CN101557321A - Method for monitoring bandwidth of interface in distributed system and device - Google Patents
Method for monitoring bandwidth of interface in distributed system and device Download PDFInfo
- Publication number
- CN101557321A CN101557321A CNA200910203429XA CN200910203429A CN101557321A CN 101557321 A CN101557321 A CN 101557321A CN A200910203429X A CNA200910203429X A CN A200910203429XA CN 200910203429 A CN200910203429 A CN 200910203429A CN 101557321 A CN101557321 A CN 101557321A
- Authority
- CN
- China
- Prior art keywords
- interface
- statistical
- primary processor
- processor
- distributed system
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method for monitoring bandwidth of interfaces in a distributed system and a device. The distributed system comprises a master processor and a plurality of slave processors. The method comprises the following steps of: setting sampling intervals and statistical intervals by the master processor and collecting statistical information from the slave processors according to the set sampling intervals in a timing mode; obtaining statistical data of all the interfaces by the slave processors and converting the statistical data into incremental data and reporting the incremental data to the master processor; and carrying out statistical processing to the received incremental data by the master processor according to the set statistical intervals in a timing mode, and calculating the utilization ratio of bandwidth of the interfaces according to the result data of statistical processing so as to monitor the bandwidth of the interfaces. The use of the invention can carry out analysis to the utilization ratio of bandwidth of the interfaces in the distributed system in a more accurate mode, and better meets the difference of upper services of the distributed system to the statistical requirements by setting the statistical intervals.
Description
Technical field
The present invention relates to the data communication field, relate in particular to the method and the device of monitoring bandwidth of interface in a kind of distributed system.
Background technology
In the data communication field, switch, router etc. has become the fastest network equipment of application popularization, has network management more easily so and have higher internet security one of the condition that necessitates in network.
Nowadays, consideration based on performance and efficient, the many designs of a lot of high-end devices based on distributed structure/architecture, based on distributed architecture design the time, how more reasonable more accurate the carry out statistics of interface flow and the calculating of bandwidth availability ratio? this just must consider the characteristic of distributed system.
Several shortcomings that distributed system exists:
Relate to the data sync between a plurality of CPU,, caused extra CPU burden in order to guarantee high reliability;
The primary processor of distributed system with may adopt different CPU from processor, when this also just requires to do some global calculation on primary processor, need to consider clock synchronization and the problem brought;
When processor is had much to do (under attack or network concussion), may cause primary processor and losing from message between processor, and then may cause further unusual generation, asynchronous as: data management, there is deviation in primary processor and may brings problems such as uncertain to network management in global calculation.
In sum, in distributed system how better the docking port bandwidth statistics of carrying out the monitoring of bandwidth and flow be to need the problem that solves.
Summary of the invention
Technical problem to be solved by this invention provides the method and the device of monitoring bandwidth of interface in a kind of distributed system, can analyze interface bandwidth utilance in the distributed system more accurately, by statistical interval is set, better met the otherness of the upper-layer service of distributed system to statistical demand.
In order to address the above problem, the invention provides the device of monitoring bandwidth of interface in a kind of distributed system, comprising: the interface management module, interface statistics module and driving processing module, wherein,
Described interface management module is used to be provided with statistical interval and after the sampling interval, the message that will comprise statistical interval sends to described interface statistics module, and the message that will comprise the sampling interval sends to described driving processing module; The described result who calculates who receives described interface statistics module transmission comes monitoring bandwidth of interface;
Described interface statistics module, be used to receive the message that comprises incremental data that described driving processing module sends, and the described message that comprises statistical interval that sends according to the described interface management module that receives, regularly the described incremental data that receives is carried out statistical disposition, result data according to statistical disposition calculates the interface bandwidth utilance, and the result who calculates is sent to described interface management module;
Described driving processing module is used for the described message that comprises the sampling interval according to the described interface management module transmission that receives, and regularly obtains the statistics of each interface, is converted to incremental data; The message that will comprise incremental data sends to described interface statistics module.
The present invention also provides the method for monitoring bandwidth of interface in a kind of distributed system, and this distributed system comprises primary processor and a plurality of from processor, comprising:
Described primary processor is provided with sampling interval and statistical interval, collects statistical information to described from processor according to the described sampling interval timing that is provided with;
Describedly obtain the statistics of each interface, be converted to incremental data and report incremental data to described primary processor from processor;
Described primary processor regularly carries out statistical disposition to the described incremental data that receives according to the described statistical interval that is provided with, and comes monitoring bandwidth of interface according to the result data calculating interface bandwidth utilance of statistical disposition.
Compared with prior art, use the present invention, can analyze interface bandwidth utilance in the distributed system more accurately,, better met the otherness of the upper-layer service of distributed system statistical demand by statistical interval is set; The reorientation in sampling interval, well consider the load problem of distributed system CPU, satisfy the needs of real-time statistics simultaneously, more reasonably all kinds of statistical informations have been added up on primary processor, made things convenient for the network management personnel that distributed system is managed and safeguards simultaneously.
Description of drawings
Fig. 1 is the schematic diagram in statistical interval and sampling interval;
Fig. 2 is the structural representation of the device of monitoring bandwidth of interface in the distributed system of the present invention;
Fig. 3 is the flow chart of the method for monitoring bandwidth of interface in the distributed system of the present invention.
Embodiment
The invention will be further described below in conjunction with the drawings and specific embodiments.
In distributed system of the present invention, generally include primary processor and a plurality of from processor, also comprise primary processor and the equipment that carries out collaborative work from processor, wherein,
Primary processor: be used to collect each from the original data on flows that processor reports, carry out the calculating of interface bandwidth utilance according to these data, and the result that will obtain store buffer area into;
From processor: be used for the converting flow packet,, report primary processor with original flow data collector, preliminary processing;
Collect the original data on flows that each reports from processor at primary processor, when carrying out bandwidth monitor, use following term usually, as shown in Figure 1:
Statistical interval: the original data on flows of primary processor to obtaining, the time period of the calculating interface bandwidth utilance of setting;
Sampling interval: primary processor and from processor time of interaction data under normal circumstances.The time interval that original data on flows is collected in i.e. timing;
Sample frequency: the number of times of actual samples in statistical interval;
Statistics duration: actual statistics duration; Wherein, under the normal condition be sampling interval * sample frequency; Under the abnormal conditions be: the primary processor statistical interval begin the time be carved into moment of current calculating.
Main design of the present invention is: according to the characteristic of distributed system, from processor according to the statistics of sample frequency timing acquiring increment and send to primary processor, primary processor is then according to the statistics of collecting, with statistical interval and sampling interval be benchmark, primary processor carries out the real-time calculating of the interface bandwidth utilance of dynamic real-time according to traffic statistics.Consider the busy extent of each processor and the situation of message time-delay simultaneously,, make the calculating of measurement period inner joint bandwidth availability ratio more rationalize sample frequency and the absolute method of dynamically considering of adding up duration as the statistics duration.
As shown in Figure 2, the device of monitoring bandwidth of interface in the distributed system of the present invention is used to calculate the interface bandwidth utilance and carries out traffic statistics, mainly comprises: the interface management module, and interface statistics module and driving processing module, wherein,
The interface management module, be used to be provided with statistical interval and sampling interval, to comprise statistical interval after being provided with, statistics and empty, add up and open and add up the message of closing and send to described interface statistics module, the message that will comprise the sampling interval after being provided with sends to the driving processing module; The described result who calculates who receives described interface statistics module transmission comes monitoring bandwidth of interface, and the result that this calculates is stored;
The interface management module also is used to provide the tissue and the alarming processing of various data demonstrations; Be responsible for the hardware interface entity to the management between the software logic mapping.
The size that the interface management module is provided with the sampling interval largely is subject to selected performance of processors, can adjust primary processor dynamically and from the mutual frequency of processor according to the load-bearing of processor, and the result of calculation of bandwidth availability ratio can not be affected.
The traffic performance that the interface management module is enabled according to the interface upper strata can be adjusted statistical interval at any time, satisfies diversified business to the different requirement of statistics susceptibility demand.
