CN103023701A - Method and device for analyzing performance parameters of network management system - Google Patents
Method and device for analyzing performance parameters of network management system Download PDFInfo
- Publication number
- CN103023701A CN103023701A CN2012105266356A CN201210526635A CN103023701A CN 103023701 A CN103023701 A CN 103023701A CN 2012105266356 A CN2012105266356 A CN 2012105266356A CN 201210526635 A CN201210526635 A CN 201210526635A CN 103023701 A CN103023701 A CN 103023701A
- Authority
- CN
- China
- Prior art keywords
- sampling period
- refresh cycle
- performance parameter
- current sampling
- variable quantity
- 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
Images
Abstract
The invention discloses a method and a device for analyzing performance parameters of a network management system. The method and the device are used for reducing errors produced when the network management system analyzes performance parameters of all communication devices and improving the accuracy of monitoring of performance of all communication devices by the network management system. The method comprises the steps of determining variations of performance parameters in the current sampling period, and determining the number of refresh cycles of a device register contained in the current sampling period, wherein the device register is used for storing statistic values of performance parameters; and according to the determined number of refresh cycles of the device register contained in the current sampling period, the refresh cycles of the device register and variations of performance parameters, calculating the change rate of performance parameters.
Description
Technical field
The present invention relates to communication technical field, relate in particular to a kind of analytical method and device of network management system performance parameter.
Background technology
At present, in communication network, usually use network management system (abbreviation webmaster) that each communication equipment in the communication network is managed concentratedly.As shown in Figure 1, traditional network management system mainly comprises following five functional: configuration management, performance management, alarm management, maintenance management and safety management.
Wherein, performance management refers to that network management system periodically carries out monitoring and the analysis of performance parameter (such as offered load, flow etc.) to its communication equipment of managing, help administrative staff's awareness network operation conditions of current and the past period, for early warning, eliminating and the network optimization of network failure provides foundation.
In traditional network management system, when carrying out the performance parameter analysis, generally be to adopt the data increment of performance parameter in the sampling interval divided by the sampling interval, thus the variation that draws performance parameter in the unit interval, the i.e. rate of change of performance parameter.
Often can occur in the practice, have certain error between the situation of change of the performance parameter of the situation of change of the performance parameter that the network management system analysis draws and communication equipment reality, and along with constantly reducing of sampling interval, this error constantly increases.The performance evaluation curve burr that finally causes the network management system analysis to draw is too many, and with communication equipment practical operation situation grave fault.
Summary of the invention
The invention provides a kind of analytical method and device of network management system performance parameter, error in order to reduce to produce when network management system is analyzed the performance parameter of each communication equipment improves network management system to the accuracy of each communication equipment monitoring performance.
The concrete technical scheme that the embodiment of the invention provides is as follows:
A kind of analytical method of network management system performance parameter comprises:
Determine the variable quantity of performance parameter in the current sampling period, and the number of the refresh cycle of the device register that comprises in definite current sampling period, described device register is used for storing the statistical value of described performance parameter;
According to number, the refresh cycle of device register and the variable quantity of described performance parameter of the described refresh cycle that comprises in the current sampling period of determining, calculate the rate of change of described performance parameter.
A kind of analytical equipment of network management system performance parameter comprises:
Processing unit, for the variable quantity of determining performance parameter in the current sampling period, and the number of the refresh cycle of the device register that comprises in definite current sampling period, described device register is used for storing the statistical value of described performance parameter;
Determining unit is used for number, the refresh cycle of device register and the variable quantity of described performance parameter according to the described refresh cycle that comprises in the current sampling period of determining, calculates the rate of change of described performance parameter.
Based on technique scheme, in the embodiment of the invention, the number of refresh cycle by the device register determining to comprise in the current sampling period, store the statistical value of performance parameter to be analyzed in this device register, behind the variable quantity of determining performance parameter in the current sampling period, number according to the refresh cycle that comprises in the current sampling period of determining, the refresh cycle of device register and the variable quantity of performance parameter, calculate the rate of change of performance parameter, thereby avoided the direct error that adopts sampling period compute performance parameters rate of change to bring in the existing performance parameter analytical method, effectively reduce the error that produces when network management system is analyzed the performance parameter of each communication equipment, improved network management system to the accuracy of each communication equipment monitoring performance.
