CN111787060A - Traffic scheduling method, system and device - Google Patents
Traffic scheduling method, system and device Download PDFInfo
- Publication number
- CN111787060A CN111787060A CN202010467398.5A CN202010467398A CN111787060A CN 111787060 A CN111787060 A CN 111787060A CN 202010467398 A CN202010467398 A CN 202010467398A CN 111787060 A CN111787060 A CN 111787060A
- Authority
- CN
- China
- Prior art keywords
- cluster
- service
- traffic
- candidate
- domain name
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
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
- H04L67/1004—Server selection for load balancing
-
- 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]
-
- 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
-
- 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
- H04L67/1004—Server selection for load balancing
- H04L67/1023—Server selection for load balancing based on a hash applied to IP addresses or costs
Abstract
The invention discloses a traffic scheduling method, a system and a device, wherein the method comprises the following steps: receiving a domain name resolution request pointing to a target domain name, and identifying a service cluster of the target domain name; screening candidate clusters from the service clusters, and determining a traffic undertaking parameter corresponding to each candidate cluster, wherein the traffic undertaking parameter is used for representing the probability of the candidate clusters for accepting the traffic of the target domain name; and determining a target cluster in each candidate cluster according to the traffic assuming parameters, and using the target cluster as a response of the domain name resolution request. According to the technical scheme, the stability of domain name resolution can be improved.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method, a system, and an apparatus for traffic scheduling.
Background
Currently, each large website usually deploys a plurality of resource servers, which can provide services to a plurality of internet users, so that the internet users can normally access the resources of the website. Specifically, when an internet user needs to access a resource of a certain website, a domain name resolution request may be sent to the domain name resolution server. After receiving the domain name resolution request, the domain name resolution server can select one resource server from the multiple resource servers as a response, and feeds back the IP address of the selected resource server to the Internet user, thereby completing the process of domain name resolution.
Currently, resource servers can be generally distinguished in a combination of "regional + operator". For example, the resource servers can be divided into multiple groups of resource servers such as "south China telecom", "north China Unicom", and the like. Subsequently, the domain name resolution server may select a resource server to respond from the partitioned resource servers according to the geographical location of the user and the network operator adopted.
However, in the existing method, a fixed resource server group is configured for a domain name in a manner of "region + operator", if network fluctuation occurs in a certain region or the load of a certain resource server group is too high, a situation that a user request cannot be responded to may be caused, which may undoubtedly affect the stability of domain name resolution.
Disclosure of Invention
The application aims to provide a traffic scheduling method, a traffic scheduling system and a traffic scheduling device, which can improve the stability of domain name resolution.
In order to achieve the above object, an aspect of the present application provides a traffic scheduling method, where the method includes: receiving a domain name resolution request pointing to a target domain name, and identifying a service cluster of the target domain name; screening candidate clusters from the service clusters, and determining a traffic undertaking parameter corresponding to each candidate cluster, wherein the traffic undertaking parameter is used for representing the probability of the candidate clusters for accepting the domain name resolution request; and determining a target cluster in each candidate cluster according to the traffic assuming parameters, and using the target cluster as a response of the domain name resolution request.
In order to achieve the above object, another aspect of the present application further provides a traffic scheduling system, including: the service cluster identification unit is used for receiving a domain name resolution request pointing to a target domain name and identifying a service cluster of the target domain name; a parameter determining unit, configured to screen candidate clusters from the service clusters, and determine a traffic entailing parameter corresponding to each candidate cluster, where the traffic entailing parameter is used to characterize a probability that the candidate cluster accepts the domain name resolution request; and the cluster determining unit is used for determining a target cluster in each candidate cluster according to the traffic assuming parameters and using the target cluster as a response of the domain name resolution request.
In order to achieve the above object, another aspect of the present application further provides a traffic scheduling apparatus, which includes a memory and a processor, where the memory is used for storing a computer program, and the computer program, when executed by the processor, implements the above traffic scheduling method.
As can be seen from the above, according to the technical solutions provided by one or more embodiments of the present application, when a domain name resolution request of a target domain name is received, a service cluster of the target domain name can be identified from a plurality of service clusters. Subsequently, the identified service clusters may be screened, thereby determining candidate clusters that can provide domain name resolution services. To determine a responsive target cluster from the candidate clusters, a traffic share parameter for each candidate cluster may be calculated, which may characterize the probability that the candidate cluster admits the target domain name traffic. Finally, according to the calculated flow bearing parameters, a target cluster can be determined and used as a response of the domain name resolution request. Therefore, the method and the device for providing the domain name resolution service do not configure a fixed resource server for the target domain name, but dynamically determine the target cluster capable of providing the service from a plurality of service clusters, so that the stability of the domain name resolution service can be ensured, and the efficient domain name resolution service can be provided.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a system architecture diagram of resource access in an embodiment of the invention;
FIG. 2 is a schematic diagram illustrating the steps of a traffic scheduling method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a feedback control loop for determining migration traffic in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a feedback control loop for determining migration flow parameters in an embodiment of the present invention;
FIG. 5 is a functional block diagram of a traffic scheduling system according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a traffic scheduling apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to the detailed description of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art without any inventive work based on the embodiments in the present application are within the scope of protection of the present application.
