CN111984416A - Performance improving method and system based on module competition - Google Patents

Performance improving method and system based on module competition Download PDF

Info

Publication number
CN111984416A
CN111984416A CN202010870103.9A CN202010870103A CN111984416A CN 111984416 A CN111984416 A CN 111984416A CN 202010870103 A CN202010870103 A CN 202010870103A CN 111984416 A CN111984416 A CN 111984416A
Authority
CN
China
Prior art keywords
performance
tasks
functional module
module
load balancing
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
Application number
CN202010870103.9A
Other languages
Chinese (zh)
Other versions
CN111984416B (en
Inventor
李泽华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Cable Tv Network Co ltd
Original Assignee
Sichuan Cable Tv Network Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sichuan Cable Tv Network Co ltd filed Critical Sichuan Cable Tv Network Co ltd
Priority to CN202010870103.9A priority Critical patent/CN111984416B/en
Publication of CN111984416A publication Critical patent/CN111984416A/en
Application granted granted Critical
Publication of CN111984416B publication Critical patent/CN111984416B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5044Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering hardware capabilities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/505Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Debugging And Monitoring (AREA)
  • Stored Programmes (AREA)

Abstract

The invention relates to the technical field of data analysis, aims to solve the problem that the performance difference of the existing functional modules has adverse effect on the system performance, and provides a performance improving method and system based on module competition, wherein the technical scheme is summarized as follows: the method comprises the steps that a plurality of functional modules are hung on the same load balancing server, the load balancing server is used for distributing tasks to the functional modules, and the functional modules can achieve the same function and are used for executing the tasks distributed by the load balancing server; acquiring the performance index of each functional module in real time, wherein the performance index is determined according to the function realized by the functional module and the performance required by the task execution; analyzing the residual performance of each functional module according to the performance index, and generating task allocation parameters according to the residual performance of each functional module; and the load balancing server adjusts the task allocation to each functional module according to the task allocation parameters. The invention can improve the overall performance of the system.

