Allocation of Virtual Machines in Datacenters

• US 20140215076A1
• Filed: 05/13/2011
• Published: 07/31/2014
• Est. Priority Date: 05/13/2011
• Status: Active Grant

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Grothues, Ingo
• Granted Patent: US 9,807,159 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: G06F 9/455 Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30

Abstract

A method of operating a datacenter comprising a plurality of hosts coupled by a network, the hosts being configurable to run a plurality of virtual machines, the method comprising: collecting network load information indicating a load of the network; determining a target allocation of one of the virtu machines at one of the hosts based on the collected network load information; and allocating the one virtual machine at the one host based on the determined target allocation.

Claims

1. A method of operating a datacenter comprising a plurality of hosts coupled by a network, the hosts being configurable to run a plurality of virtual machines, the method comprising:

collecting network load information indicating a load of the network;

creating a network profile for a virtual machine based on the collected network load information and storing said network profile;

determining a target allocation of one of the virtual machines at one of the hosts based on a comparison of a last profile sequence of the virtual machine to the stored network profile to predict a future behavior of the virtual machine; and

allocating the one virtual machine at the one host based on the determined target allocation.

2. The method of claim 1, further comprising defining at least one communication group in the datacenter, said communication group comprising at least one host.

3. The method of claim 2, wherein said communication group comprises an area of the network, said area coupling a group of hosts of said datacenter.

4. The method of claim 2, further comprising:

generating a network load profile from the network load information; and

determining the target allocation based on evaluation of the network load profile.

5. The method of claim 4, wherein the network load profile is generated for each of said at least one communication group.

6. The method of claim 5, wherein there are at least two of the communication groups, the method further comprising:

cooperatively collecting a plurality of network load profiles from each of the communication groups; and

determining the target allocation based on the plurality of network load profiles.

7. The method of claim 1, wherein the determining of the target allocation comprises considering available resources of the datacenter.

8. The method of claim 7, further comprising collecting additional load indicator information for considering the available resources of the datacenter.

9. The method of claim 1, wherein the determining of the target allocation comprises calculating and evaluating a cost function.

10. A datacenter entity comprising a processing unit, said processing unit being configured to:

generate a network load profile based on network load information indicating load of a network coupling a plurality of hosts;

create a network profile for a virtual machine based on the collected network load information and storing said network profile; and

determine a target allocation of a virtual machine at one of the hosts based on a comparison of a last profile sequence of the virtual machine to the stored network profile to predict a future behavior of the virtual machine.

11. The datacenter entity of claim 10, said processing unit being further configured to allocate the one virtual machine at the one host based on the determined target allocation.

12. The datacenter entity of claim 10, said processing unit being further configured to receive said network load information for generating said network load profile from one of the plurality of hosts.

13. The datacenter entity of claim 10, said processing unit being further configured to receive said network load information for generating said network load profile from a network node of said network.

14. The datacenter entity of claim 10, said processing unit being further configured to exchange said network load profile with a further datacenter entity.

15. The datacenter entity of claim 10, said processing unit being further configured to consider available resources of the datacenter to determine the target allocation of the virtual machine at the one of the hosts.

16. The datacenter entity of claim 15, said processing unit being further configured to collect additional load indicator information for considering the available resources of the datacenter to determine the target allocation of the virtual machine at the one of the hosts.

17. The datacenter entity of claim 10, said processing unit being further configured to calculate and evaluate a cost function to determine the target allocation of the virtual machine at the one of the hosts.

18. A program comprising instruction code on a non-transitory computer readable medium, said code when executed by a processing unit of a datacenter entity configures the processing unit as set out by claim 10.

19. A system for use in at least one datacenter comprising a plurality of hosts coupled by a network, the system comprising a datacenter entity as set out by claim 10 and at least one collecting entity configured to collect said network load information.