Description of drawings
Fig. 1 is the fundamental block diagram of existing network management system managing communication devices;
Fig. 2 is to be the sampling process schematic diagram of refresh cycle performance parameter during integral multiple in the sampling period;
Fig. 3 A is not to be the sampling process schematic diagram of refresh cycle integral multiple and sampling period performance parameter during greater than the refresh cycle in the sampling period;
Fig. 3 B is not to be the sampling process schematic diagram of refresh cycle integral multiple and sampling period performance parameter during greater than the refresh cycle in the sampling period;
Fig. 3 C is not to be the sampling process schematic diagram of refresh cycle integral multiple and sampling period performance parameter during greater than the refresh cycle in the sampling period;
Fig. 4 is not to be the sampling process schematic diagram of refresh cycle integral multiple and sampling period performance parameter during less than the refresh cycle in the sampling period;
Fig. 5 is the method detailed schematic flow sheet that embodiment of the invention performance parameter is analyzed;
Fig. 6 is the method flow diagram of specific embodiment of the invention middle port flow analysis;
Fig. 7 A is specific embodiment of the invention middle port flow curve schematic diagram;
Fig. 7 B is actual port flow change rate curve synoptic diagram in the specific embodiment of the invention;
Fig. 7 C is uncorrected port flow change rate curve schematic diagram in the specific embodiment of the invention;
Fig. 7 D is uncorrected port flow change rate curve schematic diagram in the specific embodiment of the invention;
Fig. 8 is the structural representation of the analytical equipment of embodiment of the invention performance parameter.
Embodiment
The inventor finds by analyzing; traditional performance parameter analysis produce the former of error because: the performance data of communication equipment performance parameter is stored in the device register; for the protection to communication equipment; device register can not refresh in real time; but refresh according to certain cycle; when the sampling interval of refresh cycle of device register and network management system is inconsistent, introduced error.
When network management system was opened performance parameter monitoring function, server at first read the performance data of specified performance parameter from communication equipment, and refresh cycle of device register of storing the performance data of this performance parameter.In the sampling period of the performance parameter of the refresh cycle of server comparative apparatus register and server collection communication equipment, there are following several situations:
A, when the sampling period of performance parameter is the integral multiple of refresh cycle of device register, as shown in Figure 2, T1-Tn represents n sampling period, t1, t2 ... expression respectively refreshes constantly, adjacent two time differences of refreshing between the moment are the refresh cycle, as seen, in each sampling period, the refreshing frequency of device register all is identical, wherein, refreshing frequency equals the sampling period of performance parameter divided by the refresh cycle of device register, and the transformation period that the variable quantity (also can be described as the variable quantity of performance parameter in the sampling period) of the performance parameter of adjacent double sampling acquisition this moment is corresponding and the sampling period of server match, and error can not occur.
B, not the integral multiple of the refresh cycle of device register when the sampling period of performance parameter, and the sampling period is during greater than refresh cycle of device register, shown in accompanying drawing 3A, accompanying drawing 3B and accompanying drawing 3C, T1-Tn represents n sampling period, t1, t2 ... expression respectively refreshes constantly, adjacent two time differences of refreshing between the moment are the refresh cycle, and in each sampling period, the refreshing frequency of device register is not identical.T1, interior device register of T2 sampling period refresh 3 times among the accompanying drawing 3A, and device register refreshes 4 times in the T3 sampling period; T1, interior device register of T3 sampling period refresh 3 times among the accompanying drawing 3B, and device register refreshes 4 times in the T2 sampling period; Device register refreshes 4 times in the T1 sampling period shown in the accompanying drawing 3C, and device register refreshes 3 times in T2, T3 sampling period.Two kinds of situations of ubiquity as can be known by analysis: the first situation is that the refreshing frequency of device register just in time is that the sampling period is divided by the merchant of the refresh cycle gained of device register in the sampling period; The second situation is that the refreshing frequency of device register is Duoed 1 time than the first situation in the sampling period, the transformation period that the variable quantity of performance parameter is corresponding in sampling period this moment is actual to multiply by the refresh cycle for the refreshing frequency of device register, not identical with the sampling period of server, therefore can produce error.