Description

Performance improving method and system based on module competition
Technical Field
The invention relates to the technical field of data analysis, in particular to a performance improvement method and system based on module competition.
Background
When the current information system is changed to a modularized and service design, corresponding functional modules are designed according to requirements, and for different requirements, a plurality of functional modules with the same function usually exist on the same server to execute corresponding tasks.
Because the performance of each functional module is different and the task execution capability is different, the prior art cannot track, analyze and evaluate the functional modules in real time, so that the modules with poor performance continue to operate in the system, the modules with good performance do not have the opportunity to participate in the execution of more tasks, and the information system cannot select an optimal functional module, thereby affecting the overall performance improvement of the system.
Disclosure of Invention
The invention aims to solve the problem that the performance difference of the existing functional modules has adverse effect on the system performance, and provides a performance improving method and system based on module competition.
The technical scheme adopted by the invention for solving the technical problems is as follows: the performance improving method based on module competition comprises the following steps:
step 1, hanging a plurality of functional modules on the same load balancing server, wherein the load balancing server is used for distributing tasks to the functional modules, and the functional modules can realize the same function and are used for executing the tasks distributed by the load balancing server;
step 2, acquiring the performance indexes of each functional module in real time, wherein the performance indexes are determined according to the functions realized by the functional modules and the performance required by task execution; analyzing the residual performance of each functional module according to the performance index, and generating task allocation parameters according to the residual performance of each functional module;
and 3, the load balancing server adjusts the task allocation of each functional module according to the task allocation parameters.
Specifically, in step 2, the performance indexes of the functional modules include: memory utilization of each functional module, CPU occupancy rate, hard disk space and/or speed of completing tasks.
Specifically, in step 2, the performance index of each functional module further includes: the proportion of the tasks that have been assigned to the individual functional modules.
Further, the method also comprises the following steps: and the load balancing server does not distribute the tasks to the functional modules of which the proportion of the distributed tasks reaches the preset proportion any more.
Further, the method also comprises the following steps: and counting the total number of tasks completed by each functional module in a preset time period, and if the total number of completed tasks is lower than a preset value, offline and eliminating the corresponding functional module.
In order to solve the problem that the performance difference of the existing functional modules has adverse effect on the system performance, the invention also provides a performance improving system based on module competition, which comprises: the system comprises a plurality of functional modules, a load balancing server and an index analysis unit;
the plurality of functional modules are hung on the same load balancing server, can realize the same function and are used for executing tasks distributed by the load balancing server;
the load balancing server is used for distributing tasks to the plurality of functional modules and adjusting the task distribution to each functional module according to the received task distribution parameters;
the index analysis unit is used for acquiring the performance index of each functional module in real time, and the performance index is determined according to the function realized by the functional module and the performance required by the execution task; and analyzing the residual performance of each functional module according to the performance index, generating task allocation parameters according to the residual performance of each functional module, and sending the task allocation parameters to a load balancing server.
Specifically, the performance indexes of the functional modules include: memory utilization of each functional module, CPU occupancy rate, hard disk space and/or speed of completing tasks.
Specifically, the performance index of each functional module further includes: the proportion of the tasks that have been assigned to the individual functional modules.
Further, the load balancing server is further configured to not allocate the tasks to the functional modules whose allocated task proportion reaches the preset proportion.
Further, the method also comprises the following steps: a counting unit;
the counting unit is used for counting the total number of tasks completed by each functional module in a preset time period, and if the total number of completed tasks is lower than a preset value, the corresponding functional module is offline and eliminated.
The invention has the beneficial effects that: the invention relates to a performance improving method and a system based on module competition, which formulate a specific performance index according to the function and performance requirements of functional modules, hang the modules with competition relation under the same load balancing server together, after initializing task distribution proportion according to a certain proportion, the functional modules report related performance indexes in real time when in operation, carry out comprehensive analysis on the performance indexes reported by the functional modules, and adjust task distribution parameters according to the analysis result, the load balancing server enables the functional modules with good performance to bear more tasks, the functional modules with poor performance bear less tasks, and after operating for a period of time, the functional modules with smaller task bearing proportion are offline, thereby achieving the purposes of automatically evaluating and eliminating laggard modules among the competition modules, and finally achieving the purpose of improving the overall performance of the system.
Drawings
Fig. 1 is a schematic flowchart of a performance improvement method based on module competition according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a performance enhancing system based on module competition according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The invention aims to solve the problem that the performance difference of the existing functional modules has adverse effect on the system performance, and provides a performance improving method and system based on module competition, wherein the technical scheme is summarized as follows: the method comprises the steps that a plurality of functional modules are hung on the same load balancing server, the load balancing server is used for distributing tasks to the functional modules, and the functional modules can achieve the same function and are used for executing the tasks distributed by the load balancing server; acquiring the performance index of each functional module in real time, wherein the performance index is determined according to the function realized by the functional module and the performance required by the task execution; analyzing the residual performance of each functional module according to the performance index, and generating task allocation parameters according to the residual performance of each functional module; and the load balancing server adjusts the task allocation to each functional module according to the task allocation parameters.
It can be understood that a plurality of function modules are hung on the same load balancing server, the load balancing server is used for distributing tasks to each function module, the function modules are used for executing the tasks distributed by the load balancing server, when the system runs, the performance index of each function module is obtained by the index analysis module in real time, the corresponding performance indexes of the function modules with different functions are possibly different, the current residual performance of each function module is analyzed by the obtained performance indexes, the residual performance can be reflected by the resource occupancy rate of the function module when executing the currently distributed tasks, for example, the higher the resource occupancy rate is, the worse the residual performance is, further the task distribution parameters are adjusted, the load balancing server adjusts the task distribution to each function module according to the task distribution parameters, so that the function modules with good performance can bear more tasks, the functional module with poor performance bears less tasks, so that the overall performance of the system is improved.
Examples
The performance improvement method based on module competition, as shown in fig. 1, includes the following steps:
step S1, hanging a plurality of function modules on the same load balancing server, where the load balancing server is configured to distribute tasks to the plurality of function modules, and the plurality of function modules can implement the same function and are configured to execute the tasks distributed by the load balancing server;
specifically, in practical applications, for different functional requirements, the functional modules may be multiple, and the functional modules may include: in this embodiment, a plurality of functional modules can implement the same function, that is, each functional module can execute a task to be allocated by the load balancing server.
Step S2, acquiring the performance index of each functional module in real time, wherein the performance index is determined according to the function realized by the functional module and the performance required by the execution task; analyzing the residual performance of each functional module according to the performance index, and generating task allocation parameters according to the residual performance of each functional module;
specifically, the performance index of each functional module can be obtained in real time through the performance index analysis unit, and in practical application, the performance index may be different according to the function that can be realized by the functional module, so that the performance index can be selected according to the actual requirement.
Wherein, the performance indexes of each functional module comprise: memory utilization of each functional module, CPU occupancy rate, hard disk space and/or speed of completing tasks.
It can be understood that the memory utilization rate, the CPU occupancy rate, the hard disk space and/or the task completion speed of the functional module can reflect the resource occupancy rate of the functional module, for example, if the memory utilization rate and the CPU occupancy rate are high or the remaining space of the hard disk is small, it indicates that the resource occupancy rate of the corresponding functional module is high and the remaining performance is worse. The speed of completing the task refers to the time consumed by the functional module to complete each task, and the longer the time is, the worse the remaining performance of the corresponding functional module is.
For the functional module with poor residual performance, the task allocation corresponding to the functional module with poor residual performance is less in the generated task allocation parameters, and for the functional module with good residual performance, the task allocation corresponding to the functional module with good residual performance is more in the generated task allocation parameters.
Optionally, the performance index in this embodiment further includes: the proportion of tasks that have been allocated.
Specifically, the performance index analysis unit obtains the allocated task proportion of each functional module, if the allocated task proportion is large, the task amount in the task allocation parameter can be properly reduced, and for the functional module of which the allocated task proportion reaches the preset proportion, the load balancing server does not allocate the task to the functional module any more, so that the execution efficiency of the task is improved. The preset proportion may be set according to actual conditions, for example, 20%.
And step S3, the load balancing server adjusts the task allocation to each functional module according to the task allocation parameters.
It can be understood that, before the task allocation is adjusted, the load balancing server allocates tasks in the same proportion to each functional module, and after receiving the task allocation parameters sent by the index analysis unit, adjusts the task allocation proportion, allocates fewer tasks to functional modules with fewer tasks in the task allocation parameters, and allocates more tasks to functional modules with more tasks in the task allocation parameters.
Optionally, the performance improving method based on module competition according to this embodiment further includes: and counting the total number of tasks completed by each functional module in a preset time period, and if the total number of completed tasks is lower than a preset value, offline and eliminating the corresponding functional module.
It can be understood that for the functional module with poor performance, fewer tasks are allocated in the preset time period, and for the functional module with better performance, more tasks are allocated in the preset time period, and when the number of tasks allocated in the preset time period is less than the preset value, it indicates that the performance of the corresponding functional module is too poor, and then the corresponding functional module is offline and eliminated, thereby improving the overall performance of the system. The preset value can be set according to the actual situation of the task.
Based on the above technical solution, an embodiment of the present invention further provides a performance improving system based on module competition, as shown in fig. 2, including: the system comprises a plurality of functional modules, a load balancing server and an index analysis unit;
the plurality of functional modules are hung on the same load balancing server, can realize the same function and are used for executing tasks distributed by the load balancing server;
the load balancing server is used for distributing tasks to the plurality of functional modules and adjusting the task distribution to each functional module according to the received task distribution parameters;
the index analysis unit is used for acquiring the performance index of each functional module in real time, and the performance index is determined according to the function realized by the functional module and the performance required by the execution task; and analyzing the residual performance of each functional module according to the performance index, generating task allocation parameters according to the residual performance of each functional module, and sending the task allocation parameters to a load balancing server.
It can be understood that, because the performance improvement system based on module competition according to the embodiment of the present invention is a system for implementing the performance improvement method based on module competition according to the embodiment, for the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is simpler, and for relevant points, reference may be made to the partial description of the method.

Claims (10)

1. The performance improving method based on module competition is characterized by comprising the following steps:
step 1, hanging a plurality of functional modules on the same load balancing server, wherein the load balancing server is used for distributing tasks to the functional modules, and the functional modules can realize the same function and are used for executing the tasks distributed by the load balancing server;
step 2, acquiring the performance indexes of each functional module in real time, wherein the performance indexes are determined according to the functions realized by the functional modules and the performance required by task execution; analyzing the residual performance of each functional module according to the performance index, and generating task allocation parameters according to the residual performance of each functional module;
and 3, the load balancing server adjusts the task allocation of each functional module according to the task allocation parameters.
2. The method according to claim 1, wherein in step 2, the performance index of each functional module includes: memory utilization of each functional module, CPU occupancy rate, hard disk space and/or speed of completing tasks.
3. The method according to claim 2, wherein in step 2, the performance index of each functional module further includes: the proportion of the tasks that have been assigned to the individual functional modules.
4. The method for module contention based performance improvement according to claim 3, further comprising: and the load balancing server does not distribute the tasks to the functional modules of which the proportion of the distributed tasks reaches the preset proportion any more.
5. The method for improving performance based on module competition according to any one of claims 1 to 4, further comprising: and counting the total number of tasks completed by each functional module in a preset time period, and if the total number of completed tasks is lower than a preset value, offline and eliminating the corresponding functional module.
6. A performance enhancement system based on module competition, comprising: the system comprises a plurality of functional modules, a load balancing server and an index analysis unit;
the plurality of functional modules are hung on the same load balancing server, can realize the same function and are used for executing tasks distributed by the load balancing server;
the load balancing server is used for distributing tasks to the plurality of functional modules and adjusting the task distribution to each functional module according to the received task distribution parameters;
the index analysis unit is used for acquiring the performance index of each functional module in real time, and the performance index is determined according to the function realized by the functional module and the performance required by the execution task; and analyzing the residual performance of each functional module according to the performance index, generating task allocation parameters according to the residual performance of each functional module, and sending the task allocation parameters to a load balancing server.
7. The module competition based performance enhancing system of claim 6, wherein the performance indicators of the respective functional modules comprise: memory utilization of each functional module, CPU occupancy rate, hard disk space and/or speed of completing tasks.
8. The module competition based performance enhancing system of claim 7, wherein the performance indicators of the respective functional modules further comprise: the proportion of the tasks that have been assigned to the individual functional modules.
9. The module competition based performance improvement system according to claim 8, wherein the load balancing server is further configured to not allocate tasks to the functional modules whose proportion of the allocated tasks reaches the preset proportion.
10. The module contention-based performance enhancing system according to any one of claims 6 to 9, further comprising: a counting unit;
the counting unit is used for counting the total number of tasks completed by each functional module in a preset time period, and if the total number of completed tasks is lower than a preset value, the corresponding functional module is offline and eliminated.
CN202010870103.9A 2020-08-26 2020-08-26 Performance improvement method and system based on module competition Active CN111984416B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010870103.9A CN111984416B (en) 2020-08-26 2020-08-26 Performance improvement method and system based on module competition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010870103.9A CN111984416B (en) 2020-08-26 2020-08-26 Performance improvement method and system based on module competition

Publications (2)

Publication Number Publication Date
CN111984416A true CN111984416A (en) 2020-11-24
CN111984416B CN111984416B (en) 2024-04-19

Family

ID=73439624

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010870103.9A Active CN111984416B (en) 2020-08-26 2020-08-26 Performance improvement method and system based on module competition

Country Status (1)

