CN106302809A - A kind of server performance optimization method and system - Google Patents
A kind of server performance optimization method and system Download PDFInfo
- Publication number
- CN106302809A CN106302809A CN201610832867.2A CN201610832867A CN106302809A CN 106302809 A CN106302809 A CN 106302809A CN 201610832867 A CN201610832867 A CN 201610832867A CN 106302809 A CN106302809 A CN 106302809A
- Authority
- CN
- China
- Prior art keywords
- request
- access request
- server
- user
- queue
- 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- Withdrawn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
Classifications
-
- 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
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- 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
- H04L67/56—Provisioning of proxy services
- H04L67/566—Grouping or aggregating service requests, e.g. for unified processing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention relates to a kind of server performance optimization method and system.The method includes the access request receiving user；Judge that the user sources proposing access request is same user or different user；If same user, then this access request is joined the default tail of the queue being used for optimizing the level queue of the government image that server request processes resource, form request video sequence, by server, the access request in request video sequence is pressed the sequential processing from tail of the queue to head of the queue afterwards；If different user, then this access request is joined the tail of the queue of the vertical alignment of described government image, form request vertical series, then by server process.When the present invention makes Internet Server process access request by user sources, classification is carried out, thus the performance of Internet Server is optimised control.
Description
Technical field
The invention belongs to Internet Server technical field, be specifically related to a kind of server performance optimization method and system.
Background technology
Along with the rise of the Internet, carry out data interaction by Internet Server and had become as a universal business
Demand, the user of the Internet also there will be multiformity, randomness and uncontrollability.The life of people has been come in various websites
Living, people browse different websites by various terminal units, and operate these websites and ask, and these please
Ask and include login, predetermined, purchase etc..
These requests, when receiving the request that user sends, can be processed by website, when website within a short period of time
When receiving substantial amounts of request, the quantity of request exceedes the treating capacity of website, and website there will be stopping and processing, process chaotic, place
The problems such as reason speed slows down, thus the user sending request is caused unnecessary impact.Therefore, for an Internet service
For device, take appropriate measures, optimize user and access, improve server resource and utilize, have very important meaning.
Summary of the invention
It is an object of the invention to solve above-mentioned technical problem and a kind of server performance optimization method and system be provided,
It can make server access based on network interface access request effectively be managed and control, simultaneously can also be to service
The surplus resources of device makes the assessment that can quantify.
For achieving the above object, the present invention adopts the following technical scheme that
A kind of server performance optimization method, comprises the following steps:
Receive the access request of user；
Judge that the user sources proposing access request is same user or different user；
If same user, then this access request is joined the default two dimension being used for optimizing server request process resource
The tail of the queue of the level queue of matrix model, forms request video sequence, afterwards by server to the access in request video sequence
Request is by from the sequential processing of tail of the queue to head of the queue；
If different user, then this access request is joined the tail of the queue of the vertical alignment of described government image, formed
Request vertical series, then by server process.
The present invention also aims to provide a kind of server performance to optimize system, including:
User asks receiver module, for receiving the access request of user；
User sources judge module, asks receiver module to be connected with described user, for judging that the user proposing access request comes
Source is same user or different user；
Video sequence sequence processing module, is connected with described user sources judge module, for this access request being joined
The tail of the queue of the level queue of the government image for optimizing server request process resource preset, is formed and asks horizontal sequence
Row, are then pressed from tail of the queue to the sequential processing of head of the queue the access request in request video sequence by server；
Vertical series sequence processing module, is connected with described user sources judge module, joins for sending out access request
The tail of the queue of the vertical alignment of described government image, forms request vertical series, is then processed by server.
The access request of different user, by judging the source of user, is divided by the present invention by the government image preset
It is not managed, and the order from tail of the queue to head of the queue is pressed in the connected reference request to the same user in request video sequence,
The principle sequential processing successively i.e. first processed by first access request post processing, rear access request, so that Internet Server
When processing the access request of substantial amounts of user, can classify and carry out, thus the performance of Internet Server is able to significantly
Lifting.
Accompanying drawing explanation
Fig. 1 illustrates the schematic flow sheet of the server performance optimization method of the present invention；
Fig. 2 illustrates the schematic diagram utilizing government image to request sequence；
Fig. 3 illustrates the schematic diagram of the server performance that government image represents；
Fig. 4 illustrates the structural representation of the server performance optimization system of the present invention.
