CN103441884A - SOA service quality monitoring system based on cross-layer framework - Google Patents

SOA service quality monitoring system based on cross-layer framework Download PDF

Info

Publication number
CN103441884A
CN103441884A CN2013104014437A CN201310401443A CN103441884A CN 103441884 A CN103441884 A CN 103441884A CN 2013104014437 A CN2013104014437 A CN 2013104014437A CN 201310401443 A CN201310401443 A CN 201310401443A CN 103441884 A CN103441884 A CN 103441884A
Authority
CN
China
Prior art keywords
layer
service
network
node
resource management
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2013104014437A
Other languages
Chinese (zh)
Other versions
CN103441884B (en
Inventor
吴可嘉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu IoT Research and Development Center
Original Assignee
Jiangsu IoT Research and Development Center
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu IoT Research and Development Center filed Critical Jiangsu IoT Research and Development Center
Priority to CN201310401443.7A priority Critical patent/CN103441884B/en
Publication of CN103441884A publication Critical patent/CN103441884A/en
Application granted granted Critical
Publication of CN103441884B publication Critical patent/CN103441884B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention relates to an SOA service quality monitoring system based on a cross-layer framework. A network system is divided into a node layer, a network layer and an application layer by the SOA service quality monitoring system. The node layer is deployed with a device management service, the network layer is deployed with a network layer resource management service, and the application layer is deployed with an application layer resource management service. The device management service is used for managing local resources, monitoring the node layer service and responding invoking of operating services on a node layer device. The network layer resource management service is used for measuring bandwidth of a transmission channel and predicting a network time delay. The network layer can transmit the measured bandwidth of the transmission channel and the predicted network time delay to the application layer. The application layer resource management service performs required coordinated decisions according to service quality requirements of application programs so that service quality provided by the whole network system can meet demands of node layer service quality. According to the SOA service quality monitoring system based on the cross-layer framework, various performance parameters can be monitored and fed back in real time so that the SOA service quality monitoring system based on the cross-layer framework is high in monitoring sensitivity, low in network load and high in expansibility.

Description

SOA service quality monitoring system based on cross-layer structure
Technical field
The present invention relates to a kind of Quality Monitoring Control System, especially a kind of SOA service quality monitoring system based on cross-layer structure, belong to the technical field that network service quality is monitored.
Background technology
At present, multiple network application program service Quality Monitoring Control System is arranged, this class service quality monitoring system can be monitored the utilance of offered load, software and hardware resources and the variation of system running environment etc.For example, European IST research project IST-AQUILA has developed an Inter-domain QoS index monitoring system, still, what this system adopted is centralized management, along with the expansion of network and software and hardware scale, the performance of centralized management module will become bottleneck, and the autgmentability of system can be restricted.Simultaneously, Single Point of Faliure may occur and cause the inefficacy of whole system in the centralized management module.And for example, the internet QoS supervisory control system that domestic certain telecom operators are used, although adopted the mode of multilayer monitoring to realize the monitoring management to Internet user's service quality, extensibility is stronger, but, what this system adopted is the monitor mode that regional gateway is regularly inquired about, and can not obtain timely the operation conditions of terminal equipment, and sensitivity is poor.
Summary of the invention
The objective of the invention is to overcome the deficiencies in the prior art, a kind of SOA service quality monitoring system based on cross-layer structure is provided, it can be monitored in real time and feed back multiple performance parameter, monitors highly sensitively, and offered load is low, and autgmentability is strong.
According to technical scheme provided by the invention, the described SOA service quality monitoring system based on cross-layer structure, be divided into node layer, network layer and application layer by network system; Dispose for the node layer equipment of service is provided at the node layer, in described node layer equipment, required equipment control service is set; Network layer on-premise network layer resource management service, application layer application deployment layer resource management service;
Node layer equipment by the equipment control service to the monitoring of the management of local resource, the service of node layer and response calling operation service on described node layer equipment, and guarantee the service quality supply of expecting described service call side, node layer equipment can be by the node layer service monitoring transfer of data of equipment control service to application layer;
Network layer is measured the bandwidth of transmission channel and the time delay of prediction network by the network layer resource management service, and network layer can transfer to application layer by the transmission channel bandwidth of measurement and prediction network delay;
Application layer receives the data of node layer and network layer by the application layer resource management service, and can carry out the required coordinated decision according to the quality of service requirement of application program, so that the service quality that whole network system provides meets the demand of node layer service quality.
Described each equipment control services package is containing a service list, and described service list has reflected state and the described service operation resource requirement that is currently operating at all services on described node layer equipment; The equipment control service is extracted data service is monitored from service list, and the resource on node layer equipment is distributed.
When described node layer equipment changes in the running environment that network system detected, can be by described environmental change state notifying network layer resource management service and application layer resource management service.
Advantage of the present invention: the equipment control service can the real-time perception system running environment in the variation of software and hardware, the network layer resource management service can be measured bandwidth and the prediction network delay of transmission channel, the application layer resource management service is also formulated the service coordination decision-making neatly according to the QoS requirement of application program, service quality monitoring system is by monitoring and the prediction of the service quality of cross-layer, can monitor in real time and feed back multiple performance parameter, and thering are the characteristics such as monitoring is highly sensitive, offered load is low and autgmentability is strong.
The accompanying drawing explanation
Fig. 1 is structured flowchart of the present invention.
Embodiment
Below in conjunction with concrete drawings and Examples, the invention will be further described.
As shown in Figure 1: in order to monitor in real time and feed back multiple performance parameter, improve monitoring sensitivity, reduce offered load, the present invention is divided into node layer, network layer and application layer by network system; Dispose for the node layer equipment of service is provided at the node layer, in described node layer equipment, required equipment control service is set; Network layer on-premise network layer resource management service, application layer application deployment layer resource management service;
Node layer equipment by the equipment control service to the monitoring of the management of local resource, the service of node layer and response calling operation service on described node layer equipment, and guarantee the service quality supply of expecting described service call side, node layer equipment can be by the node layer service monitoring transfer of data of equipment control service to application layer;
Network layer is measured the bandwidth of transmission channel and the time delay of prediction network by the network layer resource management service, and network layer can transfer to application layer by the transmission channel bandwidth of measurement and prediction network delay;
Application layer receives the data of node layer and network layer by the application layer resource management service, and can carry out the required coordinated decision according to the quality of service requirement of application program, so that the service quality that whole network system provides meets the demand of node layer service quality.
Particularly, at the node layer, described each equipment control services package is containing a service list, and described service list has reflected state and the described service operation resource requirement that is currently operating at all services on described node layer equipment; The equipment control service is extracted data service is monitored from service list, and the resource on node layer equipment is distributed.
Service state data by extracting from service list of equipment control service (hang-up, operation, ready etc.) are monitored each service on the equipment of place, and equipment control service meeting carrys out the distribution of management resource so that equipment reaches higher overall performance according to current resource utilization.For example, the equipment control service can be hung up some not in the service of operation, supplies the service call of other consumption of natural resource with releasing resource.In addition, in order to allow resource management service can perceive the variation of software and hardware in system running environment, equipment control service also can be when shortage of resources and lowering service quality occurring occur informing network layer resource management service and application layer resource management service, then, the application layer resource management service will be coordinated and be dispatched the service in current system, with the overall performance of optimization system.
In network layer, the network bandwidth supplies with to the service quality of the application program towards service the conclusive effect that plays, especially all the more so for the multimedia application to time-sensitive, packet loss and network congestion all can seriously have influence on the arrival rate of multi-medium data, thereby directly affect the impression of user to service quality.Therefore, the node layer is used as network condition as the network layer resource management service that input parameter offers network layer, and the network layer resource management service is used as the network bandwidth that monitors and the network delay of prediction as the application layer resource management service that output parameter offers application layer again.
In application layer, the effect of application layer resource management service is to process the data that node layer and network layer collect the decision-making of formulating service coordination according to the application program service quality of expectation.In the embodiment of the present invention, for the QoS requirement of application programs, unified and specification description, adopted the mapping method between the resource index of a kind of application oriented QoS requirement and performance oriented.In addition, the application layer resource management service is designed to also can receive the feedback information of application layer simultaneously, and when the user makes feedback to the service quality of receiving, the service coordination decision engine can be tackled more in time and neatly like this.
The application layer resource management service realizes decision-making by the service coordination decision engine, and its detailed operation principle is as follows:
Cross-layer is monitored collected network condition, the resource utilization of required service, and the variation of system running environment will offer the service coordination decision engine of resource management service together, for it, makes dynamic service coordination decision-making.The service coordination decision-making comprises whether the compatible and service of judgement service can be competent at specific task.
Whether the agreement that service compatibility refers between service can mate, and static information (for example, agreement of required internal memory, support etc.) the service coordination decision engine of the service by pre-stored can check the compatibility between service.
At first the application layer resource management service can be moved schedulability and test to estimate whether a service can be competent at specific task, for example, one shows whether service can be decoded the video flowing received in limiting time, the schedulability test process of described demonstration service is as follows, the application layer resource management service need to first start the video decode function of this demonstration service, then utilize this equipment to carry out simulation test to the snapshot of resource consumption, rather than directly in operating system nucleus, test, the high kernel load of so just having avoided test to cause, nor spend the interrupt operation system.The application layer resource management service uses the dispatching algorithm of current node to carry out the schedulability of test assignment, for example, shows that the master control node of service uses preferential (EDF) algorithm of time limit the earliest to carry out the resource of CPU management as dynamic real-time scheduling.After the frame per second of having known video, when decoding are to the demand of CPU and the parameters such as current C PU utilance obtained from the soft state table, resource management service just can be carried out the schedulability test according to following equation:
U = Σ ∀ i ∈ task Ei Pi
Wherein, U is cpu busy percentage, the time of implementation that Ei is task i, the prescribed time-limit that Pi is task i.
If U is less than the maximum of 1(EDF scheduling), just current device can be dispatched current task, and moving and in task pool ready task can within the time limit separately, complete.Otherwise this service can not be carried out this task.
As shown in Figure 1, at the node layer, ISP and user can be distributed in multiple heterogeneous network environment, all dispose the equipment control service on the various terminal equipments at their place and come the offered load on watch-dog, the resource utilization of required service and the variation of system running environment, and be responsible for sending notice to the resource management service on upper strata, this just makes monitoring have higher sensitivity; The network condition that network layer resource management service collection node layer transmits is come monitoring network bandwidth and prediction network delay; The network condition that the application layer resource management service provides according to node layer and network layer, by the resource utilization of Demand and service, and environmental change event, and further formulate the service coordination decision-making according to the quality of service requirement of application program, finally network layer and node layer are fed back.The quantity of the resource management service of network layer resource management service and application layer can be carried out corresponding increase and decrease according to the quantity of node layer equipment and the quantity of heterogeneous network, thereby guarantees lower offered load and stronger extensibility.
Set forth detail in the above description so that fully understand the present invention.But the present invention can be different from alternate manner described here and implements with multiple, and those skilled in the art can be in the situation that do similar popularization without prejudice to intension of the present invention.Therefore the present invention is not subject to the restriction of following public embodiment.

Claims (3)

1. the SOA service quality monitoring system based on cross-layer structure, is characterized in that: network system is divided into to node layer, network layer and application layer; Dispose for the node layer equipment of service is provided at the node layer, in described node layer equipment, required equipment control service is set; Network layer on-premise network layer resource management service, application layer application deployment layer resource management service;
Node layer equipment by the equipment control service to the monitoring of the management of local resource, the service of node layer and response calling operation service on described node layer equipment, and guarantee the service quality supply of expecting described service call side, node layer equipment can be by the node layer service monitoring transfer of data of equipment control service to application layer;
Network layer is measured the bandwidth of transmission channel and the time delay of prediction network by the network layer resource management service, and network layer can transfer to application layer by the transmission channel bandwidth of measurement and prediction network delay;
Application layer receives the data of node layer and network layer by the application layer resource management service, and can carry out the required coordinated decision according to the quality of service requirement of application program, so that the service quality that whole network system provides meets the demand of node layer service quality.
2. the SOA service quality monitoring system based on cross-layer structure according to claim 1, it is characterized in that: described each equipment control services package is containing a service list, and described service list has reflected state and the described service operation resource requirement that is currently operating at all services on described node layer equipment; The equipment control service is extracted data service is monitored from service list, and the resource on node layer equipment is distributed.
3. the SOA service quality monitoring system based on cross-layer structure according to claim 1, it is characterized in that: when described node layer equipment changes in the running environment that network system detected, can be by described environmental change state notifying network layer resource management service and application layer resource management service.
CN201310401443.7A 2013-09-05 2013-09-05 SOA service quality monitoring system based on cross-layer structure Active CN103441884B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310401443.7A CN103441884B (en) 2013-09-05 2013-09-05 SOA service quality monitoring system based on cross-layer structure

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310401443.7A CN103441884B (en) 2013-09-05 2013-09-05 SOA service quality monitoring system based on cross-layer structure

Publications (2)

Publication Number Publication Date
CN103441884A true CN103441884A (en) 2013-12-11
CN103441884B CN103441884B (en) 2016-06-29

Family

ID=49695552

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310401443.7A Active CN103441884B (en) 2013-09-05 2013-09-05 SOA service quality monitoring system based on cross-layer structure

Country Status (1)

Country Link
CN (1) CN103441884B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105577448A (en) * 2016-01-11 2016-05-11 北京小米移动软件有限公司 SOA (Service Oriented Architecture) system service quality monitoring method, device and server equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060031481A1 (en) * 2004-05-21 2006-02-09 Bea Systems, Inc. Service oriented architecture with monitoring
CN101719091A (en) * 2008-10-06 2010-06-02 软件股份公司 Method and monitoring system for the rule-based monitoring of a service-oriented architecture
CN102054224A (en) * 2010-12-23 2011-05-11 东莞市高鑫机电科技服务有限公司 SOA (Service Oriented Architecture)-based clothes enterprise collaborative management system development method and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060031481A1 (en) * 2004-05-21 2006-02-09 Bea Systems, Inc. Service oriented architecture with monitoring
CN101719091A (en) * 2008-10-06 2010-06-02 软件股份公司 Method and monitoring system for the rule-based monitoring of a service-oriented architecture
CN102054224A (en) * 2010-12-23 2011-05-11 东莞市高鑫机电科技服务有限公司 SOA (Service Oriented Architecture)-based clothes enterprise collaborative management system development method and system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105577448A (en) * 2016-01-11 2016-05-11 北京小米移动软件有限公司 SOA (Service Oriented Architecture) system service quality monitoring method, device and server equipment
CN105577448B (en) * 2016-01-11 2018-10-26 北京小米移动软件有限公司 SOA system services quality control method, device and server apparatus

Also Published As

Publication number Publication date
CN103441884B (en) 2016-06-29

Similar Documents

Publication Publication Date Title
Wang et al. Multimedia communications over cognitive radio networks for smart grid applications
CN112583861B (en) Service deployment method, resource allocation method, system, device and server
CN101084680B (en) Method for managing resources in a platform for telecommunication service and/or network management, corresponding platform and computer program product therefor
CN101909048B (en) Centralized trans-coding treatment method and device
CN104994123A (en) CDN cloud platform and flow scheduling method thereof
CN101695034B (en) Device and method for adjusting monitoring parameter of WEB service
CN102223419A (en) Virtual resource dynamic feedback balanced allocation mechanism for network operation system
CN104951372A (en) Method for dynamic allocation of Map/Reduce data processing platform memory resources based on prediction
CN108092855B (en) UTN flow monitoring system and method based on SDN technology
CN102110022B (en) Sensor network embedded operation system based on priority scheduling
CN101262367A (en) Collection method and device for performance data
CN103685072A (en) Method for quickly distributing network flow
CN103973815A (en) Method for unified monitoring of storage environment across data centers
CN104735095A (en) Method and device for job scheduling of cloud computing platform
CN104298550A (en) Hadoop-oriented dynamic scheduling method
CN102158404A (en) Intelligent flow control system of interactive network and implementing method thereof
CN109257304A (en) A kind of bandwidth adjusting method, device, storage medium and the network equipment
CN104427625A (en) Network resource scheduling method and system based on user experience
CN105049485B (en) A kind of Load-aware cloud computing system towards real time video processing
CN103561428A (en) Method and system for elastically distributing nodes in short message gateway cluster system
CN107203413A (en) A kind of resource data dispatches system and method
CN106357414A (en) The information exchange method and system used for base station power generation management
KR20100118357A (en) Semantic computing-based dynamic job scheduling system for distributed processing
CN110493146A (en) A kind of Edge intelligence network aware platform and control method
CN108282526A (en) Server dynamic allocation method and system between double clusters

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