The interface management module can be provided with the threshold threshold of interface bandwidth utilance; as burst flow or when under attack, if the interface bandwidth utilance is then sent alarm operation greater than the threshold threshold that is provided with; perhaps down falls interface, to arrive the purpose of the equipment of protecting.
The interface statistics module, be used to receive the message that comprises incremental data that described driving processing module sends, receive that described that described interface management module sends comprises statistical interval, statistics empties, adds up and open and add up the message of closing, and regularly the described incremental data that receives is carried out statistical disposition according to this message, carry out the calculating of interface bandwidth utilance according to the result data of statistical disposition, the result who calculates is sent to described interface management module;
When unusual (busy or message delay) takes place when, described interface statistics module is no longer considered measurement period with the employing frequency, absolute duration in the time of can using primary processor to collect data, carry out the calculating of interface bandwidth utilance, more can react actual conditions and improve the real-time accuracy of calculating.
Drive processing module (being operated in from processor), be used to receive the described message that comprises the sampling interval that described interface management module sends, regularly obtain the statistics of each interface, be converted to incremental data according to this message; The message that will comprise incremental data sends to the interface statistics module.
Drive the incremental data after processing module is changed, better assurance is provided for the accuracy and the real-time of the calculating of interface bandwidth utilance by using this incremental data.
As shown in Figure 3, the method for monitoring bandwidth of interface in the distributed system of the present invention, this distributed system comprise primary processor and a plurality of from processor, may further comprise the steps:
Step 310, primary processor are opened the statistical function switch;
Step 320, primary processor are provided with sampling interval and statistical interval;
The sampling interval of described primary processor setting is that the interface class at distributed system is provided with, and adjusts primary processor dynamically and from the mutual frequency of processor according to the load of processor.
The statistical interval of described primary processor setting is to be provided with at individual interface, and the traffic performance of being enabled according to the interface upper strata is provided with statistical interval.
Step 330, primary processor according to the described sampling interval that is provided with regularly to collecting statistical information from processor; Obtain the statistics of each interface from processor, be converted to incremental data and report incremental data to primary processor;
Wherein,, primary processor can be decomposed into route computation processor and management processor, further improve the ability of Distributed Calculation for function complexity or the higher equipment of requirement.
Step 340, primary processor regularly carry out statistical disposition to the described incremental data that receives according to the described statistical interval that is provided with, and come monitoring bandwidth of interface according to the result data calculating interface bandwidth utilance of statistical disposition, and the result of calculation that obtains is stored;
Primary processor is by OAM order or snmp management software, carries out the calculating of interface bandwidth utilance and carries out the inquiry of traffic statistics data.
Primary processor is when carrying out the calculating of interface bandwidth utilance, and the computing formula of interface bandwidth utilance can be following situation:
When the normal mild work of system, computing formula can be statistics duration=sampling interval * sample frequency;
When system takes place unusual and during the network concussion (judge that sampling interval then whether receive the reporting information of other processors):
Computing formula can for: the statistics duration=current calculating the moment point-statistical interval point zero hour;
Receipts (sending out) actual in interface rate=statistical interval are wrapped number/statistics duration.
Wherein, the interface bandwidth utilance is the interface utilance in the statistical interval.Be calculated as prerequisite with interface rate.
Interface bandwidth utilance=interface rate/interface bandwidth.
When described distributed system takes place when unusual, described primary processor is that the absolute duration when collecting data by adopting carries out the calculating of interface bandwidth utilance according to the calculating that the result data of statistical disposition carries out the interface bandwidth utilance.
Step 350, primary processor are according to the result who obtains is carried out application corresponding and processing.
Described primary processor is provided with the threshold threshold of interface bandwidth utilance, when described distributed system has burst flow or when under attack, if the interface bandwidth utilance that described primary processor judgement calculates greater than the threshold threshold of the described interface bandwidth utilance that is provided with, is then sent alarm or is carried out the operation that down falls interface.
The above; only for the preferable embodiment of the present invention, but protection scope of the present invention is not limited thereto, and anyly is familiar with the people of this technology in the disclosed technical scope of the present invention; the variation that can expect easily or replacement all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claim.
