CN109547517B - Method and device for scheduling bandwidth resources - Google Patents
Method and device for scheduling bandwidth resources Download PDFInfo
- Publication number
- CN109547517B CN109547517B CN201710867946.1A CN201710867946A CN109547517B CN 109547517 B CN109547517 B CN 109547517B CN 201710867946 A CN201710867946 A CN 201710867946A CN 109547517 B CN109547517 B CN 109547517B
- Authority
- CN
- China
- Prior art keywords
- bandwidth
- service
- node
- determining
- service node
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1036—Load balancing of requests to servers for services different from user content provisioning, e.g. load balancing across domain name servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/45—Network directories; Name-to-address mapping
- H04L61/4505—Network directories; Name-to-address mapping using standardised directories; using standardised directory access protocols
- H04L61/4511—Network directories; Name-to-address mapping using standardised directories; using standardised directory access protocols using domain name system [DNS]
Abstract
The invention provides a method and a device for scheduling bandwidth resources. Relates to the field of computer networks; the problems that the existing flow balancing technology between nodes cannot adapt to the actual network condition, the node utilization efficiency is low, and the user experience is poor are solved. The method comprises the following steps: determining a bandwidth multiplexing strategy of each service node according to the full-time bandwidth scale data of each service corresponding to each user identifier; when a domain name resolution request sent by a local Domain Name System (DNS) server is received, determining the number of resolution result IP addresses provided by each service node according to the bandwidth multiplexing strategy; and selecting a corresponding number of IP addresses from the corresponding service nodes according to the number of the IP addresses of the resolution results provided by each service node, and returning the IP addresses as the resolution results to the local DNS. The technical scheme provided by the invention is suitable for DNS traffic scheduling, and realizes traffic balance among service nodes which is adaptive to the network service bearing condition.
Description
Technical Field
The invention relates to the field of computer networks, in particular to a method and a device for scheduling bandwidth resources.
Background
With the strategic advance of 'broadband China' and the development of 'Internet +', the demand of enterprises on the Internet basic network is higher and higher.
At present, operators adopt 95 strategy charging for basic network bandwidth services (all bandwidth values are taken out, the highest value is removed, and the remaining maximum bandwidth is the charging bandwidth), and the 95 strategy is adopted for charging no matter the conditions of CDN service providers and operators, CDN service providers and bandwidth users, so in the actual process, in order to improve the bandwidth utilization rate, the most common mode is to share the bandwidth. In the internet, and in particular in content distribution networks, a content service is often provided by a plurality of distributed content servers. In order to effectively utilize the resources of all content servers, all access requests to the content need to be dispatched to the content servers in a balanced manner. In the prior art, a traffic scheduling method based on Domain Name System (DNS) resolution is mainly used, and the specific process is as follows:
1. the local DNS receives a request of a client and sends a domain name resolution request to an authoritative domain name server;
2. the authoritative domain name server returns the IP address corresponding to the domain name to the local DNS in equal proportion;
3. and the local DNS returns the IP address to the client, and the client sends a content access request to the corresponding content server according to the returned IP address.
The prior art has the following problems:
1. the fair sharing of services among users cannot be guaranteed, the bandwidth is fully utilized, secondly, no method is available for dynamic and static separation, the phenomenon that some users occupy a large amount of bandwidth due to busy service to influence other services to use the network bandwidth occurs among sharing users achieving dynamic bandwidth reuse, and the sharing effect is poor. 2. The performance differences of the content servers cannot be distinguished. The processing performance of each content server, even the network bandwidth, may be different, and if it is to be ensured that each server can process the traffic allocated to it, the traffic can be allocated according to the server with the worst performance when the equal proportion allocation is adopted, which will result in low utilization rate of the server with better performance.
3. The current operating state of the server cannot be reflected. Some clients may autonomously select a content server, which may result in traffic for this portion of the client not being controlled by the scheduling system. If the DNS load balancing scheduling system distributes other traffic evenly to the individual content servers, the load may be much greater for the content servers accessed by the portion of the request to autonomously select a content server than for the other servers.
In summary, the existing inter-node traffic balancing technology cannot adapt to the actual network situation, the node utilization efficiency is low, the enterprise cost is increased, and the user experience is poor.
Disclosure of Invention
The present invention is directed to solving the problems described above.
According to a first aspect of the present invention, a method for scheduling bandwidth resources is characterized by comprising:
determining a bandwidth multiplexing strategy of each service node according to full-time bandwidth scale data of various services corresponding to each user identifier, wherein the bandwidth multiplexing strategy comprises source user identifiers and load flow of the services loaded in each time period;
when a domain name resolution request sent by a local domain name system DNS server is received, determining the service nodes related to the domain name resolution request at the current time point and the proportion of the load flow of each service node according to the bandwidth multiplexing strategy, and further determining the number of resolution result IP addresses provided by each service node according to the proportion;
and selecting a corresponding number of IP addresses from the corresponding service nodes according to the number of the IP addresses of the resolution results provided by each service node, and returning the IP addresses as the resolution results to the local DNS.
Preferably, before the step of determining the bandwidth reuse policy of each service node according to the full-time bandwidth data of each service corresponding to each user identifier, the method further includes:
when the system is initialized, bandwidth scale data and modes of various services corresponding to each user identifier in each service node at the initial time are extracted.
Preferably, before the step of determining the bandwidth reuse policy of each service node according to the full-time bandwidth data of each service corresponding to each user identifier, the method further includes:
collecting bandwidth scale data of each current service node, wherein the bandwidth scale data at least comprises any one or more of the following information:
the node identification ID, the average bandwidth per minute of the node, the time point corresponding to the bandwidth and the unique identification code of the user service.
Preferably, the step of determining the bandwidth reuse policy of each service node according to the full-time bandwidth scale data of each service corresponding to each user identifier includes:
determining the bandwidth use conditions of different services in different time periods;
analyzing the correlation among the services which can be carried by each service node;
the flow generated by the same service is distributed to a plurality of service nodes capable of bearing the service, and the flow occupied by the service on the service node is determined according to the bandwidth use condition of each node in different time periods.
Preferably, after the step of selecting a corresponding number of IP addresses from the corresponding nodes according to the number of the resolution result IP addresses provided by each node, and returning the selected IP addresses to the local DNS as the resolution result, the method further includes:
and adjusting the bandwidth multiplexing strategy according to the change of the online service type.
According to another aspect of the present invention, there is provided a method for scheduling bandwidth resources, including:
when receiving a domain name resolution request sent by a client, sending the domain name resolution request to a GSLB (global system for Mobile communications);
receiving an analysis result obtained by the GSLB according to the bandwidth multiplexing strategy generated by the GSLB, wherein the analysis result indicates at least two service nodes, and each service node provides at least one IP address;
and returning the analysis result to the client.
According to another aspect of the present invention, there is provided a bandwidth resource scheduling apparatus, including:
the strategy generation module is used for determining a bandwidth multiplexing strategy of each service node according to the full-time bandwidth scale data of various services corresponding to each user identifier, wherein the bandwidth multiplexing strategy comprises the source user identifier of the service loaded in each time period and the loaded flow;
the traffic distribution module is used for determining the service nodes related to the domain name resolution request at the current time point and the proportion of the bearing traffic of each service node according to the bandwidth multiplexing strategy when receiving the domain name resolution request sent by the local DNS server, and further determining the number of resolution result IP addresses provided by each service node according to the proportion;
and the analysis result returning module is used for selecting a corresponding number of IP addresses from the corresponding service nodes according to the number of the analysis result IP addresses provided by each node, and returning the IP addresses as the analysis results to the local DNS.
Preferably, the apparatus further comprises:
a data collection module, configured to collect bandwidth scale data of each current service node, where the bandwidth scale data at least includes any one or more of the following information:
the node identification ID, the average bandwidth per minute of the node, the time point corresponding to the bandwidth and the unique identification code of the user service.
Preferably, the policy generation module includes:
the bandwidth use condition determining unit is used for determining the bandwidth use conditions of different services in different time periods;
a correlation analysis unit, configured to analyze correlation between services that each service node can bear;
and the traffic distribution unit is used for distributing the traffic generated by the same service to a plurality of service nodes capable of bearing the service, and determining the traffic occupied by the service on the service nodes according to the bandwidth use conditions of the nodes in different time periods.
Preferably, the policy generating module is further configured to adjust the bandwidth multiplexing policy according to a change of an online service type.
According to another aspect of the present invention, there is provided a bandwidth resource scheduling apparatus, including:
the request module is used for sending a domain name resolution request to the GSLB when receiving the domain name resolution request sent by the client;
a load balancing result receiving module, configured to receive an analysis result obtained by the GSLB according to a bandwidth multiplexing policy generated by the GSLB, where the analysis result indicates at least two service nodes, and each service node provides at least one IP address;
and the result returning module is used for returning the analysis result to the client.
The invention provides a bandwidth resource scheduling method and a device, firstly determining a bandwidth multiplexing strategy of each service node according to full-time bandwidth scale data of various services corresponding to each user identification, then analyzing and processing a received domain name resolution request according to the bandwidth multiplexing strategy, determining the service nodes related to the domain name resolution request at the current time point and the proportion of the bearing flow of each service node, further determining the number of resolution result IP addresses provided by each service node according to the proportion, selecting the corresponding number of IP addresses from the corresponding service nodes according to the number of the resolution result IP addresses provided by each service node, and returning the IP addresses to a local DNS as the resolution result. The problems that the existing flow balancing technology between nodes can not adapt to the actual network condition, the node utilization efficiency is low, and the user experience is poor are solved, and the flow balancing between service nodes which is adaptive to the network service bearing condition is realized. The bandwidth combination multiplexing among different services is realized in the same service node, and the bandwidth multiplexing rate of the node is improved; the dynamic adjustment and the combined multiplexing of the bandwidth are realized among different nodes, and the bandwidth of a plurality of nodes is optimized and combined for use at different time intervals according to a strategy, so that the bandwidth is used to the maximum extent.
Other characteristic features and advantages of the invention will become apparent from the following description of exemplary embodiments, which is to be read in connection with the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention. In the drawings, like reference numerals are used to indicate like elements. The drawings in the following description are directed to some, but not all embodiments of the invention. For a person skilled in the art, other figures can be derived from these figures without inventive effort.
Fig. 1 schematically shows a flow of a method for scheduling bandwidth resources according to an embodiment of the present invention;
fig. 2 exemplarily shows a structure of a bandwidth resource scheduling apparatus provided by a second embodiment of the present invention;
FIG. 3 exemplarily shows a structure of the policy generation module 201 in FIG. 2;
fig. 4 exemplarily shows an application environment of the bandwidth resource scheduling apparatus provided by the second embodiment of the present invention;
fig. 5 exemplarily shows a structure of still another bandwidth resource scheduling apparatus provided in the second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
By utilizing the initial bandwidth model and log data analysis, combining the corresponding relation among all services, operators and the bandwidth utilization rate, and utilizing a certain strategy, an optimal model can be set, so that the services of different peak periods of each node are combined with each other, the optimal utilization rate of each node is achieved, the bandwidth can be used to the maximum extent, and the bandwidth use cost of CDN service providers is saved.
In the prior art, a traffic scheduling method based on Domain Name System (DNS) resolution is mainly used, and the specific process is as follows:
1. the local DNS receives a request of a client and sends a domain name resolution request to an authoritative domain name server;
2. the authoritative domain name server returns the IP address corresponding to the domain name to the local DNS in equal proportion;
3. the local DNS returns the IP address to the client, and the client sends a content access request to the corresponding content server according to the returned IP address
The prior art has the following problems:
1. the fair sharing of services among users cannot be guaranteed, the bandwidth is fully utilized, secondly, no method is available for dynamic and static separation, the phenomenon that some users occupy a large amount of bandwidth due to busy service to influence other services to use the network bandwidth occurs among sharing users achieving dynamic bandwidth reuse, and the sharing effect is poor.
2. The performance differences of the content servers cannot be distinguished. The processing performance of each content server, even the network bandwidth, may be different, and if it is to be ensured that each server can process the traffic allocated to it, the traffic can be allocated according to the server with the worst performance when the equal proportion allocation is adopted, which will result in low utilization rate of the server with better performance.
3. The current operating state of the server cannot be reflected. Some clients may autonomously select a content server, which may result in traffic for this portion of the client not being controlled by the scheduling system. If the DNS load balancing scheduling system distributes other traffic evenly to the individual content servers, the load may be much greater for the content servers accessed by the portion of the request to autonomously select a content server than for the other servers.
In summary, the existing inter-node traffic balancing technology cannot adapt to the actual network situation, the node utilization efficiency is low, the enterprise cost is increased, and the user experience is poor.
In order to solve the above problems, embodiments of the present invention provide a method and an apparatus for scheduling bandwidth resources, where an optimal bandwidth reuse policy is generated by using a relevant optimization mechanism, scheduling is completed according to the bandwidth reuse policy, users in different peak periods of each node are combined with each other to achieve an optimal utilization rate of each node, and the model performs real-time optimization and dynamic adjustment along with service changes. The problems that the existing flow balancing technology between nodes can not adapt to the actual network condition, the node utilization efficiency is low, and the user experience is poor are solved, and the flow balancing between service nodes which is adaptive to the network service bearing condition is realized.
First, a first embodiment of the present invention will be described with reference to the drawings.
The embodiment of the invention provides a bandwidth resource scheduling method, and the flow of completing the balanced scheduling of service flow among nodes by using the method is shown in figure 1, and comprises the following steps:
the bandwidth size data at least comprises any one or more of the following information:
the node identification ID, the average bandwidth per minute of the node, the time point corresponding to the bandwidth and the unique identification code of the user service.
And collecting the unique identification code of the user service, wherein the unique identification code can be used for summarizing the global total bandwidth of the service, and limitation and other strategy processing are required if fluctuation and abnormity occur.
And when the system is initialized, extracting bandwidth scale data of various services corresponding to each user identifier in each service node at the initial time.
The collected bandwidth scale data can be used as a basis for generating a bandwidth multiplexing strategy. The collection can be triggered according to the system requirement to generate a new bandwidth reuse strategy; and the bandwidth reuse strategy can also be obtained by periodic collection and corresponding periodic adjustment.
102, determining a bandwidth multiplexing strategy of each service node according to full-time bandwidth scale data of various services corresponding to each user identifier;
the bandwidth multiplexing strategy comprises the source user identification of the service carried in each time interval and the carried flow.
The method specifically comprises the following steps:
1. determining the bandwidth use conditions of different services in different time periods;
2. analyzing the correlation among the services which can be carried by each service node; and performing correlation analysis through two or more than two service bandwidth models so as to measure the correlation closeness of the bandwidths in the same time, wherein the lower the correlation is, the higher the bandwidth reusability is.
3. The flow generated by the same service is distributed to a plurality of service nodes capable of bearing the service, and the flow occupied by the service on the service node is determined according to the bandwidth use condition of each node in different time periods.
For example, currently, in a Fujian area, there are 10 services of the same type, and there are 3 corresponding nodes, the optimal combination of the three nodes is completed according to the 10 services, where a certain time may be a bandwidth value per minute or 5 minutes, and a time point corresponding to the bandwidth. The method mainly carries out correlation analysis through two variable elements of the bandwidth and the time, so that the maximum use of the bandwidth of a time unit is achieved (each node has an upper bandwidth limit and is changed into an initial node attribute), and the strategy can be periodically adjusted along with the change of the bandwidth of the node.
in this step, when receiving the domain name resolution request, each service node capable of providing the service at the current time point can be determined according to the bandwidth multiplexing policy
And 105, selecting a corresponding number of IP addresses from the corresponding nodes according to the number of the IP addresses of the resolution results provided by each node by the GSLB, and returning the IP addresses as the resolution results to the local DNS.
the resolution result indicates at least two service nodes, each providing at least one IP address.
Preferably, when the online service type changes, the bandwidth reuse policy is adjusted according to the change of the online service type.
If GSLB finds that the traffic carried by a certain service node exceeds the upper limit of the bearer by reporting the summarized data, it triggers a protection mechanism to complete the corresponding bandwidth allocation according to the upper limit (i.e. within the upper limit range). And when the situation exists and the excess flow still exists after the bandwidth allocation is finished, forwarding the excess flow request to the backup strategy. The backup policy may be charged in other manners, such as per-flow charging, with a charging period (e.g., monthly or quarterly). The backup strategy can be adjusted according to the current network load and the network access user condition. And meanwhile, periodically collecting the service and the node bandwidth change condition, and dynamically adjusting and updating the scheduling strategy.
The following is a specific implementation of completing bandwidth resource debugging balance by using the bandwidth resource scheduling method provided by the embodiment of the invention:
after a user client initiates a domain name resolution request, a local DNS finally requests a bandwidth sharing strategy from a GSLB through resolution;
GSLB returns IP analysis result containing sharing strategy to local DNS; the returned result may include the IP in different service nodes, for example, two service nodes, and the allocated bandwidth ratio is 2: 1, when outputting the IP policy, two service nodes will also output the IP policy in a ratio of 2: the number of 1 outputs the IP number, so the final access and traffic distribution will be balanced by the polling access policy of DNS.
GSLB collects feedback information according to actual operation condition, and adjusts existing bandwidth sharing strategy.
After the preliminary scheduling distribution is completed, the nodes can report the information collected by the nodes to the GSLB regularly, the information comprises bandwidth scale data, after the GSLB data center receives the information, the GSLB data center can update and generate a bandwidth scheduling strategy in real time, and when the DNS requests the bandwidth scheduling strategy to be updated.
The second embodiment of the present invention will be described below with reference to the drawings.
An embodiment of the present invention provides a bandwidth resource scheduling apparatus, whose structure is shown in fig. 2, including:
a policy generation module 201, configured to determine a bandwidth multiplexing policy of each service node according to full-time bandwidth scale data of each service corresponding to each user identifier, where the bandwidth multiplexing policy includes a source user identifier of a service carried in each time period and a carried flow;
the traffic distribution module 202 is configured to, when receiving a domain name resolution request sent by a local DNS server, determine, according to the bandwidth multiplexing policy, a ratio of traffic borne by a service node and each service node related to the domain name resolution request at a current time point, and further determine, according to the ratio, the number of resolution result IP addresses provided by each service node;
and an analysis result returning module 203, configured to select, according to the number of the analysis result IP addresses provided by each node, a corresponding number of IP addresses from the corresponding service nodes, and return the IP addresses as an analysis result to the local DNS.
Preferably, the apparatus further comprises:
a data collection module 204, configured to collect bandwidth scale data of each current service node, where the bandwidth scale data at least includes any one or more of the following information:
the node identification ID, the average bandwidth per minute of the node, the time point corresponding to the bandwidth and the unique identification code of the user service.
Preferably, the structure of the policy generating module 201 is shown in fig. 3, and includes:
a bandwidth usage determining unit 2011, configured to determine bandwidth usage of different services at different time periods;
a correlation analysis unit 2012, configured to analyze correlations among services that each service node may carry;
a traffic allocating unit 2013, configured to allocate traffic generated by the same service to multiple service nodes capable of bearing the service, and determine, according to bandwidth usage of each node in different time periods, traffic occupied by the service on the service node.
Preferably, the policy generating module 201 is further configured to adjust the bandwidth multiplexing policy according to a change of an online service type.
The bandwidth resource scheduling apparatus shown in fig. 2 or 3 may be used as an independent device, and connected to a service node (CDN service node) and a GSLB to implement corresponding functions, as shown in fig. 4; or may be integrated in an existing network entity.
An embodiment of the present invention further provides a bandwidth resource scheduling apparatus, whose structure is shown in fig. 5, including:
a request module 501, configured to send a domain name resolution request to a GSLB when receiving the domain name resolution request sent by a client;
a load balancing result receiving module 502, configured to receive an analysis result obtained by the GSLB according to the bandwidth multiplexing policy generated by the GSLB, where the analysis result indicates at least two service nodes, and each service node provides at least one IP address;
a result returning module 503, configured to return the analysis result to the client.
The bandwidth resource scheduling device shown in fig. 5 can be integrated in a local DNS, and the local DNS can implement corresponding functions.
The embodiment of the invention provides a bandwidth resource scheduling method and a device, firstly determining a bandwidth multiplexing strategy of each service node according to full-time bandwidth scale data of various services corresponding to each user identifier, then analyzing and processing a received domain name resolution request according to the bandwidth multiplexing strategy, determining the service nodes related to the domain name resolution request at the current time point and the proportion of the bearing flow of each service node, further determining the number of resolution result IP addresses provided by each service node according to the proportion, selecting the corresponding number of IP addresses from the corresponding service nodes according to the number of the resolution result IP addresses provided by each service node, and returning the IP addresses to a local DNS as the resolution results. The problems that the existing flow balancing technology between nodes can not adapt to the actual network condition, the node utilization efficiency is low, and the user experience is poor are solved, and the flow balancing between service nodes which is adaptive to the network service bearing condition is realized. The bandwidth combination multiplexing among different services is realized in the same service node, and the bandwidth multiplexing rate of the node is improved; the dynamic adjustment and the combined multiplexing of the bandwidth are realized among different nodes, and the bandwidth of a plurality of nodes is optimized and combined for use at different time intervals according to a strategy, so that the bandwidth is used to the maximum extent.
The above-described aspects may be implemented individually or in various combinations, and such variations are within the scope of the present invention.
Finally, it should be noted that: the above examples are only for illustrating the technical solutions of the present invention, and are not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
The above-described aspects may be implemented individually or in various combinations, and such variations are within the scope of the present invention.
Finally, it should be noted that: the above examples are only for illustrating the technical solutions of the present invention, and are not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A bandwidth resource scheduling method for CDN service nodes is characterized by comprising the following steps:
determining a bandwidth multiplexing strategy of each service node according to full-time bandwidth scale data of various services corresponding to each user identifier, wherein the bandwidth multiplexing strategy comprises source user identifiers and load flow of the services loaded in each time period; the step of determining the bandwidth multiplexing policy of each service node comprises:
determining the bandwidth use conditions of different services in different time periods;
analyzing the correlation among the services which can be carried by each service node;
distributing the flow generated by the same service to a plurality of service nodes capable of bearing the service, and determining the flow occupied by the service on the service node according to the bandwidth use condition of each node in different time periods;
when a domain name resolution request sent by a local domain name system DNS server is received, determining the service nodes related to the domain name resolution request at the current time point and the proportion of the load flow of each service node according to the bandwidth multiplexing strategy, and further determining the number of resolution result IP addresses provided by each service node according to the proportion;
and selecting a corresponding number of IP addresses from the corresponding service nodes according to the number of the IP addresses of the resolution results provided by each service node, and returning the IP addresses as the resolution results to the local DNS.
2. The method for scheduling bandwidth resources according to claim 1, wherein before the step of determining the bandwidth multiplexing policy of each service node according to the full-time bandwidth data of each class of service corresponding to each user identifier, the method further comprises:
when the system is initialized, bandwidth scale data and modes of various services corresponding to each user identifier in each service node at the initial time are extracted.
3. The method for scheduling bandwidth resources according to claim 1, wherein before the step of determining the bandwidth multiplexing policy of each service node according to the full-time bandwidth data of each class of service corresponding to each user identifier, the method further comprises:
collecting bandwidth scale data of each current service node, wherein the bandwidth scale data at least comprises any one or more of the following information:
the node identification ID, the average bandwidth per minute of the node, the time point corresponding to the bandwidth and the unique identification code of the user service.
4. The method according to claim 3, wherein after the step of selecting a corresponding number of IP addresses from the corresponding nodes according to the number of resolution result IP addresses provided by each node, and returning the selected IP addresses to the local DNS as the resolution result, the method further comprises:
and adjusting the bandwidth multiplexing strategy according to the change of the online service type.
5. A method for scheduling bandwidth resources, comprising:
when receiving a domain name resolution request sent by a client, sending the domain name resolution request to a GSLB (global system for Mobile communications);
receiving an analysis result obtained by the GSLB according to the bandwidth multiplexing strategy generated by the GSLB, wherein the analysis result indicates at least two service nodes, and each service node provides at least one IP address;
returning the analysis result to the client;
the step of the bandwidth multiplexing strategy generated by the GSLB comprises the following steps:
determining the bandwidth use conditions of different services in different time periods;
analyzing the correlation among the services which can be carried by each service node;
the flow generated by the same service is distributed to a plurality of service nodes capable of bearing the service, and the flow occupied by the service on the service node is determined according to the bandwidth use condition of each node in different time periods.
6. A bandwidth resource scheduling device of a CDN service node is characterized by comprising:
the strategy generation module is used for determining a bandwidth multiplexing strategy of each service node according to the full-time bandwidth scale data of various services corresponding to each user identifier, wherein the bandwidth multiplexing strategy comprises the source user identifier of the service loaded in each time period and the loaded flow;
the policy generation module includes:
the bandwidth use condition determining unit is used for determining the bandwidth use conditions of different services in different time periods;
a correlation analysis unit, configured to analyze correlation between services that each service node can bear;
the traffic distribution unit is used for distributing the traffic generated by the same service to a plurality of service nodes capable of bearing the service, and determining the traffic occupied by the service on the service nodes according to the bandwidth use conditions of each node in different time periods;
the traffic distribution module is used for determining the service nodes related to the domain name resolution request at the current time point and the proportion of the bearing traffic of each service node according to the bandwidth multiplexing strategy when receiving the domain name resolution request sent by the local DNS server, and further determining the number of resolution result IP addresses provided by each service node according to the proportion;
and the analysis result returning module is used for selecting a corresponding number of IP addresses from the corresponding service nodes according to the number of the analysis result IP addresses provided by each node, and returning the IP addresses as the analysis results to the local DNS.
7. The apparatus for scheduling bandwidth resources of claim 6, further comprising:
a data collection module, configured to collect bandwidth scale data of each current service node, where the bandwidth scale data at least includes any one or more of the following information:
the node identification ID, the average bandwidth per minute of the node, the time point corresponding to the bandwidth and the unique identification code of the user service.
8. The bandwidth resource scheduling apparatus of claim 7,
the policy generation module is further configured to adjust the bandwidth multiplexing policy according to a change of an online service type.
9. A bandwidth resource scheduling apparatus, comprising:
the request module is used for sending a domain name resolution request to the GSLB when receiving the domain name resolution request sent by the client;
a load balancing result receiving module, configured to receive an analysis result obtained by the GSLB according to a bandwidth multiplexing policy generated by the GSLB, where the analysis result indicates at least two service nodes, and each service node provides at least one IP address;
the result returning module is used for returning the analysis result to the client;
the step of the bandwidth multiplexing strategy generated by the GSLB comprises the following steps:
determining the bandwidth use conditions of different services in different time periods;
analyzing the correlation among the services which can be carried by each service node;
the flow generated by the same service is distributed to a plurality of service nodes capable of bearing the service, and the flow occupied by the service on the service node is determined according to the bandwidth use condition of each node in different time periods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710867946.1A CN109547517B (en) | 2017-09-22 | 2017-09-22 | Method and device for scheduling bandwidth resources |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710867946.1A CN109547517B (en) | 2017-09-22 | 2017-09-22 | Method and device for scheduling bandwidth resources |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109547517A CN109547517A (en) | 2019-03-29 |
| CN109547517B true CN109547517B (en) | 2021-11-09 |
Family
ID=65830639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710867946.1A Active CN109547517B (en) | 2017-09-22 | 2017-09-22 | Method and device for scheduling bandwidth resources |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109547517B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10958592B2 (en) | 2019-04-12 | 2021-03-23 | Wangsu Science & Technology Co., Ltd. | Domain name bandwidth adjustment method and apparatus |
| CN110048968B (en) * | 2019-04-12 | 2021-06-22 | 网宿科技股份有限公司 | Domain name bandwidth adjusting method and device |
| CN110198344A (en) * | 2019-05-05 | 2019-09-03 | 网宿科技股份有限公司 | A kind of resource regulating method and system |
| CN110519104B (en) * | 2019-09-18 | 2022-06-14 | 深圳市梦网视讯有限公司 | Bandwidth multiplexing method and system based on peak error degree |
| CN113497817B (en) * | 2020-03-20 | 2023-04-07 | 北京金山云网络技术有限公司 | Traffic scheduling method and device, edge node of CDN (content delivery network) and server |
| CN113301074A (en) * | 2020-04-26 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data request load scheduling method and device, electronic equipment and readable storage medium |
| CN111654561B (en) * | 2020-06-04 | 2022-09-02 | 北京金山云网络技术有限公司 | Method and device for determining IP address number, electronic equipment and storage medium |
| CN113301445B (en) * | 2020-06-16 | 2023-08-01 | 阿里巴巴集团控股有限公司 | Address allocation method and device for content distribution network |
| CN114844949B (en) * | 2021-02-02 | 2023-10-27 | 北京金山云网络技术有限公司 | Service scheduling method, device, equipment and storage medium |
| CN113316261B (en) * | 2021-07-30 | 2021-10-29 | 军事科学院***工程研究院网络信息研究所 | Multi-dimensional flow comprehensive control system and flow ordering method |
| CN113891268B (en) * | 2021-11-02 | 2024-04-16 | 杨世标 | User flow charging auditing method |
| CN114500285B (en) * | 2021-12-28 | 2024-01-02 | 天翼云科技有限公司 | Bandwidth scheduling method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101052235A (en) * | 2007-05-08 | 2007-10-10 | 华为技术有限公司 | Business combing method and device for ASON special protection |
| CN101867521A (en) * | 2010-06-11 | 2010-10-20 | 郭小雪 | Multilink accessing and flow load dispatching managing method |
| CN103281254A (en) * | 2013-06-05 | 2013-09-04 | 中国电子科技集团公司第十五研究所 | Method for bandwidth dynamic allocation |
| CN103685054A (en) * | 2013-12-18 | 2014-03-26 | 武汉烽火网络有限责任公司 | Multipath load balancing method based on service awareness |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102244613A (en) * | 2011-08-11 | 2011-11-16 | 深信服网络科技（深圳）有限公司 | DNS (domain name system)-based multilink traffic balancing method, gateway and network |
| CN102739541B (en) * | 2012-06-30 | 2015-09-30 | 华为终端有限公司 | The method, apparatus and system of a kind of routing function startup and transfer of data |
| US9047129B2 (en) * | 2012-07-23 | 2015-06-02 | Adobe Systems Incorporated | Systems and methods for load balancing of time-based tasks in a distributed computing system |
| CN103825837B (en) * | 2014-02-19 | 2017-06-06 | 上海视云网络科技有限公司 | A kind of method of the Distributed C DN overall schedulings of node load |
-
2017
- 2017-09-22 CN CN201710867946.1A patent/CN109547517B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101052235A (en) * | 2007-05-08 | 2007-10-10 | 华为技术有限公司 | Business combing method and device for ASON special protection |
| CN101867521A (en) * | 2010-06-11 | 2010-10-20 | 郭小雪 | Multilink accessing and flow load dispatching managing method |
| CN103281254A (en) * | 2013-06-05 | 2013-09-04 | 中国电子科技集团公司第十五研究所 | Method for bandwidth dynamic allocation |
| CN103685054A (en) * | 2013-12-18 | 2014-03-26 | 武汉烽火网络有限责任公司 | Multipath load balancing method based on service awareness |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109547517A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109547517B (en) | Method and device for scheduling bandwidth resources | |
| Sahoo et al. | A survey on replica server placement algorithms for content delivery networks | |
| Xu et al. | Efficient NFV-enabled multicasting in SDNs | |
| CN109618002B (en) | Micro-service gateway optimization method, device and storage medium | |
| AU2013351670B2 (en) | Business scheduling method and apparatus and convergence device | |
| Zhang et al. | Proactive workload management in hybrid cloud computing | |
| US8612615B2 (en) | Systems and methods for identifying usage histories for producing optimized cloud utilization | |
| CN111345012A (en) | DNS resolution using link-level capacity of destination system | |
| CN106657287A (en) | Data access method and system | |
| CN110266822B (en) | Shared load balancing implementation method based on nginx | |
| CN103312629A (en) | Method, device and system of CDN (content delivery network) flow distribution | |
| Ruiz et al. | Big data-backed video distribution in the telecom cloud | |
| Setty et al. | Cost-effective resource allocation for deploying pub/sub on cloud | |
| CN109960586B (en) | Server state sensible four-layer load balancer and balancing method | |
| CN102932271A (en) | Method and device for realizing load balancing | |
| Tuncer et al. | Scalable cache management for ISP-operated content delivery services | |
| CN111092921A (en) | Data acquisition method, device and storage medium | |
| CN103401799A (en) | Method and device for realizing load balance | |
| Nakai et al. | On the use of resource reservation for web services load balancing | |
| JP2012118709A (en) | Distribution system, storage capacity decision program, and storage capacity decision method | |
| CN109639796A (en) | A kind of implementation of load balancing, device, equipment and readable storage medium storing program for executing | |
| Simoens et al. | Challenges for orchestration and instance selection of composite services in distributed edge clouds | |
| CN109413117B (en) | Distributed data calculation method, device, server and computer storage medium | |
| Zhang et al. | Online cost minimization for operating geo-distributed cloud CDNs | |
| CN112073223B (en) | System and method for managing and controlling operation of cloud computing terminal and cloud server |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |