Tenant selection in quota enforcing request admission mechanisms for shared applications

• US 9,760,847 B2
• Filed: 05/29/2013
• Issued: 09/12/2017
• Est. Priority Date: 05/29/2013
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Krebs, Rouven, Mehta, Arpit
• Primary Examiner(s): MARCUS, LELAND R
• Application Number:
  US13/904,729
• Publication Number:
  US 20140358620A1
• Time in Patent Office: 1,567 Days
• Field of Search: None
• CPC Class Codes: G06F 2209/5013 Request control
• CPC Class Codes: G06F 2209/5021 Priority
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: H04L 41/5009 Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
• CPC Class Codes: H04L 41/5025 by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade

Abstract

Methods, systems, and computer-readable storage media for selecting requests from a plurality of tenant queues in a multi-tenant system including actions of determining a plurality of weights, each weight being associated with a respective tenant in a set of tenants, each weight being dynamically adjusted based on a quota associated with the respective tenant for each iteration of a plurality of iterations within a period, selecting a tenant from the set of tenants based on the plurality of weights to provide a selected tenant, and transmitting a request from a request queue associated with the selected tenant for processing by a shared resource.

Claims

1. A computer-implemented method for selecting requests from a plurality of tenant queues in a multi-tenant system, the method being executed using one or more processors and comprising:

determining, by the one or more processors, a plurality of weights based on an initial set of weights provided at a beginning of a period, each weight being associated with a respective tenant in a set of tenants that share an application server instance executed by the multi-tenant system, which comprises an application server system;

receiving, by the one or more processors, a measured average response time and a measured throughput for each tenant in the set of tenants;

determining, by the one or more processors, a total of average response times for all tenants, an average response time error for the respective tenant, and a throughput error for the respective tenant based on the measured average response time, the measured throughput and a service level agreement that defines an average response time to process a quota comprising a maximum number of requests the respective tenant is allowed to send during each iteration to have a guaranteed quality of service;

dynamically adjusting, by the one or more processors, each weight based on the average response time error, the throughput error for the respective tenant, and the total of average response times for all tenants;

selecting, by the one or more processors, a tenant from the set of tenants based on the plurality of weights to provide a selected tenant; and

transmitting, by the one or more processors, a request from a request queue associated with the selected tenant for processing by a dedicated shared resource, which is isolated from other dedicated shared resources, associated with other tenants within the multi-tenant system, with regard to performance and data privacy.

2. The method of claim 1, further comprising:

identifying, from the plurality of tenants, tenants having non-empty request queues; and

including the tenants having non-empty request queues in the set of tenants.

3. The method of claim 1, further comprising determining a plurality of weight ranges based on the plurality of weights, each weight range being associated with a respective tenant in the set of tenants, wherein selecting a tenant from the set of tenants is executed based on the plurality of weight ranges.

4. The method of claim 3, further comprising normalizing weights in the plurality of weights, such that a sum of the weights in the plurality of weights is equal to 1.

5. The method of claim 3, wherein selecting a tenant from the set of tenants comprises generating a random number and selecting a tenant based on the random number and the plurality of weight ranges.

6. The method of claim 5, wherein the selected tenant is associated with a weight range, the random number falling within the weight range.

7. The method of claim 3, wherein each weight range is determined based on a total number of requests in request queues associated with tenants in the set of tenants.

8. The method of claim 1, further comprising, in response to transmitting a request from a request queue associated with the selected tenant for processing by a shared resource:

decrementing a quota associated with the selected tenant to provide a revised quota, wherein weights in a subsequent iteration are determined at least partially based on the revised quota.

9. The method of claim 1, further comprising determining a priority for each tenant in the set of tenants based on respective weights in the plurality of weights to provide a plurality of priorities, wherein selecting a tenant from the set of tenants is executed based on the plurality of priorities.

10. The method of claim 9, wherein each priority is determined based on a respective weight and a respective request weight associated with the respective tenant.

11. The method of claim 10, wherein the respective request weight is incremented in response to the respective tenant being the selected tenant.

12. The method of claim 9, wherein a tenant having a lowest priority is selected as the selected tenant.

13. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for selecting requests from a plurality of tenant queues in a multi-tenant system, the operations comprising:

determining a plurality of weights based on an initial set of weights provided at a beginning of a period, each weight being associated with a respective tenant in a set of tenants that share an application server instance executed by the multi-tenant system, which comprises an application server system;

receiving a measured average response time and a measured throughput for each tenant in the set of tenants;

determining a total of average response times for all tenants, an average response time error for the respective tenant, and a throughput error for the respective tenant based on the measured average response time, the measured throughput and a service level agreement that defines an average response time to process a quota comprising a maximum number of requests the respective tenant is allowed to send during each iteration to have a guaranteed quality of service;

dynamically adjusting each weight based on the average response time error, the throughput error for the respective tenant, and the total of average response times for all tenants;

selecting a tenant from the set of tenants based on the plurality of weights to provide a selected tenant; and

transmitting a request from a request queue associated with the selected tenant for processing by a dedicated shared resource, which is isolated from other dedicated shared resources, associated with other tenants within the multi-tenant system, with regard to performance and data privacy.

14. The computer-readable storage medium of claim 13, wherein operations further comprise determining a plurality of weight ranges based on the plurality of weights, each weight range being associated with a respective tenant in the set of tenants, wherein selecting a tenant from the set of tenants is executed based on the plurality of weight ranges.

15. The computer-readable storage medium of claim 13, wherein operations further comprise, in response to transmitting a request from a request queue associated with the selected tenant for processing by a shared resource:

decrementing a quota associated with the selected tenant to provide a revised quota, wherein weights in a subsequent iteration are determined at least partially based on the revised quota.

16. The computer-readable storage medium of claim 13, wherein operations further comprise determining a priority for each tenant in the set of tenants based on respective weights in the plurality of weights to provide a plurality of priorities, wherein selecting a tenant from the set of tenants is executed based on the plurality of priorities.

17. A system, comprising:

a computing device; and

a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for selecting requests from a plurality of tenant queues in a multi-tenant system, the operations comprising;

determining a plurality of weights based on an initial set of weights provided at a beginning of a period, each weight being associated with a respective tenant in a set of tenants that share an application server instance executed by the multi-tenant system, which comprises an application server system;

receiving a measured average response time and a measured throughput for each tenant in the set of tenants;

determining a total of average response times for all tenants, an average response time error for the respective tenant, and a throughput error for the respective tenant based on the measured average response time, the measured throughput and a service level agreement that defines an average response time to process a quota comprising a maximum number of requests the respective tenant is allowed to send during each iteration to have a guaranteed quality of service;

dynamically adjusting each weight based on the average response time error, the throughput error for the respective tenant, and the total of average response times for all tenants;

selecting a tenant from the set of tenants based on the plurality of weights to provide a selected tenant; and

transmitting a request from a request queue associated with the selected tenant for processing by a dedicated shared resource, which is isolated from other dedicated shared resources, associated with other tenants within the multi-tenant system, with regard to performance and data privacy.

18. The system of claim 17, wherein operations further comprise determining a plurality of weight ranges based on the plurality of weights, each weight range being associated with a respective tenant in the set of tenants, wherein selecting a tenant from the set of tenants is executed based on the plurality of weight ranges.

19. The system of claim 17, wherein operations further comprise, in response to transmitting a request from a request queue associated with the selected tenant for processing by a shared resource:

decrementing a quota associated with the selected tenant to provide a revised quota, wherein weights in a subsequent iteration are determined at least partially based on the revised quota.

20. The system of claim 17, wherein operations further comprise determining a priority for each tenant in the set of tenants based on respective weights in the plurality of weights to provide a plurality of priorities, wherein selecting a tenant from the set of tenants is executed based on the plurality of priorities.