CN104331332A - Virtual resource preallocation algorithm based on SLA (Service Level Agreement) - Google Patents
Virtual resource preallocation algorithm based on SLA (Service Level Agreement) Download PDFInfo
- Publication number
- CN104331332A CN104331332A CN201410611354.XA CN201410611354A CN104331332A CN 104331332 A CN104331332 A CN 104331332A CN 201410611354 A CN201410611354 A CN 201410611354A CN 104331332 A CN104331332 A CN 104331332A
- Authority
- CN
- China
- Prior art keywords
- resource
- tenant
- sla
- virtual
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a virtual resource preallocation algorithm based on SLA (Service Level Agreement). According to the virtual resource preallocation algorithm, under a multi-tenant environment of SaaS (Software As A Service), in order to ensure that QoS (Quality of Service) of multiple tenants can be simultaneously met, the SRL (Service Resource Level) can be obtained according to SLA between each tenant and a service provider to obtain the demand degree of the tenants on resources, the resources of the tenants are preallocated according to the RSL, the mapping relationship between the tenants and a corresponding virtual machine is established, the virtual resources required when the corresponding virtual machine is started are controlled according to the preallocated virtual resources, and thus the dynamic distribution of tenant resources is realized.
Description
Technical field
The present invention relates to technical field of virtualization, be specifically related to a kind of virtual resource predistribution algorithm based on SLA.
Background technology
Along with the development of Internet technology and the maturation of application software, SaaS (Software as a Service) pattern has become a kind of new software and has paid technology mode.And many tenants technology is the core technology of SaaS application, many tenants carry out resource sharing, namely refer to that all tenants on SaaS platform can share the resource such as CPU, internal memory, I/O, bandwidth of first floor system.
Many tenants technology is the core technology of SaaS application, the thought of many tenants of SaaS leaves in the same server group of SaaS service provider by the data of multiple tenant and operation flow trustship, its objective is and allow multiple tenant to share software and hardware resources, improve resource utilization, reduce the average basal facility and handling cost that are split on single tenant.Under the environment of many tenants, all tenants share software and hardware resources, and from the angle of tenant, because the SLA of tenant may be different, therefore we need to ensure that the service quality of multiple tenant is met simultaneously; From the angle of service provider, also need to realize rationalization that each tenant's resource uses and improve the satisfaction of tenant to service.Present many enterprise requirements service level agreement (SLA), SLA can ensure the performance of the IT service that enterprise pays for it, many regulations about service quality are had in SLA, according to the definition of standard, service quality comprises the nonfunctional space such as response time, handling capacity, availability, the experience of user under these relations on attributes to multi-tenant environment, needs certain technology to ensure.
And the performance objective requirement between tenant under multi-tenant environment is isolation, but influencing each other of performance between them but may be caused between the tenant sharing same resource because of competitive resource, we need by virtual technology is for this reason the service condition that tenant determines resource, to ensure the service performance of tenant, and wherein crucial be exactly a bit when delimiting logical boundary, be defined as that each tenant distributes number virtual resource, this process we be referred to as pre-allocation of resources process.
Pre-allocation resource and statistics: to the setting of tenant's virtual resource be not arbitrarily carry out but approached the demand of tenant's resource by didactic algorithm by some statisticss, the statistics on these computational resource borders can be obtained by simulated experiment when off-line by managerial personnel.
The SLA of pre-allocation resource and tenant: the setting of virtual resource is also relevant with SLA, and requirement is clearly exactly, and under similarity condition, the virtual resource of the tenant of high QoS demand is more than the preallocated resource of the tenant of low QoS demand.
The abbreviation of SLA:Service-Level Agreement, is meant to service-level agreement.
QoS (Quality of Service), Chinese " service quality " by name.It refers to that network provides a kind of ability of higher Priority Service, comprise dedicated bandwidth, shake controls and postpone the specified network flow etc. under (for real-time and interactive traffic situation), the improvement of packet loss and different WAN, LAN and MAN technology, the right of priority simultaneously ensuring often kind of flow to provide can not hinder the process of other flow.
Summary of the invention
The technical problem to be solved in the present invention is: provide a kind of virtual resource predistribution algorithm based on SLA.
