SYNCHRONIZING UPDATES ACROSS CLUSTER FILESYSTEMS

• US 20130138616A1
• Filed: 08/20/2012
• Published: 05/30/2013
• Est. Priority Date: 11/29/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Gupta, Karan, Naik, Manoj P., Schmuck, Frank B., Tewari, Renu, Shah, Mansi A.
• Granted Patent: US 9,235,594 B2
• Time in Patent Office: Days
• US Class Current: 707/690
• CPC Class Codes: G06F 11/1471 involving logging of persistent data for recovery
• CPC Class Codes: G06F 16/178 Techniques for file synchronisation in file systems
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/2379 Updates performed during online database operations; commit processing

Abstract

Embodiments of the invention relate to synchronization of data in a shared pool of configurable computer resources. An image of the filesystem changes, including data and metadata, is captured in the form of a consistency point. Sequential consistency points are created, with changes to data and metadata in the filesystem between sequential consistency captured and placed in a queue for communication to a target filesystem at a target site. The changes are communicated as a filesystem operation, with the communication limited to the changes captured and reflected in the consistency point.

Claims

1. A method comprising:

periodically creating a consistency point in a source filesystem at a file set level, each consistency point representing filesystem data and metadata at a point-in-time to establish a recovery point, the periodic creation of the consistency point including creating a first consistency point at a first point-in-time and a second consistency point at a second point-in-time;

comparing the first consistency point with the second consistency point, including identifying differences between the first and second consistency points;

mapping a source filesystem object to a target filesystem object, based upon a corresponding relationship between the source and target filesystem objects;

applying the identified differences between the first and second consistency points, including replaying the identified differences as one or more filesystem operations.

2. The method of claim 1, wherein the step of applying the identified differences employs a mapping of a source filesystem inode to a target filesystem inode.

3. The method of claim 1, wherein the step of applying the identified differences includes identifying filesystem operations on filesystem objects using file names.

4. The method of claim 1, wherein the step of applying the identified differences between the first and second consistency points includes producing an exact delta of any metadata change and any data change, and replaying only those changes reflected in the exact delta.

5. The method of claim 1, further comprising generating an output file for the identified differences and replaying the output file as a series of filesystem operations where some of the operations may be replayed concurrently to a target site.

6. The method of claim 1, further comprising replaying the output file after communication failure between the source filesystem and the target filesystem.

7. The method of claim 1, wherein the source and target filesystems are heterogeneous filesystems.

8. The method of claim 1, further comprising reverting changes at the target filesystem by moving to an older consistency point.

9. The method of claim 1, wherein the first and second consistency points are not limited to successive consistency points.

10. A method comprising:

creating a first consistency point in a source filesystem at a file set level at a first point-in-time and creating a second consistency point in the source filesystem at a second point-in-time, the first consistency point representing filesystem data and metadata at a first point-in-time to establish a first recovery point and the second consistency point representing filesystem data and metadata at a second point-in-time to establish a second consistency point;

following a communication failure associated with the source filesystem, comparing the first consistency point with the second consistency point, including identifying changes between the first and second consistency points; and

applying the identified changes between the first and second consistency points, including replaying the identified changes as a filesystem operation based upon a mapping of a source filesystem object to a target filesystem object.

11. The method of claim 10, further comprising creating a third consistency point in the source filesystem at a third point-in-time, the third consistency point being sequential with the first and second consistency point, and removing the first consistency point.