage system on behalf of the client entity, is above a second predefined amount;

causing the first data to be stored in a second storage system with a second health level above the health level.

6. The computer-implemented method of claim 5, wherein a third health level comprising an unhealthy level indicates a storage device with a higher probability of failure than the suspect level.

7. The computer-implemented method of claim 6, further comprising:

when it is determined that (i) the health level of the first storage system comprises an unhealthy level and (ii) a data parameter, associated with first data stored in the first storage system on behalf of the client entity, is above the second predefined amount;

causing the first data to be stored in a third storage system with the health level comprising the healthy level; and

causing one or more actions to be performed that disable reading or writing to a storage space of the first storage system.

8. The computer-implemented method of claim 6, further comprising:

when it is determined that (i) the health level of the first storage system comprises an unhealthy level and (ii) a data parameter, associated with first data stored in the first storage system on behalf of the client entity, is below the second predefined amount;

causing the first data to be stored in a third storage system with the health level comprising the suspect level; and

causing one or more actions to be performed that disable reading or writing to a storage space of the first storage system.

9. The computer-implemented method of claim 5, further comprising reallocating storage space of the first storage system such that it is not available for storing second data with a data parameter above the second predefined amount.

22. The computer-implemented method of claim 5, further comprising:

when it is determined that (i) the health level of the first storage system comprises an suspect level and (ii) a data parameter, associated with first data stored in the first storage system on behalf of the client entity, is below the second predefined amount;

causing the first data to be stored in a third storage system with a health level of the third storage system comprising the healthy level; and

causing one or more actions to be performed that disable writing to the first storage system.

10. A system for data storage management, comprising:

at least one memory that stores computer-executable instructions;

at least one processor configured to access the at least one memory, wherein the at least one processor is configured to execute the computer-executable instructions to;

receive, from a client entity of the system, information associated with operation of a storage device;

determine, based at least in part on the received information, health information of the storage device, the health information indicating a health level from a plurality of different health levels above a predefined health level;

receive, an operational parameter associated with data stored in the storage device on behalf of the client entity;

determine, based at least in part on the determined health information of the storage device and the received operational parameter, an instruction to execute associated with the data stored in the storage device; and

issue the instruction, the instruction causing allocation of the storage device such that data stored in the storage device is limited to data within a predefined performance criteria range.

11. The system of claim 10, wherein the information associated with operation of the storage device is based at least in part on a latency for a read request made, by the client entity, to the storage device.

12. The system of claim 10, wherein the information associated with operation of the storage device is based at least in part on a latency for a write request made, by the client entity, to the storage device.

13. The system of claim 10, wherein the plurality of different health levels comprises a multi-variable sliding scale of health levels.

14. The system of claim 13, wherein determining the instruction to execute is based at least in part on a location, of the storage device, on the sliding scale of health levels.

23. The system of claim 10, wherein the at least one memory further includes computer-executable instructions that, when executed by the at least one processor, cause the system to store the data stored in the storage device in a second storage device with a second health level above a certain health level.

15. One or more non-transitory computer-readable media collectively storing computer-executable instructions for data storage management that, when executed by one or more processors, configures the one or more processors to perform operations comprising:

determining, based at least in part on remote storage space operation information received from a client entity of a computing system, a health level of a remote storage space, the health level selected from one or more operational health levels at least between a predefined lowest operational health level and a predefined highest operational health level;

receiving an operational parameter associated with data stored in the remote storage space on behalf of the client entity;

determining, based at least in part on the determined health level of the remote storage space and the received operational parameter, a storage space allocation instruction for the one or more processors to execute associated with data stored in the remote storage space that is associated with the client entity; and

causing the execution of the storage space allocation instruction to affect the data stored in the remote storage space that is associated with the client entity such that the data stored in the remote storage space is stored in a second remote storage space with a second health level above a predefined level.

16. The one or more non-transitory computer-readable media of claim 15, wherein the remote storage space is virtually attached to the client entity of the computing system.

17. The one or more non-transitory computer-readable media of claim 15, wherein the health level of the remote storage space is based at least in part on a level on a sliding scale of health.

18. The one or more non-transitory computer-readable media of claim 17, wherein the sliding scale of health comprises at least a healthy level, a suspect level that is less healthy than the healthy level, and an unhealthy level that is less healthy than the suspect level.

19. The one or more non-transitory computer-readable media of claim 15, wherein the operation information is based at least in part on at least one of a write latency or a read latency associated with the storage space.

24. The one or more non-transitory computer-readable media of claim 15, wherein the instructions further comprise instructions that, when executed by the one or more processors, cause the computer system to disable writing to the remote storage space.