CN109710401A - A kind of cloud computing resources Cost Optimization Approach - Google Patents
A kind of cloud computing resources Cost Optimization Approach Download PDFInfo
- Publication number
- CN109710401A CN109710401A CN201811542291.1A CN201811542291A CN109710401A CN 109710401 A CN109710401 A CN 109710401A CN 201811542291 A CN201811542291 A CN 201811542291A CN 109710401 A CN109710401 A CN 109710401A
- Authority
- CN
- China
- Prior art keywords
- configuration
- early warning
- allocation optimum
- cloud
- analog machine
- 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.)
- Withdrawn
Links
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The present invention relates to field of cloud computer technology, especially a kind of cloud computing resources Cost Optimization Approach.Method of the invention is monitored by cloud, is monitored to CPU, memory, disk and the network of each cloud host installed on cloudy platform；Each monitored item setting early warning value, normal floating range and the trigger condition of early warning, are lower than lower limit value whithin a period of time or then trigger early warning higher than upper limit value；Find allocation optimum, find meet early warning value and spend it is least, be set as allocation optimum；Simulation uses data, the cost difference of each monitored item of server after allocation optimum；It is shown in the form of intuitive；The allocation optimum being arranged automatically according to recommendation carries out configuration modification；Including the resource expansions such as CPU, memory, hard-disc storage, bandwidth or reduction.It solves the problems, such as resource optimization in cloud computing, automatic amplification or reduction CPU, memory, disk and bandwidth can be needed according to business；And it can be shown with intuitive way.
Description
Technical field
The present invention relates to field of cloud computer technology, especially a kind of cloud computing resources Cost Optimization Approach.
Background technique
With popularizing for cloud computing, more application service providers are selected to cloud user, use cloud server cluster
Service.With the development of own service and the increase of user volume, the resources such as the calculating initially bought, storage, bandwidth cannot
Enough meet demands.A large number of users access causes access speed slower and slower, and the increased data of component also result in memory space
It is insufficient.This is just more powerful CPU, bigger memory and faster disk to be needed to go the operation for supporting these to service.It is existing
In monitoring resource, the alarm function in monitoring is halted, there is no analyze according to monitoring data and provide effective allocation plan.Though
The standard configuration template of all kinds of industries can be so provided, Yunmen sill can be reduced；But without tracking service condition, subsequent adjustment
There is still a need for user oneself definition for configuration needs.
Summary of the invention
Present invention solves the technical problem that being to provide a kind of method of cloud computing resources cost optimization；It solves in cloud computing
The problem of resource optimization, can need automatic amplification or reduction CPU, memory, disk and bandwidth according to business；And it can be with straight
The mode of sight is shown.
The technical solution that the present invention solves above-mentioned technical problem is:
The method the following steps are included:
Step 1: monitored by cloud, to CPU, memory, disk and the network of each cloud host installed on cloudy platform into
Row monitoring；
Step 2: each monitored item sets early warning value, the trigger condition of normal floating range and early warning is set, at one section
It is interior to be lower than lower limit value or then trigger early warning higher than upper limit value；
Step 3: finding allocation optimum, according to the early warning value of setting, all feasible resource distributions is traversed, satisfaction is found
Early warning value and spend it is least, be set as allocation optimum；
Step 4: simulation uses the number of each monitored item of server after allocation optimum under current server loading condition
According to, cost difference；It is shown in the form of curve graph, table respectively；
Step 5: setting carries out configuration modification automatically according to the allocation optimum of recommendation；Including CPU, memory, hard-disc storage,
The resource expansion of bandwidth or reduction.
The cloudy platform is to mix cloud environment for enterprise to provide the cloudy management platform of system for unified management, helps visitor
Realize cloudy Resource allocation and smoothing and management in family.
The cloud monitoring, provides cloud host CPU utilization rate, memory usage, disk utilization and network bandwidth, net
The monitoring of network handling capacity；Monitoring frequency is set as 5 minutes, 10 points or 15 minutes.
The allocation optimum is traversed all feasible within the early warning value that performance monitoring index is able to satisfy setting
Resource distribution is found meeting early warning value and spends least configuration；It comprises the concrete steps that:
A, an analog machine is created according to the current-configuration of cloud host, analog machine is pressurized to similarly to be born with current server
It carries；
B, the configuration n for selecting a non-cloud host current；
C, analog machine configuration is carried out with configuration n；
D, under the premise of using n is configured, the monitor control index of analog machine reaches in normal range (NR) set by user, and
Expense is all fewer than the configuration that front was tested, then configuring n is allocation optimum.
The step 4 specifically:
A, analog machine is pressurized to similarly loads with current server；
B, the configuration for modifying analog machine, is revised as allocation optimum；
C, cpu busy percentage, memory usage, disk utilization and network bandwidth, the network throughput of analog machine are monitored,
It shows in the form of a graph；
D, the general expenses difference for calculating allocation optimum and original configuration, shows in a tabular form.
In very good solution of the present invention cloud computing the problem of resource optimization, not only automatically expanded when business increases CPU,
Memory, disk and bandwidth can also reduce CPU, memory, disk and bandwidth in business decline automatically.And provide simulation yard
Scape, under current server loading condition, using data, the cost difference of each monitored item of server after allocation optimum, respectively
It is intuitively shown before user with graphical format, form, so that user more effectively adjusts configuration, reasonably adjusts cloud
Computing resource, so that resources costs optimize.
Detailed description of the invention
The following further describes the present invention with reference to the drawings:
Fig. 1 is that the cloudy platform resource of the present invention uses figure；
Fig. 2 is flow chart of the present invention.
Specific embodiment
As shown in FIGS. 1 and 2 operation flow of the present invention is implemented as follows:
1, cloud host monitor information is obtained.
Obtain cloud host monitoring information include: cpu busy percentage, memory usage, disk utilization and network bandwidth,
Network throughput.
Its step specifically: by being deployed in the cloud monitoring service of host, obtain running cloud host CPU and utilize
The information such as rate, memory usage, disk utilization and network bandwidth, network throughput, and number is recorded in the data of monitoring
According in library, monitoring frequency settable 5 minutes, 10 minutes, 15 minutes.
2, each monitored item sets early warning value, sets the trigger condition of normal floating range and early warning.
Its step specifically: the critical value of an early warning is set to each monitored item, whithin a period of time lower than lower limit or
Early warning will be issued higher than upper critical value.
Such as: cpu busy percentage, normal range (NR) [20%, 60%], in continuous 24 hours, monitoring value is below lower limit value
20% or it is higher than upper limit value 60%, that is, reaches the condition of early warning, trigger early warning.
3, allocation optimum is found.According to the early warning value of setting, all feasible resource distributions are traversed, finds and meets early warning value
And spend least, be set as allocation optimum.
Its step specifically:
A, an analog machine is created according to the current-configuration of cloud host, analog machine is pressurized to similarly to be born with current server
It carries.
B, the configuration for selecting a non-cloud host current, it is assumed that for configuration n；
C, analog machine configuration is carried out with configuration n；
D, under the premise of using n is configured, the monitor control index of analog machine be can achieve in normal range (NR) set by user,
And expense is all fewer than the configuration that front was tested；Configuring n is allocation optimum.
4, simulation using the data of each monitored item of server after allocation optimum, takes under current server loading condition
With difference, shown in the form of curve graph, table etc. are intuitive respectively.
Its step specifically:
A, analog machine is pressurized to similarly loads with current server
B, the configuration for modifying analog machine is revised as the allocation optimum of step 3 output.
C, cpu busy percentage, memory usage, disk utilization and network bandwidth, the network throughput of analog machine are monitored,
It shows in the form of a graph.
D, the general expenses difference for calculating allocation optimum and original configuration, shows in a tabular form.
5, the allocation optimum being arranged automatically according to recommendation carries out configuration modification, to achieve the effect that elastic telescopic, in business
Automatically CPU, memory, disk and bandwidth are expanded when increase, business decline when, can also reduce automatically CPU, memory, disk and
Bandwidth.
