Wake-on-LAN and instantiate-on-LAN in a cloud computing system

• US 9,268,586 B2
• Filed: 05/09/2012
• Issued: 02/23/2016
• Est. Priority Date: 03/08/2011
• Status: Active Grant

• Current Assignee: Rackspace US Incorporated (Apollo Global Management, Inc.)
• Original Assignee: Rackspace US Incorporated (Apollo Global Management, Inc.)
• Inventors: Voccio, Paul, Messerli, Antony Joel, Mick, Jason L., Walsh, Alexander
• Primary Examiner(s): Wai, Eric C
• Application Number:
  US13/467,686
• Publication Number:
  US 20120233331A1
• Time in Patent Office: 1,385 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 11/14 Error detection or correction of the data by redundancy in operation G06F11/16 takes precedence
• CPC Class Codes: G06F 11/1484 involving virtual machines
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45575 Starting, stopping, suspending or resuming virtual machine instances
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0626 Reducing size or complexity of storage systems
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0664 at device level, e.g. emulation of a storage device or system
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0673 Single storage device
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/461 Saving or restoring of program or task context
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: H04L 2101/622 Layer-2 addresses, e.g. medium access control [MAC] addresses
• CPC Class Codes: H04L 61/5007 : Internet protocol [IP] addresses
• 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: Y02D 10/00 : Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Several different embodiments of a flexible virtual machine management system are described. The virtual machine management system is used to instantiate, wake, move, sleep, and destroy individual operating environments in a cloud or cluster. In various embodiments, the virtual machine management system uses single messages to perform complex operations, allowing for flexible and scalable use of virtual resources in a cluster while still reducing energy consumption to the minimum possible level. In one preferred embodiment, Wake-on-LAN packets are used as the messages.

Claims

1. A method for remotely managing a hardware/software platform, the method comprising:

receiving, at a first location, using a first network interface card (NIC) associated with a hardware portion of said platform, a management packet identifying a first virtual machine associable with the platform, the virtual machine including a logical container and an operating environment;

evaluating said management packet via an instruction processor executing on said platform to determine a message type;

if the message type is a wake message, then;

evaluating whether the first virtual machine has been previously allocated;

if the first virtual machine has been previously allocated, making a logical container available and loading an operating environment encapsulating the state of the previously-allocated first virtual machine into the logical container;

if the first virtual machine has not been previously allocated, identifying an instruction sequence from the management packet, the instruction sequence suitable for instantiating a virtual machine;

making a logical container available for the first virtual machine, and executing the instruction sequence to instantiate the first virtual machine using the logical container.

2. The method of claim 1 wherein if the message is a content message, then:

evaluating whether the first virtual machine is currently active;

if the first virtual machine is currently active, then routing the content message to the first virtual machine; and

if the first virtual machine is not currently active, storing the content message temporarily;

following the steps associated with a wake message to instantiate the first virtual machine; and

routing the content message to the first virtual machine.

3. The method of claim 2, wherein prior to identifying a first virtual machine associable with the platform, identifying a first physical machine associated with the platform;

evaluating whether said first physical machine is active; and

if the first physical machine is not active, waking the first physical machine prior to evaluating whether the first virtual machine has been previously allocated.

4. The method of claim 2, wherein prior to identifying a first virtual machine associable with the platform, identifying a first set of physical machines sharing an electrical bus;

evaluating whether said first set of physical machines are active; and

if the first set of physical machines are not active, activating the electrical bus and waking a machine from the first set physical machines prior to evaluating whether the first virtual machine has been previously allocated.

5. The method of claim 1 wherein if the message is a clone message, then:

identifying a second location operable to host a virtual machine;

following the steps associated with a wake message to create a second virtual machine that is a clone of the first virtual machine, using the first virtual machine as a template;

identifying a routing rule governing the routing of messages sent to the first location and the second location; and

routing messages according to the routing rule.

6. The method of claim 5 wherein if the message is a move message, then:

following the steps associated with a clone message create a second virtual machine that is a clone of the first virtual machine;

using a routing rule redirecting all messages addressed to the first location to the second location;

routing messages according to the routing rule; and

deallocating the first virtual machine.

7. The method of claim 1 wherein if the message is a sleep message, then:

identifying a routing rule governing the routing of messages sent to the first location;

placing the first virtual machine into a sleep state; and

routing messages according to the routing rule.

8. The method of claim 7, further comprising the steps of:

after placing the first virtual machine into a sleep state;

determining whether a second virtual machine is active on the same hardware portion of the platform; and

if there is not a second virtual machine active, placing the hardware portion of the platform into a lower power state.

9. The method of claim 8, further comprising the steps of

if there is a second virtual machine active, determining whether a third virtual machine is active on the same hardware portion of the platform;

if there is not a third virtual machine active, migrating the second virtual machine to a second hardware/software platform; and

placing the hardware portion of the platform into a lower power state.

10. The method of claim 1 wherein if the message is a deallocate message, then:

identifying a routing rule governing the routing of messages sent to the first location;

deallocating the first virtual machine; and

routing messages according to the routing rule.

11. The method of claim 1, wherein prior to identifying a first virtual machine associable with the platform, identifying a first physical machine associated with the platform;

evaluating whether said first physical machine is active; and

if the first physical machine is not active, waking the first physical machine prior to evaluating whether the first virtual machine has been previously allocated.

12. The method of claim 1, wherein prior to identifying a first virtual machine associable with the platform, identifying a first set of physical machines sharing an electrical bus;

evaluating whether said first set of physical machines are active; and

if the first set of physical machines are not active, activating the electrical bus and waking a machine from the first set physical machines prior to evaluating whether the first virtual machine has been previously allocated.

13. A system for computation, the system comprising:

a combination hardware/software platform, the hardware portion of the platform including a first network interface card (NIC), a processor, a memory, a computer-readable storage medium, and a power controller;

the software portion of the platform including a hypervisor, wherein the hypervisor is associated with a plurality of logical containers, each logical container including a virtual network interface;

wherein each logical container is operable to host an operating environment; and

wherein each logical container and each operating environment can be in one of a plurality of states, including an active state, an inactive state, and an unallocated state; and

wherein the hypervisor, the logical containers, and the operating environments can be manipulated by a sequence of computer-readable instructions;

and wherein, responsive to a message received at the first NIC, the message identifying a first virtual interface associated with a first operating environment, the platform is operable to determine a message type and evaluate whether the identified first operating environment has been previously allocated and whether the identified first operating environment is active; and

take action thereon using the processor to execute a sequence of computer-readable instructions that, when executed;

if the message type indicates that the identified first operating environment should be active;

if the first operating environment has been already allocated and is active, route the message to the virtual network interface of the logical container hosting the identified first operating environment;

if the first operating environment has been already allocated but is not active, make a first logical container available on the platform and load a representation encapsulating the state of the previously-allocated first operating environment into the first logical container, and route the message to the virtual network interface of the logical container hosting the identified first operating environment;

if the first operating environment has not been already allocated, make a first logical container available;

instantiate, using one or more instructions included in the message received at the first NIC, the first identified operating environment in the first logical container; and

route the message to the virtual network interface of the logical container hosting the identified first operating environment.

14. The system of claim 13 wherein the hardware portion of the platform can be in one of a plurality of states, including an active state and a low power state;

and

wherein the power controller is operable to change the state of the hardware portion of the platform to an active state responsive to the message received at the first NIC and prior to the execution of the sequence of computer-readable instructions by the processor.

15. The system of claim 13 wherein the message uses a MAC address to identify the first virtual interface.

16. The system of claim 13 wherein the message is sent using the Ethernet protocol.