MULTI-TIERED-APPLICATION DISTRIBUTION TO RESOURCE-PROVIDER HOSTS BY AN AUTOMATED RESOURCE-EXCHANGE SYSTEM

• US 20180060106A1
• Filed: 08/24/2017
• Published: 03/01/2018
• Est. Priority Date: 08/28/2016
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: Madtha, Jivan, Beveridge, Daniel James
• Granted Patent: US 11,604,665 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/122 of virtualised topologies, e.g. software-defined networks [SDN] or network function virtualisation [NFV]
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• 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

Abstract

The current document is directed a resource-exchange system that facilitates resource exchange and sharing among computing facilities. The currently disclosed methods and systems employ efficient, distributed-search methods and subsystems within distributed computer systems that include large numbers of geographically distributed data centers to locate resource-provider computing facilities that match the resource needs of resource-consumer computing-facilities based on attribute values associated with the needed resources, the resource providers, and the resource consumers. The resource-exchange system monitors and controls resource exchanges on behalf of participants in the resource-exchange system in order to optimize resource usage within participant data centers and computing facilities. Virtual machines that provide the execution environment for multi-tiered applications described by hierarchically organized multi-tiered-application specifications are automatically distributed across one or more resource-provider-computing-facility hosts by the resource-exchange system.

Claims

1. An automated resource-exchange system comprising:

multiple resource-exchange-system participants, each comprising a computing facility that includes multiple computers, each having one or more processors and one or more memories, and a local cloud-exchange instance; and

a cloud-exchange system that is implemented on one or more physical computers, each including one or more processors and one or more memories, and that includes a cloud-exchange engine, the cloud-exchange system automatically placing virtual machines of a multi-tiered application for which remote hosting is requested by a resource-consumer resource-exchange-system participant into one or more resource-provider resource-exchange-system participants.

2. The automated resource-exchange system of claim 1 wherein the cloud-exchange system automatically places virtual machines of a multi-tiered application for which remote hosting is requested into one or more resource-provider resource-exchange-system participants by:

receiving a hosting request from the resource-consumer resource-exchange-system participant;

extracting one of a multi-tiered-application specification and a reference to a multi-tiered-application specification from the hosting request;

parsing the multi-tiered-application specification to identify groups of one or more multi-tiered-application virtual machines with equivalent hosting constraints;

generating a search expression for each identified virtual-machine group;

submitting each search expression to a distributed-search-engine component of the cloud-exchange system to obtain scored candidate host assignments for the virtual-machine group for which the search expression was generated;

selecting a set of candidate host assignments for the multi-tiered-application virtual machines with a lowest cumulative score; and

launching execution of the multi-tiered-application according to the selected set of candidate host assignments.

3. The automated resource-exchange system of claim 2 wherein the multi-tiered-application specification is encoded in a hierarchical data-encoding language according to a multi-tiered-application-specification standard.

4. The automated resource-exchange system of claim 2 wherein the hosting request may additionally contain one of a buy policy and a reference to a buy policy.

5. The automated resource-exchange system of claim 3 wherein generating a search expression for an identified virtual-machine group further comprises:

parsing the multi-tiered-application specification and, if included in the hosting request, a buy policy to identify

a general set of hosting constraints without dependencies on other virtual machines of other identified virtual-machine groups, and

a dependent set of hosting constraints that additionally include dependencies on other virtual machines of other identified virtual-machine groups; and

combining the general set of hosting constraints, requirements, and parameters and the dependent set of hosting constraints, requirements, and parameters into a search expression for the virtual-machine group;

6. The automated resource-exchange system of claim 2 wherein submitting a search expression to a distributed-search-engine component of the cloud-exchange system to obtain scored candidate host assignments for a virtual-machine group for which the search expression was generated further comprises:

submitting a general set of hosting constraints included in the search expression to the distributed-search-engine component of the cloud-exchange system to obtain a set of scored candidate host assignments; and

iteratively selecting, for each virtual machine in the virtual-machine group, members of a final set of candidate host assignments, one for each virtual machine in the virtual-machine group, according to a dependent set of hosting constraints included in the search expression.

7. The automated resource-exchange system of claim 2 wherein hosting constraints include:

affinity requirements;

network latency requirements;

operational parameters;

cost-center assignments;

service-level-agreement requirements;

compliance and regulatory requirements;

price filters;

connectivity requirements;

infrastructure-support requirements;

security requirements;

reputational requirements;

resource-exchange certification requirements;

network-bandwidth requirements;

uptime requirements;

white-list/black-list filters;

logical-switch constraints,

routing-constraints;

firewall constraints;

load-balancer constraints; and

hosting-location constraints.

8. The automated resource-exchange system of claim 2 wherein the virtual-machine groups are sorted in descending order according to the degree to which they are constrained with respect to placement for hosting.

9. The automated resource-exchange system of claim 8 wherein search expressions for the virtual-machine groups are submitted to a distributed-search-engine component according to the sorted order.

10. The automated resource-exchange system of claim 8 wherein search expressions for the virtual-machine groups are submitted in a depth-first, recursive search of a subset of the possible virtual-machine-to-host assignments.

11. The automated resource-exchange system of claim 2 wherein launching execution of the multi-tiered-application according to the selected set of candidate host assignments further comprises:

invoking a multi-tiered-application orchestrator to configure and launch the multi-tiered application according to the multi-tiered-application specification and the selected set of candidate host assignments for the multi-tiered-application virtual machines.

12. A method that increases an operational efficiency of multiple computing facilities, the method comprising:

aggregating the multiple computing facilities into a resource-exchange system, each computing facility including multiple computers, each computer having one or more processors and one or more memories, by

transforming each computing facility into a resource-exchange-system participant by including a local cloud-exchange instance in the computing facility, and

including, in the resource-exchange system, a cloud-exchange system, implemented on one or more physical computers, each including one or more processors and one or more memories, the cloud-exchange system including a cloud-exchange engine; and

increasing the operational efficiency of the resource-exchange system by automatically placing virtual machines of a multi-tiered application for which remote hosting is requested by a resource-consumer resource-exchange-system participant into one or more resource-provider resource-exchange-system participants.

13. The method of claim 12 wherein the cloud-exchange system automatically places virtual machines of a multi-tiered application for which remote hosting is requested into one or more resource-provider resource-exchange-system participants by:

receiving a hosting request from the resource-consumer resource-exchange-system participant;

extracting one of a multi-tiered-application specification and a reference to a multi-tiered-application specification from the hosting request;

parsing the multi-tiered-application specification to identify groups of one or more multi-tiered-application virtual machines with equivalent hosting constraints;

generating a search expression for each identified virtual-machine group;

submitting each search expression to a distributed-search-engine component of the cloud-exchange system to obtain scored candidate host assignments for the virtual-machine group for which the search expression was generated;

selecting a set of candidate host assignments for the multi-tiered-application virtual machines with a lowest cumulative score; and

launching execution of the multi-tiered-application according to the selected set of candidate host assignments.

14. The method of claim 13 wherein the multi-tiered-application specification is encoded in a hierarchical data-encoding language according to a multi-tiered-application-specification standard.

15. The method of claim 13 wherein generating a search expression for an identified virtual-machine group further comprises:

parsing the multi-tiered-application specification and, if included in the hosting request, a buy policy to identify

a general set of hosting constraints without dependencies on other virtual machines of other identified virtual-machine groups, and

a dependent set of hosting constraints that additionally include dependencies on other virtual machines of other identified virtual-machine groups; and

combining the general set of hosting constraints, requirements, and parameters and the dependent set of hosting constraints, requirements, and parameters into a search expression for the virtual-machine group;

16. The method of claim 13 wherein submitting a search expression to a distributed-search-engine component of the cloud-exchange system to obtain scored candidate host assignments for a virtual-machine group for which the search expression was generated further comprises:

submitting a general set of hosting constraints included in the search expression to the distributed-search-engine component of the cloud-exchange system to obtain a set of scored candidate host assignments; and

iteratively selecting, for each virtual machine in the virtual-machine group, members of a final set of candidate host assignments, one for each virtual machine in the virtual-machine group, according to a dependent set of hosting constraints included in the search expression.

17. The method of claim 13 wherein hosting constraints include:

affinity requirements;

network latency requirements;

operational parameters;

cost-center assignments;

service-level-agreement requirements;

compliance and regulatory requirements;

price filters;

connectivity requirements;

infrastructure-support requirements;

security requirements;

reputational requirements;

resource-exchange certification requirements;

network-bandwidth requirements;

uptime requirements;

white-list/black-list filters;

logical-switch constraints,

routing-constraints;

firewall constraints;

load-balancer constraints; and

hosting-location constraints.

18. The method of claim 13 wherein the virtual-machine groups are sorted in descending order according to the degree to which they are constrained with respect to placement for hosting.

19. The method of claim 18 wherein search expressions for the virtual-machine groups are submitted to a distributed-search-engine component according to the sorted order.

20. The method of claim 19 wherein search expressions for the virtual-machine groups are submitted in a depth-first, recursive search of a subset of the possible virtual-machine-to-host assignments.

21. The method of claim 13 wherein launching execution of the multi-tiered-application according to the selected set of candidate host assignments further comprises:

invoking a multi-tiered-application orchestrator to configure and launch the multi-tiered application according to the multi-tiered-application specification and the selected set of candidate host assignments for the multi-tiered-application virtual machines.

22. A physical data-storage device encoded with computer instructions that, when executed by processors within an automated resource-exchange system comprising resource-exchange-system-participant computing facilities and a cloud-exchange system, control the automated resource-exchange system to automatically increase the operational efficiency of the resource-exchange system by:

aggregating the multiple computing facilities into a resource-exchange system, each computing facility including multiple computers, each computer having one or more processors and one or more memories, by

transforming each computing facility into a resource-exchange-system participant by including a local cloud-exchange instance in the computing facility, and

including, in the resource-exchange system, a cloud-exchange system, implemented on one or more physical computers, each including one or more processors and one or more memories, the cloud-exchange system including a cloud-exchange engine; and

increasing the operational efficiency of the resource-exchange system by automatically placing virtual machines of a multi-tiered application for which remote hosting is requested by a resource-consumer resource-exchange-system participant into one or more resource-provider resource-exchange-system participants.