Adaptive storage block data distribution

• US 7,461,146 B2
• Filed: 01/20/2003
• Issued: 12/02/2008
• Est. Priority Date: 01/20/2003
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Equallogic Incorporated (Dell Technologies Inc.)
• Inventors: Long, Paula, Hayden, Peter C., Koning, G. Paul
• Primary Examiner(s): Etienne; Ario
• Assistant Examiner(s): EL CHANTI, HUSSEIN A
• Application Number:
  US10/347,898
• Publication Number:
  US 20040143637A1
• Time in Patent Office: 2,143 Days
• Field of Search: 709/217, 709223-226, 709/228, 709/213, 709/246
• US Class Current: 709/224
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

Systems and methods for providing an efficient partitioned resource server. In one embodiment, the partitioned resource server comprises a plurality of individual servers, and the individual servers appear to be equivalent to a client. Each of the individual servers may include a routing table that includes a reference for each resource that is maintained on the partitioned resource server. Requests from a client are processed as a function of the routing table to route the request to the individual server that maintains or has control over the resource of interest.

Claims

1. A system for block level data storage, comprising:

a plurality of equivalent servers each being responsible for a portion of stored blocks and each of said plurality of equivalent servers having a respective data mover process capable of communicating directly with another respective data mover process on another server of said plurality of equivalent servers for coordinating movement of blocks between the plurality of equivalent servers;

each of said plurality of equivalent servers having a respective request monitor process communicating directly with another respective request monitor process on another server of said plurality of equivalent servers

each of said plurality of equivalent servers having a respective routing table process in each server and capable of communicating with another respective routing table process on each of the other servers of said plurality of equivalent servers, each process on each server for maintaining a coordinated list of equivalent servers that identifies the volume and server for each data block moved between the servers and data blocks associated therewith;

each of said respective request monitor process monitoring client requests to its respective server and communicating with other respective request monitor process to build a global request database;

said global database identifying patterns in the client requests, wherein the client requests access blocks of data;

each of said data mover process reallocating the blocks of data of the identified patterns from one server to another server of the plurality of equivalent servers based on operational characteristics of the plurality of equivalent servers and the identified patterns.

2. A system according to claim 1, wherein each request monitor process identifies the patterns based on parameters selected from the group consisting of a number of clients accessing a data volume, a number of I/O requests, and a measure of available storage.

3. A system according to claim 1, wherein

each request monitor process identifies the patterns based on whether a group of blocks are accessed together at a frequency above a hot block criterion.

4. A system according to claim 1, wherein

the data mover process operates on data generated by the request monitor process reallocate a block of data to a selected server for improving performance.

5. A system according to claim 1, wherein

the data mover process includes a data striping algorithm for striping selected data blocks across a plurality of servers.

6. A system according to claim 1, wherein

the data mover process includes a transaction process for monitoring a transfer of data blocks between servers.

7. A system according to claim 6, wherein

the transaction process includes an error log process for logging an error detected during the transfer of data blocks.

8. A system according to claim 1, wherein

the request monitor monitors requests made of two or more data volumes.

9. A system according to claim 1, wherein

the data mover process moves data blocks associated with two or more data volumes.

10. A process for providing block level data storage, comprising:

providing a plurality of equivalent servers each being responsible for a portion of stored data blocks and each monitoring client requests received by a respective equivalent server, each of said plurality of equivalent servers having a respective request monitor process and communicating directly with another respective request monitor process on another server of said plurality of equivalent servers;

moving data blocks between the servers; and

maintaining a respective routing table at each of said plurality of equivalent servers that identifies the volume and server for each data block moved between the servers and that communicates with other respective routing tables to generate a global routing table for tracking data blocks stored across different servers on the system;

each of said respective request monitor process monitoring client requests to its respective server and communicating with other respective request monitor process to build a global request database;

said global database identifying patterns in the client requests, wherein the client requests access blocks of data;

reallocating the blocks of data of the identified patterns from one server to another server of the plurality of equivalent servers based on operational characteristics of the plurality of equivalent servers and the identified patterns.

11. The process of claim 10, wherein

the identified patterns are based on parameters selected from the group consisting of a number of clients accessing a data volume, a number of I/O requests, and a measure of available storage.

12. The process according to claim 10, wherein

the identified patterns are based on whether a group of blocks are accessed together at a frequency above a hot block criterion.

13. The process according to claim 10, wherein

data moving includes striping selected data blocks across a plurality of servers.

14. The process according to claim 10, wherein

data moving includes monitoring a transfer of data blocks between servers.

15. The process according to claim 14, further including

generating an error log for logging an error detected during the transfer of data blocks.

16. The process according to claim 10, wherein

monitoring requests includes monitoring requests made of two or more data volumes.