ARCHIVING DATA FOR A DISTRIBUTED FILESYSTEM

• US 20130110779A1
• Filed: 12/21/2012
• Published: 05/02/2013
• Est. Priority Date: 05/03/2010
• Status: Active Grant

• Current Assignee: Panzura, Inc.
• Original Assignee: Panzura, Inc.
• Inventors: Taylor, John Richard, Chou, Randy Yen-pang, Davis, Andrew P.
• Granted Patent: US 8,799,414 B2
• Time in Patent Office: Days
• US Class Current: 707/624
• CPC Class Codes: G06F 16/113 Details of archiving lifecycle management in storage systems G06F3/0649; backup systems G06F11/1446
• CPC Class Codes: G06F 16/1844 Management specifically adapted to replicated file systems
• CPC Class Codes: G06F 16/185 Hierarchical storage management [HSM] systems, e.g. file migration or policies thereof details of archiving G06F16/11

Abstract

The disclosed embodiments provide a system that archives data for a distributed filesystem. Two or more cloud controllers collectively manage distributed filesystem data that is stored in one or more cloud storage systems; the cloud controllers cache and ensure data consistency for the stored data. During operation, a cloud controller determines that a cloud file in a previously stored data snapshot is no longer being actively referenced in the distributed filesystem. The cloud controller transfers this cloud file from the (first) cloud storage system to an archival cloud storage system, thereby reducing storage costs while preserving the data in the cloud file in case it is ever needed again.

Claims

1. A computer-implemented method for archiving data for a distributed filesystem, the method comprising:

collectively managing the data of the distributed filesystem using two or more cloud controllers, wherein collectively managing the data comprises;

upon receiving in a cloud controller new data from a client, sending from the cloud controller an incremental metadata snapshot for the new data, wherein the incremental metadata snapshot is received by the other cloud controllers of the distributed filesystem;

storing the data for the distributed filesystem in one or more cloud storage systems, wherein the cloud controllers cache and ensure data consistency for data stored in the cloud storage systems; and

sending an incremental data snapshot containing the new data from the cloud controller to a first cloud storage system;

at a subsequent time, determining that a cloud file in the incremental data snapshot is no longer actively referenced in the distributed filesystem; and

transferring the cloud file from the first cloud storage system to an archival cloud storage system.

2. The computer-implemented method of claim 1,

wherein write requests to the archival cloud storage system are immediately written to persistent storage in the archival cloud storage system;

wherein performing a data access in the archival cloud storage system in response to a read request takes one or more hours;

wherein the storage costs for the archival cloud storage system are substantially lower than the storage costs for a non-archival cloud storage system; and

wherein transferring the cloud file to the archival cloud storage system preserves the cloud file for future use while reducing storage costs for the distributed filesystem.

3. The computer-implemented method of claim 2, wherein determining that the cloud file is no longer actively referenced comprises:

periodically taking snapshots for the distributed filesystem;

analyzing file metadata changes for a time interval using two or more snapshots to determine that all of the data blocks stored in the cloud file were marked as deleted during the time interval;

determining that the cloud file actually storing the data blocks is still being stored in the first cloud storage system; and

transferring the cloud file from the first cloud storage system to the archival cloud storage system.

4. The computer-implemented method of claim 2, wherein determining that the cloud file is no longer actively referenced comprises:

tracking the status of each data block in the cloud file;

determining that all of the data blocks in the cloud file are associated with one or more files that have been marked as deleted in the metadata of the distributed filesystem;

determining that the cloud file is still being stored in the first cloud storage system; and

transferring the cloud file from the first cloud storage system to the archival cloud storage system.

5. The computer-implemented method of claim 4, wherein determining that all of the data blocks in the cloud file are associated with files that have been deleted from the distributed filesystem further comprises:

adding the cloud file to a delete list for a specified interval; and

only transferring the cloud file from the first cloud storage system to the archival cloud storage system if the contents of the cloud file are not accessed during the specified interval.

6. The computer-implemented method of claim 2, wherein transferring the cloud file from the first cloud storage system to the archival cloud storage system further comprises:

adding information for the cloud file to a lookup structure that facilitates accessing data from the archival cloud storage system based on at least one of when the archived data was actively referenced in the distributed filesystem and when the archived data stopped being actively referenced in the distributed filesystem; and

deleting the cloud file from the first cloud storage system.

7. The computer-implemented method of claim 6, wherein transferring the cloud file from the first cloud storage system to the archival cloud storage system further comprises:

transferring one or more snapshots to the archival cloud storage system; and

adding information for the one or more snapshots to the lookup structure.

8. The computer-implemented method of claim 7, wherein transferring the cloud file from the first cloud storage system to the archival cloud storage system further comprises:

determining that data for a deleted data file due to be archived spans two or more cloud files; and

writing the data for the deleted data file to the archival cloud storage system as a single contiguous unit.

9. The computer-implemented method of claim 2,

wherein the cloud controller manages the transfer of the cloud file from the first cloud storage system to the archival cloud storage system;

and

wherein the cloud controller prioritizes the transfer as a low-priority job to ensure that the file access performance of clients of the cloud controller is not negatively impacted.

10. The computer-implemented method of claim 9, wherein the transfer of the cloud file is delayed until the load of the distributed filesystem is low and a timeframe in which the cost of network bandwidth is low.