Detailed description of the invention
Below, in conjunction with example, substantive distinguishing features and the advantage of the present invention are further described, but the present invention not office
It is limited to listed embodiment.
See shown in Fig. 1-3, a kind of server performance optimization method, comprise the following steps:
Receive the access request of user；
Judge that the user sources proposing access request is same user or different user；
If same user, then this access request is joined the default two dimension being used for optimizing server request process resource
The tail of the queue of the level queue of matrix model 10, forms request video sequence, afterwards by server to the visit in request video sequence
The request of asking is by the sequential processing from tail of the queue to head of the queue；
If different user, then this access request is joined the tail of the queue of the vertical alignment of described government image 10, shape
Become request vertical series, then by server process.
In the present invention, described default government image 10 refers to shown in Fig. 2-3, and it is one can represent server
The matrix of overall static capabilities quantized values N, each unit in matrix represents the process user that of server is available
The resource of access request；This matrix, for the access request of same user, is listed the horizontal dimensions management of two-dimensional matrix in, is added
Level queue, such as multiple requests of same user, including asking 1, request 2, request 3, request 4 list the level teams of horizontal dimensions in
In row, then first entered, by message, the order gone out afterwards by server and process, make message be performed, and for different users'
Concurrent access request, then by server process in the vertical alignment of the vertical dimensions adding two-dimensional matrix, the access of user please
After asking addition level queue and vertical alignment, two-dimensional matrix formed as it is shown on figure 3, in have the space of numeral 1,2,3 to be formed number
Territory, block 13 is expressed as the dynamic resource of server and uses quantized values U, and the nil region 12 that numeric area 13 is surrounded represents
Server free resource quantized values F, whole region 11 representative server static capabilities quantized values N of this two-dimensional matrix, this
Sample can be with the dynamic resource utilization rate (U/N) of statistical server, resource idleness (F/N) by this government image preset
And server redundancy resource utilization (N-F)/N.
In the present invention, the access request initially accessed of the same user that described in described request video sequence, head of the queue refers to,
The access request of the up-to-date access of the same user that described tail of the queue refers to.
The described access request to asking in video sequence is by from the sequential processing of tail of the queue to head of the queue, the access the most first accessed
Request post processing, the request of up-to-date access first processes.
It should be noted that in the present invention, described request video sequence is corresponding to the connection of the access request of same user
Efficiency, the vertical sequence of described request is corresponding to the concurrent joint efficiency of the concurrent access request of different user, and the present invention is by interconnection
Network users the joint efficiency of access request be separately managed with concurrent efficiency, Internet service can be promoted significantly
The performance of device, improves the response speed of server.
The access request of different user, by judging the source of user, is divided by the present invention by the government image preset
It is not managed, and the order from tail of the queue to head of the queue is pressed in the connected reference request to the same user in request video sequence,
The principle sequential processing successively i.e. first processed by first access request post processing, rear access request, so that Internet Server
When processing the access request of substantial amounts of user, can classify and carry out, thus the performance of Internet Server is able to significantly
Lifting.
Improve as one, in order to further promote the performance of server, an access request is being added described asking
After asking in video sequence, further comprising the steps of:
Judge whether the access request in described request video sequence reaches very first time threshold value；
If reaching very first time threshold value, then delete the access request wherein reaching very first time threshold value.
Implementing, described very first time threshold value can be 1 second.The visit of sequence in judging described request video sequence
The request of asking i.e. deletes this access request after reaching 1 second.
By judging whether the access request in request video sequence reaches very first time threshold value, and reaching the very first time
During threshold value, delete this access request reaching very first time threshold value so that data are by timing effectively management, so that request water
Access request in flat sequence is maintained a stable quantitative value, such that it is able to it is nearer to make server effectively process
Access request rather than simultaneously process multiple access request of same user, the even visit farther out before a very long time
Ask request, thus significantly reduce the access request processing pressure of server so that server can process more quickly
The access request of effect, alleviates the expense of server, thus also improves response speed and the performance of server.
Improve as one, in order to promote the performance of server further, an access request is being added described request
After in vertical series, further comprising the steps of:
Judge whether the concurrent access request in this request vertical series reaches the second time threshold；
If it is, delete the access request reaching very first time threshold value in this request vertical series.
Implementing, described second time threshold can be 1 second.In judging request vertical series, the access of sequence please
Ask and after reaching 1 second, i.e. delete this access request.
By judging whether the access request in request vertical series reaches very first time threshold value, and reaching for the second time
During threshold value, delete this access request reaching the second time threshold so that data are by timing effectively management, so that request is hung down
Access request in direct-sequence row is maintained a stable quantitative value, such that it is able to make server manage limit of power at which
The most effectively process concurrent access request, without the concurrent request processing ability beyond server, thus significantly reduce
The concurrent access request processing pressure of server so that server can process effective concurrent access request more quickly, from
And also improve response speed and the performance of server.
It should be noted that the present invention is by the optimal control in above-mentioned server process access request so that server
When the access request outside processing, it is all the time in its limit of power, without beyond its limit of power, thus can also be real
Existing server total data ability, the calculating of performance parameter also quantify.
Shown in Figure 4, the present invention also aims to provide a kind of server performance Optimal Control System, including:
User asks receiver module, for receiving the access request of user；
User sources judge module, asks receiver module to be connected with described user, for judging that the user proposing access request comes
Source is same user or different user；
Video sequence sequence processing module, is connected with described user sources judge module, for this access request being joined
The tail of the queue of the level queue of the government image for optimizing server request process resource preset, is formed and asks horizontal sequence
Row, are then pressed from tail of the queue to the sequential processing of head of the queue the access request in request video sequence by server；
Vertical series sequence processing module, is connected with described user sources judge module, joins for sending out access request
The tail of the queue of the vertical alignment of described government image, forms request vertical series, is then processed by server.
In the present invention, described default government image 10 refers to shown in Fig. 2-3, and it is one can represent server
The matrix of static capabilities quantized values N, each unit in matrix represents the process access request that of server is available
Resource；For the access request of same user, list the horizontal dimensions management of two-dimensional matrix in, add level queue, as same
Multiple requests of user, including asking 1, request 2, request 3, request 4 list in the level queue of horizontal dimensions, then by servicing
Device is first entered the order gone out afterwards and processes by message, makes message be performed, and for the concurrent access request of different users,
By server process in the vertical alignment of the vertical dimensions then adding two-dimensional matrix, the request of user adds level queue with vertical
After queue, two-dimensional matrix formed as it is shown on figure 3, in have numeral 1,2,3 space formed numeric area 13 be expressed as server
Dynamic resource use quantized values U, the nil region 12 representative server idling-resource that numeric area 13 is surrounded quantifies number
Value F, whole region 11 representative server static capabilities quantized values N of this two-dimensional matrix, the Two-Dimensional Moment so preset by this
Battle array model can be with the dynamic resource utilization rate (U/N) of statistical server, resource idleness (F/N) and server redundancy resource utilization
(N-F)/N.
In the present invention, the access request initially accessed of the same user that described in described request video sequence, head of the queue refers to,
The access request of the up-to-date access of the same user that described tail of the queue refers to.
Described presses from tail of the queue to the sequential processing of head of the queue, the visit the most first accessed the access request in request video sequence
Ask that request post processing, the request of up-to-date access first process.
It should be noted that in the present invention, described request video sequence corresponding to same user the company of access request
Connecing efficiency, the vertical sequence of described request is corresponding to the concurrent joint efficiency of the concurrent access request of different user, and the present invention is by mutually
On-line customer the joint efficiency of access request be separately managed with concurrent efficiency, the Internet clothes can be promoted significantly
The performance of business device, improves the response speed of server,
The access request of different user, by judging the source of user, is managed by the present invention respectively, and to asking horizontal sequence
The connected reference request of the same user in row by by from tail of the queue to the order of head of the queue, i.e. by first access request post processing, visit afterwards
The principle sequential processing successively that the request of asking first processes, so that Internet Server is in the access request processing substantial amounts of user
Time, can classify and carry out, thus the performance of Internet Server is significantly promoted.
Improving as one, in order to further promote the performance of server, described system also includes:
Video sequence TIMEOUT removing module, is connected with described video sequence sequence processing module, is used for judging to ask water
When access request in flat sequence reaches very first time threshold value, delete this access request reaching very first time threshold value.
Implementing, described very first time threshold value can be 1 second.In judging request video sequence, the access of sequence please
Ask and after reaching 1 second, i.e. delete this access request.
Judge to ask whether the access request in video sequence reaches first by video sequence TIMEOUT removing module
Time threshold, and when reaching very first time threshold value, delete this access request reaching very first time threshold value so that data are by fixed
Shi Youxiao manages, so that the access request in request video sequence is maintained a stable quantitative value, such that it is able to
Server is made effectively to process nearer access request rather than process multiple access request of same user, even simultaneously
Access request farther out before a very long time, thus significantly reduce the access request processing pressure of server so that
Server can process effective access request more quickly, alleviates the expense of server, thus also improves server
Response speed and performance.
Improving as one, in order to promote the performance of server further, described system may further comprise:
Vertical series TIMEOUT removing module, is connected with described vertical series sequence processing module, for asking in judgement
When asking the concurrent access request in vertical series to reach the second time threshold, delete in this request vertical series and reach the very first time
The access request of threshold value.
Implementing, described second time threshold can be 1 second.In judging request vertical series, the access of sequence please
Ask and after reaching 1 second, i.e. delete this access request.
Judge to ask whether the access request in vertical series reaches first by vertical series TIMEOUT removing module
Time threshold, and when reaching the second time threshold, delete this access request reaching the second time threshold so that data are by fixed
Shi Youxiao manages, so that the access request in request vertical series is maintained a stable quantitative value, such that it is able to
Server is made effectively to process concurrent access request, at beyond the concurrent request of server in managing limit of power at which
Reason ability, thus significantly reduce the concurrent access request processing pressure of server so that server can more rapid be located in
The effective concurrent access request of reason, thus also improve response speed and the performance of server.
It should be noted that the present invention is by the optimal control in above-mentioned server process access request so that server
When the access request outside processing, it is all the time in its limit of power, without beyond its limit of power, thus can also be real
Existing server total data ability, the calculating of performance parameter also quantify.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvements and modifications, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
1. a server performance optimization method, it is characterised in that comprise the following steps:
Receive the access request of user；
Judge that the user sources proposing access request is same user or different user；
If same user, then this access request is joined the default two dimension being used for optimizing server request process resource
The tail of the queue of the level queue of matrix model, forms request video sequence, afterwards by server to the access in request video sequence
Request is by from the sequential processing of tail of the queue to head of the queue；
If different user, then this access request is joined the tail of the queue of the vertical alignment of described government image, formed
Request vertical series, then by server process.
Server performance optimization method the most according to claim 1, it is characterised in that described an access request is added
After in request video sequence, further comprising the steps of:
Judge whether the access request in described request video sequence reaches very first time threshold value；
If reaching very first time threshold value, then delete the access request reaching very first time threshold value in this request video sequence.
Server performance optimization method the most according to claim 2, it is characterised in that described very first time threshold value is 1 second.
4. according to server performance optimization method described in claim 1 or 3, it is characterised in that an access request is being added
After in described request vertical series, further comprising the steps of:
Judge whether the concurrent access request in this request vertical series reaches the second time threshold；
If it is, delete the access request reaching very first time threshold value in this request vertical series.
Server performance optimization method the most according to claim 4, it is characterised in that described second time threshold is 1 second.
6. a server performance optimizes system, it is characterised in that including:
User asks receiver module, for receiving the access request of user；
User sources judge module, asks receiver module to be connected with described user, for judging that the user proposing access request comes
Source is same user or different user；
Video sequence sequence processing module, is connected with described user sources judge module, for this access request being joined
The tail of the queue of the level queue of the government image for optimizing server request process resource preset, is formed and asks horizontal sequence
Row, are then pressed from tail of the queue to the sequential processing of head of the queue the access request in request video sequence by server；
Vertical series sequence processing module, is connected with described user sources judge module, joins for sending out access request
The tail of the queue of the vertical alignment of described government image, forms request vertical series, is then processed by server.
The most according to claim 6, server performance optimizes system, it is characterised in that including:
Video sequence request timed out removing module, is connected with described video sequence sequence processing module, is used for judging described asking
After asking the access request in video sequence whether to reach very first time threshold value, delete in this request video sequence and reach the very first time
The access request of threshold value.
The most according to claim 7, server performance optimizes system, it is characterised in that described very first time threshold value is 1 second.
9. optimize system according to server performance described in claim 6 or 8, it is characterised in that including:
Vertical series request timed out removing module, is connected with described vertical series sequence processing module, for asking in judgement
After asking the concurrent access request in vertical series to reach the second time threshold, delete in this request vertical series and reach the very first time
The access request of threshold value.
The most according to claim 9, server performance optimizes system, it is characterised in that described second time threshold is 1 second.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610832867.2A CN106302809A (en) | 2016-09-20 | 2016-09-20 | A kind of server performance optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610832867.2A CN106302809A (en) | 2016-09-20 | 2016-09-20 | A kind of server performance optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106302809A true CN106302809A (en) | 2017-01-04 |
Family
ID=57711622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610832867.2A Withdrawn CN106302809A (en) | 2016-09-20 | 2016-09-20 | A kind of server performance optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106302809A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117742923A (en) * | 2023-12-26 | 2024-03-22 | 上海数禾信息科技有限公司 | Distributed concurrency request control method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6732242B2 (en) * | 2002-03-28 | 2004-05-04 | Intel Corporation | External bus transaction scheduling system |
| CN101741802A (en) * | 2009-12-24 | 2010-06-16 | 中国科学院计算技术研究所 | Data mapping method for OFDMA system base station |
| CN103118076A (en) * | 2013-01-11 | 2013-05-22 | 烽火通信科技股份有限公司 | Upgraded server cluster system and load balancing method thereof |
| CN103516536A (en) * | 2012-06-26 | 2014-01-15 | 重庆新媒农信科技有限公司 | Server service request parallel processing method based on thread number limit and system thereof |
-
2016
- 2016-09-20 CN CN201610832867.2A patent/CN106302809A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6732242B2 (en) * | 2002-03-28 | 2004-05-04 | Intel Corporation | External bus transaction scheduling system |
| CN101741802A (en) * | 2009-12-24 | 2010-06-16 | 中国科学院计算技术研究所 | Data mapping method for OFDMA system base station |
| CN103516536A (en) * | 2012-06-26 | 2014-01-15 | 重庆新媒农信科技有限公司 | Server service request parallel processing method based on thread number limit and system thereof |
| CN103118076A (en) * | 2013-01-11 | 2013-05-22 | 烽火通信科技股份有限公司 | Upgraded server cluster system and load balancing method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117742923A (en) * | 2023-12-26 | 2024-03-22 | 上海数禾信息科技有限公司 | Distributed concurrency request control method, device, equipment and medium |
| CN117742923B (en) * | 2023-12-26 | 2024-09-13 | 上海数禾信息科技有限公司 | Distributed concurrency request control method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021244211A1 (en) | Blockchain message processing method and apparatus, computer and readable storage medium | |
| WO2019085405A1 (en) | Customer service staff session allocation method, electronic device， and computer-readable storage medium | |
| CN101917490B (en) | Method and system for reading cache data | |
| CN104243481B (en) | A kind of method and system of power information acquisition advance data processing | |
| US10706062B2 (en) | Method and system for exchanging data from a big data source to a big data target corresponding to components of the big data source | |
| Ogden et al. | {MODI}: Mobile deep inference made efficient by edge computing | |
| CN111898023A (en) | Message pushing method and device, readable storage medium and computing equipment | |
| CN111813573B (en) | Communication method of management platform and robot software and related equipment thereof | |
| CN106815254A (en) | A kind of data processing method and device | |
| US20220383198A1 (en) | Method for asynchronous federated learning, method for predicting business service, apparatus, and system | |
| CN109462631A (en) | Data processing method, device, storage medium and electronic device | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN110830384A (en) | Method, device and system for limiting service flow | |
| CN106126352A (en) | The asynchronous method and device reporting and submitting information | |
| CN107295067A (en) | Across the method and apparatus of screen identification user | |
| CN205540723U (en) | Information retrieval system based on cloud calculates | |
| CN105808518A (en) | Data form filling system based on browser plug-in and integrating method thereof | |
| US20170272538A1 (en) | Service Provision | |
| CN106302809A (en) | A kind of server performance optimization method and system | |
| CN105389748A (en) | Public service system | |
| US20160086211A1 (en) | System and method for real-time, rules-based social media amplification | |
| CN103916368A (en) | Method and apparatus for realizing data processing among different data sources | |
| CN102902593A (en) | Protocol distribution processing system based on cache mechanism | |
| CN104063461B (en) | Handle the method and system that user accesses the request of webpage | |
| CN115168767A (en) | Voucher uploading method, device, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20170104 |