Prefetching remote files on local disk space

• US 7,865,468 B2
• Filed: 02/29/2008
• Issued: 01/04/2011
• Est. Priority Date: 02/29/2008
• Status: Expired due to Fees

• Current Assignee: LinkedIn Corporation (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Naineni, Malahal R.
• Primary Examiner(s): LE, DEBBIE M
• Application Number:
  US12/040,332
• Publication Number:
  US 20090222453A1
• Time in Patent Office: 1,040 Days
• Field of Search: 707204-205
• US Class Current: 707/636
• CPC Class Codes: G06F 16/172 Caching, prefetching or hoarding of files

Abstract

A technique for enhancing the transfer of files from a source network host to a destination network host includes accessing a file stored on the source host from the destination host, caching a local copy of the file on the destination host, and prefetching all remaining files in a file system group of which the file is a member by caching local copies thereof on the destination host.

Claims

1. A method for enhancing the transfer of files from a source network host to a destination network host via a communication interface, comprising:

accessing a file stored on said source host from said destination host via said communication interface;

said accessing being initiated by a request to open said file for reading or writing at said destination host as part of a destination host work session involving a file system group that contains said file;

said destination host copying contents of said file from said source host to said destination host via said communication interface and caching a local copy of said file on said destination host;

said accessing being completed by opening said cached local copy of said file on said destination host;

said destination host using prefetch logic to determine what files constitute said file system group; and

said destination host prefetching all remaining files in said file system group determined by said prefetch logic by copying contents of said remaining files from said source host to said destination host via said communication interface and caching local copies thereof on said destination host so that said remaining files are accessible locally at said destination host for use during said work session.

2. A method in accordance with claim 1, wherein said file access operation comprises said destination host opening said file for modification.

3. A method in accordance with claim 1, wherein said caching includes creating a copy of said file in a file system on said destination host.

4. A method in accordance with claim 1, wherein said file system group is one of a file system directory, a file system storage volume, a project, a user or group, or a set of files with common filename characters.

5. A method in accordance with claim 1, wherein said prefetching includes assigning a priority to said file system group and prefetching said file system group according to said priority relative to priorities of other file system groups.

6. A method in accordance with claim 5, wherein said priority is based on an access time of a most recently accessed file in said file system group.

7. A method in accordance with claim 5, further including removing said file system group from said destination host according to said priority relative to other file system groups cached on said destination host and in accordance with available caching storage.

8. A network host, comprising:

a data processor;

a first data storage resource;

a file system managing files on said first data storage resource;

a cache manager in communication with said file system, said cache manager being adapted to;

access a file stored on a second data storage resource via a communication interface;

said access being initiated by a request to open said file for reading or writing at said network host as part of a network host work session involving a file system group that contains said file;

initiate copying of contents of said file from said second data storage resource to said network host via said communication interface and cache a local copy of said file on said first data storage resource;

complete said accessing by enabling said file system to open said cached local copy of said file on said first data storage resource;

using prefetch logic determine what files constitute said file system group;

prefetch all remaining files in said file system group determined by said prefetch logic by initiating copying of contents of said remaining files from said second data storage resource to said network host via said communication interface and caching local copies thereof on said first data storage resource so that said remaining files are accessible locally at said network host during said work session.

9. A system in accordance with claim 8, wherein said file access operation comprises opening said file for modification on said second data storage resource.

10. A system in accordance with claim 8, wherein said caching includes creating a copy of said file on said first data storage resource.

11. A system in accordance with claim 8, wherein said file system group is one of a file system directory, a file system storage volume, a project, a user or group, or a set of files with common filename characters.

12. A system in accordance with claim 11, wherein said prefetch includes assigning a priority to said file system group and prefetching said file system group according to said priority relative to priorities of other file system groups, and wherein said file system is further adapted to periodically remove a file system group from said first data storage system based on a priority of said file system group and in accordance with available caching storage.

13. A system in accordance with claim 12, wherein said priority is based on an access time of a most recently accessed file in said file system group.

14. A computer program product, comprising:

one or more computer useable storage media;

program logic associated with said computer useable media for programming a data processing platform to enhance the transfer of files from a source network host to a destination network host via a communication interface, as by;

accessing a file stored on said source host from said destination host via said communication interface;

said accessing being initiated by a request to open said file for reading or writing at said destination host as part of a destination host work session involving a file system group that contains said file;

said destination host copying contents of said file from said source host to said destination host via said communication interface and caching a local copy of said file on said destination host;

said accessing being completed by opening said cached local copy of said file on said destination host;

said destination host using prefetch logic to determine what files constitute said file system group; and

said destination host prefetching all remaining files in said file system group determined by said prefetch logic by copying contents of said remaining files from said source host to said destination host via said communication interface and caching local copies thereof on said destination host so that said remaining files are accessible locally at said destination host for use during said work session.

15. A computer program product in accordance with claim 14, wherein said file access operation comprises opening said file for modification on said source host from said destination host.

16. A computer program product in accordance with claim 14, wherein said caching includes creating a copy of said file in a file system on said destination host.

17. A computer program product in accordance with claim 14, wherein said file system group is one of a file system directory, a file system storage volume, a project, a user or group, or a set of files with common filename characters.

18. A computer program product in accordance with claim 17, wherein said prefetching includes assigning a priority to said file system group and prefetching said file system group according to said priority relative to priorities of other file system groups.

19. A computer program product in accordance with claim 18, wherein said priority is based on an access time of a most recently accessed file in said file system group.

20. A computer program product in accordance with claim 18, wherein further including removing said file system group from said destination host according to said priority relative to other file system groups cached on said destination host and in accordance with available caching storage.