CN111078354A - Rapid scheduling method in cloud computing field - Google Patents
Rapid scheduling method in cloud computing field Download PDFInfo
- Publication number
- CN111078354A CN111078354A CN201911155793.3A CN201911155793A CN111078354A CN 111078354 A CN111078354 A CN 111078354A CN 201911155793 A CN201911155793 A CN 201911155793A CN 111078354 A CN111078354 A CN 111078354A
- Authority
- CN
- China
- Prior art keywords
- pool
- physical host
- host
- list
- physical
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45562—Creating, deleting, cloning virtual machine instances
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention provides a quick scheduling method in the field of cloud computing, which comprises the following steps: each physical host reports self state information to a physical host monitoring pool in real time, the physical host monitoring pool matches a sub capacity pool for the physical host, and the list of the sub capacity pool sorts and stores the sub capacity pool; the cloud platform receives request information for creating the virtual host and executes a scheduling program; allocating capabilities labels according to the parameter requirements for creating the virtual host; matching one of the sub-capabilites pool according to the requested capabilites label; the matched sub capacity pool returns to the physical host with the highest priority in the list; and taking the physical host with the highest priority returned in the last step as a new virtual host, and ending the program. The invention has the beneficial effects that: the screening, weighting and sorting processes of the physical host are innovatively placed in the spontaneous refreshing of the background period through the data structure of the capabilities pool and the list, and the decoupling is realized with the creation request process of the new virtual host, so that the calculation times and time after the request is received are greatly saved.
Description
Technical Field
The invention relates to the field of cloud computing, in particular to a quick scheduling method in the field of cloud computing.
Background
Cloud Computing (Cloud Computing) is a kind of distributed Computing, and means that a huge data Computing processing program is decomposed into countless small programs through a network "Cloud", and then the small programs are processed and analyzed by a system composed of a plurality of servers to obtain results and are returned to a user.
In the cloud computing process, as more physical hosts are involved, the models and functions of the physical hosts may be different, and the network, the storage and the computing are in a separated state, the selection of a proper physical host is very important when the virtual host for cloud computing is deployed, and meanwhile, the scheduling speed and the user experience are influenced by the scheduling mode of the virtual host for cloud computing, which is more important.
At present, a common scheduling mode in the cloud computing field is a three-layer or two-layer (a two-layer and a two-layer are combined into one layer) mode, each time a virtual host is scheduled to a proper physical host, each of the three layers is screened once to filter out physical hosts which do not meet customer requirements (physical hosts which do not meet conditions are screened out of candidate hosts of the virtual host).
The first layer is capability (i.e. capability set matching), and physical hosts without specific attributes, such as whether storage capability, computing capability, high-performance cpu, etc., are available are removed;
the second layer is a Filter (namely capacity quantity filtering), and filters out physical hosts which do not meet the requirement of the quantity of functional equipment, such as the number of CPU cores, the number of GPU cores, the free size of a memory, the free size of a disk, the IO limit size of a network card and the like;
the third layer is weight (namely weight sorting), physical hosts which pass the screening of the first two layers are sorted according to a preset weight proportion, and finally, only the physical host with the highest weight is selected as the host for deploying the virtual host.
In the current three-layer scheduling mode, screening, filtering and weighting calculation are performed, each layer needs to calculate all candidate items, for example, a capability layer has three capability sets, a Filter layer has 10 Filter filters, a Weighter layer has 10 Weighter devices, and each screened virtual host needs to perform calculation for 3+10+10 times. If 1000 physical hosts are in a cloud platform area, and the last 800 physical hosts in the thousand physical hosts meet the creation requirement of the user virtual host, the last selected host is obtained only through 1000 × 3+1000 × 10+800 × 10 times of calculation when the request for creating the virtual host is scheduled, the calculation time cost is too high, and when the virtual host deployment request enters the cloud platform, the cloud platform starts to classify and screen the physical hosts one by one, and finally, the new virtual host deployment request is too long each time, so that the user experience is poor.
Disclosure of Invention
In view of this, the present invention aims to provide a fast scheduling method in the cloud computing field, which achieves similar effects of screening and weighting calculation in the current three-tier scheduling mode through data structures of a capability pool and a list, and meanwhile innovatively puts the screening, weighting and sorting processes of candidate physical hosts in the spontaneous refreshing of a background period, and uses a storage space to change time, thereby shortening the scheduling time and improving the user experience.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a fast scheduling method in the field of cloud computing comprises the following steps:
s1, each physical host reports self state information to a physical host monitoring pool, the physical host monitoring pool receives the state information, a capability label set (capability label set) is matched with a sub-capability pool containing the physical host state information for the physical host, and the list of the sub-capability pool sorts and stores the sub-capability pool;
s2, the cloud platform receives request information for creating the virtual host and executes a scheduling program;
s3, allocating a capabilitylsilabel to the request according to the parameter requirement of the request information on the virtual host to be created;
s4, sequentially matching a plurality of sub-capability spots in the physical host monitoring pool according to the requested capability spots until the capability spots matched with one sub-capability spot include the requested capability spots;
s5, the matched sub capability pools return to the physical host with the highest priority in the list;
and S6, taking the physical host with the highest priority returned in the step S5 as a new virtual host, and ending the program.