C, when sampling period of performance parameter during less than refresh cycle of device register, as shown in Figure 4, T1-Tn represents n sampling period, t1, t2 ... expression respectively refreshes constantly, adjacent two time differences of refreshing between the moment are the refresh cycle, the refreshing frequency of device register is 0 time or 1 time within a sampling period, if the refreshing frequency of device register is 1 time in the sampling period, then the variable quantity of performance parameter is the variable quantity of the performance parameter after device register refreshes once in the sampling period, if the refreshing frequency of device register is 0 time in the sampling period, then the variable quantity of performance parameter is 0 in the sampling period.The refreshing frequency of T1, interior device register of T4 sampling period is 0 time in the accompanying drawing 4, and the refreshing frequency of device register is 1 time in T2, T3 sampling period.As seen, the transformation period corresponding to variable quantity of performance parameter do not conform to the sampling period of server in the sampling period, therefore produced error.
According to above-mentioned analysis, a kind of analytical method of network management system performance parameter is provided in the embodiment of the invention, can improve network management system to the accuracy of the analysis of the performance parameter of communication equipment, performance parameter analytical error.
Below in conjunction with accompanying drawing the preferred embodiment of the present invention is elaborated.
As shown in Figure 5, in the embodiment of the invention, the method detailed flow process that server is analyzed the performance parameter of each communication equipment in the network management system is as follows:
Step 501: determine the variable quantity of performance parameter in the current sampling period, and the number of the refresh cycle of the device register that comprises in definite current sampling period, this device register is used for the statistical value of this performance parameter of storage.
In the invention process, at the variable quantity of determining performance parameter in the current sampling period, and before the number of the refresh cycle of the device register that comprises in definite current sampling period, start-up time, the refresh cycle of obtaining the sampling period of collection of server performance parameter and storing the device register of this performance parameter, and record the performance parameter statistical value of each sampling instant and each sampling instant.
In a specific implementation, take the network management system that adopts Simple Network Management Protocol (SNMP) as example, communication equipment in network management system arranges following management information base (ManagementInformation Base, MIB) node: at communication equipment the MIB node of monitoring for the refresh cycle of the device register of memory property parameter is set; At communication equipment the MIB node that monitoring is stored in the statistical information of the performance parameter in the device register is set; The MIB node that is set the start-up time of monitoring communications equipment and monitors each sampling instant at communication equipment.
After the sampling period of performance parameter is set in network system, startup is during to the sampling task of the performance parameter of communication equipment, can obtain the statistical value of performance parameter of start-up time, refresh cycle, each sampling instant and each sampling instant of device register by each MIB node of above setting.
In the embodiment of the invention, determine the number of refresh cycle of comprising in the current sampling period by refresh cycle of sampling period and device register relatively, specific as follows:
If the sampling period is the integral multiple of refresh cycle, the number of the refresh cycle that comprises in the current sampling period is that the sampling period is divided by the merchant of refresh cycle gained;
If the sampling period is not the integral multiple of refresh cycle, and the sampling period is less than the refresh cycle, whether the variable quantity of judging the performance parameter in the current sampling period equals null value, if equal, the number of determining refresh cycle of comprising in the current sampling period is zero, otherwise, determine that the number of refresh cycle of comprising in the current sampling period is 1;
If the sampling period is not the integral multiple of refresh cycle, and the sampling period greater than the refresh cycle, according to sampling period, refresh cycle, start-up time, current sampling instant and last sampling instant, determine the number of refresh cycle of comprising in the current sampling period.
Wherein, when the number of the refresh cycle of determining to comprise in the current sampling period was zero, the rate of change of retention parameter was constant, was about to the performance parameter variations rate of performance parameter variations rate corresponding to last sampling period as the current sampling period.
In a specific implementation, not the integral multiple of refresh cycle in the sampling period, and in the situation of sampling period greater than the refresh cycle, determine being implemented as follows of number of refresh cycle of comprising in the current sampling period: adopt formula T/t+y to calculate the number of the refresh cycle that comprises in the current sampling period, T represents the sampling period, t represents the refresh cycle, and y represents corrected parameter, and "/" expression is divided exactly; Wherein, as { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]＞0 o'clock, y equals 1; As { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]≤0 o'clock, y equals 0, M
0The start-up time of indication equipment register, M
iRepresent current sampling instant, M
I-1Last sampling instant, " % " represents remainder.
In the embodiment of the invention, according to the statistical value of the performance parameter of the statistical value of the performance parameter of current sampling instant and a upper sampling instant, determine the variable quantity of the performance parameter in the current sampling period.Particularly, the statistical value of the performance parameter of current sampling instant deducts the statistical value of the performance parameter of a sampling instant, can obtain the variable quantity of the performance parameter in the current sampling period.
Step 502: according to number, the refresh cycle of device register and the variable quantity of performance parameter of the refresh cycle that comprises in the current sampling period of determining, the rate of change of compute performance parameters.
Particularly, adopt formula Δ x
i÷ (k * t) calculates the rate of change of performance parameter, wherein, and Δ x
iThe variable quantity that represents performance parameter in the current sampling period, k represent the number of refresh cycle of comprising in the current sampling period, and t represents the refresh cycle.
In the practical application, the mapping program of network management system performance monitoring is drawn the performance parameter variations rate in current sampling period in current sampling instant, repeat the process of the performance parameter variations rate in above-mentioned current sampling period of calculating, when the performance parameter acquisition tasks finishes, can draw out the curve of the Changing Pattern of this performance parameter of reflection.
Below by a specific embodiment process of carrying out the performance parameter analysis that provides in the embodiment of the invention is specifically described, the port flow take the performance parameter of server monitoring as communication equipment in this specific embodiment is as example.
At first, at the following MIB node of arranging of communication equipment:
The MIB node of refresh cycle of device register of the traffic statistics information of each port of monitoring communications equipment is set;
The MIB node of the traffic statistics information of each port of monitoring communications equipment is set, adopts x in this specific embodiment
iThe traffic statistics value that the expression server obtains adopts Δ x
iThe variable quantity that represents the double traffic statistics value of obtaining;
The MIB node of the sampling instant of monitoring communications device start time and monitoring server is set, adopts M in this specific embodiment
0The start-up time (being the start-up time of device register) of expression communication equipment, M
iGet access to the sampling instant of current sampling on the expression server.
Secondly, adopt T to represent the sampling period that arranges on the network management system in this specific embodiment, adopt a
iThe variation of expression port flow unit interval, the i.e. rate of change of port flow.
As shown in Figure 6, to carry out the specific implementation process that port flow analyzes as follows for network management system:
Step 601: after in network management system, sampling period T being set, start the sampling task of communication equipment port flow, the refresh cycle t of fetch equipment register-stored port flow, the statistical value x of current port flow
i, M start-up time of device register
0, current sampling instant M
i
Step 602: compare the size of the refresh cycle t of sampling period T and device register, if T 〉=t, execution in step 603, otherwise, execution in step 606;
Step 603: judge whether sampling period T can be divided exactly by the refresh cycle t of device register, if, execution in step 604, otherwise, execution in step 605;
Step 604: according to formula a
i=Δ x
i÷ T calculates the rate of change of port flow, Δ x
iRepresent the variable quantity of flow in the current sampling period, then execution in step 607;
Step 605: according to formula a
i=Δ x
i÷ [(T/t+y) * t] calculates the rate of change of port flow, then turns execution in step 607, and wherein, "/" expression is divided exactly, and y represents corrected parameter, as { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]＞0 o'clock, y equals 1; As { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]≤0 o'clock, y equals 0, M
0The start-up time of indication equipment register, M
iRepresent current sampling instant, M
I-1Last sampling instant, " % " represents remainder;
Step 606: judge Δ x
iWhether equal zero, if equal zero, the last sampling period is calculated the rate of change of the port flow that obtains as the rate of change of the port flow in current sampling period, then execution in step 607; If be not equal to zero, adopt formula a
i=Δ x
i÷ t calculates the rate of change of the port flow in current sampling period, and then execution in step 607;
Step 607: the mapping program of the performance monitoring of network management system is drawn the rate of change of the port flow in current sampling period in current sampling instant, when the next sampling period arrives, repeat above-mentioned steps 601-step 606, and the rate of change of the port flow that obtains of draw calculation, until acquisition tasks finishes, can obtain the curve that reflects that the communication equipment port flow changes.