Claims (10)
1, the device of monitoring bandwidth of interface in a kind of distributed system is characterized in that, comprising:
The interface management module, interface statistics module and driving processing module, wherein,
Described interface management module is used to be provided with statistical interval and after the sampling interval, the message that will comprise statistical interval sends to described interface statistics module, and the message that will comprise the sampling interval sends to described driving processing module; The described result who calculates who receives described interface statistics module transmission comes monitoring bandwidth of interface;
Described interface statistics module, be used to receive the message that comprises incremental data that described driving processing module sends, and the described message that comprises statistical interval that sends according to the described interface management module that receives, regularly the described incremental data that receives is carried out statistical disposition, result data according to statistical disposition calculates the interface bandwidth utilance, and the result who calculates is sent to described interface management module;
Described driving processing module is used for the described message that comprises the sampling interval according to the described interface management module transmission that receives, and regularly obtains the statistics of each interface, is converted to incremental data; The message that will comprise incremental data sends to described interface statistics module.
2, device as claimed in claim 1 is characterized in that,
It is to adjust primary processor dynamically and from the mutual frequency of processor according to the load of processor that described interface management module is provided with the sampling interval.
3, device as claimed in claim 1 is characterized in that,
It is according to the traffic performance that the interface upper strata is enabled statistical interval to be set that described interface management module is provided with statistical interval.
4, device as claimed in claim 1 is characterized in that,
Described interface management module also is used to be provided with the threshold threshold of interface bandwidth utilance, as burst flow or when under attack, if the interface bandwidth utilance that judgement obtains, is then sent alarm greater than the threshold threshold of the described interface bandwidth utilance that is provided with or is carried out the operation that down falls interface.
5, device as claimed in claim 1 is characterized in that,
When described distributed system takes place when unusual, the calculating that described interface statistics module is carried out the interface bandwidth utilance according to the result data of statistical disposition is the absolute duration when adopting primary processor to collect data, carries out the calculating of interface bandwidth utilance.
6, the method for monitoring bandwidth of interface in a kind of distributed system, this distributed system comprises primary processor and a plurality of from processor, it is characterized in that, comprising:
Described primary processor is provided with sampling interval and statistical interval, collects statistical information to described from processor according to the described sampling interval timing that is provided with;
Describedly obtain the statistics of each interface, be converted to incremental data and report incremental data to described primary processor from processor;
Described primary processor regularly carries out statistical disposition to the described incremental data that receives according to the described statistical interval that is provided with, and comes monitoring bandwidth of interface according to the result data calculating interface bandwidth utilance of statistical disposition.
7, method as claimed in claim 6 is characterized in that,
The sampling interval of described primary processor setting is that the interface class at distributed system is provided with, and adjusts primary processor dynamically and from the mutual frequency of processor according to the load of processor.
8, method as claimed in claim 6 is characterized in that,
The statistical interval of described primary processor setting is to be provided with at individual interface, and the traffic performance of being enabled according to the interface upper strata is provided with statistical interval.
9, method as claimed in claim 6 is characterized in that,
It is further comprising the steps of,
Described primary processor is provided with the threshold threshold of interface bandwidth utilance, when described distributed system has burst flow or when under attack, if the interface bandwidth utilance that described primary processor judgement calculates greater than the threshold threshold of the described interface bandwidth utilance that is provided with, is then sent alarm or is carried out the operation that down falls interface.
