System and method for caching network file systems

• US 8,626,866 B1
• Filed: 08/10/2011
• Issued: 01/07/2014
• Est. Priority Date: 04/25/2005
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Lango, Jason Ansel, English, Robert M., Eastham, Paul Christopher, Zheng, Qinghua, Quirion, Brian Mederic, Griess, Peter, Amdur, Matthew Benjamin, Ayyar, Kartik, Tsai, Robert Lieh-Yuan, Grunwald, David, Wagner, J. Chris, Ackaouy, Emmanuel, Prakash, Ashish
• Primary Examiner(s): Nguyen, Thu Ha
• Application Number:
  US13/206,705
• Time in Patent Office: 881 Days
• Field of Search: 709/203, 709/216, 709/204, 709/214, 709/217, 709/218, 711/118, 711/119, 711/120, 711/133, 711/134, 711/136, 711/137, 711/138, 711/148
• US Class Current: 709/216
• CPC Class Codes: G06F 15/167 using a common memory, e.g. mailbox
• CPC Class Codes: G06F 2003/0697 device management, e.g. handlers, drivers, I/O schedulers
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0643 Management of files
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: H04L 67/565 Conversion or adaptation of application format or content adding application control or application functional data H04L67/561
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 67/59 Providing operational support to end devices by off-loading in the network or by emulation, e.g. when they are unavailable

Abstract

A network caching system has a multi-protocol caching filer coupled to an origin server to provide storage virtualization of data served by the filer in response to data access requests issued by multi-protocol clients over a computer network. The multi-protocol caching filer includes a file system configured to manage a sparse volume that “virtualizes” a storage space of the data to thereby provide a cache function that enables access to data by the multi-protocol clients. To that end, the caching filer further includes a multi-protocol engine configured to translate the multi-protocol client data access requests into generic file system primitive operations executable by both the caching filer and the origin server.

Claims

1. A network caching system, comprising:

a caching computer having a processor and configured to receive a data access request from a client for data, the caching computer coupled to an origin computer;

the caching computer further configured to send a fetch on demand (FOD) request to the origin computer to obtain attributes associated with the data;

the caching computer further configured to receive the attributes associated with the data and determine whether attributes associated with the data at the caching computer differ from the attributes received from the origin computer;

the caching computer to service the data access request in response to the caching computer determining that the attributes at the caching computer do not differ from the attributes received from the origin computer; and

the caching computer to acquire the data and the attributes associated with the data from the origin computer in response to the caching computer determining that the attributes at the caching computer differ from the attributes received from the origin computer.

2. The network caching system of claim 1, wherein a multi-protocol engine of the caching computer converts the received data access request into a generic operating system message executable by the caching computer and the origin computer of the network caching system.

3. The network caching system of claim 1, further comprising:

a local cache of the caching computer, the local cache including a sparse volume configured to serve the data requested by the client, wherein the sparse volume includes at least one absent block representing that the data is missing from the sparse volume, wherein the missing data of the absent block is stored on the origin computer and retrieved using the FOD request in a manner that is transparent to the client.

4. The network caching system of claim 3, wherein the sparse volume includes a cache volume, and wherein the cache volume includes one or more storage devices coupled to the caching computer.

5. The network caching system of claim 4, further comprising:

a remote update engine (RUE) of the caching computer, the RUE configured to forward any file system operations that modify the cache volume to the origin computer of the network caching system.

6. The network caching system of claim 3, further comprising:

a truncator of the caching computer, the truncator configured to implement a cache ejection policy to reclaim storage space if the sparse volume becomes full.

7. The network caching system of claim 1, wherein the data is associated with one of a file and a logical unit number.

8. The network caching system of claim 1, wherein the caching computer to service the data access request further comprises:

the caching computer further configured to determine whether the data is located at the caching computer;

in response to determining that the data is located at the caching computer, the caching computer further configured to send the data to the client; and

in response to determining that the data is not located at the caching computer, the caching computer further configured to acquire the data from the origin computer and send the data to the client.

9. The network caching system of claim 1, wherein the caching computer is configured to determine whether the data is resident at the caching computer without hashing a file handle associated with the data access request.

10. A method for operating a network caching system, comprising:

receiving, at a caching computer having a processor, a data access request for data from a client, wherein the caching computer is coupled to an origin computer;

sending a fetch on demand (FOD) request from the caching computer to the origin computer to obtain attributes associated with the data;

receiving, at the caching computer, the attributes associated with the data from the origin computer;

determining, at the caching computer, whether attributes associated with the data at the caching computer differ from the attributes received from the origin computer;

in response to determining that the attributes at the caching computer do not differ from the attributes received from the origin computer, servicing the data access request; and

in response to determining that the attributes at the caching computer differ from is the attributes received from the origin computer, acquiring the data and the attributes associated with the data from the origin computer.

11. The method of claim 10, further comprising:

maintaining the data as one of a file and a logical unit number.

12. The method of claim 10, further comprising:

including a modification time of the data and a creation time of the data as the attributes of the data.

13. The method of claim 12, further comprising:

indicating that the data has been modified since being cached at the caching computer by a change occurring in the attributes.

14. The method of claim 10, further comprising:

embodying the FOD request as a remote volume read message.

15. The method of claim 10, wherein servicing the data access request further comprises:

determining whether the data is located at the caching computer;

in response to determining the data is located at the caching computer, sending the data to the client; and

in response to determining that the data is not located at the caching computer, acquiring the data from the origin computer and sending the data to the client.

16. The method of claim 15, wherein determining whether the data is located at the caching computer is determined without hashing a file handle of the data access request.

17. A non-transitory computer-readable storage medium containing executable program instructions executed by a processor, comprising:

program instructions that receive a data access request for data from a client at a caching computer coupled to an origin computer;

program instructions that send a fetch on demand (FOD) request to the origin computer to obtain attributes associated with the data;

program instructions that receive the attributes associated with the data and determine whether attributes associated with the data at the caching computer differ from the attributes received from the origin computer;

program instructions that, in response to determining that the attributes at the caching computer do not differ from the attributes received from the origin computer, service the data access request; and

program instructions that, in response to determining that the attributes at the caching computer differ from the attributes received from the origin computer, acquire the data and the attributes associated with the data from the origin computer.

18. The non transitory computer-readable storage medium of claim 17, wherein the program instructions that service the data access request further comprise:

program instructions that determine whether the data is located at the caching computer;

program instruction that, in response to determining that the data is located at the caching computer, send the data to the client; and

program instructions that, in response to determining that the data is not located at the caching computer, acquire the data from the origin computer and send the data to the client.