CN107451031A - A kind of server cpu busy percentage instantaneous peak value filter method and device - Google Patents
A kind of server cpu busy percentage instantaneous peak value filter method and device Download PDFInfo
- Publication number
- CN107451031A CN107451031A CN201710631040.XA CN201710631040A CN107451031A CN 107451031 A CN107451031 A CN 107451031A CN 201710631040 A CN201710631040 A CN 201710631040A CN 107451031 A CN107451031 A CN 107451031A
- Authority
- CN
- China
- Prior art keywords
- cpu busy
- busy percentage
- variance
- real time
- time data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3024—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
- G06F11/3419—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment by assessing time
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a kind of server cpu busy percentage instantaneous peak value filter method and device based on wavelet analysis, it is related to server monitoring, monitoring data filtration art.Server cpu busy percentage instantaneous peak value filter method disclosed herein, including:The calculating for seeking variance based on small echo is carried out to cpu busy percentage real time data, wherein, the calculating for ask variance is based on a reference value of the period belonging to the cpu busy percentage real time data;By the variance yields of the cpu busy percentage real time data calculated compared with the variance threshold values of the period belonging to the cpu busy percentage real time data, if the variance yields of the cpu busy percentage real time data calculated is more than or equal to the variance threshold values of the period, the cpu busy percentage real time data is filtered out.
Description
Technical field
The present invention relates to server monitoring, monitoring data filtration art, and in particular to a kind of service based on wavelet analysis
Device cpu busy percentage instantaneous peak value filtering scheme.
Background technology
With the rapid development of Internet, the monitoring of server becomes essential in the monitoring of data center, and pass
In the server monitoring of system often there is instantaneous, invalid peak value or valley in cpu busy percentage, make the data result that monitors inclined
From actual conditions, monitoring accuracy and the validity to server cpu busy percentage can not be ensured.
For example, in the data center of ten thousand grades of server farms, Servers-all in the process of running, can be different degrees of
The instantaneous interim card of appearance or momentary load is fully loaded with caused by other external factor so that the CPU of whole data center is used
Trend analysis and availability analysis are influenced to different extents, cause the inaccuracy of analysis result, value to have a greatly reduced quality.More than
Challenge and bring great limitation for the server cpu busy percentage analysis at large-scale data center, have a strong impact on extensive number
According to the development of center resources usage trend, and then as where the bottleneck entirely developed.
The content of the invention
Provided herein is a kind of server cpu busy percentage instantaneous peak value filter method and device, can solve in correlation technique
The problem of monitoring accuracy and low validity of cpu busy percentage.
Disclosed herein is a kind of server cpu busy percentage instantaneous peak value filter method, including:
The calculating for seeking variance based on small echo is carried out to cpu busy percentage real time data, wherein, ask the calculating of variance to be
Based on a reference value of the period belonging to the cpu busy percentage real time data;
By the period belonging to the variance yields of the cpu busy percentage real time data calculated and the cpu busy percentage real time data
Variance threshold values be compared, if the variance yields of the cpu busy percentage real time data calculated be more than or equal to the period side
Poor threshold value, then the cpu busy percentage real time data is filtered out.
Alternatively, the above method also includes:
If the variance yields of the cpu busy percentage real time data calculated is less than the variance threshold values of the period, by CPU profits
With rate real time data and its time attribute store to server cpu busy percentage when m- sequence library in, wherein, the CPU
The time attribute of utilization rate real time data includes the time segment information belonging to the cpu busy percentage real time data.
Alternatively, the above method also includes:Batch cpu busy percentage data in different time sections are averaged in advance
Calculating, a reference value using the average value of cpu busy percentage in the different time sections calculated as each period.
Alternatively, it is above-mentioned also to include:The variance threshold values of different time sections are pre-configured with, wherein, according to different time sections
The variance threshold values of the empirical cumulative value configuration different time sections of the reasonable cpu busy percentage of server.
Alternatively, it is above-mentioned also to include:Sending agency using multiple cpu busy percentages, connection Distributed C PU utilization rates connect respectively
Module is received to obtain cpu busy percentage real time data.
There is disclosed herein a kind of server cpu busy percentage instantaneous peak value filter, including at least the side based on small echo
Poor computing module and instantaneous peak value filtering module, wherein:
The variance computing module based on small echo, asking based on small echo is carried out to the cpu busy percentage real time data of acquisition
The calculating of variance, wherein, the calculating for ask variance be using a reference value of the period belonging to the cpu busy percentage real time data as
Basis;
The instantaneous peak value filtering module, the cpu busy percentage that the variance computing module based on small echo is calculated are real
When data variance yields compared with the variance threshold values of the period belonging to the cpu busy percentage real time data, if calculating
The variance yields of cpu busy percentage real time data is more than or equal to the variance threshold values of the period, then by the cpu busy percentage real time data
Filter out.
Alternatively, in said apparatus, the instantaneous peak value filtering module, in the cpu busy percentage real time data calculated
When variance yields is less than the variance threshold values of the period, the cpu busy percentage real time data and its time attribute are stored to server
Cpu busy percentage when m- sequence library in, wherein, the time attribute of the cpu busy percentage real time data includes CPU profits
With the time segment information belonging to rate real time data.
Alternatively, said apparatus also includes:A reference value computing module, in advance to batch cpu busy percentage in different time sections
The calculating that data are averaged, using the average value of cpu busy percentage in the different time sections calculated as each period
A reference value.
Alternatively, said apparatus also includes:Filtering policy storehouse based on variance, be provided with the variance of different time sections in advance
Threshold value, wherein, according to the variance of the empirical cumulative value of the reasonable cpu busy percentage of the server of different time sections configuration different time sections
Threshold value.
Alternatively, said apparatus also includes multiple cpu busy percentages transmission proxy module, and each cpu busy percentage sends agency
Module connects a Distributed C PU utilization rate receiving module respectively;
The cpu busy percentage sends proxy module, and the Distributed C PU utilization rates receiving module connected to it sends CPU profits
With rate real time data;
The Distributed C PU utilization rate receiving modules, the cpu busy percentage real time data received is sent respectively to the base
Variance computing module, the instantaneous peak value filtering module and a reference value computing module in small echo.
Technical scheme compensate for traditional server monitoring cpu busy percentage and instantaneous, invalid peak often be present
Value, that is, the deficiencies of data result that monitors deviates actual conditions, using a reference value changed over time and the side of dynamic change
Difference is combined, and the filtering policy of the variance based on time attribute is calculated with the variance based on small echo and mutually relied on, and is effectively increased
The accuracy and validity of server cpu busy percentage real-time waveform analysis, no matter being utilized in large-scale data central server CPU
The analysis application of rate availability, or in large-scale server cluster cpu busy percentage trend analysis application, it is respectively provided with very high technology
Value.
Brief description of the drawings
Fig. 1 is server cpu busy percentage instantaneous peak value filter apparatus configuration schematic diagram in the embodiment of the present invention;
Fig. 2 is Distributed C PU utilization rates receiving module and transmission proxy module principle schematic in the embodiment of the present invention;
Fig. 3 is a reference value computing module principle schematic in the embodiment of the present invention;
Fig. 4 is the variance computing module principle schematic based on small echo in the embodiment of the present invention;
Fig. 5 is the filtering policy storehouse principle schematic based on variance in the embodiment of the present invention.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with embodiment pair
Technical solution of the present invention is described in further detail.It should be noted that in the case where not conflicting, embodiments herein and
Feature in embodiment can be arbitrarily mutually combined.
Present inventor proposes that the service application that a server is run is different, and the residing period is different, business
It is different using the access pressure undertaken, it can cause the cpu busy percentage of server normal, large range of fluctuation occur, because
This, can use the variance threshold values with time attribute to filter instantaneous cpu busy percentage peak value, so as to improve server
The accuracy and validity of cpu busy percentage real-time waveform analysis.
Based on above-mentioned thought, the present embodiment provides a kind of server cpu busy percentage instantaneous peak value filter method, main bag
Include:
The calculating for seeking variance based on small echo is carried out to cpu busy percentage real time data, wherein, ask the calculating of variance to be
Based on a reference value of the period belonging to the cpu busy percentage real time data;
By the period belonging to the variance yields of the cpu busy percentage real time data calculated and the cpu busy percentage real time data
Variance threshold values be compared, if the variance yields of the cpu busy percentage real time data calculated be more than or equal to the period side
Poor threshold value, then the cpu busy percentage real time data is filtered out.
In addition to above-mentioned filter operation, if the variance yields of the cpu busy percentage real time data calculated is less than the period
Variance threshold values, then the cpu busy percentage real time data and its time attribute are stored to the when m- sequence of server cpu busy percentage
In database, wherein, the time attribute of cpu busy percentage real time data includes the period belonging to the cpu busy percentage real time data
Information.
Wherein, a reference value of different time sections precalculates, i.e., in advance to batch cpu busy percentage in different time sections
The calculating that data are averaged, using the average value of cpu busy percentage in the different time sections calculated as each period
A reference value.
The variance threshold values of different time sections can also tire out according to the experience of the reasonable cpu busy percentage of server of different time sections
Product value is pre-configured with.
A kind of server cpu busy percentage instantaneous peak value filter is also provided herein, mainly includes the variance based on small echo
Computing module and instantaneous peak value filtering module.
Variance computing module based on small echo, the cpu busy percentage real time data of acquisition is carried out seeking variance based on small echo
Calculating, wherein, the calculating for ask variance is based on a reference value of the period belonging to the cpu busy percentage real time data
's;
Instantaneous peak value filtering module, the cpu busy percentage that the variance computing module based on small echo calculates is counted in real time
According to variance yields compared with the variance threshold values of the period belonging to the cpu busy percentage real time data, if calculate CPU profit
It is more than or equal to the variance threshold values of the period with the variance yields of rate real time data, then filters the cpu busy percentage real time data
Fall.
In addition, this paper design is considered to calculate variance and the characteristics of based on variance policy filtering based on small echo, using connecing
Receiving each cpu busy percentage transmission Agent in the processing end multiple Distributed C PU utilization rates receiving module waiting for server ends of deployment please
Connection is asked, gives full play to the characteristics of multiterminal are to multiterminal, when both sides can not establish effective connection, also second, the 3rd connects
Debit is attached for it;Include multiple server end cpu busy percentages and send proxy module, and each server end CPU is sharp
Proxy module, which is sent, with rate is connected with a Distributed C PU utilization rate receiving module.So.After connection is established, server end CPU
Utilization rate sends agency's Distributed C PU utilization rate receiving modules per second for sending cpu busy percentage to connection, completes data communication.
Said apparatus can also include a reference value computing module, be mainly used in getting Distributed C PU utilization rates reception mould
The batch cpu busy percentage data that block receives, sampling originally, calculate benchmark of the average value as the period of this group of sample value
Value, because a reference value meeting dynamic change of different time sections, a reference value are just accompanied with time attribute.
Instantaneous peak value filtering module, can be by reading side corresponding to current slot in the filtering policy storehouse based on variance
Poor threshold value, compared with the variance yields that the variance computing module based on small echo calculates.Wherein, the filtering policy based on variance
Be provided with the variance threshold values of different time sections in storehouse in advance.
With reference to the accompanying drawings, the specific implementation to technical scheme is described in detail.For example, with one group of sample base
Quasi- value calculate two periods cpu busy percentage variance yields, using three Distributed C PU utilization rates receiving modules respectively with respectively
Cpu busy percentage, which is sent, to be acted on behalf of the mode of dynamic equalization connection and describes technical scheme implementation process.
Provided herein is the server cpu busy percentage instantaneous peak value filter based on wavelet analysis, its structure such as Fig. 1
It is shown, including:(1) the variance computing module of instantaneous peak value filtering module, (2) a reference value computing module, (3) based on small echo, (4)
Filtering policy storehouse based on variance, (5) Distributed C PU utilization rates receiving module, (6) server end cpu busy percentage send agency
Module.
Wherein, server end cpu busy percentage sends proxy module and established effectively with Distributed C PU utilization rates receiving module
After connection, transmission cpu busy percentage data per second to receiving terminal;Multiple Distributed C PU utilization rates receiving modules are disposed simultaneously to wait
Each cpu busy percentage of server end sends Agent and asks connection, can not be built with first recipient with ensureing to work as to send to act on behalf of
During vertical effectively connection, also second, the 3rd recipient trial is attached for it.This principle is as shown in Figure 2.
After cpu busy percentage data are received, a reference value computing module samples this in the batch data, as calculated in full example
1:00 to 3:The a reference value of 00 this period, sampling every 10 minutes of this when takes a point, takes 12 points to be calculated as a reference value altogether
Sample, then take the average value of this group of sample value, this average value is a reference value as the period, as shown in Figure 3.Its
In, because a reference value meeting dynamic change of different time sections, a reference value are all accompanied with time attribute, it is effective to indicate its institute
Time range.
Based on a reference value that variance computing module based on small echo is then calculated by a reference value computing module, to distribution
The batch cpu busy percentage real time data that cpu busy percentage receiving module is got ask the calculating of variance, the variance yields calculated
Time attribute is equally attached, principle is as shown in Figure 4.
Filtering policy storehouse based on variance devises the mode of the variance threshold values dynamic change of different time sections, takes into full account
The characteristics of originally will constantly changing over time in server cpu busy percentage running, differing greatly, and this policy library
Summarized and drawn by the accumulation of protracted experience, therefore, the waveform based on this can be effectively ensured in the filtering policy storehouse based on variance
Filtering can be completely the same with actual conditions.Its principle is as shown in Figure 5.
Finally, the variance as corresponding to instantaneous peak value filtering module reads current slot in the filtering policy storehouse based on variance
Threshold value, compared with the variance yields that the variance computing module based on small echo calculates, if variance yields is more than or equal to variance threshold values
Illustrate that instantaneous peak value fluctuation is excessive and do not meet normal fluctuation range, filter out;Conversely, then retain and be deposited into server
Cpu busy percentage when m- sequence library in.
It is noted that the time attribute being referred to herein, including the acquisition time of cpu busy percentage real time data or its
Affiliated time segment information, and period corresponding to a reference value etc. and the information of time correlation.
From above-described embodiment as can be seen that technical scheme introduces the server cpu busy percentage based on wavelet analysis
Variance yields calculates, can be accurately and efficiently by server cpu busy percentage with reference to the filtering policy of the variance based on time attribute
Invalid, the instantaneous peak value occurred during monitoring is to filtering out, so that the server cpu busy percentage data monitored are complete
Tally with the actual situation entirely.
One of ordinary skill in the art will appreciate that all or part of step in the above method can be instructed by program
Related hardware is completed, and described program can be stored in computer-readable recording medium, such as read-only storage, disk or CD
Deng.Alternatively, all or part of step of above-described embodiment can also be realized using one or more integrated circuits.Accordingly
Ground, each module/unit in above-described embodiment can be realized in the form of hardware, can also use the shape of software function module
Formula is realized.The application is not restricted to the combination of the hardware and software of any particular form.
It is described above, it is only the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all this
Within the spirit and principle of invention, any modification, equivalent substitution and improvements done etc., the protection model of the present invention should be included in
Within enclosing.
Claims (10)
1. a kind of server cpu busy percentage instantaneous peak value filter method, including:
The calculating for seeking variance based on small echo is carried out to cpu busy percentage real time data, wherein, the calculating for ask variance is with this
Based on a reference value of period belonging to cpu busy percentage real time data;
By the side of the period belonging to the variance yields of the cpu busy percentage real time data calculated and the cpu busy percentage real time data
Poor threshold value is compared, if the variance yields of the cpu busy percentage real time data calculated is more than or equal to the variance threshold of the period
Value, then filter out the cpu busy percentage real time data.
2. the method as described in claim 1, it is characterised in that methods described also includes:
If the variance yields of the cpu busy percentage real time data calculated is less than the variance threshold values of the period, by the cpu busy percentage
Real time data and its time attribute store to server cpu busy percentage when m- sequence library in, wherein, the CPU is utilized
The time attribute of rate real time data includes the time segment information belonging to the cpu busy percentage real time data.
3. method as claimed in claim 1 or 2, it is characterised in that methods described also includes:
In advance to the calculating that batch cpu busy percentage data are averaged in different time sections, the different time that will be calculated
A reference value of the average value of cpu busy percentage as each period in section.
4. method as claimed in claim 3, it is characterised in that methods described also includes:
The variance threshold values of different time sections are pre-configured with, wherein, according to the warp of the reasonable cpu busy percentage of the server of different time sections
Test the variance threshold values of accumulated value configuration different time sections.
5. method as claimed in claim 3, it is characterised in that methods described also includes:
Agency, which is sent, using multiple cpu busy percentages connects Distributed C PU utilization rates receiving module respectively to obtain cpu busy percentage reality
When data.
A kind of 6. server cpu busy percentage instantaneous peak value filter, including at least the variance computing module based on small echo and wink
When peak value filtering module, wherein:
The variance computing module based on small echo, the cpu busy percentage real time data of acquisition is carried out seeking variance based on small echo
Calculating, wherein, the calculating for ask variance is based on a reference value of the period belonging to the cpu busy percentage real time data
's;
The instantaneous peak value filtering module, the cpu busy percentage that the variance computing module based on small echo calculates is counted in real time
According to variance yields compared with the variance threshold values of the period belonging to the cpu busy percentage real time data, if calculate CPU profit
It is more than or equal to the variance threshold values of the period with the variance yields of rate real time data, then filters the cpu busy percentage real time data
Fall.
7. device as claimed in claim 6, it is characterised in that
The instantaneous peak value filtering module, it is less than the side of the period in the variance yields of the cpu busy percentage real time data calculated
During poor threshold value, the cpu busy percentage real time data and its time attribute are stored to the when m- sequence number of server cpu busy percentage
According in storehouse, wherein, the time attribute of the cpu busy percentage real time data includes the time belonging to the cpu busy percentage real time data
Segment information.
8. device as claimed in claims 6 or 7, it is characterised in that described device also includes:
A reference value computing module, in advance to the calculating that batch cpu busy percentage data are averaged in different time sections, it will count
A reference value of the average value of cpu busy percentage as each period in the different time sections calculated.
9. device as claimed in claim 8, it is characterised in that described device also includes:
Filtering policy storehouse based on variance, be provided with the variance threshold values of different time sections in advance, wherein, according to different time sections
The variance threshold values of the empirical cumulative value configuration different time sections of the reasonable cpu busy percentage of server.
10. device as claimed in claim 9, it is characterised in that described device also includes the transmission of multiple cpu busy percentages and acts on behalf of mould
Block, each cpu busy percentage send proxy module and connect a Distributed C PU utilization rate receiving module respectively;
The cpu busy percentage sends proxy module, and the Distributed C PU utilization rates receiving module connected to it sends cpu busy percentage
Real time data;
The Distributed C PU utilization rate receiving modules, the cpu busy percentage real time data received is sent respectively to described based on small
The variance computing module of ripple, the instantaneous peak value filtering module and a reference value computing module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710631040.XA CN107451031A (en) | 2017-07-28 | 2017-07-28 | A kind of server cpu busy percentage instantaneous peak value filter method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710631040.XA CN107451031A (en) | 2017-07-28 | 2017-07-28 | A kind of server cpu busy percentage instantaneous peak value filter method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107451031A true CN107451031A (en) | 2017-12-08 |
Family
ID=60489541
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710631040.XA Pending CN107451031A (en) | 2017-07-28 | 2017-07-28 | A kind of server cpu busy percentage instantaneous peak value filter method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107451031A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101355567A (en) * | 2008-09-03 | 2009-01-28 | 中兴通讯股份有限公司 | Method for protecting safety of route-exchanging device central processing unit |
CN106886478A (en) * | 2017-02-22 | 2017-06-23 | 郑州云海信息技术有限公司 | A kind of data filtering method and monitoring server |
US20170201548A1 (en) * | 2016-01-08 | 2017-07-13 | Secureworks Holding Corporation | Systems and Methods for Security Configuration |
-
2017
- 2017-07-28 CN CN201710631040.XA patent/CN107451031A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101355567A (en) * | 2008-09-03 | 2009-01-28 | 中兴通讯股份有限公司 | Method for protecting safety of route-exchanging device central processing unit |
US20170201548A1 (en) * | 2016-01-08 | 2017-07-13 | Secureworks Holding Corporation | Systems and Methods for Security Configuration |
CN106886478A (en) * | 2017-02-22 | 2017-06-23 | 郑州云海信息技术有限公司 | A kind of data filtering method and monitoring server |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106469376B (en) | Risk control method and equipment | |
CN109766210A (en) | Service fusing control method, service fusing control device and server cluster | |
CN106202569A (en) | A kind of cleaning method based on big data quantity | |
CN103425568A (en) | Method and device for processing log information | |
CN104915247A (en) | Real time data calculation method and system | |
CN105610616A (en) | Method and system for performing statistics to obtain average flow of single IP (Internet Protocol) of access network based on ICP (Internet Content Provider) activity | |
CN109146653B (en) | Distributed environment-based accounting daily cutting checking method and device | |
CN108492150B (en) | Method and system for determining entity heat degree | |
DE102012224270A1 (en) | Connect a synchronous cross-domain transaction activity to a single system | |
CN111181800B (en) | Test data processing method and device, electronic equipment and storage medium | |
CN106487601A (en) | Resource monitoring method, apparatus and system | |
CN116049146B (en) | Database fault processing method, device, equipment and storage medium | |
CN106598700A (en) | Second-level high availability realization method of virtual machine based on pacemaker | |
CN108319539A (en) | A kind of method and system generating GPU card slot position information | |
CN110290467A (en) | The acquisition methods and device of dwell point, shopping centre service range, influence factor | |
CN114244718A (en) | Power transmission line communication network equipment management system | |
CN106790409A (en) | Load-balancing method and its system based on the treatment of electric business platform user historical data | |
CN107451031A (en) | A kind of server cpu busy percentage instantaneous peak value filter method and device | |
CN111654417A (en) | Evaluation method and device, storage medium, processor and train | |
CN104581794A (en) | Method and system for middleware business troubleshooting | |
CN106815724A (en) | Charging pile and charging method | |
CN115795403A (en) | Storage equipment slow fault detection method, system and storage medium | |
CN108062395A (en) | A kind of track traffic big data analysis method and system | |
DE102019131038B4 (en) | Detection of event storms | |
CN112308731A (en) | Cloud computing method and system for multitask concurrent processing of acquisition system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171208 |