The port flow of supposing this specific embodiment middle port communication equipment at the uniform velocity increases, and the change curve of its flow is shown in accompanying drawing 7A, and the change rate curve of its flow is shown in accompanying drawing 7B.
For the situation of sampling period T more than or equal to refresh cycle t, after network management system is analyzed this port flow, if sampling period T is the integral multiple of refresh cycle t, then need not to carry out any correction and can reach curve shown in the accompanying drawing 7B; If sampling period T is not the integral multiple of refresh cycle t, before not revising, can there be fluctuation to a certain degree in the change rate curve of its flow shown in accompanying drawing 7D, after the method that adopts the specific embodiment of the invention to provide is revised, just can reach the effect shown in the accompanying drawing 7B.
For the situation of sampling period T less than refresh cycle t, before not revising, the change rate curve of its flow can not accurately reflect the actual change of flow shown in accompanying drawing 7C, revise through the method that the specific embodiment of the invention provides, just can reach the effect shown in the accompanying drawing 7B.
Based on same inventive concept, the embodiment of the invention also provides a kind of analytical equipment of network management system performance parameter, and the implementation of this device can referring to the description of said method, repeat part and repeat no more, as shown in Figure 8, this device mainly comprises with lower unit:
Determining unit 802 is used for number, the refresh cycle of device register and the variable quantity of performance parameter according to the refresh cycle that comprises in the current sampling period of determining, the rate of change of compute performance parameters.
Wherein, also comprise acquiring unit 803, be used for start-up time, the refresh cycle obtain the sampling period of collection of server performance parameter and store the device register of this performance parameter, and record the statistical value of the performance parameter of each sampling instant and each sampling instant.
Wherein, processing unit 801 specifically is used for:
If the sampling period is the integral multiple of refresh cycle, the number of the refresh cycle that comprises in the current sampling period is that the sampling period is divided by the merchant of refresh cycle gained;
If the sampling period is not the integral multiple of refresh cycle, and the sampling period is less than the refresh cycle, whether the variable quantity of judging the performance parameter in the current sampling period equals null value, if equal, the number of determining refresh cycle of comprising in the current sampling period is zero, otherwise, determine that the number of refresh cycle of comprising in the current sampling period is 1;
If the sampling period is not the integral multiple of refresh cycle, and the sampling period greater than the refresh cycle, according to sampling period, refresh cycle, start-up time, current sampling instant and last sampling instant, determine the number of refresh cycle of comprising in the current sampling period.
In a specific implementation, processing unit 801 specifically is used for:
If the sampling period is not the integral multiple of refresh cycle, and the sampling period greater than the refresh cycle, adopt formula T/t+y to calculate the number of the refresh cycle that comprises in the current sampling period, T represents the sampling period, t represents the refresh cycle, and y represents corrected parameter, and "/" expression is divided exactly;
Wherein, as { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]＞0 o'clock, y equals 1; As { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]≤0 o'clock, y equals 0, M
0The start-up time of indication equipment register, M
iRepresent current sampling instant, M
I-1Last sampling instant, " % " represents remainder.
Wherein, processing unit 801 specifically is used for:
According to the statistical value of the performance parameter of the statistical value of the performance parameter of current sampling instant and a upper sampling instant, determine the variable quantity of the performance parameter in the current sampling period.
