SYSTEM, DEVICE AND PROCESS FOR DYNAMIC TENANT STRUCTURE ADJUSTMENT IN A DISTRIBUTED RESOURCE MANAGEMENT SYSTEM

• US 20170318091A1
• Filed: 04/29/2016
• Published: 11/02/2017
• Est. Priority Date: 04/29/2016
• 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: KE, Xiaodi, CHEN, Chong, LAM, Jason T.S., GUO, Lei
• Granted Patent: US 10,193,977 B2
• Time in Patent Office: Days
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 41/5054 Automatic deployment of services triggered by the service manager, e.g. service implementation by automatic configuration of network components
• CPC Class Codes: H04L 47/821 Prioritising resource allocation or reservation requests
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context

Abstract

Methods and systems of managing workloads and resources for tenants structured as a hierarchical tenant queue defining a resource distribution policy. The tenants are modified and the system responds with dynamic adjustments to the hierarchical tenant queue and workload distribution. A rule-based workload management engine defines rules for actions for the workload to respond to the dynamic update.

Claims

1. A process for managing workloads and resources in a distributed resource management system, the process comprising:

in response to an update to a tenant of a hierarchical queue, receiving, by at least one processor from a rule-based workload management engine, an action for at least one workload of the tenant, the hierarchical queue defining a resource distribution policy, the at least one workload associated with a resource request;

updating, by the at least one processor, the hierarchical tenant queue based on the update by applying the action for the at least one workload associated with the resource request, without interrupting the workload; and

scheduling the workload based on the updated hierarchical tenant queue.

2. The process of claim 1, further comprising defining, by the at least one processor, rules for the rule-based workload management engine, a rule having a component for the action for the workload.

3. The process of claim 2, the rule having a component for a tenant event to determine that the rule is applicable to the update.

4. The process of claim 2, the rule having a component for a workload matching expression to determine that the rule is applicable to the workload.

5. The process of claim 2, further comprising sending a request to the rule-based workload management engine for the action in response to detecting the update, the request comprising the update and the workload associated with the resource request for the tenant.

6. The process of claim 4, further comprising identifying, by the rule-based workload management engine, the rule based on the component for the tenant event, the component for the workload matching expression, and the component for the action for the workload, and receiving the rule in response to the request.

7. The process of claim 1, further comprising, by the rule-based workload management engine:

defining rules, each rule having an action for a workload;

identifying, from the rules, a set of rules applicable to the update;

filtering the set of rules using the workload associated with the resource request for the tenant;

upon determining that the filtered set of rules include multiple rules, ordering the filtered set of rules based on a priority sequence; and

returning actions for the workload associated with the resource request for the tenant from the ordered, filtered set of rules.

8. The process of claim 1, further comprising:

applying a default action to move the workload associated with the resource request for the tenant to a Lost &

Found queue.

9. The process of claim 5, further comprising determining that no rules are applicable to the dynamic update and returning one or more default rules to move the workload associated with the resource request for the tenant to a Lost &

Found queue.

10. The process of claim 1, wherein applying the action for the workload associated with the resource request for the tenant comprises applying a default action to move the workload to a Lost &

Found queue.

11. The process of claim 10 further comprising determining that there are no applicable actions to the workload associated with the resource request for the tenant prior to applying the default action.

12. The process of claim 10, further comprising moving the workload from the Lost &

Found queue back to the hierarchical queue.

13. A distributed resource management system for managing workloads and resources comprising:

a data storage device persistently storing a plurality of tenants structured as a hierarchical tenant queue defining a resource distribution policy;

at least one processor configured for;

a rule-based workload management engine defining rules, each rule defining an action for a workload;

a workload management agent to;

detect a dynamic update to a tenant of the hierarchical queue, the tenant having at least one workload associated with a resource request for the tenant;

receive, from the rule-based workload management engine, a rule defining an action for the workload associated with the resource request for the tenant; and

update the data structure for the hierarchical queue by applying the action for the at least one workload associated with the resource request for the tenant and without interrupting the workload.

14. The system of claim 13, further comprising defining, by the at least one processor, rules for the rule-based workload management engine, a rule having a component for the action for the workload.

15. The system of claim 14, the rule having a component for a tenant event to determine that the rule is applicable to the update.

16. The system of claim 14, the rule having a component for a workload matching expression to determine that the rule is applicable to the workload.

17. The system of claim 14, the rules comprising one or more default rules to move the workload associated with the resource request for the tenant to a Lost &

Found queue.

18. A device for managing workloads and resources in a distributed resource management system, the device having a processor and a memory storing instructions to configure the processor with a rule-based workload management engine to:

receive a notification of an update to a tenant of a hierarchical queue, the hierarchical queue defining a resource distribution policy;

retrieve an action for at least one workload of the tenant, the at least one workload associated with a resource request; and

return the action to the at least one processor to adjust the hierarchical tenant queue without interrupting the workload.

19. The device of claim 18, wherein the rule-based workload management engine has rules with a component for the action for the workload.

20. The device of claim 19, wherein the rule-based workload management engine has rules with a component for a tenant event to determine that the rule is applicable to the update.

21. The device of claim 19, wherein the rule-based workload management engine has rules with a component for a workload matching expression to determine that the rule is applicable to the workload.