The technical solution adopted in the present invention is:
A kind of virtual resource predistribution algorithm based on SLA, under the multi-tenant environment of SaaS, in order to ensure that many tenants QoS can meet simultaneously, according to the SLA between user and service provider, obtain the horizontal SRL of its Service Source, obtain the desirability of tenant for resource, be the predistribution that tenant carries out resource according to the height of Service Source level again, set up the mapping relations between tenant and respective virtual machine, by virtual resource required during these preallocated virtual resources control virtual machine activations, realize the dynamic assignment to tenant's resource.
The process of described pre-allocation of resources is as follows:
1) SLA according to tenant obtains the horizontal SRL of Service Source:
Tenant's
, variable is wherein the qos parameter of corresponding tenant and the quantized value of Service Management parameter respectively;
The horizontal SRL of Service Source according to the height of tenant SLA level, reflect its to the demand of system resource number, he is the function of parameter in SLA by the constraint of various QoS parameter QoS in SLA;
Wherein:
Weight w
ivalue be determined by the relation of this QoS variable and system resource, the relation of this qos parameter and system resource is closer, and the weighted value of this parameter is larger,
When qos parameter is positive correlation characteristic,
, namely the larger expression service quality of the value of qos parameter is better,
When qos parameter is negative correlation characteristic,
, namely the less expression service quality of the value of qos parameter is better;
Q
maxrepresent the optimal value that service provider can provide on this qos parameter,
Q
irepresent the value on i-th component in SLA;
2) calculating of preallocated various resource is needed during virtual machine initialization:
For the userbase k determined, obtain an optimization resource vector
, wherein each variable R
irepresenting certain system resource required when providing optimised service, comprising the resources such as CPU, internal memory, hard disk;
Vector
, represent the requirement vector be made up of the SRL of m tenant;
Preallocated various resource is needed to pass through matrix during virtual machine initialization corresponding to tenant
Obtain.
Mapping relations between described tenant and respective virtual machine, be exactly system resource in resource pool and the mapping relations between virtual application, the corresponding virtual application of each tenant, concerning tenant, the services request of virtual application is needed to the support of underlying resource, therefore can set up the corresponding relation of tenant and bottom hardware resource carrying out preallocated to the virtual resource of tenant while.
When there being new tenant to add SaaS application platform, carry out the initial work of respective virtual machine, then pass through the virtual resource of pre-allocation of resources algorithm determination virtual machine.
Beneficial effect of the present invention: the present invention is according to the SLA between user and service provider, the predistribution value of the virtual system resource of each tenant is determined by virtualized technology, by virtual resource required during these preallocated virtual resources control virtual machine activations, realize the dynamic assignment to tenant's resource, to significant based on the performance isolation of the virtual resource allocation of service-level agreement to many tenants under multi-tenant environment.
Accompanying drawing explanation
Fig. 1 is optimization resource data store form schematic diagram of the present invention;
Fig. 2 is pre-allocation of resources algorithm flow schematic diagram of the present invention;
Wherein, VM represents virtual machine.
Embodiment
Below according to Figure of description, in conjunction with specific embodiments, the present invention is further described:
A kind of virtual resource predistribution algorithm based on SLA, under the multi-tenant environment of SaaS, in order to ensure that many tenants QoS can meet simultaneously, according to the SLA between user and service provider, obtain the horizontal SRL of its Service Source, obtain the desirability of tenant for resource, be the predistribution that tenant carries out resource according to the height of Service Source level again, set up the mapping relations between tenant and respective virtual machine, by virtual resource required during these preallocated virtual resources control virtual machine activations, realize the dynamic assignment to tenant's resource.
The process of described pre-allocation of resources is as follows:
1) SLA according to tenant obtains the horizontal SRL of Service Source:
Tenant's
, variable is wherein the qos parameter of corresponding tenant and the quantized value of Service Management parameter respectively;
The horizontal SRL of Service Source according to the height of tenant SLA level, reflect its to the demand of system resource number, he is the function of parameter in SLA by the constraint of various QoS parameter QoS in SLA;
Wherein:
Weight w
ivalue be determined by the relation of this QoS variable and system resource, the relation of this qos parameter and system resource is closer, and the weighted value of this parameter is larger, and such as, the weight w of the variablees such as response time is larger than the w value of security.
