METHOD AND SYSTEM FOR MULTI-TENANT RESOURCE DISTRIBUTION

• US 20170244784A1
• Filed: 04/29/2016
• Published: 08/24/2017
• Est. Priority Date: 02/19/2016
• Status: Active Grant

• Current Assignee: Huawei Cloud Computing Technologies Company Limited (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: LAM, Jason T.S., CHEN, Chong, GUO, Lei, KE, Xiaodi
• Granted Patent: US 10,609,129 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 9/505 considering the load
• 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: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30

Abstract

In a distributed computing network, requests for allocation of resources to tenant workloads and messages identifying resource availability are received and aggregated. Resources are allocated to the workloads in accordance with a distribution policy defining values for resource entitlements of the tenants. The values include pre-emption quantities. In response to determining that a quantity of resources allocated for workloads of a first tenant is less than the tenant'"'"'s pre-emption quantity, processing of another workload from a second tenant is interrupted to re-allocate resources from the second tenant'"'"'s workload to the first tenant'"'"'s workload.

Claims

1. A method of allocating resources in a distributed computing network comprising a plurality of tenants, the method comprising:

receiving a plurality of requests from said tenants for allocation of resource quantities to workloads from said tenants;

allocating resources to said workloads in accordance with a distribution policy defining values for resource entitlements of said tenants, at least one of the values including a pre-emption quantity for a first tenant; and

in response to determining that a first quantity of resources allocated for a workload of a first tenant is less than the pre-emption quantity for said first tenant, interrupting processing of a workload from a second tenant to re-allocate a second quantity of resources from said workload of said second tenant to said workload of said first tenant.

2. The method of claim 1, wherein said values comprise reserve quantities, and wherein allocating resources comprises allocating a reserve quantity of resources to workloads from a tenant independently of a quantity of resources requested by said tenant.

3. The method of claim 1, wherein said values define maximum quantities of resources for at least some of said tenants, and wherein said allocating comprises allocating to a tenant its maximum quantity of resources, wherein said maximum quantity is less than a quantity of idle resources available for allocation to workloads from said tenant.

4. The method of claim 1, wherein said distribution policy comprises resource allocation weightings for users belonging to ones of said tenants.

5. The method of claim 4, wherein said allocating resources comprises allocating resources to workloads from said users according to said weighting values.

6. The method of claim 1, wherein said values comprise proportional values each defining a proportional share of available resources.

7. The method of claim 6, wherein said tenants comprise a plurality of parent tenants, each with at least one child tenant, and said distribution policy defines hierarchical resource entitlements of said tenants, with entitlements of child tenants defined as proportional shares of parent tenants.

8. The method of claim 1, wherein said values comprise absolute values each defining a number of resource units.

9. The method of claim 1, wherein said values comprise proportional values defining a proportional value of available resources and absolute values defining a number of resource units.

10. The method of claim 1, wherein said distributed computing system comprises resources in a plurality of resource pools, and wherein said allocating comprises allocating resources of a first resource pool to a first set of tenants and allocating resources of a second resource pool to a second set of tenants.

11. The method of claim 10, wherein at least one tenant is part of both said first set of tenants and said second set of tenants.

12. The method of claim 10, comprising defining a data structure defining a distribution policy for each one of said resource pools.

13. The method of claim 1, wherein interrupting a workload comprises selecting said second tenant from among said plurality of tenants based on a comparison of a resource entitlement of said second tenant and resources allocated to said second tenant.

14. A distributed computing system, comprising:

a plurality of resource servers;

a master server comprising;

a resource collection module for receiving messages identifying available resources associated with said resource servers;

a demand collection module for receiving messages identifying resource requests from tenants of said distributed computing system;

a data structure comprising a distribution policy for said resources, said distribution policy containing values for resource entitlements of said tenants, said values comprising pre-emption values defining a quantity of said resources which can be allocated to a tenant by interrupting processing of a workload;

a distributed resource manager for allocating resources to workloads from said tenants according to said distribution policy.

15. The distributed computing system of claim 14, wherein said values comprise reserve values each defining a minimum quantity of said resources to be allocated to a tenant.

16. The distributed computing system of claim 14, wherein said values comprise maximum values defining a maximum quantity of resources to a tenant.

17. The distributed computing system of claim 14, wherein said distribution policy comprises resource allocation weightings for users belonging to ones of said tenants.

18. The distributed computing system of claim 14, wherein said values comprise proportional values each defining a proportional share of available resources.

19. The distributed computing system of claim 18, wherein said tenants comprise a plurality of parent tenants, each with at least one child tenant, and said distribution policy defines heirarchical resource entitlements of said tenants, with entitlements of child tenants defined as proportional shares of parent tenants.

20. The distributed computing system of claim 14, wherein said values comprise absolute values each defining a number of resource units.

21. The distributed computing system of claim 14, wherein said values comprise proportional values each defining a proportional value of available resources and absolute values each defining a number of resource units.

22. The distributed computing system of claim 14, wherein said resources comprise resources in a plurality of resource pools.

23. The distributed computing system of claim 14, wherein data structure comprises a distribution policy for each one of said resource pools.

24. The distributed computing system of claim 23, wherein said distribution policy for a first one of said resource pools defines a first group of tenants with access to said first one of said resource pools, and said distribution policy for a second one of said resource pools defines a second group of tenants with access to said second one of said resource pools.

25. The distributed computing system of claim 24, wherein at least one tenant is part of both said first and second groups.