Further, when the state information of each physical host changes, reporting new state information to the physical host monitoring pool in real time, receiving the new state information by the physical host monitoring pool, adjusting the sub-capabilities pool for the physical host according to the new state information of the physical host, and sequencing and storing the physical host by the list of the adjusted sub-capabilities pool.
Further, the cloud platform receives a request for creating the virtual host, and the request information includes all parameter requirements for creating the virtual host.
Further, in the step S3, according to the parameter requirement for creating the virtual host in the request information, the capabilities label allocated to the request is a union of parameter ranges that satisfy the parameter requirements for creating the virtual host.
Further, the sub-capabilities pool has different capabilities labels, which are adjustable.
Further, in the sub-capabilities pool with different capabilities labels, each list represents an ordered set of physical hosts that satisfies the requirement of creating a virtual host.
Further, the actual storage of the capabilities pool data structure is Map or structured storage.
Furthermore, each list in the sub capability pools has different self attributes, the list automatically sorts the physical machines in the list according to the self attributes, and the physical hosts in each list automatically sort according to sorting conditions.
Further, the physical host with the highest priority is the physical host at the topmost layer or the physical host at the bottommost layer of the list according to the list attribute.
Compared with the prior art, the fast scheduling method in the cloud computing field has the following advantages:
according to the rapid scheduling method in the cloud computing field, the storage space is used for changing the time, and the effects similar to those of screening and weighted computing in the prior art are achieved through the data structure of capabilities pool and list. And the state change of the physical host is updated to the capability room data structure in real time, so that the accuracy and timeliness of the information are ensured. When a request for creating the virtual host is received, the capabilities label of the request is matched with the capabilities labels of the sub-capabilities, and the physical host with the highest priority of the matched sub-capabilities is output, so that the calculation times and time after the request is received are greatly saved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic diagram of a fast scheduling method in the cloud computing field according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, a fast scheduling method in the cloud computing field includes the following steps:
s1, each physical host reports self state information to a physical host monitoring pool, the physical host monitoring pool receives the state information, a subpalability pool containing the physical host state information is matched with the physical host, and list of the subpalability pool sorts and stores the subpalability pool;
s2, the cloud platform receives request information for creating the virtual host and executes a scheduling program;
s3, allocating a capabilitylsilabel to the request according to the parameter requirement of the request information on the virtual host to be created;
s4, sequentially matching a plurality of sub-capability spots in the physical host monitoring pool according to the requested capability spots until the capability spots matched with one sub-capability spot include the requested capability spots;
s5, the matched sub capability pools return to the physical host with the highest priority in the list;
and S6, taking the physical host with the highest priority returned in the step S5 as a new virtual host, and ending the program.
When the state information of each physical host changes, reporting new state information to the physical host monitoring pool in real time, receiving the new state information by the physical host monitoring pool, adjusting the sub-capabilities pool for the physical host according to the new state information of the physical host, and sequencing and storing the physical host by the list of the adjusted sub-capabilities pool.
The cloud platform receives a request for creating the virtual host, and the request information comprises all parameter requirements for creating the virtual host.
In step S3, according to the parameter requirement for creating the virtual host in the request information, the capabilities label allocated to the request is a union of parameter ranges that satisfy the parameter requirements for creating the virtual host.
The subpartitities pool has different subpartitities labels, the subpartitities labels are used for segmenting a plurality of attribute values of the physical host, a plurality of attributes are selected from the plurality of attributes, a section is taken from the attribute segmented values, then a union set is taken, and the attribute segmentation and selection of the subpartitities labels can be adjusted.
In the child capabilites pool with different capabilites labels, each list represents an ordered set of a class of physical hosts that meets the requirements for creating a virtual host.
The actual storage of the capabilities pool data structure is Map or structured storage.
The list in each sub capability pool has different self attributes, the list automatically sorts the physical machines in the list according to the self attributes, and the physical host in each list automatically sorts according to the sorting conditions.
And the physical host with the highest priority is the physical host at the topmost layer or the physical host at the bottommost layer of the list according to the list attribute.
When the number of different capabilities labels to be allocated, which are set by a program, is 10, the number of different sub-capabilities pool in the capabilities pool is 20, and the physical host with the highest priority in the list is located at the topmost end, the scheduling process of the scheme is as follows:
s1, each physical host reports self state information to a physical host monitoring pool, the physical host monitoring pool receives the state information, a capability label including the state information of the physical host is matched for the physical host, and the capability of the sub capability labels is sorted and stored in an MAP form;
s2, the cloud platform receives request information for creating the virtual host and executes a scheduling program;
s3, sequentially matching 10 different capabilities labels set by a program according to the parameter requirements of the virtual host to be created in the request information, and finally allocating the capabilities labels (capability label sets) meeting the parameter requirements to the request;
s4, sequentially matching 20 sub-capabilities pool inside the physical host monitoring pool according to the requested capabilities label set until the capabilities label matched to one sub-capability pool contains the requested capabilities label;
s5, the matched sub capability pools return to the top host (the topmost physical host) in the list;
and S5, taking the top host returned in the step S5 as a new virtual host, and ending the program.
The total number of times of calculation in the whole scheduling process is less than or equal to 20 times, and the total number of times of calculation when the request for creating the virtual machine is matched with the capabilities label set is less than or equal to 30 times, which is far less than the total number of times of calculation in the scheduling, screening and weighting processes of the current common scheme, so that the time consumption for creating the virtual machine request can be obviously shortened.
The scheduling method innovatively puts the screening, weighting and sorting processes of the physical host in the spontaneous refreshing of the background period, and realizes the decoupling with the creating request process of a new virtual host, and does not occupy the time of the creating request of the virtual host. And the scheduling of the new virtual host can be quickly matched to the final list only by adding a proper capability label, and the top or bottom candidate physical host of the list is obtained to be used as the final host.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A fast scheduling method in the field of cloud computing is characterized by comprising the following steps:
s1, each physical host reports self state information to a physical host monitoring pool, the physical host monitoring pool receives the state information, a subpalability pool containing the physical host state information is matched with the physical host, and list of the subpalability pool sorts and stores the subpalability pool;
s2, the cloud platform receives request information for creating the virtual host and executes a scheduling program;
s3, allocating a capabilitylsilabel to the request according to the parameter requirement of the request information on the virtual host to be created;
s4, sequentially matching a plurality of sub-capability spots in the physical host monitoring pool according to the requested capability spots until the capability spots matched with one sub-capability spot include the requested capability spots;
s5, the matched sub capability pools return to the physical host with the highest priority in the list;
and S6, taking the physical host with the highest priority returned in the step S5 as a new virtual host, and ending the program.
2. The fast scheduling method in the cloud computing field according to claim 1, wherein: when the state information of each physical host changes, reporting new state information to the physical host monitoring pool in real time, receiving the new state information by the physical host monitoring pool, adjusting the sub-capabilities pool for the physical host according to the new state information of the physical host, and sequencing and storing the physical host by the list of the adjusted sub-capabilities pool.
3. The fast scheduling method in the cloud computing field according to claim 1, wherein: the cloud platform receives a request for creating the virtual host, and the request information comprises all parameter requirements for creating the virtual host.
4. The fast scheduling method in the cloud computing field according to claim 1, wherein: in step S3, according to the parameter requirement for creating the virtual host in the request information, the capabilities label allocated to the request is a union of parameter ranges that satisfy the parameter requirements for creating the virtual host.
5. The fast scheduling method in the cloud computing field according to claim 1, wherein: the subpartitions pool has different subpartitions labels, which are adjustable.
6. The fast scheduling method in the cloud computing field according to claim 5, wherein: in the child capabilites pool with different capabilites labels, each list represents an ordered set of a class of physical hosts that meets the requirements for creating a virtual host.
7. The fast scheduling method in the cloud computing field according to claim 1, wherein: the storage of the capabilities pool data structure is Map or structured storage.
8. The fast scheduling method in the cloud computing field according to claim 1, wherein: the list in each sub capability pool has different self attributes, the list automatically sorts the physical machines in the list according to the self attributes, and the physical host in each list automatically sorts according to the sorting conditions.