When qos parameter is positive correlation characteristic,
, namely the larger expression service quality of the value of qos parameter is better,
When qos parameter is negative correlation characteristic,
, namely the less expression service quality of the value of qos parameter is better;
Q
maxrepresent the optimal value that service provider can provide on this qos parameter,
Q
irepresent the value on i-th component in SLA;
2) calculating of preallocated various resource is needed during virtual machine initialization:
After obtaining its Service Source level according to the SLA of tenant, just obtaining the desirability of tenant for resource, is the predistribution that tenant carries out resource according to the height of Service Source level, for this reason, and the concept of definition optimization resource.
When optimization resource refers to that the userbase of tenant is k, in order to provide the resource required for optimised service to tenant, this resource variable wherein comprises the resources such as CPU, internal memory, hard disk.
Service state when optimised service refers to that the indices of service quality all meets the optimal value that web services can provide.
The acquisition of optimization resource tests by a large amount of analog simulations the mean value obtained primarily of keeper when off-line, and wherein the file layout of optimization resource can be as shown in Figure l.
For the userbase k determined, obtain an optimization resource vector
, wherein each variable R
irepresenting certain system resource required when providing optimised service, comprising the resources such as CPU, internal memory, hard disk;
Vector
, represent the requirement vector be made up of the SRL of m tenant;
Preallocated various resource is needed to pass through matrix during virtual machine initialization corresponding to tenant
Obtain.
When for tenant's predistribution virtual resource, also need the corresponding relation set up between virtual machine and tenant, as shown in Figure 2.
Mapping relations between described tenant and respective virtual machine, be exactly system resource in resource pool and the mapping relations between virtual application, the corresponding virtual application of each tenant, concerning tenant, the services request of virtual application is needed to the support of underlying resource, therefore can set up the corresponding relation of tenant and bottom hardware resource carrying out preallocated to the virtual resource of tenant while.
When there being new tenant to add SaaS application platform, carry out the initial work of respective virtual machine, then pass through the virtual resource of pre-allocation of resources algorithm determination virtual machine.
Claims (4)
1. the virtual resource predistribution algorithm based on SLA, it is characterized in that: under the multi-tenant environment of SaaS, according to the SLA between user and service provider, obtain the horizontal SRL of its Service Source, obtain the desirability of tenant for resource, be the predistribution that tenant carries out resource according to the height of Service Source level again, set up the mapping relations between tenant and respective virtual machine, by virtual resource required during these preallocated virtual resources control virtual machine activations, realize the dynamic assignment to tenant's resource.
2. a kind of virtual resource predistribution algorithm based on SLA according to claim 1, is characterized in that: the process of described pre-allocation of resources is as follows:
1) SLA according to tenant obtains the horizontal SRL of Service Source:
Tenant's
, variable is wherein the qos parameter of corresponding tenant and the quantized value of Service Management parameter respectively;
Wherein:
Weight w
ivalue be determined by the relation of this QoS variable and system resource, the relation of this qos parameter and system resource is closer, and the weighted value of this parameter is larger,
When qos parameter is positive correlation characteristic,
,
When qos parameter is negative correlation characteristic,
;
Q
maxrepresent the optimal value that service provider can provide on this qos parameter,
Q
irepresent the value on i-th component in SLA;
2) calculating of preallocated various resource is needed during virtual machine initialization:
For the userbase k determined, obtain an optimization resource vector
, wherein each variable R
irepresent certain system resource required when providing optimised service;
Vector
, represent the requirement vector be made up of the SRL of m tenant;
Preallocated various resource is needed to pass through matrix during virtual machine initialization corresponding to tenant
Obtain.
3. a kind of virtual resource predistribution algorithm based on SLA according to claim 1 or 2, is characterized in that: the mapping relations between described tenant and respective virtual machine, is exactly system resource in resource pool and the mapping relations between virtual application.
4. a kind of virtual resource predistribution algorithm based on SLA according to claim 3, it is characterized in that: when there being new tenant to add SaaS application platform, carry out the initial work of respective virtual machine, then pass through the virtual resource of pre-allocation of resources algorithm determination virtual machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410611354.XA CN104331332B (en) | 2014-11-04 | 2014-11-04 | A kind of virtual resource method for pre-distributing based on SLA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410611354.XA CN104331332B (en) | 2014-11-04 | 2014-11-04 | A kind of virtual resource method for pre-distributing based on SLA |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104331332A true CN104331332A (en) | 2015-02-04 |
| CN104331332B CN104331332B (en) | 2017-07-21 |
Family
ID=52406066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410611354.XA Active CN104331332B (en) | 2014-11-04 | 2014-11-04 | A kind of virtual resource method for pre-distributing based on SLA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104331332B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105938577A (en) * | 2015-03-03 | 2016-09-14 | 国际商业机器公司 | Building a multi-tenant portal application |
| CN106897094A (en) * | 2017-02-24 | 2017-06-27 | 郑州云海信息技术有限公司 | SaaS software deployments method and device under a kind of cloud environment |
| CN106897115A (en) * | 2017-02-24 | 2017-06-27 | 郑州云海信息技术有限公司 | SaaS software deployments method and device under a kind of cloud environment |
| CN107294765A (en) * | 2017-04-28 | 2017-10-24 | 西安电子科技大学 | A kind of network function virtualizes collaborating trust management method |
| CN108459898A (en) * | 2017-02-20 | 2018-08-28 | 阿里巴巴集团控股有限公司 | A kind of recovery method as resource and device |
| CN109189553A (en) * | 2018-08-17 | 2019-01-11 | 烽火通信科技股份有限公司 | Network service and virtual resource multiple target matching process and system |
| CN109992418A (en) * | 2019-03-25 | 2019-07-09 | 华南理工大学 | The multi-tenant big data platform resource priority level scheduling method and system of SLA perception |
| CN110163731A (en) * | 2019-04-30 | 2019-08-23 | 广州市中智软件开发有限公司 | Method for building up, system and the storage medium of the room of virtually bidding of intermediary sevices supermarket |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101051942A (en) * | 2007-04-02 | 2007-10-10 | 北京亿阳信通软件研究院有限公司 | Method and device for determining business parameter grade quantizing range of business service |
| US20140007097A1 (en) * | 2012-06-29 | 2014-01-02 | Brocade Communications Systems, Inc. | Dynamic resource allocation for virtual machines |
| CN104009939A (en) * | 2014-05-29 | 2014-08-27 | 中国联合网络通信集团有限公司 | Service resource distribution method and system |
| CN104010028A (en) * | 2014-05-04 | 2014-08-27 | 华南理工大学 | Dynamic virtual resource management strategy method for performance weighting under cloud platform |
-
2014
- 2014-11-04 CN CN201410611354.XA patent/CN104331332B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101051942A (en) * | 2007-04-02 | 2007-10-10 | 北京亿阳信通软件研究院有限公司 | Method and device for determining business parameter grade quantizing range of business service |
| US20140007097A1 (en) * | 2012-06-29 | 2014-01-02 | Brocade Communications Systems, Inc. | Dynamic resource allocation for virtual machines |
| CN104010028A (en) * | 2014-05-04 | 2014-08-27 | 华南理工大学 | Dynamic virtual resource management strategy method for performance weighting under cloud platform |
| CN104009939A (en) * | 2014-05-29 | 2014-08-27 | 中国联合网络通信集团有限公司 | Service resource distribution method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105938577A (en) * | 2015-03-03 | 2016-09-14 | 国际商业机器公司 | Building a multi-tenant portal application |
| US10798213B2 (en) | 2015-03-03 | 2020-10-06 | International Business Machines Corporation | Building a multi-tenant portal application |
| CN108459898A (en) * | 2017-02-20 | 2018-08-28 | 阿里巴巴集团控股有限公司 | A kind of recovery method as resource and device |
| CN106897094A (en) * | 2017-02-24 | 2017-06-27 | 郑州云海信息技术有限公司 | SaaS software deployments method and device under a kind of cloud environment |
| CN106897115A (en) * | 2017-02-24 | 2017-06-27 | 郑州云海信息技术有限公司 | SaaS software deployments method and device under a kind of cloud environment |
| CN107294765A (en) * | 2017-04-28 | 2017-10-24 | 西安电子科技大学 | A kind of network function virtualizes collaborating trust management method |
| CN107294765B (en) * | 2017-04-28 | 2020-08-28 | 西安电子科技大学 | Network function virtualization self-adaptive trust management method |
| CN109189553A (en) * | 2018-08-17 | 2019-01-11 | 烽火通信科技股份有限公司 | Network service and virtual resource multiple target matching process and system |
| CN109992418A (en) * | 2019-03-25 | 2019-07-09 | 华南理工大学 | The multi-tenant big data platform resource priority level scheduling method and system of SLA perception |
| CN109992418B (en) * | 2019-03-25 | 2023-01-06 | 华南理工大学 | SLA-aware resource priority scheduling method and system for multi-tenant big data platform |
| CN110163731A (en) * | 2019-04-30 | 2019-08-23 | 广州市中智软件开发有限公司 | Method for building up, system and the storage medium of the room of virtually bidding of intermediary sevices supermarket |
| CN110163731B (en) * | 2019-04-30 | 2021-07-27 | 广州市中智软件开发有限公司 | Method, system and storage medium for establishing virtual bidding room of intermediary service supermarket |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104331332B (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104331332A (en) | Virtual resource preallocation algorithm based on SLA (Service Level Agreement) | |
| US10305747B2 (en) | Container-based multi-tenant computing infrastructure | |
| US10623481B2 (en) | Balancing resources in distributed computing environments | |
| WO2020258920A1 (en) | Network slice resource management method and apparatus | |
| JP5837206B2 (en) | Method and apparatus for providing isolated virtual space | |
| CN106385329B (en) | Processing method, device and the equipment of resource pool | |
| CN107222531B (en) | Container cloud resource scheduling method | |
| US20130111027A1 (en) | Accessing physical resources in a cloud computing environment | |
| CN105610715B (en) | A kind of cloud data center multi-dummy machine migration scheduling method of planning based on SDN | |
| CN102567077B (en) | Virtualized resource distribution method based on game theory | |
| CN110661842B (en) | Resource scheduling management method, electronic equipment and storage medium | |
| WO2019091387A1 (en) | Method and system for provisioning resources in cloud computing | |
| CN107450977A (en) | The resource management dispatching method towards GPGPU clusters based on YARN | |
| DE112021006130T5 (en) | AUTOMATED ORCHESTRATION OF CONTAINERS THROUGH EVALUATION OF MICROSERVICES | |
| CN102981929A (en) | Management method and system for disk mirror images | |
| CN110321198B (en) | Container cloud platform computing resource and network resource cooperative scheduling method and system | |
| US11093288B2 (en) | Systems and methods for cluster resource balancing in a hyper-converged infrastructure | |
| CN109471725A (en) | Resource allocation methods, device and server | |
| CN106155764A (en) | The method and device of scheduling virtual machine input and output resource | |
| US20160057206A1 (en) | Application profile to configure and manage a software defined environment | |
| CN114356543A (en) | Kubernetes-based multi-tenant machine learning task resource scheduling method | |
| CN103268253A (en) | Intelligent scheduling management method for multi-scale parallel rendering jobs | |
| Ghribi | Energy efficient resource allocation in cloud computing environments | |
| CN109960579A (en) | A kind of method and device of adjustment business container | |
| CN107872405A (en) | Distributed bandwidth allocation and regulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180813 Address after: 250101 S06 tower, 1036, Chao Lu Road, hi tech Zone, Ji'nan, Shandong. Patentee after: SHANDONG LANGCHAO YUNTOU INFORMATION TECHNOLOGY Co.,Ltd. Address before: No. 1036, Shandong high tech Zone wave road, Ji'nan, Shandong Patentee before: INSPUR ELECTRONIC INFORMATION INDUSTRY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 250101 S06 tower, 1036, Chao Lu Road, hi tech Zone, Ji'nan, Shandong. Patentee after: SHANDONG INSPUR CLOUD INFORMATION TECHNOLOGY Co.,Ltd. Address before: 250101 S06 tower, 1036, Chao Lu Road, hi tech Zone, Ji'nan, Shandong. Patentee before: SHANDONG LANGCHAO YUNTOU INFORMATION TECHNOLOGY Co.,Ltd. Address after: 250101 S06 tower, 1036, Chao Lu Road, hi tech Zone, Ji'nan, Shandong. Patentee after: Tidal Cloud Information Technology Co.,Ltd. Address before: 250101 S06 tower, 1036, Chao Lu Road, hi tech Zone, Ji'nan, Shandong. Patentee before: SHANDONG INSPUR CLOUD INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 250100 No. 1036 Tidal Road, Jinan High-tech Zone, Shandong Province, S01 Building, Tidal Science Park Patentee after: Inspur cloud Information Technology Co.,Ltd. Address before: 250101 S06 tower, 1036, Chao Lu Road, hi tech Zone, Ji'nan, Shandong. Patentee before: Tidal Cloud Information Technology Co.,Ltd. |