11. The computer-implemented method of claim 2,

wherein sending the incremental data snapshot to the first cloud storage system comprises mirroring the incremental data snapshot to the archival cloud storage system;

and

wherein transferring the cloud file from the first cloud storage system to the archival cloud storage system comprises deleting the cloud file from the first cloud storage system.

12. The computer-implemented method of claim 2,

wherein the cloud storage system is unaware of the organization and structure of the distributed filesystem;

wherein data stored in the distributed filesystem is indexed using a global address space;

wherein data is stored in the cloud storage system as cloud files, wherein each cloud file is uniquely indexed in the global address space;

wherein a second cloud controller receiving the incremental metadata snapshot uses a metadata entry in the incremental metadata snapshot to retrieve data in the incremental data snapshot; and

wherein using the metadata entry to retrieve data in the incremental data snapshot comprises;

determining from the metadata entry that a desired data block in the incremental data snapshot is not presently stored in the second cloud controller;

using a global address stored in the metadata entry to identify a cloud file in the cloud storage system that includes the data block;

downloading the identified cloud file to the second cloud controller; and

using an offset stored in the metadata entry to determine the location of the data block in the cloud file.

13. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for archiving data from a distributed filesystem, the method comprising:

collectively managing the data of the distributed filesystem using two or more cloud controllers, wherein collectively managing the data comprises;

upon receiving in a cloud controller new data from a client, sending from the cloud controller an incremental metadata snapshot for the new data, wherein the incremental metadata snapshot is received by the other cloud controllers of the distributed filesystem;

storing the data for the distributed filesystem in one or more cloud storage systems, wherein the cloud controllers cache and ensure data consistency for data stored in the cloud storage systems; and

sending an incremental data snapshot containing the new data from the cloud controller to a first cloud storage system;

at a subsequent time, determining that a cloud file in the incremental data snapshot is no longer actively referenced in the distributed filesystem; and

transferring the cloud file from the first cloud storage system to an archival cloud storage system.

14. The non-transitory computer-readable storage medium of claim 13,

wherein write requests to the archival cloud storage system are immediately written to persistent storage in the archival cloud storage system;

wherein performing a data access in the archival cloud storage system in response to a read request takes one or more hours;

wherein the storage costs for the archival cloud storage system are substantially lower than the storage costs for a non-archival cloud storage system; and

wherein transferring the cloud file to the archival cloud storage system preserves the cloud file for future use while reducing storage costs for the distributed filesystem.

15. The non-transitory computer-readable storage medium of claim 14, wherein determining that the cloud file is no longer actively referenced comprises:

periodically taking snapshots for the distributed filesystem;

analyzing file metadata changes for a time interval using two or more snapshots to determine that all of the data blocks stored in the cloud file were deleted during the time interval;

determining that the cloud file is still being stored in the first cloud storage system; and

transferring the cloud file from the first cloud storage system to the archival cloud storage system.

16. The non-transitory computer-readable storage medium of claim 14, wherein determining that the cloud file is no longer actively referenced comprises:

tracking the status of each data block in the cloud file;

determining that all of the data blocks in the cloud file are associated with one or more files that have been deleted from the distributed filesystem;

determining that the cloud file is still being stored in the first cloud storage system; and

transferring the cloud file from the first cloud storage system to the archival cloud storage system.

17. The non-transitory computer-readable storage medium of claim 16, wherein determining that all of the data blocks in the cloud file are associated with files that have been deleted from the distributed filesystem further comprises:

adding the cloud file to a delete list for a specified interval; and

only transferring the cloud file from the first cloud storage system to the archival cloud storage system if the contents of the cloud file are not accessed during the specified interval.

18. The non-transitory computer-readable storage medium of claim 14, wherein transferring the cloud file from the first cloud storage system to the archival cloud storage system further comprises:

adding information for the cloud file to a lookup structure that facilitates accessing data from the archival cloud storage system based on at least one of when the archived data was actively referenced in the distributed filesystem and when the archived data stopped being actively referenced in the distributed filesystem; and

deleting the cloud file from the first cloud storage system.

19. The non-transitory computer-readable storage medium of claim 18, wherein transferring the cloud file from the first cloud storage system to the archival cloud storage system further comprises:

transferring one or more snapshots to the archival cloud storage system; and

adding information for the one or more snapshots to the lookup structure.

20. A cloud controller that archives data from a distributed filesystem, comprising:

a processor;

a storage mechanism that stores metadata for the distributed filesystem; and

a storage management mechanism;

wherein two or more cloud controllers collectively manage the data of the distributed filesystem, wherein collectively managing the data comprises;

upon receiving in a cloud controller new data from a client, sending from the cloud controller an incremental metadata snapshot for the new data, wherein the incremental metadata snapshot is received by the other cloud controllers of the distributed filesystem;

storing the data for the distributed filesystem in one or more cloud storage systems, wherein the storage management mechanisms of the cloud controllers are configured to cache and ensure data consistency for data stored in the cloud storage systems; and

sending an incremental data snapshot containing the new data from the cloud controller to a first cloud storage system; and

wherein the storage management mechanism is configured to;

at a subsequent time, determine that a cloud file in the incremental data snapshot is no longer actively referenced in the distributed filesystem; and

transfer the cloud file from the first cloud storage system to an archival cloud storage system.