9. The fast scheduling method in the cloud computing field according to claim 1, wherein: and the physical host with the highest priority is the physical host at the topmost layer or the physical host at the bottommost layer of the list according to the list attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911155793.3A CN111078354A (en) | 2019-11-22 | 2019-11-22 | Rapid scheduling method in cloud computing field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911155793.3A CN111078354A (en) | 2019-11-22 | 2019-11-22 | Rapid scheduling method in cloud computing field |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111078354A true CN111078354A (en) | 2020-04-28 |
Family
ID=70311721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911155793.3A Pending CN111078354A (en) | 2019-11-22 | 2019-11-22 | Rapid scheduling method in cloud computing field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111078354A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646052A (en) * | 2011-02-16 | 2012-08-22 | 中国移动通信集团公司 | Virtual machine deployment method, device and system |
| CN103577265A (en) * | 2012-07-25 | 2014-02-12 | 田文洪 | Method and device of offline energy-saving dispatching in cloud computing data center |
| CN104008002A (en) * | 2014-06-17 | 2014-08-27 | 电子科技大学 | Target host selection method for deploying virtual machine under cloud platform environment |
| CN104793982A (en) * | 2014-01-20 | 2015-07-22 | 联想(北京)有限公司 | Method and device for establishing virtual machine |
| CN107038064A (en) * | 2017-04-18 | 2017-08-11 | 腾讯科技（深圳）有限公司 | Virtual machine management method and device, storage medium |
| CN108241531A (en) * | 2016-12-23 | 2018-07-03 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus for distributing resource for virtual machine in the cluster |
| US20180239633A1 (en) * | 2016-07-07 | 2018-08-23 | Tencent Technology (Shenzhen) Company Limited | Method, apparatus, and system for creating virtual machine, control device, and storage medium |
| CN109885400A (en) * | 2019-01-18 | 2019-06-14 | 北京百度网讯科技有限公司 | Method and apparatus for sending instruction |
-
2019
- 2019-11-22 CN CN201911155793.3A patent/CN111078354A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646052A (en) * | 2011-02-16 | 2012-08-22 | 中国移动通信集团公司 | Virtual machine deployment method, device and system |
| CN103577265A (en) * | 2012-07-25 | 2014-02-12 | 田文洪 | Method and device of offline energy-saving dispatching in cloud computing data center |
| CN104793982A (en) * | 2014-01-20 | 2015-07-22 | 联想(北京)有限公司 | Method and device for establishing virtual machine |
| CN104008002A (en) * | 2014-06-17 | 2014-08-27 | 电子科技大学 | Target host selection method for deploying virtual machine under cloud platform environment |
| US20180239633A1 (en) * | 2016-07-07 | 2018-08-23 | Tencent Technology (Shenzhen) Company Limited | Method, apparatus, and system for creating virtual machine, control device, and storage medium |
| CN108241531A (en) * | 2016-12-23 | 2018-07-03 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus for distributing resource for virtual machine in the cluster |
| CN107038064A (en) * | 2017-04-18 | 2017-08-11 | 腾讯科技（深圳）有限公司 | Virtual machine management method and device, storage medium |
| CN109885400A (en) * | 2019-01-18 | 2019-06-14 | 北京百度网讯科技有限公司 | Method and apparatus for sending instruction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6803403B2 (en) | Dedicated agent pool allocation method, electronics and computer readable storage media | |
| CN111176852A (en) | Resource allocation method, device, chip and computer readable storage medium | |
| CN110569322A (en) | Address information analysis method, device and system and data acquisition method | |
| CN111045795A (en) | Resource scheduling method and device | |
| CN113110938B (en) | Resource allocation method and device, computer equipment and storage medium | |
| CN102141978A (en) | Method and system for classifying texts | |
| CN110300130B (en) | Resource scheduling method and device, electronic equipment and storage medium | |
| WO2018171412A1 (en) | Pedestrian search method and apparatus | |
| US10977082B2 (en) | Resource allocation optimization support system and resource allocation optimization support method | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN108241531A (en) | A kind of method and apparatus for distributing resource for virtual machine in the cluster | |
| CN111158828A (en) | User interface determining method and device of application program APP and storage medium | |
| CN110347602A (en) | Multitask script execution and device, electronic equipment and readable storage medium storing program for executing | |
| CN109002342B (en) | OpenStack-based method and system for directionally scheduling computing resources | |
| CN107992351B (en) | Hardware resource allocation method and device and electronic equipment | |
| CN110297959A (en) | Date storage method, device, storage medium and Edge Server | |
| CN109582461A (en) | A kind of calculation resource disposition method and system for linux container | |
| CN111078354A (en) | Rapid scheduling method in cloud computing field | |
| CN111599015B (en) | Spatial polygon gridding filling method and device under constraint condition | |
| CN115665157B (en) | Balanced scheduling method and system based on application resource types | |
| JP6991960B2 (en) | Image recognition device, image recognition method and program | |
| CN117170848A (en) | Resource scheduling method and device | |
| CN111158595A (en) | Enterprise-level heterogeneous storage resource scheduling method and system | |
| CN114267440B (en) | Medical order information processing method and device and computer readable storage medium | |
| CN107193650B (en) | Method and device for scheduling display card resources in distributed cluster |
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 |