Hybrid data tiering

Patent metadata

Field	Value
Publication number	US-10936238-B2
Application number	US-201816195845-A
Country	US
Kind code	B2
Filing date	Nov 19, 2018
Priority date	Nov 28, 2017
Publication date	Mar 2, 2021
Grant date	Mar 2, 2021

Abstract

Hybrid data tiering, including: replicating multiple data objects from a first storage location on a first computer system to a second storage location at a second computer system; identifying, in accordance with a retention policy, some of the multiple data objects to continue storing at the first storage location, wherein all of the multiple data objects remain stored at the second storage location; and selecting the identified some of the multiple data objects to remain stored at the first storage location.

First claim

What is claimed is:

1. A method comprising:
replicating multiple data objects from a first storage location on a first computer system to a second storage location at a second computer system;
selecting, in accordance with a retention policy, some of the multiple data objects to continue storing at the first storage location,
wherein the retention policy specifies that a greater number of references by applications to a given object correspond to a higher priority for the given object remaining stored at the first storage location,
wherein all of the multiple data objects remain stored at the second storage location, and
wherein, in response to a request for one of the multiple data objects not stored at the first storage location, the one of the multiple data objects not stored at the first storage location is retrieved from the second storage location.

2. The method of claim 1 , wherein the first storage location is part of a storage system at a first geographic location, and wherein the second storage location is implemented within a remote, cloud services provider.

3. The method of claim 2 , wherein the cloud services provider implements the second storage location as data object store or block storage.

4. The method of claim 1 , wherein the first storage location is part of a local storage system at a first geographic location, and wherein the second storage location is implemented within a remote storage system.

5. The method of claim 1 , wherein the retention policy is based upon a historical pattern of storage access from one or more processes operating on storage at the first storage location.

6. The method of claim 1 , wherein the retention policy specifies different retention behavior for different users, or wherein the retention policy specifies different retention behavior for different priority processes operating at the first storage location.

7. The method of claim 1 , wherein the selected data objects to remain stored at the first storage location correspond to a data backup, and wherein the retention policy specifies a length of time for the selected data objects to remain stored at the first storage location based on an expected window of time within which data backup is expected to be referenced, and wherein the data objects among the multiple data objects not selected to remain stored at the first storage location are deleted.

8. The method of claim 1 , wherein one or more given data objects not selected to remain stored at the first storage location are not removed until after the one or more given data objects are successfully stored at the second storage location.

9. An apparatus comprising:
one or more hardware processors;
one or more data storage resources; and
a hybrid data tiering controller module configured to:
replicate multiple data objects from a first storage location on a first computer system to a second storage location at a second computer system;
select, in accordance with a retention policy, some of the multiple data objects to continue storing at the first storage location,
wherein the retention policy specifies that a greater number of references by applications to a given object correspond to a higher priority for the given object remaining stored at the first storage location,
wherein all of the multiple data objects remain stored at the second storage location, and
wherein, in response to a request for one of the multiple data objects not stored at the first storage location, the one of the multiple data objects not stored at the first storage location is retrieved from the second storage location.

10. The apparatus of claim 9 , wherein the first storage location is part of a storage system at a first geographic location, and wherein the second storage location is implemented within a remote, cloud services provider.

11. The apparatus of claim 9 , wherein the cloud services provider implements the second storage location as data object store or block storage.

12. The apparatus of claim 9 , wherein the first storage location is part of a local storage system at a first geographic location, and wherein the second storage location is implemented within a remote storage system.

13. The apparatus of claim 9 , wherein the retention policy is based upon a historical pattern of storage access from one or more processes operating on storage at the first storage location.

14. The apparatus of claim 9 , wherein the retention policy specifies different retention behavior for different users, or wherein the retention policy specifies different retention behavior for different priority processes operating at the first storage location.

15. The apparatus of claim 9 , wherein the selected data objects to remain stored at the first storage location correspond to a data backup, and wherein the retention policy specifies a length of time for the selected data objects to remain stored at the first storage location based on an expected window of time within which data backup is expected to be referenced, and wherein the data objects among the multiple data objects not selected to remain stored at the first storage location are deleted.

16. The apparatus of claim 9 , wherein one or more given data objects not selected to remain stored at the first storage location are not removed until after the one or more given data objects are successfully stored at the second storage location.

17. A computer program product disposed upon a computer readable storage medium, the computer program product comprising computer program instructions that, when executed, cause a computer to carry out the steps of:
replicating multiple data objects from a first storage location on a first computer system to a second storage location at a second computer system;
selecting, in accordance with a retention policy, some of the multiple data objects to continue storing at the first storage location,
wherein the retention policy specifies that a greater number of references by applications to a given object correspond to a higher priority for the given object remaining stored at the first storage location,
wherein all of the multiple data objects remain stored at the second storage location,
and wherein, in response to a request for one of the multiple data objects not stored at the first storage location, the one of the multiple data objects not stored at the first storage location is retrieved from the second storage location.

18. The computer program product of claim 17 , wherein the first storage location is part of a storage system at a first geographic location, and wherein the second storage location is implemented within a remote, cloud services provider.

Assignees

• Pure Storage Inc

Inventors

• Power Tyler
• Cox Mark
• Emberson Mark

Classifications

• G06F3/0649

  Lifecycle management · CPC title

• G06F3/0619

  in relation to data integrity, e.g. data losses, bit errors · CPC title

• G06F3/0683

  Plurality of storage devices · CPC title

• G06F3/0604

  Improving or facilitating administration, e.g. storage management · CPC title

• G06F3/0685

  Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays · CPC title