SYSTEMS, METHODS AND ALGORITHMS FOR LOGICAL MOVEMENT OF DATA OBJECTS

• US 20140207954A1
• Filed: 01/18/2013
• Published: 07/24/2014
• Est. Priority Date: 01/18/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Calo, Seraphin B., Dilmaghani, Raheleh B., Lee, Kang-Won, Pappas, Vasileios, Raghavendra, Ramya, Verma, Dinesh C.
• Granted Patent: US 9,560,127 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: G06F 16/1827 Management specifically adapted to NAS management of storage area networks [SAN] G06F3/067
• CPC Class Codes: G06F 9/00 Arrangements for program control, e.g. control units program control for peripheral devices G06F13/10
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services

Abstract

The present disclosure relates generally to the field of logical movement of data objects. In various examples, the logical movement of data objects may reduce or eliminate network hotspots (e.g., avoid formation of hotspots, remove existing hotspots and/or reduce the magnitude of hotspots). In various examples, the logical movement of data objects may be implemented in the form of systems, methods and/or algorithms.

Claims

1. A method implemented in a computer system for movement of at least one data object from a first server to a second server, the method comprising:

advertising by the second server the data object to be available at the second server, wherein the data object is advertised as available at the second server while the data object is still at the first server;

receiving by the second server a request for the data object; and

receiving by the second server the data object after the data object has been moved from the first server.

2. The method of claim 1, wherein the second server responds to the request with the received data object.

3. The method of claim 1, wherein the first server responds to the request with the data object.

4. The method of claim 1, wherein the first server and the second server are within a data center.

5. The method of claim 1, wherein the first server and the second server are part of at least one of:

(a) an IP-based network; and

(b) a named data network.

6. A method implemented in a computer system for movement of at least one data object between at least two of a plurality of servers, the method comprising:

determining a frequency of accesses to the data object, wherein the determined frequency of accesses is determined in at least one of a prior time period and a current time period;

predicting a frequency of accesses to the data object, wherein the predicted frequency of accesses is predicted for at least one future time period and wherein the predicted frequency of accesses is predicted based at least in part upon the determined frequency of accesses;

determining, based at least in part upon the predicted frequency of accesses, a future placement location of the data object on at least one of the plurality of servers, wherein the future placement location of the data object is on a server different from the server on which the data object currently resides;

routing at least one request to the server at the future placement location of the data object before the data object has been moved to the server at the future placement location; and

upon receiving an Nth request for the data object in the current time period, serving the request from the server on which the data object currently resides and moving the data object to the server at the future placement location.

7. The method of claim 6, further comprising determining the frequency of accesses to the data object in the prior time period and in the current time period.

8. The method of claim 6, further comprising determining the frequency of accesses to the data object in a plurality of prior time periods.

9. The method of claim 6, wherein the determining the future placement location of the data object on at least one of the plurality of servers is further based at least in part upon a configuration of a network of which the server on which the data object currently resides and the server at the future placement location form a part.

10. The method of claim 6, wherein the determining the future placement location of the data object on at least one of the plurality of servers is carried out to minimize or avoid one or more hotspots.

11. The method of claim 6, wherein N is an integer between 1 and 1,000, inclusive.

12. The method of claim 6, further comprising:

after the data object is moved to the server at the future placement location, continuing to serve the data object from the server at the future placement location until a new placement of the data object at another one of the servers is determined.

13. The method of claim 6, wherein the servers are within a data center.

14. The method of claim 6, wherein the servers are part of at least one of:

(a) an IP-based network; and

(b) a named data network.

15. The method of claim 6, wherein the determining the frequency of accesses to the data object comprises measuring the frequency of accesses to the data object and wherein the measured frequency of accesses is measured in at least one of a prior time period and a current time period.

16. The method of claim 15, wherein the predicted frequency of accesses is predicted for at least one future time period and wherein the predicted frequency of accesses is predicted based at least in part upon the measured frequency of accesses.

17. The method of claim 6, wherein routing is performed by a plurality of computers.