10, method as claimed in claim 6 is characterized in that,
When described distributed system takes place when unusual, the calculating that described primary processor carries out the interface bandwidth utilance according to the result data of statistical disposition is by adopting the absolute duration when collecting data, carrying out the calculating of interface bandwidth utilance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910203429XA CN101557321B (en) | 2009-05-21 | 2009-05-21 | Method for monitoring bandwidth of interface in distributed system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910203429XA CN101557321B (en) | 2009-05-21 | 2009-05-21 | Method for monitoring bandwidth of interface in distributed system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101557321A true CN101557321A (en) | 2009-10-14 |
| CN101557321B CN101557321B (en) | 2011-09-21 |
Family
ID=41175275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910203429XA Active CN101557321B (en) | 2009-05-21 | 2009-05-21 | Method for monitoring bandwidth of interface in distributed system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101557321B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977130A (en) * | 2010-10-19 | 2011-02-16 | 中兴通讯股份有限公司 | Method and device for monitoring bandwidth of Ethernet port in real time |
| CN102158391A (en) * | 2010-11-12 | 2011-08-17 | 华为数字技术有限公司 | Method and device for adjusting link bandwidth |
| CN102780563A (en) * | 2011-05-12 | 2012-11-14 | 国基电子（上海）有限公司 | Multi-core network device and power saving method thereof |
| CN113468234A (en) * | 2021-05-31 | 2021-10-01 | 济南浪潮数据技术有限公司 | Monitoring data processing method, device and system and storage medium |
| CN113794655A (en) * | 2020-07-17 | 2021-12-14 | 北京京东尚科信息技术有限公司 | Flow monitoring method and device, computer storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101282305B (en) * | 2008-05-22 | 2010-07-21 | 杭州华三通信技术有限公司 | Bandwidth control method for distributed system as well as service plate |
-
2009
- 2009-05-21 CN CN200910203429XA patent/CN101557321B/en active Active
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101977130A (en) * | 2010-10-19 | 2011-02-16 | 中兴通讯股份有限公司 | Method and device for monitoring bandwidth of Ethernet port in real time |
| CN102158391A (en) * | 2010-11-12 | 2011-08-17 | 华为数字技术有限公司 | Method and device for adjusting link bandwidth |
| CN102780563A (en) * | 2011-05-12 | 2012-11-14 | 国基电子（上海）有限公司 | Multi-core network device and power saving method thereof |
| CN113794655A (en) * | 2020-07-17 | 2021-12-14 | 北京京东尚科信息技术有限公司 | Flow monitoring method and device, computer storage medium and electronic equipment |
| CN113468234A (en) * | 2021-05-31 | 2021-10-01 | 济南浪潮数据技术有限公司 | Monitoring data processing method, device and system and storage medium |
| CN113468234B (en) * | 2021-05-31 | 2023-12-22 | 济南浪潮数据技术有限公司 | Monitoring data processing method, device, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101557321B (en) | 2011-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106330602B (en) | A kind of virtual tenant network monitoring method of cloud computing and system | |
| US8576724B2 (en) | Method, system, and computer program product, for correlating special service impacting events | |
| US7899936B2 (en) | Device in a modularized system for effecting time-stamping of events/reference events | |
| CN108259194B (en) | Network fault early warning method and device | |
| CN101557321B (en) | Method for monitoring bandwidth of interface in distributed system and device | |
| CN101094427B (en) | System and method for collecting signaling message from whole network | |
| CN106533832B (en) | Network flow detection system based on distributed deployment | |
| CN103580905B (en) | A kind of method for predicting, system and flow monitoring method, system | |
| CN101668301A (en) | Method and device for monitoring operation state of node in short message center | |
| US9298583B2 (en) | Network traffic based power consumption estimation of information technology systems | |
| CN104038383A (en) | Switch based process level network message analysis method | |
| CN101617501A (en) | Communication network is operated | |
| US8634324B2 (en) | Method and apparatus for providing signature based predictive maintenance in communication networks | |
| CN103986775A (en) | Fault information collecting system based on digital cluster PDT base station | |
| CN100484032C (en) | Method for processing abnormal overturn of host machine | |
| CN112511383A (en) | Network traffic monitoring method and device | |
| CN201022199Y (en) | An integrated network management device | |
| CN108667680B (en) | Monitoring system and method for multilink real-time data stream transmission | |
| CN102833027B (en) | A kind of synchronous regime monitoring method based on time migration | |
| Zabasta et al. | Automatic wireless meters reading for water distribution network in Talsi city | |
| US9306822B2 (en) | Method and system for silent trunk failure detection | |
| CN102736604A (en) | Centralized monitoring management system for command communication factors | |
| CN102833772B (en) | A kind of judge wireless base station single channel by and the method and apparatus of business configuration hidden danger | |
| TW201038009A (en) | Real-time traffic measurement system of IP network centralized network management and distributed nodes | |
| CN203251141U (en) | Visual network recording analysis and operation maintenance support system of intelligent transformer station |
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 |