TECHNIQUES FOR ENSURING RESOURCES ACHIEVE PERFORMANCE METRICS IN A MULTI-TENANT STORAGE CONTROLLER

• US 20130074091A1
• Filed: 09/18/2012
• Published: 03/21/2013
• Est. Priority Date: 09/20/2011
• Status: Abandoned Application

• Current Assignee: Mayadata, Inc.
• Original Assignee: Mayadata, Inc.
• Inventors: Xavier, Felix, Mukkara, Umasankar
• Application Number:
  US13/622,077
• Publication Number:
  US 20130074091A1
• Time in Patent Office: Days
• US Class Current: 718/104
• CPC Class Codes: G06F 2209/504 Resource capping
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• 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 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• 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

Techniques for ensuring performance metrics are met by resources in a multi-tenant storage controller are presented. Each resource of the multi-tenant storage controller is tracked on a per tenant bases. Usage limits are enforced on per resource and per tenant bases for the multi-tenant storage controller.

Claims

1. A method implemented in a non-transitory machine-readable storage medium and processed by one or more processors of a machine configured to perform the method, comprising:

allocating, on the machine, a resource service for each resource of a multi-tenant storage controller to each tenant;

tracking, on the machine, each tenant identity for each tenant for each resource service used by that tenant for the multi-tenant storage controller; and

enforcing, on the machine, a usage limit on the multi-tenant storage controller for each tenant for each resource service.

2. The method of claim 1 further comprising, creating, by the machine, a task queue for every task of a particular tenant.

3. The method of claim 2, wherein creating further includes identifying a tag associated with each task that identifies that task as belonging to a specific tenant.

4. The method of claim 3, wherein identifying further includes giving the tasks of the task queue for the particular tenant a pre-assigned percentage of processing within the multi-tenant storage controller based on a portion of the usage limit associated with processing throughput.

5. The method of claim 1 further comprising, creating, by the machine, a disk Input/Output (I/O) queue for all I/O associated with a particular tenant.

6. The method of claim 5, wherein creating further includes identifying a tag associated with each I/O that identifies that I/O as belonging to a specific tenant.

7. The method of claim 6, wherein identifying further includes giving the I/O of the I/O queue for the particular tenant a pre-assigned percentage of I/O access within the multi-tenant storage controller based on a portion of the usage limit associated with Input/Output Operations Per Second.

8. The method of claim 1 further comprising, keeping, by the machine, outstanding cache allocation on a per tenant bases.

9. The method of claim 8, wherein keeping further includes enforcing a portion of the usage limit associated with cache buffering when a free pool is near capacity based on the outstanding cache allocation.

10. The method of claim 1 further comprising, keeping, by the machine, a tenant identifier that identifies a particular tenant associated with each network packet of the multi-tenant storage controller.

11. The method of claim 10, wherein keeping further includes enforcing a network bandwidth rate using a portion of the usage limits on a per tenant bases.

12. The method of claim 1, wherein enforcing further includes identifying multiple components to the usage limit including:

a processing throughput limit, an Input/Output Operations Per Second limit, a cache buffering limit, and a network bandwidth limit.

13. A method implemented in a non-transitory machine-readable storage medium and processed by one or more processors of a machine configured to perform the method, comprising:

tagging, on the machine, each resource request to identify a particular tenant in a multi-tenant storage cloud environment, each resource associated with a multi-tenant storage controller;

minimizing, on the machine, kernel level interactions between threads of different tenants in the multi-tenant storage cloud environment; and

enforcing, on the machine, specific resource limits for each resource on a per tenant bases when using the multi-tenant storage controller.

14. The method of claim 13, wherein tagging further includes including a tenant identifier tag for tasks designated for access to particular processors of the multi-tenant storage controller.

15. The method of claim 13, wherein tagging further includes including a tenant identifier tag for Input/Output (I/O) designated disk access on the multi-tenant storage controller.

16. The method of claim 13, wherein tagging further includes including a tenant identifier tag for cache buffering designated for memory caching on the multi-tenant storage controller.

17. The method of claim 13, wherein tagging further includes including a tenant identifier tag for network packets designated for network bandwidth rates on the multi-tenant storage controller.

18. The method of claim 13, wherein enforcing further includes identifying each specific resource limit for each tenant based on a Service Level Agreement (SLA) for that tenant.

19. A system, comprising:

a cloud storage environment having one or more processors, memory, and storage, the cloud storage environment situated in a cloud environment and accessed over a network; and

the memory configured with a resource enforcement manager implemented as executable instructions that process on the one or more processors of the cloud storage environment;

wherein the resource enforcement manager is configured to track resource usage on a per tenant bases for each tenant of a multi-tenant storage controller, and the resource enforcement manager is configured to enforce usage limits on per resource and per tenant bases for the multi-tenant storage controller.

20. The system of claim 19, wherein the multi-tenant storage controller includes storage resources for:

processing throughput, Input/Output (I/O) operations, caching, and network bandwidth.