Distributing lookup operations in a striped storage system

• US 8,176,246 B1
• Filed: 07/26/2011
• Issued: 05/08/2012
• Est. Priority Date: 01/28/2008
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Jernigan, Richard P. IV, Thoppai, Omprakaash
• Primary Examiner(s): Gu, Shawn X
• Application Number:
  US13/190,629
• Time in Patent Office: 287 Days
• Field of Search: None
• US Class Current: 711/113
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 2212/262 configured as RAID
• CPC Class Codes: G06F 2212/466 Metadata, control data
• CPC Class Codes: H04L 67/561 Adding application-functional data or data for application control, e.g. adding metadata
• CPC Class Codes: H04L 67/5682 Policies or rules for updating, deleting or replacing the stored data

Abstract

The present invention provides a mechanism for storing and accessing attributes of a data container (e.g., characteristics such as a name of a data container used to perform a lookup operation against the data container) in cache memory within storage systems in a cluster of storage systems. Further, a mechanism is provided so that an attribute of a data container is inserted into a cache memory of preferably one storage system (in the cluster) that caches metadata of the data container (e.g., information describing the data container). As a result, a lookup operation for a data container is directed to and served by the storage system that caches the metadata and the attribute of the data container. The lookup request is not relayed to a storage system that maintains a central directory of attributes of all data containers in the cluster.

Claims

1. A method for distributing lookup operations in a cluster, comprising:

maintaining, at a D-module of the cluster, mappings between a data container attribute of a data container and an inode value of the data container;

determining at the D-module an identification (ID) of a second D-module of the cluster for caching the data container attribute;

selecting the inode value for the data container attribute, wherein the second D-module services a lookup request for the data container attribute and services a metadata request for the data container;

receiving the metadata request of the data container from an N-module of the cluster; and

in response to receiving the lookup request, satisfying the lookup request by the second D-module.

2. The method of claim 1, further comprising configuring the N-module to receive a request from a client and configuring the N-module to communicate with the second D-module.

3. The method of claim 1, further comprising configuring each of the D-modules to communicate with the N-module.

4. The method of claim 1, wherein the data container attribute comprises a name of the data container.

5. The method of claim 1, wherein the data container attribute comprises infrequently changing data and wherein metadata comprises data that is changed more frequently than the infrequently changing data.

6. The method of claim 1, further comprising applying a first function to the data container attribute to determine the ID of the second D-module, wherein the inode value for the data container attribute is selected so that upon application of a second function on the inode value for the data container attribute, a value is selected equal to the determined ID, whereby the lookup request and the metadata request are directed to the second D-module without sending the lookup request and the metadata request to the D-module maintaining the mappings.

7. The method of claim 1, further comprising:

in response to receiving the lookup request for the data container attribute, determining by the second D-module whether requested metadata for the data container attribute is cached at the D-module; and

if the metadata is not cached, avoiding deletion of the requested data container attribute.

8. The method of claim 1, wherein an inode value comprises an index of an inode data structure configured to store metadata about the data container.

9. The method of claim 1, wherein the data container comprises a file.

10. A system configured to distribute lookup operations in a cluster, comprising:

a D-module of the cluster configured to maintain mappings between a data container attribute of a data container and an inode value of the data container;

the D-module further configured to determine an identification (ID) of a second D-module of the cluster for caching the data container attribute;

the D-module further configured to select the inode value as the data container attribute, wherein the second D-module services a lookup request for the data container attribute and services a metadata request for the data container;

an N-module of the cluster configured to send the metadata request of the data container; and

the second D-module further configured to, in response to receiving the lookup request, satisfy the lookup request.

11. The system of claim 10, wherein the N-module is configured to receive a request from a client and further configured to communicate with the second D-module.

12. The system of claim 10, wherein each of the D-modules is further configured to communicate with the N-module.

13. The system of claim 10, wherein the data container attribute comprises a name of the data container.

14. The system of claim 10, wherein the data container attribute comprises infrequently changing data and wherein metadata comprises data that is changed more frequently than the infrequently changing data.

15. The system of claim 10, wherein the D-module is further configured to apply a first function to the data container attribute to determine the ID of the second D-module, wherein the inode value for the data container attribute is selected so that upon application of a second function on the inode value for the data container attribute, a value is selected equal to the determined ID, whereby the lookup request and the metadata request are directed to the second D-module without sending the lookup request and the metadata request to the D-module maintaining the mappings.

16. The system of claim 10, further comprising:

the second D-module further configured to, in response to receiving the lookup request for the data container attribute, determine whether requested metadata for the data container attribute is cached at the D-module, wherein if the metadata is not cached, deletion of the requested data container attribute is avoided.

17. The system of claim 10, wherein an inode value comprises an index of an inode data structure configured to store metadata about the data container.

18. The system of claim 10, wherein the data container comprises a file.

19. A non-transitory computer-program product embodied in a computer readable medium, comprising:

program instructions that maintain, at a D-module of a cluster, mappings between a data container attribute of a data container and an inode value of the data container;

program instructions that determine at the D-module an identification (ID) of a second D-module of the cluster for caching the data container attribute;

program instructions that select the inode value for the data container attribute, wherein the second D-module services a lookup request for the data container attribute and services a metadata request for the data container;

program instructions that receive the metadata request of the data container from an N-module of the cluster; and

program instructions that, in response to receiving the lookup request, satisfy the lookup request by the second D-module.

20. The computer-program product of claim 19, further comprising program instructions that apply a first function to the data container attribute to determine the ID of the second D-module, wherein the inode value for the data container attribute is selected so that upon application of a second function on the inode value for the data container attribute, a value is selected equal to the determined ID, whereby the lookup request and the metadata request are directed to the second D-module without sending the lookup request and the metadata request to the D-module maintaining the mappings.