Wherein, determining unit 802 specifically is used for:
Adopt formula Δ x
i÷ (k * t) calculates the rate of change of performance parameter, wherein, and Δ x
iThe variable quantity that represents performance parameter in the current sampling period, k represent the number of refresh cycle of comprising in the current sampling period, and t represents the refresh cycle.
Based on technique scheme, in the embodiment of the invention, the number of refresh cycle by the device register determining to comprise in the current sampling period, storage performance parameter statistical value to be analyzed in this device register, behind the variable quantity of determining performance parameter in the current sampling period, number according to the refresh cycle that comprises in the current sampling period of determining, the refresh cycle of device register and the variable quantity of performance parameter, calculate the rate of change of performance parameter, thereby avoided the direct error that adopts sampling period compute performance parameters rate of change to bring in the existing performance parameter analytical method, effectively reduce the error that produces when network management system is analyzed the performance parameter of each communication equipment, improved network management system to the accuracy of each communication equipment monitoring performance.
And, the performance parameter analytical method that the embodiment of the invention provides is wireless to take device resource and bandwidth, and can have higher accuracy by guaranteed performance parameter analysis result, the problems such as burr, periodic swinging occur in the result curve of having avoided adopting existing performance parameter analytical method to cause.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these are revised and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also is intended to comprise these changes and modification interior.
Claims (12)
1. the analytical method of a network management system performance parameter is characterized in that, comprising:
Determine the variable quantity of performance parameter in the current sampling period, and the number of the refresh cycle of the device register that comprises in definite current sampling period, described device register is used for storing the statistical value of described performance parameter;
According to number, the refresh cycle of device register and the variable quantity of described performance parameter of the described refresh cycle that comprises in the current sampling period of determining, calculate the rate of change of described performance parameter.
2. the method for claim 1 is characterized in that, determines the variable quantity of performance parameter in the current sampling period, and before the number of the refresh cycle of the device register that comprises in definite current sampling period, also comprises:
Start-up time, the refresh cycle of obtaining the sampling period of collection of server performance parameter and storing the device register of described performance parameter, and record the statistical value of the performance parameter of each sampling instant and each sampling instant.
3. method as claimed in claim 2 is characterized in that, determines the number of described refresh cycle of comprising in the current sampling period, comprising:
If the described sampling period is the integral multiple of described refresh cycle, the number of the described refresh cycle that comprises in the current sampling period is that the sampling period is divided by the merchant of described refresh cycle gained;
If the described sampling period is not the integral multiple of described refresh cycle, and the described sampling period is less than the described refresh cycle, whether the variable quantity of judging the performance parameter in the described current sampling period equals null value, if equal, the number of determining described refresh cycle of comprising in the current sampling period is zero, otherwise, determine that the number of described refresh cycle of comprising in the current sampling period is 1;
If the described sampling period is not the integral multiple of described refresh cycle, and the described sampling period is greater than the described refresh cycle, according to described sampling period, described refresh cycle, described start-up time, current sampling instant and last sampling instant, determine the number of refresh cycle of comprising in the current sampling period.
4. method as claimed in claim 3, it is characterized in that, according to described sampling period, described refresh cycle, described start-up time, current sampling instant and last sampling instant, determine the number of refresh cycle of comprising in the current sampling period, specifically comprise:
Adopt formula T/t+y to calculate the number of the refresh cycle that comprises in the current sampling period, T represents the sampling period, and t represents the refresh cycle, and y represents corrected parameter, and "/" expression is divided exactly;
Wherein, as { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]＞0 o'clock, y equals 1; As { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]≤0 o'clock, y equals 0, M
0The start-up time of indication equipment register, M
iRepresent current sampling instant, M
I-1Last sampling instant, " % " represents remainder.
5. such as claim 2,3 or 4 each described methods, it is characterized in that, determine the variable quantity of the performance parameter in the current sampling period, comprising:
According to the statistical value of the performance parameter of the statistical value of the performance parameter of current sampling instant and a upper sampling instant, determine the variable quantity of the performance parameter in the current sampling period.
6. method as claimed in claim 5 is characterized in that, calculates the rate of change of described performance parameter, comprising:
Adopt formula Δ x
i÷ (k * t) calculates the rate of change of performance parameter, wherein, and Δ x
iThe variable quantity that represents performance parameter in the current sampling period, k represent the number of refresh cycle of comprising in the current sampling period, and t represents the refresh cycle.
7. the analytical equipment of a network management system performance parameter is characterized in that, comprising:
Processing unit, for the variable quantity of determining performance parameter in the current sampling period, and the number of the refresh cycle of the device register that comprises in definite current sampling period, described device register is used for storing the statistical value of described performance parameter;
Determining unit is used for number, the refresh cycle of device register and the variable quantity of described performance parameter according to the described refresh cycle that comprises in the current sampling period of determining, calculates the rate of change of described performance parameter.
8. device as claimed in claim 7, it is characterized in that, also comprise acquiring unit, be used for start-up time, the refresh cycle obtain the sampling period of collection of server performance parameter and store the device register of described performance parameter, and record the statistical value of the performance parameter of each sampling instant and each sampling instant.
9. device as claimed in claim 8 is characterized in that, described processing unit specifically is used for:
If the described sampling period is the integral multiple of described refresh cycle, the number of the described refresh cycle that comprises in the current sampling period is that the sampling period is divided by the merchant of described refresh cycle gained;
If the described sampling period is not the integral multiple of described refresh cycle, and the described sampling period is less than the described refresh cycle, whether the variable quantity of judging the performance parameter in the described current sampling period equals null value, if equal, the number of determining described refresh cycle of comprising in the current sampling period is zero, otherwise, determine that the number of described refresh cycle of comprising in the current sampling period is 1;
If the described sampling period is not the integral multiple of described refresh cycle, and the described sampling period is greater than the described refresh cycle, according to described sampling period, described refresh cycle, described start-up time, current sampling instant and last sampling instant, determine the number of refresh cycle of comprising in the current sampling period.
10. device as claimed in claim 9 is characterized in that, described processing unit specifically is used for:
If the described sampling period is not the integral multiple of described refresh cycle, and the described sampling period greater than the described refresh cycle, adopt formula T/t+y to calculate the number of the refresh cycle that comprises in the current sampling period, T represents the sampling period, t represents the refresh cycle, and y represents corrected parameter, and "/" expression is divided exactly;
Wherein, as { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]＞0 o'clock, y equals 1; As { [(the M that satisfies condition
I-1-M
0) %t]-[(M
i-M
0) %t]≤0 o'clock, y equals 0, M
0The start-up time of indication equipment register, M
iRepresent current sampling instant, M
I-1Last sampling instant, " % " represents remainder.
11. such as claim 8,9 or 10 described devices, it is characterized in that described processing unit specifically is used for:
According to the statistical value of the performance parameter of current sampling instant and the performance parameter statistical value of a upper sampling instant, determine the variable quantity of the performance parameter in the current sampling period.
12. device as claimed in claim 11 is characterized in that, described determining unit specifically is used for:
Adopt formula Δ x
i÷ (k * t) calculates the rate of change of performance parameter, wherein, and Δ x
iThe variable quantity that represents performance parameter in the current sampling period, k represent the number of refresh cycle of comprising in the current sampling period, and t represents the refresh cycle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210526635.6A CN103023701B (en) | 2012-12-07 | 2012-12-07 | The analytical method of performance parameter and device in network management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210526635.6A CN103023701B (en) | 2012-12-07 | 2012-12-07 | The analytical method of performance parameter and device in network management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103023701A true CN103023701A (en) | 2013-04-03 |
| CN103023701B CN103023701B (en) | 2015-08-05 |
Family
ID=47971855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210526635.6A Active CN103023701B (en) | 2012-12-07 | 2012-12-07 | The analytical method of performance parameter and device in network management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103023701B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468782A (en) * | 2014-12-05 | 2015-03-25 | 北京国双科技有限公司 | Network data obtaining method and device |
| CN106326068A (en) * | 2016-08-17 | 2017-01-11 | 东软集团股份有限公司 | Resource index monitoring method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6219705B1 (en) * | 1998-11-12 | 2001-04-17 | Paradyne Corporation | System and method of collecting and maintaining historical top communicator information on a communication device |
| CN101051964A (en) * | 2007-05-21 | 2007-10-10 | 杭州华三通信技术有限公司 | Method and system and device for collecting flow data |
| CN101237352A (en) * | 2008-03-05 | 2008-08-06 | 杭州华三通信技术有限公司 | Traffic data collection method, system and device |
-
2012
- 2012-12-07 CN CN201210526635.6A patent/CN103023701B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6219705B1 (en) * | 1998-11-12 | 2001-04-17 | Paradyne Corporation | System and method of collecting and maintaining historical top communicator information on a communication device |
| CN101051964A (en) * | 2007-05-21 | 2007-10-10 | 杭州华三通信技术有限公司 | Method and system and device for collecting flow data |
| CN101237352A (en) * | 2008-03-05 | 2008-08-06 | 杭州华三通信技术有限公司 | Traffic data collection method, system and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104468782A (en) * | 2014-12-05 | 2015-03-25 | 北京国双科技有限公司 | Network data obtaining method and device |
| CN104468782B (en) * | 2014-12-05 | 2017-11-14 | 北京国双科技有限公司 | Network Data Capture method and device |
| CN106326068A (en) * | 2016-08-17 | 2017-01-11 | 东软集团股份有限公司 | Resource index monitoring method and device |
| CN106326068B (en) * | 2016-08-17 | 2019-01-25 | 东软集团股份有限公司 | The monitoring method and device of resource metrics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103023701B (en) | 2015-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8234229B2 (en) | Method and apparatus for prediction of computer system performance based on types and numbers of active devices | |
| CN103117879B (en) | A kind of computer hardware operational factor network monitoring system | |
| CN103064778B (en) | A kind of server performance method of testing, Apparatus and system | |
| CN109344178A (en) | A kind of data sheet real-time statistical method, device, equipment and readable storage medium storing program for executing | |
| CN112751726B (en) | Data processing method and device, electronic equipment and storage medium | |
| US20180039895A1 (en) | Data predicting method and apparatus | |
| CN103714004A (en) | JVM online memory leak analysis method and system | |
| CN104407688A (en) | Virtualized cloud platform energy consumption measurement method and system based on tree regression | |
| CN100484032C (en) | Method for processing abnormal overturn of host machine | |
| CN104820663A (en) | Method and device for discovering low performance structural query language (SQL) statements, and method and device for forecasting SQL statement performance | |
| CN103401881A (en) | Data collection system and method based on intelligent instrument | |
| JP2019095822A (en) | Parameter setting method, data analysis device, data analysis system, and program | |
| CN113986595A (en) | Abnormity positioning method and device | |
| CN103580924A (en) | Fault location method, device and system | |
| CN108537243A (en) | A kind of violation alarm method and device | |
| CN112005207A (en) | Creating statistical analysis of data for transmission to a server | |
| CN105183627A (en) | Server performance prediction method and system | |
| CN103023701A (en) | Method and device for analyzing performance parameters of network management system | |
| CN109614289A (en) | A kind of memory node monitoring method, system, equipment and computer storage medium | |
| KR102059112B1 (en) | IoT STREAM DATA QUALITY MEASUREMENT INDICATORS AND PROFILING METHOD FOR INTERNET OF THINGS AND SYSTEM THEREFORE | |
| CN115357451A (en) | Real-time monitoring and alarming device and method for dynamic power consumption of server | |
| CN102487334B (en) | Method and device for determining associated alarm information | |
| CN111162964B (en) | Intelligent station message integrity analysis method and system | |
| CN106933718A (en) | Method for monitoring performance and device | |
| CN111650909A (en) | Intelligent control system and method for sewage treatment process, readable storage medium and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |