CN112929292A - Flow scheduling method, system, equipment and storage medium based on machine room comparison - Google Patents
Flow scheduling method, system, equipment and storage medium based on machine room comparison Download PDFInfo
- Publication number
- CN112929292A CN112929292A CN202110248285.0A CN202110248285A CN112929292A CN 112929292 A CN112929292 A CN 112929292A CN 202110248285 A CN202110248285 A CN 202110248285A CN 112929292 A CN112929292 A CN 112929292A
- Authority
- CN
- China
- Prior art keywords
- machine room
- scheduling
- client
- default
- service quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 96
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 230000001360 synchronised effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 239000000523 sample Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the application discloses a flow scheduling method, a flow scheduling system, flow scheduling equipment and a flow scheduling storage medium based on machine room comparison. According to the technical scheme, the client detection data and the machine room service quality parameters are acquired from the database regularly, the client detection data and the machine room service quality parameters corresponding to the default machine room are detected, when the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, a new machine room and the default machine room are selected to construct a comparison group, and the machine room service quality parameters of the comparison group are compared in real time to conduct flow switching scheduling corresponding to the client. By adopting the technical means, the flow switching scheduling is carried out by comparing the service quality parameters of the machine room, so that the influence of network link detection errors on the flow scheduling can be reduced, the availability of network service is ensured, the network service quality is improved, and the adaptability of system flow scheduling is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of communication networks, in particular to a flow scheduling method, a flow scheduling system, flow scheduling equipment and a flow scheduling storage medium based on machine room comparison.
Background
At present, when a network service party provides network services for a client, some network problems may occasionally occur in a link between the client and a certain machine room, so that the client cannot access the corresponding machine room, and at this time, user traffic scheduling needs to be performed to guide the user traffic to other accessible machine rooms, thereby ensuring the availability of the network services of the corresponding client. When traffic scheduling is performed, a client generally sends a probe data packet to a server room, collects probe data (such as packet loss rate and round trip time) from a user to each room, and then summarizes the detected data to a server background for analysis. The server background determines that the network link is abnormal by analyzing the detection data of the client, then triggers flow scheduling, and schedules the flow of the abnormal client to a machine room with a normal network to continue providing service.
However, in an area with a relatively small number of active users, the amount of the client detection data is relatively small, and the accuracy of network link detection is easily affected, thereby affecting the traffic scheduling of the system and reducing the network service quality.
Disclosure of Invention
The embodiment of the application provides a flow scheduling method, a flow scheduling system, a flow scheduling device and a flow scheduling storage medium based on machine room comparison, which can reduce the influence of network link detection errors on flow scheduling, guarantee the availability of network services and improve the quality of the network services.
In a first aspect, an embodiment of the present application provides a traffic scheduling method based on machine room comparison, including:
the method comprises the steps that client detection data and machine room service quality parameters are obtained from a database regularly, the client detection data mark the quality of a network link from a client to a corresponding machine room, and the machine room service quality parameters are determined according to preset machine room service indexes;
detecting the client detection data and the machine room service quality parameters corresponding to a default machine room, if the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, selecting a new machine room and the default machine room to construct a comparison group, and performing flow switching scheduling of the corresponding client by comparing the machine room service quality parameters of the comparison group in real time.
In a second aspect, an embodiment of the present application provides a traffic scheduling system based on machine room contrast, including:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for periodically acquiring client detection data and machine room service quality parameters from a database, the client detection data identifies the quality of a network link from a client to a corresponding machine room, and the machine room service quality parameters are determined according to preset machine room service indexes;
and the scheduling module is used for detecting the client detection data and the machine room service quality parameters corresponding to a default machine room, selecting a new machine room and the default machine room to construct a comparison group if the client detection data is not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, and performing flow switching scheduling of the corresponding client by comparing the machine room service quality parameters of the comparison group in real time.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory and one or more processors;
the memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for traffic scheduling based on machine room contrast according to the first aspect.
In a fourth aspect, embodiments of the present application provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the method for traffic scheduling based on machine room contrast according to the first aspect.
According to the method and the device, the client detection data and the machine room service quality parameters are acquired from the database regularly, the client detection data and the machine room service quality parameters corresponding to the default machine room are detected, when the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, a new machine room and the default machine room are selected to construct a comparison group, and the machine room service quality parameters of the comparison group are compared in real time to conduct flow switching scheduling corresponding to the client. By adopting the technical means, the flow switching scheduling is carried out by comparing the service quality parameters of the machine room, so that the influence of network link detection errors on the flow scheduling can be reduced, the availability of network service is ensured, and the network service quality is improved.
In addition, the embodiment of the application carries out corresponding flow scheduling decision through different detection states of the machine room, so that the network service quality can be guaranteed in real time, and the adaptability of system flow scheduling is improved.
