Operation of a data processing network having a plurality of geographically spaced-apart data centers

• US 10,135,691 B2
• Filed: 05/22/2015
• Issued: 11/20/2018
• Est. Priority Date: 03/15/2011
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens Healthcare GMBH (Siemens AG)
• Inventors: Dominick, Lutz, Dorn, Karlheinz, Ukis, Vladyslav
• Primary Examiner(s): Taylor, Nicholas R
• Assistant Examiner(s): Shiu, Ho T
• Application Number:
  US14/720,125
• Publication Number:
  US 20150256412A1
• Time in Patent Office: 1,278 Days
• CPC Class Codes: G06F 9/5033 considering data affinity
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/342 between virtual entities, e.g. orchestrators, SDN or NFV entities
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1021 based on client or server locations
• CPC Class Codes: H04L 67/131 Protocols for games, networked simulations or virtual reality
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal

Abstract

A method and a device are disclosed for operating a data processing network which includes a plurality of geographically spaced-apart data centers and a large number of client computers, data being transmittable between each of the client computers and at least to one of the data centers, wherein one or more virtual servers is operateable in each of the data centers. According to at least one embodiment, access data is collected including information on geographical location of the client, geographical location of the virtual servers and the degree of utilization of the virtual servers. The access data collected is analyzed and, using the result of analysis, a migration plan, which is improved with respect to the mean latency, is created for the deployment of the virtual servers among the data centers. The virtual servers are migrated between the data centers in accordance with the migration plan.

Claims

1. A method of operating a data processing network, the data processing network including a plurality of virtual servers distributed among a plurality of geographically spaced data centers in different geographical locations, each of the virtual servers configured to run application backend modules, each of the application backend modules configured to support a plurality of clients via application frontend modules installed therein, the method comprising:

collecting information indicating the geographic locations of clients accessing the plurality of virtual servers and a number of the clients associated with each of the plurality of data centers, the collecting including storing the information in a database;

identifying an over-utilized one of the plurality of data centers by analyzing the information stored in the database to identify the over-utilized data center based on at least the geographic locations of the data centers, the geographic locations of the clients and a load threshold such that the number of the clients associated with the over-utilized data center is greater than or equal to the load threshold; and

migrating a first one of the plurality of virtual servers and the clients supported thereby from the over-utilized data center to an under-utilized one of the plurality of data centers such that the application backend modules supporting the clients associated with the first one of the virtual servers are run on the under-utilized data center, the migrating including,

allocating separate data slices to each of the plurality of virtual servers such that each of the data slices includes data and the information stored in the database that is associated with a respective one of the plurality of virtual servers, and

migrating the first virtual server, the plurality of clients supported thereby and the data slice associated with the first virtual server from the over-utilized data center to the under-utilized data center such that the information collected in the database is migrated with the data from the over-utilized data center to the under-utilized data center.

2. The method of claim 1, wherein the collecting includes collecting information on a time and duration of data processing tasks requested by the clients, and information indicating which of the plurality of virtual servers is associated with the data processing tasks.

3. The method of claim 2, wherein the collecting further includes collecting information on geographical locations of the clients, and geographical locations of the plurality of virtual servers, and the number of clients accessing the plurality of virtual servers.

4. The method of claim 1, wherein the identifying includes determining the number of the clients registered on each of the plurality of virtual servers.

5. The method of claim 1, wherein the migrating determines the first one of the plurality of virtual servers to migrate based at least in part on a geographic location of the plurality of virtual servers and the geographic locations of the clients supported thereby.

6. The method of claim 1, further comprising:

creating a migration plan having instructions regarding the migration of the first one of the plurality of virtual servers.

7. The method of claim 6, wherein the creating creates the migration plan such that the first one of the plurality of virtual servers are migrated to one of the data centers geographically closer to the clients supported thereby while improving the utilization of the plurality of virtual servers.

8. The method of claim 1, wherein the under-utilized data center is one of the plurality of data centers that is geographically closer the clients supported by the first virtual server as compared to other ones of the plurality of data centers whose loads are also less than the load threshold.