CN105979532A - Performance-capacity analysis early warning method and device for service processing system - Google Patents
Performance-capacity analysis early warning method and device for service processing system Download PDFInfo
- Publication number
- CN105979532A CN105979532A CN201610232819.XA CN201610232819A CN105979532A CN 105979532 A CN105979532 A CN 105979532A CN 201610232819 A CN201610232819 A CN 201610232819A CN 105979532 A CN105979532 A CN 105979532A
- Authority
- CN
- China
- Prior art keywords
- performance
- business
- main frame
- data
- business main
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a performance-capacity analysis early warning method and device for a service processing system. The performance-capacity analysis early warning method comprises the steps of acquiring multiple items of service index data of each service and processing performance index data of at least one service host of the service by taking the service as a unit; calculating an operation index and a capability index of the service host according to the service index data and the performance index data; calculating the variation trend of each item of service index data of the service according to each service index of the service; calculating a capability index predictive value of the at least one service host in N predetermined periods in the future by being combined with a prediction model according to the capability index, the variation trend of each item of service index data and a weight ratio of each service index; acquiring a performance state of the service host in the N predetermined periods in the future according to the capability index predictive value; and calculating the configuration amount required to be increased or decreased in the N predetermined periods in the future according to the performance state.
Description
Technical field
The present invention relates to performance capability analysis technical field, be specifically related to the performance of a kind of transaction processing system
Volumetric analysis method for early warning and device.
Background technology
Mobile communication business processing system is the properly functioning basic guarantee of mobile service and support, is guaranteeing
While the accuracy of transaction processing system and reliability, the how support of enterprise transaction processing system
Usefulness, and realize the high return-on-investment of transaction processing system, it is achieved the reasonable disposition of resource, the most gradually
Become current mobile operator relevant departments focus of attention.
The place capacity main puzzlement that faces of planning in mobile communication business processing system and challenge:
Along with the increase of the business datum amount of each business, can current operation system meet future
Demand, within following a period of time, if need dilatation, along with the variation tendency of business datum amount, industry
Business system needs to increase to configure and still reduces configuration, and needs how many how many configuration of increase or minimizings join
Put？Whether existing capacity bottleneck point there is also？There is also some potential appearances in the middle of operation system
How amount performance bottleneck problem, find.
The subject matter that mobile subscriber exists at operation system place capacity management aspect at present:
(1) lack to the forecast analysis of business future development (type of service, business function, customer volume,
Performance requirement etc.).
(2) lack capacity management role, and its flow document, regulation and standardization is clear
Clear understanding.
(3) lack the analysis causing operation system capacity problem root.
(4) lack collection substantial amounts of, performance data accurately and accumulation.
In a word, owing to lacking the relation analysis instrument of effective business and equipment performance, in the face of magnanimity
Service feature data, data analysis based on traditional database (such as oracle), performance is slow, efficiency
Low, it is impossible to both forecast analysis development trend in the future, cause that the problems referred to above occur.
Summary of the invention
The technical problem to be solved is to provide the performance capability of a kind of transaction processing system
Analysis and early warning method and device, it is possible to the performance of transaction processing system is carried out early warning analysis.
The technical scheme is that
On the one hand, the invention provides a kind of performance capability analysis and early warning method of transaction processing system, institute
State transaction processing system and include multiple business main frame, it is characterised in that including:
S1, in units of business, gather in the scheduled time the multinomial operational indicator data of each business with
And process the performance indications data of at least one business main frame of this business；
S2a, use big Data Analysis Platform, the data of the multiple business gathered carried out parallel computation,
Performance indications data according at least one business main frame described and operation Index for Calculation model, calculate
Operation index at least one business main frame described；And according to described operation index and Capability index meter
Calculate model and be calculated the Capability index of this at least one business main frame；
S2b, according to the multinomial operational indicator data of each business gathered in the scheduled time, calculate
The data volume of each operational indicator data of this business variation tendency in each predetermined period, its
Including growth trend or minimizing trend；
S3, the Capability index according at least one business main frame described, each operational indicator of this business
The variation tendency of the data volume of data and the weight ratio of each operational indicator data of this business, in conjunction with
Forecast model, calculates the Capability index of this at least one business main frame in following N number of predetermined period
Predictive value；
S4, by the Capability index predictive value of at least one business main frame described and each performance state indicator threshold value
Contrast, according to comparing result, show that this at least one business main frame is in following N number of predetermined period
Performance state；
S5, the performance state of this at least one business main frame according to prediction, calculate this at least one industry
Business main frame needs the capacity configuration amount increased in following N number of predetermined period or needs the capacity reduced
Configuration amount.
On the other hand, the invention provides the performance capability analysis and early warning device of a kind of transaction processing system,
Including data acquisition server and big Data Analysis Platform；
Described data acquisition server includes:
Described acquisition module, in units of business, gathers the multinomial of the scheduled time each business interior
Operational indicator data and process the performance indications data of at least one business main frame of this business；
Sending module, for being sent to big Data Analysis Platform by the data of collection；
Described big Data Analysis Platform includes that receiver module, data divide module and multiple data process mould
Block；
Receiver module, for receiving the collection data that described data acquisition module sends；
Data divide module, for the collection data received are divided into multiple data block, each number
According to block at least includes the data that a business is corresponding；
Each data processing module includes:
Run Index for Calculation module, for according to the performance indications data of at least one business main frame described with
And run Index for Calculation model, it is calculated the operation index of at least one business main frame described；
Capability index computing module, for calculating according to described operation index and Capability index computation model
Capability index to this at least one business main frame；
Variation tendency computing module, for the multinomial operational indicator number according to the business gathered in the scheduled time
According to, calculate the change in each predetermined period of the data volume of each operational indicator data of this business
Change trend, it includes growth trend or minimizing trend；
Predictor calculation module, for the Capability index according at least one business main frame described, this business
The variation tendency of data volume of each operational indicator data and each operational indicator of this business
The weight ratio of data, in conjunction with forecast model, calculate in following N number of predetermined period this at least one
The predictive value of the Capability index of business main frame；
Performance state obtains module, for the predictive value by the Capability index of at least one business main frame described
Compare with each performance state indicator threshold value, according to comparative result, draw this at least one business main frame
Performance state in following N number of predetermined period；
Configuration computing module, for the performance state of this at least one the business main frame according to prediction, calculates
Need the capacity configuration amount increased in going out following N number of predetermined period or need the capacity configuration amount reduced.
The performance capability analysis and early warning method and device of a kind of transaction processing system that the present invention provides, with industry
Business is for unit, according to the data volume of business and the performance indications data of the business main frame processing this business,
The change using Capability index and business datum amount that corresponding computation model respectively obtains business main frame becomes
Gesture, then according to Capability index and the growth trend of business datum amount of business main frame, utilizes prediction mould
Type, calculates the predictive value of the Capability index of the business main frame after following N number of predetermined period, according to prediction
The performance state of value judgement business main frame, the present invention can be according to the variation tendency of portfolio and business master
The performance indications data of machine, are predicted the Capability index of future services main frame, it is achieved that at business
The performance capability analysis and early warning of reason system, and according to the performance state of business main frame, provide increase capacity and join
Put or reduce the suggestion of capacity configuration so that the performance state of business main frame within following a period of time
Maintain performance health status, and when the performance state of business main frame is performance bottleneck state, to user
Carry out alarm prompt, in order to take appropriate measures in time.
Accompanying drawing explanation
Fig. 1 is the performance capability analysis and early warning method of a kind of transaction processing system of the embodiment of the present invention one
Flow chart；
Fig. 2 is that the performance capability analysis and early warning device of a kind of transaction processing system of the embodiment of the present invention two shows
It is intended to；
Fig. 3 is the internal connection figure of data processing module in embodiment two.
Detailed description of the invention
Being described principle and the feature of the present invention below in conjunction with accompanying drawing, example is served only for explaining this
Invention, is not intended to limit the scope of the present invention.
Embodiment one, a kind of performance capability analysis and early warning method of transaction processing system.Below in conjunction with Fig. 1
The method providing the present embodiment illustrates.
See Fig. 1, S1, in units of business, gather the multinomial industry of each business in the scheduled time
Business achievement data and process the performance indications data of at least one business main frame of this business.
Concrete, transaction processing system includes a lot of business main frames, due to the data volume of each business
May be very big, therefore a business may need multiple stage business main frame to be jointly processed by.One business
Comprise multinomial operational indicator data, such as, in mobile communication business, comprise ticket amount, bill number and use
The multinomial operational indicator data such as family number of request.The present embodiment in units of business, each industry of Real-time Collection
The multinomial operational indicator data being engaged in and at least one business main frame (the most multiple industry processing this business
Business main frame) performance indications data, performance indications data refer to business main frame cpu busy percentage or
Memory usage.When the business main frame that business is corresponding has multiple, first gather each business main frame
Performance indications data, then the performance indications data of each business main frame are added up, as always
The performance indications data of body.
S2a, use big Data Analysis Platform, the data of the multiple business gathered carried out parallel computation,
Performance indications data according at least one business main frame described and operation Index for Calculation model, calculate
Operation index at least one business main frame described；And according to described operation index and Capability index meter
Calculate model and be calculated the Capability index of this at least one business main frame.
Concrete, after step S1 acquires the data that each business is corresponding, due to the data volume gathered
Very big, therefore the data gathered are imported big Data Analysis Platform, by big Data Analysis Platform to collection
Data carry out piecemeal every part carried out parallel computation process, every part at least includes a business
Corresponding data.Wherein, for every a part of data, according at least one industry that each business is corresponding
The business performance indications data of main frame and the operation Index for Calculation model pre-build, be calculated this extremely
The operation index of a few business main frame, wherein, the operation index of business main frame is the highest, then it represents that this industry
Business main frame is the busiest.Then, according to operation index and the energy pre-build of this at least one business main frame
Power Index for Calculation model, is calculated the Capability index of this at least one business main frame.
S2b, multinomial operational indicator data according to the business of Real-time Collection, calculate each of this business
The data volume of item operational indicator data variation tendency in each predetermined period, it includes growth trend
Or minimizing trend.
Concrete, according to each operational indicator data volume, i.e. basis of each business of Real-time Collection
Each operational indicator data volume of each business gathered, utilizes inertia forecasting algorithm to calculate this industry
Each the operational indicator of business variation tendency in each predetermined period, such as, can calculate each
The variation tendency of each operational indicator data volume of this business in it, it is also possible to should in calculating each moon
The variation tendency of each operational indicator data volume of business, wherein, variation tendency can be growth trend
Or minimizing trend.
S3, the Capability index according at least one business main frame described, each operational indicator of this business
The weight ratio of each operational indicator of the variation tendency of data volume and this business, in conjunction with forecast model,
Calculate the predictive value of the Capability index of this at least one business main frame in following N number of predetermined period.
Concrete, according to the Capability index of aforementioned at least one calculated business main frame, this business every
The variation tendency of one operational indicator data volume and the weight ratio of each operational indicator of this business, knot
Close the forecast model pre-build, calculate this at least one business after following N number of predetermined period
The predictive value of the Capability index of main frame, such as, the Capability index of this at least one business main frame after 10 months
Predictive value.As before, such as one business includes ticket amount, bill amount and user's number of request, these three industry
The variation tendency of business achievement data amount is the most different, presumable for growth trend, have for minimizing trend,
The variation tendency percentage ratio of each operational indicator quantity also can be different, therefore, and each for this business
The weight ratio that item operational indicator is differently configured, the weight ratio of each operational indicator reflects this business and refers to
The mark influence degree to business host performance.
S4, by the predictive value of the Capability index of at least one business main frame described and each performance state indicator threshold
Value contrasts, and according to comparing result, show that this at least one business main frame is at following N number of predetermined period
Interior performance state.
Concrete, step S3 calculates this at least one business main frame in following N number of predetermined period
Capability index predictive value, this Capability index predictive value is contrasted with each performance state indicator threshold value,
According to comparing result, obtain this at least one business main frame performance state within following N number of cycle, its
In, performance state includes performance bottleneck, performance health status and performance idle state, say, that
By the Capability index predictive value of this at least one business main frame respectively with performance bottleneck state index threshold value, property
Health status metrics-thresholds and performance idle state index threshold value can contrast, obtain this at least one
Business main frame performance state within N number of cycle.
S5, the performance state of this at least one business main frame according to prediction, calculate following N number of predetermined
Need the capacity configuration amount increased in cycle or need the capacity configuration amount reduced.
Concrete, when the performance state of at least one business main frame aforementioned is performance bottleneck state, it should
Increase CPU configuration, so that the performance state of this at least one business main frame is protected in N number of predetermined period
Hold in health status；When the performance state of at least one business main frame aforementioned is performance idle state, should
This minimizing CPU configures, so that the performance state of this at least one business main frame is in N number of predetermined period
It is maintained at health status；When the performance state of at least one business main frame aforementioned is performance health status,
It is increased without CPU configuration also without reducing CPU configuration.Wherein, increase CPU configuration can be presented as
Increase the CPU configuration of a certain business main frame, it is also possible to increase processes the business main frame of each business
Quantity.
When this at least one business main frame performance state in following N number of predetermined period reaches performance bottle
During neck-shaped state, use reverse method, extrapolate the time needing to increase configuration and need the capacity increased to join
The amount of putting, so that this at least one business main frame reaches performance health status；When predicting this at least one industry
When business main frame performance state in following N number of predetermined period is performance idle state, use reverse method,
Extrapolate the time needing to reduce configuration and need the capacity configuration amount reduced, so that this at least one industry
Business main frame reaches performance health status.Such as, forecast analysis is passed through, it is predicted that business main frame is following 10
Performance bottleneck state can be reached the when of individual month, at this point it is possible to use reverse method, such as, retrodict this
When the cpu busy percentage of business main frame is 60%, carries out dilatation, i.e. increase configuration, it may be determined that increase and join
The time put and the configuration amount that should increase, so that this business main frame is in following N number of predetermined period one
Straight holding performance health status.Being in property when this at least one business main frame was at following 10 months when
During energy idle condition, it is also adopted by reverse method, determines and reduce the time of configuration and need the configuration amount reduced.
Additionally, be property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy bottleneck, generate early warning information and alert, in order to related personnel processes timely.
Embodiment two, the performance capability analysis and early warning device of a kind of transaction processing system.Below in conjunction with Fig. 2
The device provided the present embodiment with Fig. 3 is described.
Seeing Fig. 2, the device that the present embodiment provides includes that data acquisition server 1 and big data analysis are put down
Platform 2；Described data acquisition server 1 includes:
Data acquisition module 11, is used in units of business, the multinomial business of each business of Real-time Collection
Achievement data and process the performance indications data of at least one business main frame of this business；
First sending module 12, for being sent to big Data Analysis Platform 20 by the data of collection；
Described big Data Analysis Platform 2 includes that receiver module 21, data divide module 22 and multiple data
Processing module 23；
Receiver module 21, for receiving the collection data that described data acquisition module sends；
Data divide module 22, for the collection data received are divided into multiple data block, each
Data block at least includes the data that a business is corresponding.
Seeing Fig. 3, each data processing module 23 includes:
Run Index for Calculation module 231, for the performance indications number according at least one business main frame described
According to this and run Index for Calculation model, it is calculated the operation index of at least one business main frame described；
Capability index computing module 232, based on according to described operation index and Capability index computation model
Calculate the Capability index obtaining this at least one business main frame；
Variation tendency computing module 233, for referring to according to the multinomial business of the business gathered in the scheduled time
Mark, calculates the change in each predetermined period of each operational indicator data volume of this business and becomes
Gesture, it includes growth trend or minimizing trend；
Predictor calculation module 234, for the Capability index according at least one business main frame described, is somebody's turn to do
The variation tendency of each operational indicator data volume of business and each operational indicator of this business
Weight ratio, in conjunction with forecast model, calculates this at least one business master in following N number of predetermined period
The predictive value of the Capability index of machine；
Performance state obtains module 235, pre-for by the Capability index of at least one business main frame described
Measured value compares with each performance state indicator threshold value, according to comparative result, draws this at least one business
Main frame performance state in following N number of predetermined period；
Configuration computing module 236, for the performance state of this at least one the business main frame according to prediction,
Need in calculating following N number of predetermined period increase capacity configuration amount or need to reduce capacity configuration amount.
Wherein, described performance state includes performance bottleneck, performance health status and performance idle shape
State；Described configuration computing module 236 specifically for: when predicting this at least one business main frame in future
When performance state in N number of predetermined period is performance bottleneck state, calculate the capacity configuration needing to increase
Amount, to reach performance health status；When predicting this at least one business main frame in following N number of predetermined week
When performance state in phase is performance idle state, calculate the capacity configuration amount needing to reduce, with reaching property
Can health status.
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
Can bottleneck time, described configuration computing module 236 specifically for: use reverse method, extrapolate needs
Increase the time of configuration and need the capacity configuration amount increased, so that this at least one business main frame reaches
Performance health status；Or, when predicting this at least one business main frame in following N number of predetermined period
Performance state when being performance idle state, described configuration computing module 236, specifically for: use
Pushing manipulation, extrapolates the time needing to reduce configuration and needs the capacity configuration amount reduced, so that this is at least
One business main frame reaches performance health status.
The performance capability analysis and early warning device of the transaction processing system that the present embodiment provides also includes that early warning divides
Analysis server 3；Each data processing module 23 described also includes:
Second sending module 237, for being sent to pre-by the performance state of at least one business main frame described
Alert Analysis server 3；
Described early warning analysis server 3, for receiving the performance state of at least one business main frame described,
And when the performance state of at least one business main frame described is performance bottleneck state, generate corresponding early warning
Information alerts.
The performance capability analysis and early warning method and device of a kind of transaction processing system that the present invention provides, with industry
Business is for unit, according to the data volume of business and the performance indications data of the business main frame processing this business,
The change using Capability index and business datum amount that corresponding computation model respectively obtains business main frame becomes
Gesture, then according to Capability index and the growth trend of business datum amount of business main frame, utilizes prediction mould
Type, calculates the predictive value of the Capability index of the business main frame after following N number of predetermined period, according to prediction
The performance state of value judgement business main frame, the present invention can be according to the variation tendency of portfolio and business master
The performance indications data of machine, are predicted the Capability index of future services main frame, it is achieved that at business
The performance capability analysis and early warning of reason system, and according to the performance state of business main frame, be given increase configuration or
Person reduces the suggestion of configuration so that the maintaining property of performance state of business main frame within following a period of time
Energy health status, and when the performance state of business main frame is performance bottleneck state, alert to user
Prompting, in order to take appropriate measures in time；It addition, use big Data Analysis Platform to a lot of business
The performance of main frame carries out distributed analysis early warning, can realize the distributed variable-frequencypump to data, improves number
According to treatment effeciency.
In the description of this specification, reference term " embodiment one ", " example ", " concrete example ",
Or the description of " some examples " etc. means to combine this embodiment or example describes concrete grammar, device or
Person's feature is contained at least one embodiment or the example of the present invention.In this manual, to above-mentioned art
The schematic representation of language is necessarily directed to identical embodiment or example.And, the concrete spy of description
Levy, method, device or feature can with in one or more embodiments in office or example in an appropriate manner
In conjunction with.Additionally, in the case of the most conflicting, those skilled in the art can be by this specification
The feature of the different embodiments described or example and different embodiment or example is combined and combines.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all in the present invention
Spirit and principle within, any modification, equivalent substitution and improvement etc. made, should be included in this
Within bright protection domain.
Claims (8)
1. a performance capability analysis and early warning method for transaction processing system, described transaction processing system bag
Include multiple business main frame, it is characterised in that including:
S1, in units of business, gather in the scheduled time the multinomial operational indicator data of each business with
And process the performance indications data of at least one business main frame of this business；
S2a, use big Data Analysis Platform, the data of the multiple business gathered carried out parallel computation,
Performance indications data according at least one business main frame described and operation Index for Calculation model, calculate
Operation index at least one business main frame described；And according to described operation index and Capability index meter
Calculate model and be calculated the Capability index of this at least one business main frame；
S2b, according to the multinomial operational indicator data of each business gathered in the scheduled time, calculate
The data volume of each operational indicator data of this business variation tendency in each predetermined period, its
Including growth trend or minimizing trend；
S3, the Capability index according at least one business main frame described, each operational indicator of this business
The variation tendency of the data volume of data and the weight ratio of each operational indicator data of this business, in conjunction with
Forecast model, calculates the Capability index of this at least one business main frame in following N number of predetermined period
Predictive value；
S4, by the Capability index predictive value of at least one business main frame described and each performance state indicator threshold value
Contrast, according to comparing result, show that this at least one business main frame is in following N number of predetermined period
Performance state；
S5, the performance state of this at least one business main frame according to prediction, calculate this at least one industry
Business main frame needs the capacity configuration amount increased in following N number of predetermined period or needs the capacity reduced
Configuration amount.
The performance capability analysis and early warning method of a kind of transaction processing system the most as claimed in claim 1,
It is characterized in that, described performance state includes performance bottleneck, performance health status and performance idle
State；
Described step S5 specifically includes:
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy bottleneck, need to increase capacity configuration amount, to reach performance health status；
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy health status, do not make the change of capacity configuration amount；
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy idle condition, it is desirable to reduce capacity configuration amount, to reach performance health status.
The performance capability analysis and early warning method of a kind of transaction processing system the most as claimed in claim 2,
It is characterized in that, when predicting this at least one business main frame performance shape in following N number of predetermined period
When state is performance bottleneck state, use reverse method, extrapolate the time needing to increase configuration and need to increase
The capacity configuration amount added, so that this at least one business main frame reaches performance health status；
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy idle condition, employing reverse method, extrapolate the time needing to reduce configuration and the appearance of needs minimizing
Amount configuration amount, so that this at least one business main frame reaches performance health status.
The performance capability analysis and early warning side of a kind of transaction processing system the most as claimed in claim 2 or claim 3
Method, it is characterised in that when predicting this at least one business main frame property in following N number of predetermined period
When energy state is performance bottleneck state, generates early warning information and alert.
5. the performance capability analysis and early warning device of a transaction processing system, it is characterised in that include number
According to acquisition server and big Data Analysis Platform；
Described data acquisition server includes:
Data acquisition module, in units of business, gathers the multinomial of the scheduled time each business interior
Operational indicator data and process the performance indications data of at least one business main frame of this business；
Sending module, for being sent to big Data Analysis Platform by the data of collection；
Described big Data Analysis Platform includes that receiver module, data divide module and multiple data process mould
Block；
Receiver module, for receiving the collection data that described data acquisition module sends；
Data divide module, for the collection data received are divided into multiple data block, each number
According to block at least includes the data that a business is corresponding；
Each data processing module includes: run Index for Calculation module, for according to described at least one
The performance indications data of business main frame and operation Index for Calculation model, be calculated at least one industry described
The operation index of business main frame；
Capability index computing module, for calculating according to described operation index and Capability index computation model
Capability index to this at least one business main frame；
Variation tendency computing module, for the multinomial operational indicator number according to the business gathered in the scheduled time
According to, calculate the change in each predetermined period of the data volume of each operational indicator data of this business
Change trend, it includes growth trend or minimizing trend；
Predictor calculation module, for the Capability index according at least one business main frame described, this business
The variation tendency of data volume of each operational indicator data and each operational indicator of this business
The weight ratio of data, in conjunction with forecast model, calculate in following N number of predetermined period this at least one
The predictive value of the Capability index of business main frame；
Performance state acquisition module, for the predictive value by the Capability index of at least one business main frame described
Compare with each performance state indicator threshold value, according to comparative result, draw this at least one business main frame
Performance state in following N number of predetermined period；
Configuration computing module, for the performance state of this at least one the business main frame according to prediction, calculates
Need the capacity configuration amount increased in going out following N number of predetermined period or need the capacity configuration amount reduced.
The performance capability analysis and early warning device of a kind of transaction processing system the most as claimed in claim 5,
It is characterized in that, described performance state includes performance bottleneck, performance health status and performance idle
State；
Described configuration computing module specifically for:
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy bottleneck, calculate the capacity configuration amount needing to increase, to reach performance health status；
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy idle condition, calculate the capacity configuration amount needing to reduce, to reach performance health status.
The performance capability analysis and early warning device of a kind of transaction processing system the most as claimed in claim 6,
It is characterized in that, when predicting this at least one business main frame performance shape in following N number of predetermined period
When state is performance bottleneck state, described configuration computing module specifically for:
Use reverse method, extrapolate the time needing to increase configuration and need the capacity configuration amount increased,
So that this at least one business main frame reaches performance health status；
Or,
It is property when predicting this at least one business main frame performance state in following N number of predetermined period
During energy idle condition, described configuration computing module, specifically for:
Use reverse method, extrapolate the time needing to reduce configuration and need the capacity configuration amount reduced,
So that this at least one business main frame reaches performance health status.
The performance capability analysis and early warning dress of a kind of transaction processing system the most as claimed in claims 6 or 7
Put, it is characterised in that described device also includes early warning analysis server；
Described big Data Analysis Platform also includes:
Sending module, for being sent to early warning analysis clothes by the performance state of at least one business main frame described
Business device；
Described early warning analysis server, for receiving the performance state of at least one business main frame described, and
When the performance state of at least one business main frame described is performance bottleneck state, generate corresponding early warning letter
Breath alerts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610232819.XA CN105979532B (en) | 2016-04-15 | 2016-04-15 | Performance capacity analysis early warning method and device of service processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610232819.XA CN105979532B (en) | 2016-04-15 | 2016-04-15 | Performance capacity analysis early warning method and device of service processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105979532A true CN105979532A (en) | 2016-09-28 |
| CN105979532B CN105979532B (en) | 2020-01-03 |
Family
ID=56989566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610232819.XA Active CN105979532B (en) | 2016-04-15 | 2016-04-15 | Performance capacity analysis early warning method and device of service processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105979532B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391341A (en) * | 2017-07-21 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of fault early warning method and device |
| CN109543891A (en) * | 2018-11-09 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Method for building up, equipment and the computer readable storage medium of capacity prediction model |
| CN109728923A (en) * | 2017-10-27 | 2019-05-07 | 中移(苏州)软件技术有限公司 | A kind of cloud platform running state monitoring method for early warning and device |
| CN109783332A (en) * | 2018-12-12 | 2019-05-21 | 平安科技（深圳）有限公司 | Server alarm method and system based on data modeling |
| CN110266603A (en) * | 2019-06-27 | 2019-09-20 | 公安部第一研究所 | Authentication business network flow analysis system and method based on http protocol |
| CN112087344A (en) * | 2019-06-13 | 2020-12-15 | 烽火通信科技股份有限公司 | State data acquisition method and system |
| CN113360250A (en) * | 2021-08-09 | 2021-09-07 | 连连宝(杭州)信息技术有限公司 | Application service resource control method, device, equipment and medium |
| CN116908704A (en) * | 2023-09-07 | 2023-10-20 | 江西五十铃汽车有限公司 | Method, device and medium for SOH estimation and correction of power battery |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170599A (en) * | 2007-11-30 | 2008-04-30 | 中国移动通信集团重庆有限公司 | Network device load prediction method |
| CN102082703A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团贵州有限公司 | Method and device for monitoring equipment performance of service supporting system |
| US20130145367A1 (en) * | 2011-09-27 | 2013-06-06 | Pneuron Corp. | Virtual machine (vm) realm integration and management |
-
2016
- 2016-04-15 CN CN201610232819.XA patent/CN105979532B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170599A (en) * | 2007-11-30 | 2008-04-30 | 中国移动通信集团重庆有限公司 | Network device load prediction method |
| CN102082703A (en) * | 2009-11-26 | 2011-06-01 | 中国移动通信集团贵州有限公司 | Method and device for monitoring equipment performance of service supporting system |
| US20130145367A1 (en) * | 2011-09-27 | 2013-06-06 | Pneuron Corp. | Virtual machine (vm) realm integration and management |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391341A (en) * | 2017-07-21 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of fault early warning method and device |
| CN109728923B (en) * | 2017-10-27 | 2022-01-28 | 中移(苏州)软件技术有限公司 | Cloud platform running state monitoring and early warning method and device |
| CN109728923A (en) * | 2017-10-27 | 2019-05-07 | 中移(苏州)软件技术有限公司 | A kind of cloud platform running state monitoring method for early warning and device |
| CN109543891A (en) * | 2018-11-09 | 2019-03-29 | 深圳前海微众银行股份有限公司 | Method for building up, equipment and the computer readable storage medium of capacity prediction model |
| CN109543891B (en) * | 2018-11-09 | 2022-02-01 | 深圳前海微众银行股份有限公司 | Method and apparatus for establishing capacity prediction model, and computer-readable storage medium |
| CN109783332A (en) * | 2018-12-12 | 2019-05-21 | 平安科技（深圳）有限公司 | Server alarm method and system based on data modeling |
| CN109783332B (en) * | 2018-12-12 | 2022-05-17 | 平安科技（深圳）有限公司 | Server warning method and system based on data modeling |
| CN112087344A (en) * | 2019-06-13 | 2020-12-15 | 烽火通信科技股份有限公司 | State data acquisition method and system |
| CN112087344B (en) * | 2019-06-13 | 2022-04-29 | 烽火通信科技股份有限公司 | State data acquisition method and system |
| CN110266603A (en) * | 2019-06-27 | 2019-09-20 | 公安部第一研究所 | Authentication business network flow analysis system and method based on http protocol |
| CN113360250A (en) * | 2021-08-09 | 2021-09-07 | 连连宝(杭州)信息技术有限公司 | Application service resource control method, device, equipment and medium |
| CN113360250B (en) * | 2021-08-09 | 2021-12-14 | 连连宝(杭州)信息技术有限公司 | Application service resource control method, device, equipment and medium |
| CN116908704A (en) * | 2023-09-07 | 2023-10-20 | 江西五十铃汽车有限公司 | Method, device and medium for SOH estimation and correction of power battery |
| CN116908704B (en) * | 2023-09-07 | 2024-04-09 | 江西五十铃汽车有限公司 | Method, device and medium for SOH estimation and correction of power battery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105979532B (en) | 2020-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105979532A (en) | Performance-capacity analysis early warning method and device for service processing system | |
| CN103164279B (en) | Cloud computing resources distribution method and system | |
| Perakis et al. | Robust controls for network revenue management | |
| Mao et al. | Faster deliveries and smarter order assignments for an on-demand meal delivery platform | |
| CN109039821A (en) | Network flow monitoring method, device, computer equipment and storage medium | |
| WO2019001278A1 (en) | Actuarial forecasting method and device for medical benefits fund, and computer device | |
| CN108038040A (en) | Computer cluster performance indicator detection method, electronic equipment and storage medium | |
| CN109523276A (en) | The pre-warning monitoring method and device of customer complaint | |
| CN108550047A (en) | The prediction technique and device of trading volume | |
| KR20150043338A (en) | Updating cached database query results | |
| CN101540016A (en) | Queueing time estimation method | |
| US20200090296A1 (en) | Transport capacity monitoring | |
| CN108154252A (en) | Method and apparatus for estimating the flow deadline | |
| CN106339578B (en) | A kind of patient in hospital of more strategy fusion is registered recommendation method | |
| CN105022729A (en) | User preference determination method and device | |
| CN109035021A (en) | A kind of monitoring method, device and the equipment of index of trading | |
| CA2948836A1 (en) | Systems and methods for cashier scheduling | |
| CN111047264A (en) | Logistics task allocation method and device | |
| CN110738451A (en) | Monitoring method and device for courier cross-region behavior, storage medium and electronic equipment | |
| CN105825683B (en) | A kind of road traffic condition evaluation method | |
| WO2021042541A1 (en) | Shopping guide method and apparatus in new retail model, device and storage medium | |
| CN109543877B (en) | Multi-user electricity stealing and leakage meter discrimination method and device under same feeder line | |
| CN107480832A (en) | Short-term power predicating method, device and electronic equipment | |
| JP2015082928A (en) | Estimation program, estimation device, and estimation method | |
| Xu et al. | A periodic-review base-stock inventory system with sales rejection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |