Efficient read by reconstruction

Patent metadata

Field	Value
Publication number	US-12008266-B2
Application number	US-202217724149-A
Country	US
Kind code	B2
Filing date	Apr 19, 2022
Priority date	Sep 15, 2010
Publication date	Jun 11, 2024
Grant date	Jun 11, 2024

Abstract

A method for efficient reads by reconstruction may determining an expected read latency for reading data from a primary read location of a plurality of storage devices, determining an expected reconstruction latency for reconstructing the data using reconstruction data, wherein portions of the reconstruction data are stored at a plurality of alternative read locations of the plurality of storage devices, reading the portions of the reconstruction data from the plurality of alternative read locations of the plurality of storage devices, and reconstructing the data stored at the primary read location using the reconstruction data, wherein the expected reconstruction latency is lower than the expected read latency.

First claim

What is claimed:

1. A storage system comprising:
a plurality of storage devices; and
a storage controller operatively coupled to the storage devices, the storage controller comprising a processing device, the processing device configured to implement steps comprising:
determining an expected read latency for reading data from a primary read location of the plurality of storage devices;
determining an expected reconstruction latency for reconstructing the data using reconstruction data, wherein portions of the reconstruction data are stored at a plurality of alternative read locations of the plurality of storage devices;
reading the portions of the reconstruction data from the plurality of alternative read locations of the plurality of storage devices; and
reconstructing the data stored at the primary read location using the reconstruction data, wherein the expected reconstruction latency is lower than the expected read latency.

2. The storage system of claim 1 further comprising determining that the expected reconstruction latency is lower than the expected read latency by a set threshold.

3. The storage system of claim 1 wherein a read location comprises a die of a storage device.

4. The storage system of claim 1 wherein the expected reconstruction latency is determined based on at least one of a die queue depth, a drive queue depth, or a device profile for the each of the plurality of alternative read locations and the expected read latency is determined based on at least one of a die queue depth, a drive queue depth, or a latency profile for the primary read location.

5. The storage system of claim 1 wherein the processing device is further configured to implement steps comprising:
determining a second expected read latency for reading second data from a primary read location for the second data of the plurality of storage devices;
determining a second expected reconstruction latency for reconstructing the second data using reconstruction data stored at a plurality of alternative read locations for the second data of the plurality of storage devices;
determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction, wherein the second expected reconstruction latency is lower than the second expected read latency; and
reading the second data from the primary read location of the second data.

6. The storage system of claim 5 wherein determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction comprises determining that at least one drive of the plurality of storage devices has a quantity of active dies that exceeds a threshold.

7. The storage system of claim 5 wherein determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction comprises determining that at least one die of the plurality of storage devices will exceed a power consumption limit.

8. A method of efficient reads by reconstruction, comprising:
determining an expected read latency for reading data from a primary read location of a plurality of storage devices;
determining an expected reconstruction latency for reconstructing the data using reconstruction data, wherein portions of the reconstruction data are stored at a plurality of alternative read locations of the plurality of storage devices;
reading the portions of the reconstruction data from the plurality of alternative read locations of the plurality of storage devices; and
reconstructing the data stored at the primary read location using the reconstruction data, wherein the expected reconstruction latency is lower than the expected read latency.

9. The method of claim 8 wherein the expected reconstruction latency is lower than the expected read latency by a set threshold.

10. The method of claim 8 wherein a read location comprises a die of a storage device.

11. The method of claim 8 , wherein the expected reconstruction latency is determined based on at least one of a die queue depth, a drive queue depth, or a device profile for the each of the plurality of alternative read locations and the expected read latency is determined based on at least one of a die queue depth, a drive queue depth, or a latency profile for the primary read location.

12. The method of claim 8 , further comprising:
determining a second expected read latency for reading second data from a primary read location for the second data of the plurality of storage devices;
determining a second expected reconstruction latency for reconstructing the second data using reconstruction data stored at a plurality of alternative read locations for the second data of the plurality of storage devices;
determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction, wherein the second expected reconstruction latency is lower than the second expected read latency; and
reading the second data from the primary read location of the second data.

13. The method of claim 12 wherein determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction comprises determining that at least one drive of the plurality of storage devices has a quantity of active dies that exceeds a threshold.

14. The method of claim 12 wherein determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction comprises determining that at least one die of the plurality of storage devices will exceed a power consumption limit.

15. A non-transitory computer readable storage medium storing instructions, which when executed, cause a processing device of a storage controller to implement steps comprising:
determining an expected read latency for reading data from a primary read location of a plurality of storage devices;
determining an expected reconstruction latency for reconstructing the data using second reconstruction data, wherein portions of the second reconstruction data are stored at a plurality of alternative read locations of the plurality of storage devices;
reading the portions of the reconstruction data from the plurality of alternative read locations of the plurality of storage devices; and
reconstructing the data stored at the primary read location using the reconstruction data, wherein the expected reconstruction latency is lower than the expected read latency.

16. The non-transitory computer readable storage medium of claim 15 , wherein a read location comprises a die of a storage device.

17. The non-transitory computer readable storage medium of claim 15 wherein the expected reconstruction latency is determined based on at least one of a die queue depth, a drive queue depth, or a device profile for the each of the plurality of alternative read locations and the expected read latency is determined based on at least one of a die queue depth, a drive queue depth, or a latency profile for the primary read location.

18. The non-transitory computer readable storage medium of claim 17 wherein determining that at least one storage device of the plurality of storage devices will reach a resource limit during read by reconstruction comprises determining that at least one Drive of the plurality of storage devices has a quantity of active dies that exceeds a threshold.

19. The non-transitory computer readable storage medium o

Assignees

• Pure Storage Inc

Inventors

• Wang Vincent
• Fay Mark
• He Jun
• Fan Renjie
• Colgrove John

Classifications

• G06F3/0634

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

• G06F3/0653

  Monitoring storage devices or systems · CPC title

• G06F3/0629

  Configuration or reconfiguration of storage systems · CPC title

• G06F3/0613

  in relation to throughput · CPC title

• G06F3/0655

  Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices · CPC title