COMPRESSION SAMPLING IN TIERED STORAGE

• US 20170090776A1
• Filed: 09/25/2015
• Published: 03/30/2017
• Est. Priority Date: 09/25/2015
• Status: Active Grant

• Current Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Original Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Inventors: Kowles, Andrew M.
• Granted Patent: US 9,766,816 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/0611 in relation to response time
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Abstract

A method for data steering in tiered storage is described. In one embodiment, the method includes ranking a plurality of storage areas of a storage device according to at least one property of the plurality of storage areas. In some embodiments, the plurality of storage areas include at least a first storage area and a second storage area. The method includes obtaining a sample of data at the storage device, passing the sample of data through one or more compression codecs, and analyzing a result of passing the sample of data through the one or more compression codecs. In some embodiments, the result includes a score of compression savings associated with the sample of data. The method includes storing the data in one of the plurality of storage areas based at least in part on the analyzing the result of passing the sample of data through the one or more compression codecs.

Claims

1. A method for data steering in tiered storage, comprising:

ranking a plurality of storage areas of a storage device according to at least one property of the plurality of storage areas, the plurality of storage areas including at least a first storage area and a second storage area;

obtaining a sample of data at the storage device;

passing the sample of data through one or more compression codecs;

analyzing a result of passing the sample of data through the one or more compression codecs, wherein the result includes a score of compression savings associated with the sample of data; and

storing the data in one of the plurality of storage areas based at least in part on the analyzing the result of passing the sample of data through the one or more compression codecs.

2. The method of claim 1, comprising:

prior to passing the sample of data or in parallel with passing the sample of data through the one or more compression codecs, passing the sample through a data heat detection algorithm to detect one or more aspects of the data.

3. The method of claim 2, comprising:

passing the sample of data through a first compression algorithm while passing the sample of data through a second compression algorithm different than the first compression algorithm;

passing the sample through the heat detection algorithm while passing the sample of data through the first and second compression algorithms;

analyzing a result of passing the sample of data through the first and second compression algorithms and the heat detection algorithm; and

analyzing the result in relation to a history of past results of the analyzing.

4. The method of claim 2, comprising:

identifying a type of data based at least in part on the analyzing; and

upon determining the data is more likely than not to be metadata, compressing the data using a compression codec and output encoding optimized for metadata.

5. The method of claim 1, comprising:

detecting a file system type associated with the data based at least in part on analyzing the result of passing the sample of data through the one or more compression codecs; and

steering the data to one of the plurality of storage areas based at least in part on the detected file system type.

6. The method of claim 1, comprising:

based at least in part on data patterns learned from prior analysis of passing prior samples through the one or more compression codecs, bypassing at least one of;

passing samples of subsequent data through the heat detection algorithm; and

passing samples of subsequent data through the one or more compression codecs.

7. The method of claim 1, comprising:

analyzing multiple copies of the sample of data simultaneously, wherein the analyzing the multiple copies of the sample of data comprises passing the multiple copies of the sample of data through the one or more compression codecs using a different compression algorithm per copy of the sample; and

steering the data to one of the plurality of storage areas based at least in part on the analyzing of the multiple copies of the sample.

8. The method of claim 1, wherein the storage device includes a shingled storage area and a non-shingled storage area, the method comprising:

upon determining the sample of data satisfies a low compressibility threshold, based in least in part on passing the sample of data through the one or more compression codecs, storing the data in the shingled storage area; and

upon determining the sampled data satisfies a high compressibility threshold, based in least in part on passing the sample of data through the one or more compression codecs, storing the data in a non-shingled storage area.

9. The method of claim 1, wherein the storage device includes an array of disks, the method comprising:

determining which disks in the array of disks are active; and

steering the sampled data towards one or more active disks in the array of disks while bypassing one or more non-active disks in the array of disks to avoid a latency associated with spun-down disks of the non-active disks.

10. The method of claim 1, comprising:

sampling new data in real time as the new data is received to be written to the storage device.

11. The method of claim 1, wherein the at least one property of the plurality of storage areas includes one or more of type of storage media, media latency, reliability, data retention, addressability, data storage durability, media durability, media rate, write speed, read speed, sustained write speed, sector overhead time, head switch time, cylinder switch time, power consumption, and operation history.

12. A computing device configured for data steering in tiered storage, comprising:

a processor;

memory in electronic communication with the processor, wherein the memory stores computer executable instructions that when executed by the processor cause the processor to perform the steps of;

ranking a plurality of storage areas of a storage device according to at least one property of the plurality of storage areas, the plurality of storage areas including at least a first storage area and a second storage area;

obtaining a sample of data at the storage device;

passing the sample of data through one or more compression codecs;

analyzing a result of passing the sample of data through one or more compression codecs, wherein the result includes a score of compression savings associated with the sample of data; and

storing the data in one of the plurality of storage areas based at least in part on the analyzing the result of passing the sample of data through the one or more compression codecs.

13. The computing device of claim 12, wherein the instructions executed by the processor cause the processor to perform the step of:

prior to passing the sample of data through the one or more compression codecs, passing the sample through a data heat detection algorithm to detect one or more aspects of the data.

14. The computing device of claim 13, wherein the instructions executed by the processor cause the processor to perform the steps of:

passing the sample of data through a first compression algorithm while passing the sample of data through a second compression algorithm different than the first compression algorithm;

passing the sample through the heat detection algorithm while passing the sample of data through the first and second compression algorithms;

analyzing a result of passing the sample of data through the first and second compression algorithms and the heat detection algorithm; and

analyzing the result in relation to a history of past results of the analyzing.

15. The computing device of claim 13, wherein the instructions executed by the processor cause the processor to perform the step of:

identifying a type of data based at least in part on the analyzing; and

upon determining the data is more likely than not to be metadata, compressing the data using a compression code and output encoding optimized for metadata.

16. The computing device of claim 12, wherein the instructions executed by the processor cause the processor to perform the steps of:

detecting a file system type associated with the data based at least in part on analyzing the result of passing the sample of the data through the one or more compression codecs; and

steering the data to one of the plurality of storage areas based at least in part on the detected file system type.

17. The computing device of claim 12, wherein the instructions executed by the processor cause the processor to perform the steps of:

based at least in part on data patterns learned from prior analysis of passing prior samples through the one or more compression codecs, bypassing at least one of;

passing samples of subsequent data through the heat detection algorithm; and

passing samples of subsequent data through the one or more compression codecs.

18. The computing device of claim 12, wherein the instructions executed by the processor cause the processor to perform the steps of:

analyzing multiple samples of data simultaneously, wherein the analyzing multiple samples of data comprises passing the multiple samples through the one or more compression codecs using a different compression algorithm per sample; and

steering the data to one of the plurality of storage areas based at least in part on the analyzing of the multiple samples.

19. A non-transitory computer-readable storage medium storing computer executable instructions that when executed by a processor cause the processor to perform the steps of:

ranking a plurality of storage areas of a storage device according to at least one property of the plurality of storage areas, the plurality of storage areas including at least a first storage area and a second storage area;

obtaining a sample of data at the storage device;

passing the sample of data through one or more compression codecs;

analyzing a result of passing the sample of data through one or more compression codecs, wherein the result includes a score of compression savings associated with the sample of data; and

storing the data in one of the plurality of storage areas based at least in part on the analyzing the result of passing the sample of data through the one or more compression codecs.

20. The computer-program product of claim 19, wherein the instructions executed by the processor cause the processor to perform the steps of:

prior to passing the sample of data through the one or more compression codecs, passing the sample through a data heat detection algorithm to detect one or more aspects of the data;

passing the sample of data through a first compression algorithm while passing the sample of data through a second compression algorithm different than the first compression algorithm;

passing the sample through the heat detection algorithm while passing the sample of data through the first and second compression algorithms;

analyzing a result of passing the sample of data through the first and second compression algorithms and the heat detection algorithm; and

analyzing the result in relation to a history of past results of the analyzing.