Claims (6)
1. a kind of cloud computing resources Cost Optimization Approach, which is characterized in that the method the following steps are included:
Step 1: being monitored by cloud, CPU, memory, disk and the network of each cloud host installed on cloudy platform are supervised
It surveys；
Step 2: each monitored item sets early warning value, the trigger condition of normal floating range and early warning is set, whithin a period of time
Early warning is then triggered lower than lower limit value or higher than upper limit value；
Step 3: finding allocation optimum, according to the early warning value of setting, all feasible resource distributions is traversed, finds and meets early warning
It is worth and cost is least, is set as allocation optimum；
Step 4: simulation uses the data of each monitored item of server after allocation optimum under current server loading condition, takes
Use difference；It is shown in the form of curve graph, table respectively；
Step 5: setting carries out configuration modification automatically according to the allocation optimum of recommendation；Including CPU, memory, hard-disc storage, bandwidth
Resource expansion or reduction.
2. the method according to claim 1, wherein the cloudy platform is to mix cloud environment for enterprise to provide
The cloudy management platform of system for unified management helps client to realize cloudy Resource allocation and smoothing and management.
3. the method according to claim 1, wherein the cloud monitors, cloud host CPU utilization rate, interior is provided
Deposit utilization rate, disk utilization and network bandwidth, network throughput monitoring；Monitoring frequency is set as 5 minutes, 10 points or 15 points
Clock.
4. the method according to claim 1, wherein the allocation optimum, can be expired in performance monitoring index
Within the early warning value set enough, all feasible resource distributions are traversed, find meeting early warning value and spend least configuration；
It comprises the concrete steps that:
A, an analog machine is created according to the current-configuration of cloud host, analog machine is pressurized to similarly to be loaded with current server；
B, the configuration n for selecting a non-cloud host current；
C, analog machine configuration is carried out with configuration n；
D, under the premise of using n is configured, the monitor control index of analog machine reaches in normal range (NR) set by user, and expense
All fewer than the configuration that front was tested, then configuring n is allocation optimum.
5. according to the method described in claim 3, it is characterized in that, the allocation optimum, can be expired in performance monitoring index
Within the early warning value set enough, all feasible resource distributions are traversed, find meeting early warning value and spend least configuration；
It comprises the concrete steps that:
A, an analog machine is created according to the current-configuration of cloud host, analog machine is pressurized to similarly to be loaded with current server；
B, the configuration n for selecting a non-cloud host current；
C, analog machine configuration is carried out with configuration n；
D, under the premise of using n is configured, the monitor control index of analog machine reaches in normal range (NR) set by user, and expense
All fewer than the configuration that front was tested, then configuring n is allocation optimum.
6. method according to any one of claims 1 to 5, which is characterized in that the step 4 specifically:
A, analog machine is pressurized to similarly loads with current server；
B, the configuration for modifying analog machine, is revised as allocation optimum；
C, cpu busy percentage, memory usage, disk utilization and network bandwidth, the network throughput of analog machine are monitored, with song
The form of line chart is shown；
D, the general expenses difference for calculating allocation optimum and original configuration, shows in a tabular form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542291.1A CN109710401A (en) | 2018-12-17 | 2018-12-17 | A kind of cloud computing resources Cost Optimization Approach |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542291.1A CN109710401A (en) | 2018-12-17 | 2018-12-17 | A kind of cloud computing resources Cost Optimization Approach |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109710401A true CN109710401A (en) | 2019-05-03 |
Family
ID=66255764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811542291.1A Withdrawn CN109710401A (en) | 2018-12-17 | 2018-12-17 | A kind of cloud computing resources Cost Optimization Approach |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109710401A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704851A (en) * | 2019-09-18 | 2020-01-17 | 上海联蔚信息科技有限公司 | Public cloud data processing method and device |
| CN112162853A (en) * | 2020-09-18 | 2021-01-01 | 北京浪潮数据技术有限公司 | Method and system for setting CPU frequency of cloud host, electronic equipment and storage medium |
| WO2022166582A1 (en) * | 2021-02-05 | 2022-08-11 | 华为技术有限公司 | Network management method, apparatus, device, and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050102318A1 (en) * | 2000-05-23 | 2005-05-12 | Microsoft Corporation | Load simulation tool for server resource capacity planning |
| CN103164279A (en) * | 2011-12-13 | 2013-06-19 | 中国电信股份有限公司 | Method and system for distributing cloud computing resources |
| US20160094410A1 (en) * | 2014-09-30 | 2016-03-31 | International Business Machines Corporation | Scalable metering for cloud service management based on cost-awareness |
| CN105471671A (en) * | 2015-11-10 | 2016-04-06 | 国云科技股份有限公司 | Method for customizing monitoring rules of cloud platform resources |
| CN107506241A (en) * | 2017-08-25 | 2017-12-22 | 郑州云海信息技术有限公司 | A kind of flexible method of cloud platform automatic elastic |
| CN107995028A (en) * | 2017-11-27 | 2018-05-04 | 于茵 | Cloud computing management system |
-
2018
- 2018-12-17 CN CN201811542291.1A patent/CN109710401A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050102318A1 (en) * | 2000-05-23 | 2005-05-12 | Microsoft Corporation | Load simulation tool for server resource capacity planning |
| CN103164279A (en) * | 2011-12-13 | 2013-06-19 | 中国电信股份有限公司 | Method and system for distributing cloud computing resources |
| US20160094410A1 (en) * | 2014-09-30 | 2016-03-31 | International Business Machines Corporation | Scalable metering for cloud service management based on cost-awareness |
| CN105471671A (en) * | 2015-11-10 | 2016-04-06 | 国云科技股份有限公司 | Method for customizing monitoring rules of cloud platform resources |
| CN107506241A (en) * | 2017-08-25 | 2017-12-22 | 郑州云海信息技术有限公司 | A kind of flexible method of cloud platform automatic elastic |
| CN107995028A (en) * | 2017-11-27 | 2018-05-04 | 于茵 | Cloud computing management system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704851A (en) * | 2019-09-18 | 2020-01-17 | 上海联蔚信息科技有限公司 | Public cloud data processing method and device |
| CN112162853A (en) * | 2020-09-18 | 2021-01-01 | 北京浪潮数据技术有限公司 | Method and system for setting CPU frequency of cloud host, electronic equipment and storage medium |
| WO2022166582A1 (en) * | 2021-02-05 | 2022-08-11 | 华为技术有限公司 | Network management method, apparatus, device, and computer readable storage medium |
| CN114938334A (en) * | 2021-02-05 | 2022-08-23 | 华为技术有限公司 | Network management method, device, equipment and computer readable storage medium |
| CN114938334B (en) * | 2021-02-05 | 2024-10-18 | 华为技术有限公司 | Network management method, device, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10248671B2 (en) | Dynamic migration script management | |
| US9135071B2 (en) | Selecting processing techniques for a data flow task | |
| US20140358844A1 (en) | Workflow controller compatibility | |
| US20160292608A1 (en) | Multi-cluster management method and device | |
| CN109710401A (en) | A kind of cloud computing resources Cost Optimization Approach | |
| US11528194B2 (en) | Enterprise control plane for data streaming service | |
| US10936375B2 (en) | Hyper-converged infrastructure (HCI) distributed monitoring system | |
| US11126506B2 (en) | Systems and methods for predictive data protection | |
| CN106210124B (en) | Unified cloud data center monitoring system | |
| CN103678579A (en) | Optimizing method for small-file storage efficiency | |
| US9785515B2 (en) | Directed backup for massively parallel processing databases | |
| US8892557B2 (en) | Optimal persistence of a business process | |
| JP6269140B2 (en) | Access control program, access control method, and access control apparatus | |
| CN110532058B (en) | Management method, device and equipment of container cluster service and readable storage medium | |
| KR102556186B1 (en) | Artificial intelligence development platform managing method, device, and medium | |
| CN113867957A (en) | Method and device for realizing elastic expansion of number of cross-cluster containers | |
| CN110347546B (en) | Dynamic adjustment method, device, medium and electronic equipment for monitoring task | |
| US11836365B2 (en) | Automatically adjusting storage system configurations in a storage-as-a-service environment using machine learning techniques | |
| JP5692355B2 (en) | Computer system, control system, control method and control program | |
| CN113377500B (en) | Resource scheduling method, device, equipment and medium | |
| CN115878121A (en) | Terminal code increment compiling method, system, device, server and storage medium | |
| CN111199386A (en) | Workflow engine and implementation method thereof | |
| CN113138772A (en) | Method and device for constructing data processing platform, electronic equipment and storage medium | |
| US20230125503A1 (en) | Coordinated microservices | |
| CN112948206B (en) | Time sequence log management system based on cloud computing and electronic equipment comprising same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190503 |