Country Link
CN (1) CN111984416B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1243611A (en) * 1997-02-07 2000-02-02 西门子公司 Load balancing of several independently working modules of power supply installation
US20060233106A1 (en) * 2005-04-14 2006-10-19 Microsoft Corporation Stateless, affinity-preserving load balancing
JP2009087223A (en) * 2007-10-02 2009-04-23 Fujitsu Ltd Module having function of adjusting processing performance, method of adjusting processing performance, and program for adjusting processing performance
CN105760998A (en) * 2016-02-16 2016-07-13 国电南瑞科技股份有限公司 Frequency modulation resource calling optimization decision system introducing competition mechanism and method thereof
CN109902901A (en) * 2017-12-11 2019-06-18 广东智动力知识产权运营有限公司 Method for allocating tasks, device, storage medium and computer equipment
CN110995802A (en) * 2019-11-22 2020-04-10 北京奇艺世纪科技有限公司 Task processing method and device, storage medium and electronic device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1243611A (en) * 1997-02-07 2000-02-02 西门子公司 Load balancing of several independently working modules of power supply installation
US20060233106A1 (en) * 2005-04-14 2006-10-19 Microsoft Corporation Stateless, affinity-preserving load balancing
JP2009087223A (en) * 2007-10-02 2009-04-23 Fujitsu Ltd Module having function of adjusting processing performance, method of adjusting processing performance, and program for adjusting processing performance
CN105760998A (en) * 2016-02-16 2016-07-13 国电南瑞科技股份有限公司 Frequency modulation resource calling optimization decision system introducing competition mechanism and method thereof
CN109902901A (en) * 2017-12-11 2019-06-18 广东智动力知识产权运营有限公司 Method for allocating tasks, device, storage medium and computer equipment
CN110995802A (en) * 2019-11-22 2020-04-10 北京奇艺世纪科技有限公司 Task processing method and device, storage medium and electronic device

Also Published As

Publication number Publication date
CN111984416B (en) 2024-04-19

Similar Documents

Publication Publication Date Title
CN111176852A (en) Resource allocation method, device, chip and computer readable storage medium
CN103401947A (en) Method and device for allocating tasks to multiple servers
CN104796422A (en) Online customer service staff equilibrium assignment method and online customer service staff equilibrium assignment device
CN104243405A (en) Request processing method, device and system
CN104239154B (en) Job scheduling method and job scheduler in a kind of Hadoop clusters
CN110830964B (en) Information scheduling method, internet of things platform and computer readable storage medium
CN108874623A (en) Distributed type assemblies method for monitoring performance, device, equipment, system and storage medium
CN110210789A (en) Resource distribution dispatching method, the device, equipment of power grid test business
CN103763740A (en) Method and device for balancing loads of single boards
CN103455375B (en) Load-monitoring-based hybrid scheduling method under Hadoop cloud platform
CN103902384A (en) Method and device for allocating physical machines for virtual machines
CN105791166B (en) A kind of method and system of load balancing distribution
CN114244718A (en) Power transmission line communication network equipment management system
CN104702664B (en) Method and system for controlling task server
CN106775975B (en) Process scheduling method and device
CN116471277A (en) Computing power distribution method, computing power distribution device, server and computer readable storage medium
CN117573373B (en) CPU virtualization scheduling method and system based on cloud computing
CN110879753B (en) GPU acceleration performance optimization method and system based on automatic cluster resource management
CN111984416B (en) Performance improvement method and system based on module competition
CN105468455A (en) Dynamic task distribution method and apparatus for multiple devices
CN114257515A (en) Bandwidth secondary scheduling method and device
CN109918577B (en) Monitoring method and device for social software
CN107870815B (en) Task scheduling method and system of distributed system
CN110795251A (en) Method and equipment for determining terminal operation parameters
CN110995863A (en) Data center load distribution method and system based on load demand characteristics

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
CB02 Change of applicant information
CB02 Change of applicant information

Country or region after: China

Address after: No. 19/20, 1st Floor, Unit 3, Building 1, Section 2, Huayang Avenue, Huayang Town, Tianfu New District, Chengdu City, Sichuan Province, 610000

Applicant after: China Radio and television Sichuan Network Co.,Ltd.

Address before: Floor 19 / 20, unit 3, building 1, Section 2, Huayang Avenue, Huayang Town, Tianfu New District, Chengdu, Sichuan 610000

Applicant before: SICHUAN CABLE TV NETWORK CO.,LTD.

Country or region before: China

GR01 Patent grant
GR01 Patent grant