Drawings
Fig. 1 is a flowchart of a traffic scheduling method based on machine room comparison according to an embodiment of the present application;
fig. 2 is a schematic diagram of a traffic scheduling framework in the first embodiment of the present application;
fig. 3 is a schematic diagram of traffic scheduling based on different detection states according to an embodiment of the present application;
fig. 4 is a flow chart of traffic switching scheduling based on machine room comparison in the first embodiment of the present application;
fig. 5 is a schematic structural diagram of a traffic scheduling system based on machine room comparison according to a second embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The application provides a flow scheduling method based on machine room comparison, which aims to ensure that client detection data of a default machine room are normal, and when corresponding machine room service quality parameters are abnormal, the machine room service quality parameters are compared by constructing a machine room comparison group, and then flow scheduling is carried out on the flow of the client between the machine rooms in the comparison group, so that network service quality is guaranteed, and the influence of network detection data errors on system flow scheduling is avoided. Compared with the traditional traffic scheduling mode, the traffic scheduling method generally determines the network link condition based on the client detection data during traffic scheduling, and then correspondingly performs traffic scheduling. However, the actual network condition cannot be accurately reflected only based on the client detection data, the amount of the client detection data is relatively small in an area with a relatively small number of active users (one tenth of the clients are generally selected for network detection), and the actual network condition cannot be intuitively reflected by a small amount of the client detection data, so that when the traffic scheduling is performed based on the client detection data, the traffic scheduling effect is relatively poor, and the network service quality cannot be improved. Therefore, the traffic scheduling method based on machine room comparison is provided to solve the problem of traffic scheduling errors based on network detection in the prior art.
The first embodiment is as follows:
fig. 1 is a flowchart of a traffic scheduling method based on machine room comparison according to an embodiment of the present invention, where the traffic scheduling method based on machine room comparison provided in this embodiment may be executed by a traffic scheduling device based on machine room comparison, the traffic scheduling device based on machine room comparison may be implemented in a software and/or hardware manner, and the traffic scheduling device based on machine room comparison may be formed by two or more physical entities or may be formed by one physical entity. Generally, the traffic scheduling device based on the machine room contrast can be a server host, a traffic scheduling system server, or other computing devices.
The following description will be given by taking the traffic scheduling device based on machine room comparison as an example of a main body for executing the traffic scheduling method based on machine room comparison. Referring to fig. 1, the traffic scheduling method based on machine room comparison specifically includes:
s110, regularly acquiring client detection data and machine room service quality parameters from a database, wherein the client detection data identifies the quality of a network link from a client to a corresponding machine room, and the machine room service quality parameters are determined according to preset machine room service indexes;
according to the method and the device, the client detection data and the machine room service quality parameters are used as basic data of client user traffic scheduling, and traffic scheduling strategies are generated and implemented accordingly. Referring to fig. 2, a schematic diagram of a traffic scheduling framework of the present application is provided, where the client detection data and the quality of service parameters of the machine room are stored in a database, so that a traffic scheduling decision layer (i.e., a traffic scheduling device based on machine room comparison in the embodiment of the present application) can periodically query the data, a corresponding traffic scheduling policy is made based on the queried basic data, and the traffic scheduling policy is periodically updated to a scheduling policy table. The driving module periodically queries and acquires the scheduling strategy updated by the scheduling strategy table, and performs traffic scheduling of each client based on the scheduling strategy updated in real time, so that traffic scheduling efficiency is improved, and network service use experience of users is optimized.
Specifically, before this, an interface adaptation module is provided, and the interface adaptation module is responsible for data collection and is used for collecting and summarizing client detection data and machine room service quality parameters from respective data sources. The interface adaptation modules as different data sources have different access modes and access frequencies to different data, can be compatible with different interfaces and are convenient to configure and manage; data of different dimensions can be stored in a sub-table mode, and the expiration time of the data is correspondingly recorded, so that the data can be updated in real time; the data acquired correspondingly can be preprocessed, so that the query and use of a subsequent flow scheduling decision layer are facilitated; in addition, the data cached to the database is periodically backed up to prevent data loss. The interface adaptation module obtains the required data from different nodes and caches the data in the database after preprocessing (such as aggregation, sorting and the like). The data of each dimension can be used as an independent table for being called by a flow scheduling decision layer. It should be noted that, in order to facilitate data query invocation, corresponding timestamp information may be added corresponding to each part of data, so as to facilitate real-time query acquisition of data by the data scheduling decision layer.
It should be noted that, in the embodiment of the present application, the client detection data identifies the network link quality from the client to each computer room. In order to obtain the network link quality from the client to each machine room, service nodes for detection need to be deployed at the machine rooms of the network service side, the client sends heartbeat messages and test messages to the service nodes of each machine room at regular time, the service nodes return the received messages to the client, the client determines corresponding network detection results according to the heartbeat messages and the test messages, network link conditions from the client to each machine room are judged according to the network detection results, corresponding client detection data are generated, and the client detection data are stored in a database through an adaptive interface module. There are many ways to obtain the detection data of the client, which are not described herein. For the quality of service parameters of the machine room, the quality of service parameters of the machine room are determined according to preset machine room service indexes, which can be different indexes corresponding to different application scenes, such as video output pause rate, network request success rate, network request reply time consumption, and the like. And quantifying the machine room service quality parameters of each machine room by setting corresponding machine room service indexes corresponding to each machine room, and regularly updating the service quality parameter values to the database.
In addition, in the implementation of the present application, the database periodically updates the client detection data and the quality of service parameters of the computer room. It can be understood that, according to the embodiment of the application, the detection data of the client and the service quality parameters of the machine room are updated regularly, so that the freshness of the basic data can be guaranteed, the scheduling strategy made in real time can be adapted to the current network service condition, and the accurate automatic network scheduling effect is further realized.
S120, detecting the client detection data and the machine room service quality parameters corresponding to a default machine room, if the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, selecting a new machine room and the default machine room to construct a comparison group, and performing flow switching scheduling of the corresponding client by comparing the machine room service quality parameters of the comparison group in real time.
Further, the flow scheduling decision layer correspondingly performs detection analysis based on the acquired client detection data and the machine room service quality parameters, and generates corresponding scheduling strategies according to different detection states to perform automatic flow scheduling.
Specifically, referring to fig. 3, in a normal case, when the detected data of the client and the service quality parameter of the machine room are not abnormal, the traffic scheduling of the system is performed based on the "PLAN" state by default, and the traffic of the corresponding client is scheduled to the default machine room by a preset default scheduling policy. The default scheduling strategy is an optimal scheduling scheme which is preferably selected by combining the service quality and the bandwidth cost of the computer room network. And comparing the network service quality and the bandwidth cost of each computer room in advance, and preferably selecting one computer room as a default computer room. And when traffic scheduling is subsequently performed, firstly, traffic of the corresponding client is scheduled to a default machine room. It can be understood that when the client detection data and the machine room service quality parameters from the client to the default machine room are normal, the default machine room is preferentially selected to provide the network service for the corresponding client, so that the network service with the optimal comprehensive bandwidth cost and network service quality is provided.
Further, client detection data and network service quality are detected through a flow scheduling decision layer, when the client detection data and the machine room service quality parameters corresponding to the default machine room are detected to be synchronous and abnormal, a scheduling machine room is selected based on the client detection data corresponding to each machine room, and the flows of all the clients corresponding to the default machine room are scheduled to the scheduling machine room. When the synchronous abnormity of the client detection data and the network service quality parameters is detected, flow scheduling is carried out based on the 'ACT IVE' state, when the client detection data shows abnormity and the synchronous abnormity of the network service quality parameters occurs, a scheduling decision is considered to be required to be made immediately based on the client detection data at present, one machine room is selected as a scheduling machine room, all clients corresponding to the current default machine room are scheduled to the scheduling machine room, and the scheduling machine room provides network service so as to guarantee the network service quality of the system.
In an embodiment, when detecting that the client detection data and the machine room service quality parameter corresponding to the default machine room are synchronous and abnormal, the traffic scheduling decision layer may further select a set number of machine rooms from each machine room as alternative machine rooms according to the network quality scores and the machine room capacity parameters of each machine room, allocate user weights of each alternative machine room based on the network quality scores and the corresponding bandwidth costs, and schedule the traffic of the abnormal client (i.e., the client corresponding to the default machine room) to the corresponding alternative machine rooms based on the user weights. Specifically, network quality scores from the client to each machine room are determined according to the client detection data by using a preset scoring rule, so that the network service quality can be guaranteed only when the user traffic is dispatched to the machine rooms, and meanwhile, the service capacity upper limit of each service machine room cannot be exceeded. Before this, the corresponding machine rooms with the network quality scores lower than the preset network quality score threshold value need to be screened out. It can be understood that by filtering out the machine rooms with lower network quality scores, the finally determined alternative machine rooms can be ensured to meet the traffic scheduling requirement, and the number of samples selected by the alternative machine rooms is reduced. Further, when the candidate machine rooms are selected, the machine rooms are sorted according to the network quality scores, and the machine rooms with the top N (8 in the embodiment of the application) network quality scores optimal are selected as the initial candidate machine rooms according to the sorting from high to low of the network quality scores. And further referring to historical data, and judging whether the network quality scores of the machine rooms are stable or not in the first N selected initial candidate machine rooms according to the historical data. It can be understood that, when the network quality of a part of computer rooms is unstable, the network quality score occasionally appears to be higher, but the network quality score is lower more often, and in order to ensure that the network link corresponding to the selected candidate computer room is relatively stable, it is necessary to refer to the information of the candidate computer rooms selected in the past, and based on the part of historical data, the first M computer rooms (4 in the embodiment of the present application) that can always appear in the initial candidate computer room list in a specified time period are selected from the initial candidate computer rooms as the candidate computer rooms. It will be appreciated that if a room can remain at the top N bits of the room network quality score ranking over time, the network quality of the room is considered to be guaranteed and is therefore selected as the alternative room. And after the alternative machine rooms are determined, distributing the user traffic weight corresponding to each alternative machine room. In the weight distribution stage, more refined machine room flow weight distribution is performed according to the bandwidth cost, the network quality score, the machine room capacity threshold value and the like of the machine room, so that extra and excessive service cost is avoided during scheduling. Specifically, initial user weights are set according to the machine room network quality scores, and the network quality scores of the alternative machine rooms are normalized and uniformly set to be values between 0 and 10000 correspondingly to the alternative machine rooms. It will be appreciated that a higher value results in a higher proportion of users. For example, assume that the network quality scores of the 4 candidate rooms are S1, S2, S3, and S4, respectively. The user weights assigned to the alternative machine rooms are respectively as follows:
R1＝S1/(S1+S2+S3+S4)；
R2＝S2/(S1+S2+S3+S4)；
R3＝S3/(S1+S2+S3+S4)；
R4＝S4/(S1+S2+S3+S4)。
and based on the determined user weight, further adjusting the user weight by referring to the bandwidth cost of the computer room. It can be understood that each room has a weight of bandwidth cost, which represents the bandwidth price of each room, and the higher the bandwidth price, the higher the price that the room needs to spend with the same user weight. The bandwidth cost coefficient is a numerical value with a value of (0, 1), and the user weight obtained by calculation can be directly multiplied by the coefficient to obtain the user weight after the comprehensive bandwidth cost adjustment, in addition, the embodiment of the application also adjusts the user weight according to the machine room capacity threshold value of each alternative machine room, and can be understood that the maximum user number which can be borne by one machine room is limited and corresponds to each machine room, and the user number born by each machine room can be calculated and obtained on the basis of the weight and the total dispatching user number of the corresponding region, and whether the number of the users of the corresponding alternative machine room exceeds the machine room capacity threshold value or not is judged according to the user weight from high to low, if the user number exceeds the machine room capacity threshold value, the user needs to be transmitted to the next alternative machine room, and so on, the final user weight is obtained, and then the user traffic of the client corresponding to the default machine room is scheduled to each alternative machine room based on the user weight.
After that, when detecting that the client detection data corresponding to the default machine room is recovered to normal, scheduling the traffic of all corresponding clients back to the default machine room; and when the client detection data corresponding to the scheduling machine room and the machine room service quality parameters are detected to be synchronous and abnormal, circularly reselecting the scheduling machine room and scheduling the flow of all clients to the reselected scheduling machine room. It can be understood that, considering that the default computer room can provide the network service with the optimal comprehensive bandwidth cost and network service quality, when the detection data of the client corresponding to the default computer room is recovered to be normal, the client originally scheduled to the scheduling computer room is returned to the default computer room, so as to ensure that the corresponding client can use the network service with the optimal bandwidth cost and network service quality. In addition, if the corresponding client traffic is switched from the default machine room to the scheduling machine room and cannot enable the corresponding client detection data and the network service quality parameters to be recovered to be normal, that is, when the current scheduling machine room cannot provide normal network service for the client scheduled from the default machine room to the scheduling machine room, one machine room needs to be selected from the machine rooms again to serve as the scheduling machine room, and the traffic of the part of clients is scheduled to a new scheduling machine room. And by analogy, carrying out flow switching scheduling by circularly selecting a scheduling machine room until finally determining the scheduling machine room capable of providing normal network service.
Further, if the client detection data and the machine room service quality parameters corresponding to all the scheduled machine rooms are not recovered to be normal, the flow of all the clients is scheduled to the cloud host. When all dispatching machine rooms are circulated or the dispatching machine rooms capable of providing normal network service cannot be found, in order to guarantee the network service of the corresponding client side, the flow of all the client sides corresponding to the default machine room is dispatched to the CLOUD host, and the flow is dispatched based on the CLOUD state. In the "CLOUD" state, computer room services are deployed in the CLOUD in advance by means of computing services provided by a CLOUD manufacturer, so that network services are subsequently provided for clients scheduled to a CLOUD host, and the availability of the network services of the clients is ensured in real time.
On the other hand, when detecting the client detection data and the machine room service quality parameters of the default machine room, if the client detection data is not detected to be abnormal but the machine room service quality parameters are abnormal, a network detection error may occur due to fewer client detection data samples. And at the moment, a comparison group is constructed by selecting a new machine room and a default machine room, and the flow switching scheduling of the corresponding client is carried out by comparing the machine room service quality parameters of the comparison group in real time. Specifically, referring to fig. 4, the flow switching scheduling process based on machine room comparison includes:
s1201, switching and scheduling the flow of the client corresponding to the default machine room with the set proportion to the new machine room;
and S1202, detecting the machine room service quality parameters of the new machine room in real time based on the client with the set proportion, and switching and dispatching the flow of all the remaining clients corresponding to the default machine room to the new machine room if the corresponding machine room service quality parameters are determined to be normal.
Referring to fig. 3, when comparing the rooms, first, traffic switching scheduling is performed based on the "AB 1" state, and a comparison group is constructed by selecting a new room and a default room, and comparing whether the network service will reply or not. For example, traffic of 10% of clients corresponding to the default machine room is scheduled to a new machine room, whether the network service of the 10% of clients is recovered to be normal is observed, if the quality parameter of the machine room service corresponding to the part of clients is recovered to be normal, it is indicated that the new machine room can provide normal network service for each client corresponding to the default machine room, and at this time, all the remaining clients corresponding to the default machine room are scheduled to the new machine room based on the "AB 2" state scheduling traffic, so as to ensure that the network service of all the clients is used normally.
In one embodiment, when a new machine room and the default machine room are selected to construct a comparison group, the machine room with the optimal machine room service quality parameter is selected from the machine rooms in real time to serve as the new machine room. It can be understood that, in order to avoid frequently replacing a new machine room for machine room comparison, in the embodiment of the present application, each machine room is compared according to the machine room service quality parameter, and a machine room with the optimal machine room service quality parameter is preferably selected as the new machine room. Therefore, the network service of the corresponding client can be quickly recovered, and the phenomenon that the network service use of a user is influenced due to overlong time consumed by flow switching scheduling based on machine room comparison is avoided.
In addition, if the corresponding machine room service quality parameters are determined to be abnormal, a new machine room and the default machine room are selected again in a circulating mode to construct a new comparison group, and the flow of the client side with the set proportion is switched and scheduled to the newly selected machine room for flow switching and scheduling. When the quality of service parameter of the machine room corresponding to the new machine room is abnormal, it indicates that the current new machine room cannot provide the normal network service for the 10% client, at this time, the new machine room is selected again through circulation, and the traffic scheduling mode based on the "AB 1" state is repeated until the new machine room capable of providing the normal network service is found. And scheduling the traffic of all clients corresponding to the default machine room to the cloud host if the corresponding machine room service quality parameters are not recovered to be normal after all the comparison groups are circulated. Similarly, in order to guarantee the network service of the corresponding client, the traffic of all the clients corresponding to the default machine room is scheduled to the CLOUD host, and the traffic is scheduled based on the "CLOUD" state. In the "CLOUD" state, computer room services are deployed in the CLOUD in advance by means of computing services provided by a CLOUD manufacturer, so that network services are subsequently provided for clients scheduled to a CLOUD host, and the availability of the network services of the clients is ensured in real time.
On the other hand, during the period of carrying out flow switching scheduling based on the comparison group, if the condition that the real-time service quality parameters of the machine room of the default machine room are recovered to be normal is detected, the flow of the client with the set proportion is switched and scheduled back to the default machine room. It can be understood that by switching the traffic back to the default computer room, the network service with the optimal comprehensive bandwidth cost and network service quality can be provided, so as to optimize the use experience of the user.
And during the period of carrying out traffic switching scheduling based on the comparison group, if the traffic of all the clients corresponding to the default machine room is scheduled to a new machine room, detecting that the service quality parameters of the new machine room in real time are abnormal, and switching and scheduling the traffic of all the clients corresponding to the default machine room back to the default machine room. Similarly, since the new computer room cannot provide normal network services, the availability of the network services is ensured by switching and scheduling the traffic back to the default computer room and then performing the traffic switching and scheduling again.
Finally, based on the scheduling policy specified by the traffic scheduling decision layer corresponding to different detection states, referring to fig. 2, by setting a driving module, the driving module further invokes a corresponding module interface to enable the scheduling policy to take effect according to the corresponding scheduling policy specified in real time. Furthermore, the dispatching rules in the dispatching strategy are synchronized to the client by a service layer, so that the client sends the service request to a dispatching target machine room according to the dispatching rules to achieve the purpose of dispatching the flow.
The client detection data and the machine room service quality parameters are obtained from the database regularly, the client detection data and the machine room service quality parameters corresponding to the default machine room are detected, when the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, a new machine room and the default machine room are selected to construct a comparison group, and the machine room service quality parameters of the comparison group are compared in real time to carry out flow switching scheduling corresponding to the client. By adopting the technical means, the flow switching scheduling is carried out by comparing the service quality parameters of the machine room, so that the influence of network link detection errors on the flow scheduling can be reduced, the availability of network service is ensured, and the network service quality is improved. In addition, the embodiment of the application carries out corresponding flow scheduling decision through different detection states of the machine room, so that the network service quality can be guaranteed in real time, and the adaptability of system flow scheduling is improved.
Example two:
on the basis of the foregoing embodiment, fig. 5 is a schematic structural diagram of a traffic scheduling system based on machine room comparison according to a second embodiment of the present application. Referring to fig. 5, the traffic scheduling system based on machine room comparison provided in this embodiment specifically includes: an acquisition module 21 and a scheduling module 22.
The obtaining module 21 is configured to obtain, periodically from a database, client detection data and machine room service quality parameters, where the client detection data identifies network link quality from a client to a corresponding machine room, and the machine room service quality parameters are determined according to preset machine room service indexes;
the scheduling module 22 is configured to detect the client detection data and the machine room service quality parameters corresponding to a default machine room, select a new machine room and the default machine room to construct a comparison group if the client detection data is not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, and perform traffic switching scheduling on the corresponding client by comparing the machine room service quality parameters of the comparison group in real time.
The client detection data and the machine room service quality parameters are obtained from the database regularly, the client detection data and the machine room service quality parameters corresponding to the default machine room are detected, when the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, a new machine room and the default machine room are selected to construct a comparison group, and the machine room service quality parameters of the comparison group are compared in real time to carry out flow switching scheduling corresponding to the client. By adopting the technical means, the flow switching scheduling is carried out by comparing the service quality parameters of the machine room, so that the influence of network link detection errors on the flow scheduling can be reduced, the availability of network service is ensured, and the network service quality is improved. In addition, the embodiment of the application carries out corresponding flow scheduling decision through different detection states of the machine room, so that the network service quality can be guaranteed in real time, and the adaptability of system flow scheduling is improved.
The traffic scheduling system based on machine room comparison provided by the second embodiment of the present application can be used for executing the traffic scheduling method based on machine room comparison provided by the first embodiment of the present application, and has corresponding functions and beneficial effects.
Example three:
an embodiment of the present application provides an electronic device, and with reference to fig. 6, the electronic device includes: a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The memory 32 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the traffic scheduling method based on machine room matching according to any embodiment of the present application (for example, an obtaining module and a scheduling module in a traffic scheduling system based on machine room matching). The communication module 33 is used for data transmission. The processor executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory, that is, the above-mentioned traffic scheduling method based on machine room comparison is realized. The input device 34 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 35 may include a display device such as a display screen. The electronic device provided above can be used to execute the traffic scheduling method based on machine room comparison provided in the first embodiment, and has corresponding functions and beneficial effects
Example four:
embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method for traffic scheduling based on machine room contrast, where the storage medium may be any of various types of memory devices or storage devices. Of course, the storage medium containing the computer-executable instructions provided in the embodiments of the present application is not limited to the above-described traffic scheduling method based on machine room comparison, and may also perform related operations in the traffic scheduling method based on machine room comparison provided in any embodiments of the present application.
The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.
Claims (13)
1. A traffic scheduling method based on machine room comparison is characterized by comprising the following steps:
the method comprises the steps that client detection data and machine room service quality parameters are obtained from a database regularly, the client detection data mark the quality of a network link from a client to a corresponding machine room, and the machine room service quality parameters are determined according to preset machine room service indexes;
detecting the client detection data and the machine room service quality parameters corresponding to a default machine room, if the client detection data are not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, selecting a new machine room and the default machine room to construct a comparison group, and performing flow switching scheduling of the corresponding client by comparing the machine room service quality parameters of the comparison group in real time.
2. The traffic scheduling method based on machine room comparison according to claim 1, wherein performing traffic switching scheduling of a corresponding client by comparing the quality of service parameters of the machine room of the comparison group in real time comprises:
switching and scheduling the flow of the client corresponding to the default machine room with the set proportion to the new machine room;
and detecting the machine room service quality parameters of the new machine room in real time based on the client with the set proportion, and switching and dispatching the flow of all the remaining clients corresponding to the default machine room to the new machine room if the corresponding machine room service quality parameters are determined to be normal.
3. The traffic scheduling method based on machine room comparison according to claim 2, after detecting the quality of service parameter of the machine room of the new machine room in real time based on a client with a set proportion, further comprising:
if the corresponding machine room service quality parameters are determined to be abnormal, circularly reselecting a new machine room and the default machine room to construct a new comparison group, and switching and scheduling the flow of the client with the set proportion to the newly selected machine room to perform flow switching and scheduling;
and switching and dispatching the flow of the client with the set proportion back to the default machine room if the real-time quality of service parameters of the machine room of the default machine room are detected to be recovered to normal.
4. The traffic scheduling method based on machine room comparison according to claim 3, wherein after a new comparison group is constructed by cyclically reselecting a new machine room and the default machine room, and the traffic switching scheduling of the client with a set proportion is performed to the newly reselected machine room for traffic switching scheduling, the method further comprises:
and if the corresponding machine room service quality parameters are not recovered to be normal after all the comparison groups are circulated, dispatching the flow of all the clients corresponding to the default machine room to the cloud host.
5. The traffic scheduling method based on machine room comparison according to claim 2, wherein after switching and scheduling the traffic corresponding to all clients of the default machine room to the new machine room, the method further comprises:
and switching and dispatching the flow of all clients corresponding to the default machine room back to the default machine room when the real-time abnormal service quality parameters of the machine room of the new machine room are detected.
6. The traffic scheduling method based on machine room comparison according to claim 1, wherein selecting a new machine room and the default machine room to construct a comparison group comprises:
and selecting the machine room with the optimal service quality parameters of the machine rooms from the machine rooms in real time as the new machine room.
7. The traffic scheduling method based on machine room comparison according to claim 1, wherein before detecting the client probe data and the quality of service parameter of the machine room corresponding to a default machine room, the method further comprises:
and scheduling the flow of the corresponding client to the default machine room based on a preset default scheduling strategy.
8. The traffic scheduling method based on machine room comparison according to claim 7, wherein after the traffic of the corresponding client is scheduled to the default machine room based on the pre-configured default scheduling policy, the method further comprises:
and when the client detection data corresponding to the default machine room and the machine room service quality parameters are detected to be synchronous and abnormal, selecting a scheduling machine room based on the client detection data corresponding to each machine room, and scheduling the flow of all clients corresponding to the default machine room to the scheduling machine room.
9. The traffic scheduling method based on machine room comparison according to claim 8, wherein after the traffic of all clients corresponding to the default machine room is scheduled to the scheduling machine room, the method further comprises:
when detecting that the client detection data corresponding to the default machine room is recovered to normal, scheduling the flow of all corresponding clients back to the default machine room;
and when the client detection data corresponding to the scheduling machine room and the machine room service quality parameters are detected to be synchronous and abnormal, circularly reselecting the scheduling machine room and scheduling the flow of all clients to the reselected scheduling machine room.
10. The traffic scheduling method based on machine room comparison according to claim 9, after the scheduling machine room is selected again in a loop and the traffic of all clients is scheduled to the selected scheduling machine room, further comprising:
and if the client detection data and the machine room service quality parameters corresponding to all the scheduled machine rooms are not recovered to be normal, scheduling the flow of all the clients to the cloud host.
11. A traffic scheduling system based on machine room contrast is characterized by comprising:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for periodically acquiring client detection data and machine room service quality parameters from a database, the client detection data identifies the quality of a network link from a client to a corresponding machine room, and the machine room service quality parameters are determined according to preset machine room service indexes;
and the scheduling module is used for detecting the client detection data and the machine room service quality parameters corresponding to a default machine room, selecting a new machine room and the default machine room to construct a comparison group if the client detection data is not detected to be abnormal and the corresponding machine room service quality parameters are abnormal, and performing flow switching scheduling of the corresponding client by comparing the machine room service quality parameters of the comparison group in real time.
12. An electronic device, comprising:
a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method for farm-based collation traffic scheduling of any of claims 1-10.
13. A storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform the method for traffic scheduling based on room collation according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110248285.0A CN112929292A (en) | 2021-03-07 | 2021-03-07 | Flow scheduling method, system, equipment and storage medium based on machine room comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110248285.0A CN112929292A (en) | 2021-03-07 | 2021-03-07 | Flow scheduling method, system, equipment and storage medium based on machine room comparison |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112929292A true CN112929292A (en) | 2021-06-08 |
Family
ID=76171792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110248285.0A Pending CN112929292A (en) | 2021-03-07 | 2021-03-07 | Flow scheduling method, system, equipment and storage medium based on machine room comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112929292A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009046644A1 (en) * | 2007-10-09 | 2009-04-16 | Huawei Technologies Co., Ltd. | A method and device for traffic flow switching |
| US20110096678A1 (en) * | 2007-08-10 | 2011-04-28 | 7Signal Oy | End-to-end service quality monitoring method and system in a radio network |
| CN104683182A (en) * | 2015-02-15 | 2015-06-03 | 上海帝联信息科技股份有限公司 | Method and device for detecting network service quality of IDC machine room |
| CN105389213A (en) * | 2015-10-26 | 2016-03-09 | 珠海格力电器股份有限公司 | Data center system and configuration method therefor |
| CN106571977A (en) * | 2016-10-24 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Data transmission method and device |
| CN107465708A (en) * | 2016-06-02 | 2017-12-12 | 腾讯科技（深圳）有限公司 | A kind of CDN bandwidth scheduling systems and method |
| CN108199861A (en) * | 2016-12-08 | 2018-06-22 | 腾讯科技（深圳）有限公司 | A kind of computer lab management method and device |
| CN109921960A (en) * | 2019-03-27 | 2019-06-21 | 北京百度网讯科技有限公司 | A kind of IDC network of computer room abnormality test method and device |
| CN110943887A (en) * | 2019-11-29 | 2020-03-31 | 广州市百果园信息技术有限公司 | Probe scheduling method, device, equipment and storage medium |
| CN111245684A (en) * | 2020-01-13 | 2020-06-05 | 智者四海（北京）技术有限公司 | Traffic scheduling method and device, electronic equipment and computer readable medium |
-
2021
- 2021-03-07 CN CN202110248285.0A patent/CN112929292A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110096678A1 (en) * | 2007-08-10 | 2011-04-28 | 7Signal Oy | End-to-end service quality monitoring method and system in a radio network |
| WO2009046644A1 (en) * | 2007-10-09 | 2009-04-16 | Huawei Technologies Co., Ltd. | A method and device for traffic flow switching |
| CN104683182A (en) * | 2015-02-15 | 2015-06-03 | 上海帝联信息科技股份有限公司 | Method and device for detecting network service quality of IDC machine room |
| CN105389213A (en) * | 2015-10-26 | 2016-03-09 | 珠海格力电器股份有限公司 | Data center system and configuration method therefor |
| CN107465708A (en) * | 2016-06-02 | 2017-12-12 | 腾讯科技（深圳）有限公司 | A kind of CDN bandwidth scheduling systems and method |
| CN106571977A (en) * | 2016-10-24 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Data transmission method and device |
| CN108199861A (en) * | 2016-12-08 | 2018-06-22 | 腾讯科技（深圳）有限公司 | A kind of computer lab management method and device |
| CN109921960A (en) * | 2019-03-27 | 2019-06-21 | 北京百度网讯科技有限公司 | A kind of IDC network of computer room abnormality test method and device |
| CN110943887A (en) * | 2019-11-29 | 2020-03-31 | 广州市百果园信息技术有限公司 | Probe scheduling method, device, equipment and storage medium |
| CN111245684A (en) * | 2020-01-13 | 2020-06-05 | 智者四海（北京）技术有限公司 | Traffic scheduling method and device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7631034B1 (en) | Optimizing node selection when handling client requests for a distributed file system (DFS) based on a dynamically determined performance index | |
| CN110519365B (en) | Method for changing equipment service and service changing system | |
| US20180225346A1 (en) | Data processing method, device and system | |
| CN111818159B (en) | Management method, device, equipment and storage medium of data processing node | |
| US20210006505A1 (en) | A bursty traffic allocation method, device and proxy server | |
| US20100005468A1 (en) | Black-box performance control for high-volume throughput-centric systems | |
| US20210065083A1 (en) | Method for changing device business and business change system | |
| CN110809060B (en) | Monitoring system and monitoring method for application server cluster | |
| CN107908465A (en) | The method for scheduling task of big data platform | |
| CN101156379B (en) | Method and system for selecting service quality policy | |
| US20220012611A1 (en) | Method and machine learning manager for handling prediction of service characteristics | |
| CN112910798B (en) | Automatic flow scheduling method, system, equipment and storage medium | |
| CN112711479A (en) | Load balancing system, method and device of server cluster and storage medium | |
| US9588983B2 (en) | Data classification for adaptive synchronization | |
| CN112929292A (en) | Flow scheduling method, system, equipment and storage medium based on machine room comparison | |
| CN112328254A (en) | Performance optimization method and device of data synchronization software | |
| CN106210120B (en) | A kind of recommended method and its device of server | |
| CN113448747B (en) | Data transmission method, device, computer equipment and storage medium | |
| US10313253B2 (en) | Non-blocking request processing method and device | |
| CN116166181A (en) | Cloud monitoring method and cloud management platform | |
| EP3599547A1 (en) | Elastic storage volume type selection and optimization engine for public cloud environments | |
| CN111182523A (en) | Method, device, terminal and storage medium for realizing card selection | |
| CN110377417A (en) | Data routing method and device | |
| CN117395178B (en) | Quality monitoring method based on network division | |
| CN116095180B (en) | Log return routing method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |