Compartmentalized overcommitting of resources

• US 10,574,527 B2
• Filed: 05/09/2016
• Issued: 02/25/2020
• Est. Priority Date: 05/09/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Billore, Ashish, Kairali, Sudheesh S.
• Primary Examiner(s): Whipple, Brian
• Assistant Examiner(s): Fan, John
• Application Number:
  US15/149,205
• Publication Number:
  US 20170324810A1
• Time in Patent Office: 1,387 Days
• Field of Search: 709226
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 41/0895 Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
• 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 41/5051 Service on demand, e.g. definition and deployment of services in real time
• 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 41/5096 wherein the managed service relates to distributed or central networked applications
• 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: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences

Abstract

As disclosed herein a computer-implemented method includes providing a plurality of resource allocation zones corresponding to a plurality of overcommit policies. The method further includes receiving a request for a resource for a tenant, and determining a selected overcommit policy corresponding to an anticipated resource need. The method further includes selecting a resource allocation zone for the tenant from the plurality of resource allocation zones, and providing the resource to the tenant. A computer program product and a computer system corresponding to the above method are also disclosed herein.

Claims

1. A method comprising:

receiving an available computing device data set including information indicative of;

(i) an identity of a plurality of computer devices with each computer device including an amount of allocated computing resources, and (ii) for each given computer device of the plurality of computer devices, operational parameter values characterizing performance and capabilities of the given computer device;

for each given computer device of the plurality of computer devices;

defining an overcommit policy for the given computer device, with each overcommit policy including a set of machine logic based rules for determining a supplemental amount of allocated computing resources to allocate to a tenant workload being performed on the given computer device in circumstances where a tenant'"'"'s workload temporarily requires more than a predetermined baseline amount of computing resources, and

implementing, on the given computer device, the defined overcommit policy for the given computer device;

responsive to implementing the defined overcommit policy for each given computer device of the plurality of computer devices, grouping the plurality of computer devices into a plurality of overcommit zones, where all computer devices in a given zone of the plurality of zones have the same implemented overcommit policy;

receiving a cloud resource provisioning request including information indicative of ;

(i) identification of a prospective tenant workload, and (ii) information indicative of which computing resources are critical to workload performance;

selecting an overcommit zone based, at least in part, on the information indicative of which computing resources are critical to workload performance indicated by the cloud resource provisioning request and the overcommit policy of the plurality of computer devices grouped into the selected overcommit zone;

performing the prospective tenant workload on at least one computer device grouped into the selected overcommit zone, with the performance including at least one instance of performing some of the prospective tenant workload using some supplemental resources allocated to the at least one of the computer device grouped into the selected overcommit zone based on the implemented overcommit policy of the at least one computer device grouped into the selected overcommit zone; and

for the at least one computer device of the plurality of computer devices grouped into the selected overcommit zone, monitoring usage of the supplemental amount of allocated computing resources in performance of the prospective tenant workload.

2. The method of claim 1 further comprising:

determining that the supplemental amount of allocated resources yields sub-optimal performance of the prospective tenant workload based, at least in part, on the monitored usage;

determining an identity of a second computer device of the plurality of computer devices with an overcommit policy providing an improved supplemental amount of allocated resources for performing the prospective tenant workload; and

migrating the prospective tenant workload to the second computer device for performance of the prospective tenant workload.

3. The method of claim 1 wherein:

each overcommit zone includes two or more computer devices;

the plurality of overcommit zones include at least a first overcommit zone, a second overcommit zone, and a third overcommit zone;

the first overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to computer processing throughput;

the second overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to random access memory (RAM); and

the third overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to computer data storage space.

4. The method of claim 3 wherein the first overcommit policy implemented on a first computer device of the plurality of computer device includes the following machine logic based rule:

a maximum predetermined number of virtual central processing units (CPUs) provisioned by each processor core of the first computer device.

5. The method of claim 1 wherein the amount of computing resources includes an amount of memory.

6. The method of claim 1 wherein the information, included in the cloud resource provisioning request, indicative of information indicative of which computing resources are critical to workload performance includes at least one of the following types of information:

(i) information indicative of how critical the prospective tenant workload is relative to a service level agreement, (ii) information indicative of how critical optimal memory use is for operation of the prospective tenant workload, and (iii) information indicative of how critical optimal provisioning of CPUs is to operation of the prospective tenant workload.

7. A computer program product (CPP) comprising:

a machine readable storage device; and

computer code stored on the machine readable storage device, with the computer code including instructions for causing a processor(s) set to perform operations including the following;

receiving an available computing device data set including information indicative of;

(i) an identity of a plurality of computer devices with each computer device including an amount of allocated computing resources, and (ii) for each given computer device of the plurality of computer devices, operational parameter values characterizing performance and capabilities of the given computer device,

for each given computer device of the plurality of computer devices;

defining an overcommit policy for the given computer device, with each overcommit policy including a set of machine logic based rules for determining a supplemental amount of allocated computing resources to allocate to a tenant workload being performed on the given computer device in circumstances where a tenant'"'"'s workload temporarily requires more than a predetermined baseline amount of computing resources, and

implementing, on the given computer device, the defined overcommit policy of determined for the given computer device,

responsive to implementing the defined overcommit policy for each given computer device of the plurality of computer devices, grouping the plurality of computer devices into a plurality of overcommit zones, where all computer devices in a given zone of the plurality of zones have the same implemented overcommit policy,

receiving a cloud resource provisioning request including information indicative of;

(i) identification of a prospective tenant workload, and (ii) information indicative of which computing resources are critical to workload performance,

selecting an overcommit zone based, at least in part, on the information indicative of which computing resources are critical to workload performance indicated by the cloud resource provisioning request and the overcommit policy of the plurality of computer devices grouped into the selected overcommit zone,

performing the prospective tenant workload on at least one computer device grouped into the selected overcommit zone, with the performance including at least one instance of performing some of the prospective tenant workload using some supplemental resources allocated to the at least one of the computer device grouped into the selected overcommit zone based on the implemented overcommit policy of the at least one computer device grouped into the selected overcommit zone, and

for the at least one computer device of the selected plurality of computer devices grouped into the selected overcommit zone, monitoring usage of the supplemental amount of allocated computing resources in performance of the prospective tenant workload.

8. The CPP of claim 7 wherein the computer code further includes instructions for causing the processor(s) set to perform the following operations:

determining that the supplemental amount of allocated resources yields sub-optimal performance of the prospective tenant workload based, at least in part, on the monitored usage;

determining an identity of a second computer device of the plurality of computer devices with an overcommit policy providing an improved supplemental amount of allocated resources for performing the prospective tenant workload; and

migrating the prospective tenant workload to the second computer device for performance of the prospective tenant workload.

9. The CPP of claim 7 wherein:

each overcommit zone includes two or more computer devices;

the plurality of overcommit zones include at least a first overcommit zone, a second overcommit zone, and a third overcommit zone;

the first overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to computer processing throughput;

the second overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to random access memory (RAM); and

the third overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to computer data storage space.

10. The CPP of claim 9 wherein the first overcommit policy implemented on a first computer device of the plurality of computer device includes the following machine logic based rule:

a maximum predetermined number of virtual central processing units (CPUs) provisioned by each processor core of the first computer device.

11. The CPP of claim 7 wherein the amount of computing resources includes an amount of memory.

12. The CPP of claim 7 wherein the information, included in the cloud resource provisioning request, indicative of information indicative of which computing resources are critical to workload performance includes at least one of the following types of information:

(i) information indicative of how critical the prospective tenant workload is relative to a service level agreement, (ii) information indicative of how critical optimal memory use is for operation of the prospective tenant workload, and (iii) information indicative of how critical optimal provisioning of CPUs is to operation of the prospective tenant workload.

13. A computer system (CS) comprising:

a processor(s) set;

a machine readable storage device; and

computer code stored on the machine readable storage device, with the computer code including instructions for causing the processor(s) set to perform operations including the following;

receiving an available computing device data set including information indicative of;

(i) an identity of a plurality of computer devices with each computer device including an amount of allocated computing resources, and (ii) for each given computer device of the plurality of computer devices, operational parameter values characterizing performance and capabilities of the given computer device,

for each given computer device of the plurality of computer devices;

defining an overcommit policy for the given computer device, with each overcommit policy including a set of machine logic based rules for determining a supplemental amount of allocated computing resources to allocate to a tenant workload being performed on the given computer device in circumstances where a tenant'"'"'s workload temporarily requires more than a predetermined baseline amount of computing resources, and

implementing, on the given computer device, the defined overcommit policy of determined for the given computer device,

responsive to implementing the defined overcommit policy for each given computer device of the plurality of computer devices, grouping the plurality of computer devices into a plurality of overcommit zones, where all computer devices in a given zone of the plurality of zones have the same implemented overcommit policy,

receiving a cloud resource provisioning request including information indicative of;

(i) identification of a prospective tenant workload, and (ii) information indicative of which computing resources are critical to workload performance,

selecting an overcommit zone based, at least in part, on the information indicative of which computing resources are critical to workload performance indicated by the cloud resource provisioning request and the overcommit policy of the plurality of computer devices grouped into the selected overcommit zone,

performing the prospective tenant workload on at least one computer device grouped into the selected overcommit zone, with the performance including at least one instance of performing some of the prospective tenant workload using some supplemental resources allocated to the at least one of the computer device grouped into the selected overcommit zone based on the implemented overcommit policy of the at least one computer device grouped into the selected overcommit zone, and

for the at least one computer device of the plurality of computer devices grouped into the selected overcommit zone, monitoring usage of the supplemental amount of allocated computing resources in performance of the prospective tenant workload.

14. The CS of claim 13 wherein the computer code further includes instructions for causing the processor(s) set to perform the following operations:

determining that the supplemental amount of allocated resources yields sub-optimal performance of the prospective tenant workload based, at least in part, on the monitored usage;

determining an identity of a second computer device of the plurality of computer devices with an overcommit policy providing an improved supplemental amount of allocated resources for performing the prospective tenant workload; and

migrating the prospective tenant workload to the second computer device for performance of the prospective tenant workload.

15. The CS of claim 13 wherein:

each overcommit zone includes two or more computer devices;

the plurality of overcommit zones include at least a first overcommit zone, a second overcommit zone, and a third overcommit zone;

the first overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to computer processing throughput;

the second overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to random access memory (RAM); and

the third overcommit zone has an overcommit policy with a set of machine logic based rules including a supplemental amount of allocated computing resources corresponding to computer data storage space.

16. The CS of claim 15 wherein the first overcommit policy implemented on a first computer device of the plurality of computer device includes the following machine logic based rule:

a maximum predetermined number of virtual central processing units (CPUs) provisioned by each processor core of the first computer device.

17. The CS of claim 13 wherein the information, included in the cloud resource provisioning request, indicative of information indicative of which computing resources are critical to workload performance includes at least one of the following types of information:

(i) information indicative of how critical the prospective tenant workload is relative to a service level agreement, (ii) information indicative of how critical optimal memory use is for operation of the prospective tenant workload, and (iii) information indicative of how critical optimal provisioning of CPUs is to operation of the prospective tenant workload.