STORAGE REPLICATION SYSTEMS AND METHODS

• US 20110145357A1
• Filed: 12/15/2009
• Published: 06/16/2011
• Est. Priority Date: 12/15/2009
• Status: Active Grant

• Current Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Original Assignee: Symantec Corporation (NortonLifeLock Inc.)
• Inventors: Saeed, Tariq
• Granted Patent: US 8,700,726 B2
• Time in Patent Office: Days
• US Class Current: 709/213
• 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]

Abstract

Systems and methods for information storage replication are presented. In one embodiment a storage flow control method includes estimating in a primary data server what an outstanding request backlog trend is for a remote secondary data server; determining a relationship of an outstanding request backlog trend to a threshold; and notifying a client that the primary data server can not service additional requests if the trend exceeds the threshold. In one embodiment the estimating comprises: sampling a number of outstanding messages at a plurality of fixed time intervals; and determining if there is a trend in the number of outstanding messages over the plurality of fixed time intervals. It is appreciated the estimating can be performed in a variety of ways, (e.g., utilizing an average, a moving average, etc). Determining the trend can include determining if values monotonically increase. The estimating in the primary server can be performed without intruding on operations of the remote secondary data server. The primary data server and the secondary data server can have a variety of configurations (e.g., a mirrored configuration, a RAID5 configuration, etc.).

Claims

1. A storage flow control method:

estimating in a primary data server what an outstanding request backlog trend is for a remote secondary data server;

determining a relationship of said outstanding request backlog trend to a threshold;

notifying a client that said primary data server can not service additional requests if said outstanding request backlog trend exceeds said threshold; and

forwarding a storage request and corresponding information to said secondary server if said outstanding request backlog trend does not exceed said outstanding request backlog threshold.

2. A storage flow control method of claim 1 wherein said estimating comprises:

sampling a number of outstanding messages at a plurality of fixed time intervals; and

determining if there is said outstanding request backlog trend in said number of outstanding messages over said plurality of fixed time intervals.

3. A storage flow control method of claim 1 wherein said determining said trend includes determining if values monotonically increase.

4. A storage flow control method of claim 1 wherein said estimating in said primary server is performed without intruding on operations of said remote secondary data server.

5. A storage flow control method of claim 1 wherein said primary data server and said secondary data server have a mirrored configuration.

6. A storage flow control method of claim 1 wherein said primary data server and said secondary data server have a RAID5 configuration.

7. A storage flow control method of claim 1 wherein said estimating is based upon a moving average of outstanding requests to said secondary data server.

8. A computer readable storage medium having stored thereon, computer-executable instructions that when executed by a computing device cause the computing device to perform a method comprising:

estimating in a primary data server what an outstanding request backlog trend is for a remote secondary data server;

determining a relationship of said outstanding request backlog trend to a threshold;

notifying a client that said primary data server can not service additional requests if said outstanding request backlog trend exceeds said threshold; and

forwarding a storage request and corresponding information to said secondary server if said outstanding request backlog trend does not exceed said outstanding request backlog threshold.

9. The computer readable storage medium of claim 8 wherein said estimating comprises:

sampling a number of outstanding messages at a plurality of fixed time intervals; and

determining if there is said outstanding request backlog trend in said number of outstanding messages over said plurality of fixed time intervals.

10. The computer readable storage medium of claim 8 wherein said determining said trend includes determining if values monotonically increases.

11. The computer readable storage medium of claim 8 wherein said estimating in said primary sever is performed without intruding on operations of said remote secondary data server.

12. The computer readable storage medium of claim 8 wherein said primary data server and said secondary data server have a mirrored configuration.

13. The computer readable storage medium of claim 8 wherein said primary data server and said secondary data server have a RAID5 configuration.

14. The computer readable storage medium of claim 8 wherein said estimating is based upon a moving average of outstanding requests to said secondary data server.

15. A system, comprising:

a computer system having a processor coupled to a computer readable storage media and executing computer readable code which causes the computer system to perform a method of;

estimating in a primary data server what an outstanding request backlog trend is for a remote secondary data server;

determining a relationship of said outstanding request backlog trend to a threshold;

notifying a client that said primary data server can not service additional requests if said outstanding request backlog trend exceeds said threshold; and

forwarding a storage request and corresponding information to said secondary server if said outstanding request backlog trend does not exceed said outstanding request backlog threshold.

16. The system of claim 15 wherein said estimating comprises:

sampling a number of outstanding messages at a plurality of fixed time intervals; and

determining if there is said outstanding request backlog trend in said number of outstanding messages over said plurality of fixed time intervals.

17. The system of claim 15 wherein said determining said trend includes determining if values monotonically increases.

18. The system of claim 15 wherein said estimating in said primary server is performed without intruding on operations of said remote secondary data server.

19. The system of claim 15 wherein said primary data server and said secondary data server have a mirrored configuration.

20. The system of claim 15 wherein said primary data server and said secondary data server have a RAID5 configuration.