The traffic scheduling method provided by the application can be applied to a load balancing server. Referring to fig. 1, the load balancing server may be connected to a domain name resolution server, so as to receive a domain name resolution request sent by the domain name resolution server. In addition, the load balancing server may also detect information of each service cluster currently existing, so that the load balancing server may determine, from the plurality of service clusters, a part of the service clusters suitable for serving the current domain name resolution request. Subsequently, the load balancing server can screen out a target cluster from the part of service clusters according to a certain strategy, and feeds the target cluster back to the domain name resolution server as a response, so that the domain name resolution server can complete the domain name resolution work.
Referring to fig. 2, taking a load balancing server as an example, a traffic scheduling method according to an embodiment of the present application may include the following steps.
S1: receiving a domain name resolution request pointing to a target domain name, and identifying a service cluster of the target domain name.
In this embodiment, when a user client needs to access a resource of a certain website, a domain name resolution request pointing to a target domain name of the website may be sent to a domain name resolution server. After receiving the domain name resolution request, the domain name resolution server may forward the domain name resolution request to the load balancing server, and obtain a response result of the domain name resolution request from the load balancing server.
In this embodiment, the service clusters providing services for the target domain name may not need to be grouped according to regions or operators, but may provide resource access services for the target domain name in a unified manner. In order to ensure the Service Quality, each Service cluster may detect the indexes of the user client, such as delay, jitter, packet loss, etc., in advance, and generate a Quality of Service parameter (QoS) of each Service cluster based on the indexes. The qos parameters may be stored in the central server, so that the load balancing server may obtain the qos parameters from the central server when the qos parameters need to be used. Of course, the qos parameters may also be downloaded to the load balancing server, and the qos parameters are updated periodically by the load balancing server. Thus, when the service quality parameters need to be used, the load balancing server can directly read the required service quality parameters.
It should be noted that, the present application is not limited to the manner of generating the qos parameters, as long as the qos parameters can be normally obtained. In addition, for different user clients, the same service cluster may correspond to different quality of service parameters, and specifically, the quality of service parameter of a certain service cluster in the current situation may be determined according to the IP address of the user client initiating the domain name resolution request.
In this embodiment, after receiving the domain name resolution request sent by the domain name resolution server, the load balancing server may identify a target domain name carried in the domain name resolution request, and identify a service cluster providing a service for the target domain name from a plurality of service clusters. Specifically, the service clusters may be classified according to domain names of the services, and of course, the same service cluster may serve a plurality of different domain names, so the same service cluster may be classified into a plurality of classes of domain names. Thus, after the load balancing server identifies the target domain name, the service cluster included in the category corresponding to the target domain name can be used as the service cluster of the identified target domain name.
S3: and screening candidate clusters from the service clusters, and determining a traffic assuming parameter corresponding to each candidate cluster, wherein the traffic assuming parameter is used for representing the probability of the candidate cluster accepting the traffic of the target domain name.
In this embodiment, in order to determine, in real time, a target cluster providing a service for a user client from among the identified service clusters, a current operating state parameter of each service cluster may be obtained. In particular, the operating state parameters of the service cluster may cover a wide range of data. For example, the bandwidth occupied by the current time target domain name in the service cluster, the total bandwidth of the current time service cluster, the CPU utilization of the current time target domain name in the service cluster, the number of HTTP requests newly generated by the current time target domain name in the service cluster, the number of TCP connections generated by the current time target domain name in the service cluster, the total number of TCP connections in the current time service cluster, the bandwidth occupied by newly added traffic in the current time service cluster, the maximum bandwidth supported by the service cluster, and the like may be included. The working state parameters may be detected by the load balancing server in real time, or detected by other devices in the network, and then obtained by the load balancing server in real time.
In this embodiment, the load balancing server may further screen out a candidate cluster capable of providing normal service for the target domain name from the service cluster based on the acquired various pieces of information. In particular, some of the service clusters may be currently in an abnormal state, and such some clusters may be identified. Therefore, the cluster which cannot provide service for the domain name resolution request at present can be determined by identifying the identifier with the characteristic abnormal state. In addition, the load of some clusters may be high, and these clusters cannot serve domain name resolution requests. Therefore, the clusters that cannot provide services for the domain name resolution request can be first removed from the identified service clusters.
In an embodiment, for the remaining service clusters capable of providing the service for the target domain name, the service quality parameters of the remaining service clusters may be obtained, and the remaining service clusters may be sorted according to the service quality parameters. Specifically, the remaining service clusters may be sorted in the descending order of the service quality parameter, so that the service cluster in the higher order can provide a service with better quality for the target domain name.
In this embodiment, for one service cluster, if a newly added traffic is generated for a target domain name in a current network, the newly added traffic may be completely received by the same service cluster, or due to a higher load of the service cluster, the service cluster may receive only a part of the newly added traffic, and other traffic may be received by one or more other service clusters. In view of this, in the present embodiment, the situation of traffic migration and traffic sharing can be analyzed.
In one embodiment, for a certain service cluster, the current load of the service cluster at the current time may be calculated. The current load can be obtained by comprehensive calculation according to the working state parameters. Specifically, a first ratio between a bandwidth occupied by the target domain name in the service cluster at the current time and a total bandwidth of the service cluster may be calculated. A second ratio between the number of connections of the target domain name in the service cluster at the current time and the total number of connections of the service cluster may then be calculated. Finally, the CPU utilization of the service cluster at the current time may be obtained, and the maximum value between the first ratio, the second ratio, and the CPU utilization may be used as the current load of the service cluster. The formula can be expressed as:
L(c,t)＝max{bw(c,t)/bw_limit,cpu(c,t),conn(c,t)/conn_limit}
wherein L (c, t) represents the current load of the service cluster c at the current time t, bw (c, t) represents the bandwidth occupied by the target domain name in the service cluster at the current time, bw _ limit represents the total bandwidth of the service cluster, CPU (c, t) represents the CPU utilization rate of the service cluster at the current time, conn (c, t) represents the number of connections of the target domain name in the service cluster at the current time, and conn _ limit represents the total number of connections of the service cluster.
In this embodiment, the service clusters at different times may all correspond to different loads. Subsequently, the migration traffic transferred to other service clusters from the newly added traffic of the target domain name at the current time can be calculated according to the load of the service clusters at each time. Specifically, the current load of the service cluster at the current time and the historical load of the service cluster at the previous time may be calculated in the manner described above. Then, a first difference between the current load and a load threshold may be calculated, and a second difference between the current load and the historical load may be calculated. The load threshold may be a preset fixed value, where the load threshold may represent a threshold value at which the service cluster can provide stable service, and if the current load of the service cluster exceeds the load threshold, it indicates that the service cluster is not suitable for receiving excessive new traffic. A first product of the first difference and the proportional gain may then be calculated, and a second product of the second difference and the differential gain may be calculated. The proportional gain and the differential gain may also be fixed values set in advance, and the proportional gain and the differential gain may be respectively used as weighting coefficients of the first difference and the second difference. Finally, the sum of the first product, the second product and the migration traffic at the previous time may be used as the migration traffic at the current time. And the migration flow at the last moment can be calculated in an iterative manner in the previous way. The above process can be expressed as:
d(c,t)＝d(c,t-1)+g_p(L(c,t)-th)+g_d(L(c,t)-L(c,t-1))
wherein d (c, t) represents the migration traffic of the service cluster at the current moment, d (c, t-1) represents the migration traffic of the service cluster at the previous moment, g _ p represents a proportional gain, L (c, t) represents the current load of the service cluster, th represents a load threshold, g _ d represents a differential gain, and L (c, t-1) represents the historical load of the service cluster at the previous moment.
In practical applications, the process of determining the migration traffic of the service cluster may be implemented by a feedback control loop. Specifically, referring to fig. 3, the input of the feedback control loop may be newly added traffic (demand) of the target domain name at the current time, and a part of the newly added traffic (d) needs to be allocated to other service clusters, and the part of the newly added traffic may be finally determined by the feedback control loop. In the feedback control loop, the difference between the newly added traffic and the migration traffic may be used as an assumed traffic (nL), and the assumed traffic is received by the current service cluster, and because the assumed traffic is introduced, the load of the service cluster may be changed, so that the current load is generated. The current load may be generated by an STF (Service Time Filter) module. Specifically, the STF module may calculate the current load according to the following formula:
L(t)＝a L(t-1)+nL(t)
where L (t) represents the current load at the current time, a is an adjustment coefficient between 0 and 1, L (t-1) represents the historical load at the previous time, and nl (t) represents the above-mentioned assumed flow rate.
After generating the current load, an error load (e) may be generated based on the current load (L) and a load threshold (th), and the error load may be adjusted by the controller to a value of the migration flow. Subsequently, the value of the migration flow can be further adjusted through the feedback loop to the value of the assumed flow, so that the migration flow and the assumed flow can be determined according to the input newly-increased flow according to the regulation and control of the feedback control loop. The delay unit added in the simulated feedback control loop can be used for representing the delay of an observation period and the deployment delay of the domain name resolution server.
However, in an actual domain name resolution server, when facing a new traffic of a target domain name, an absolute value of a migration traffic cannot be controlled, and only a probability (or percentage) of distribution of the new traffic in different service clusters can be controlled. Therefore, after determining the migration traffic and the assumed traffic of the service cluster, it is further required to determine a traffic migration parameter (dp) representing a traffic migration probability and a traffic assumed parameter representing a traffic assumed probability, respectively, based on the migration traffic and the assumed traffic.
Specifically, for a certain service cluster, newly added traffic at the current time may be determined, and migration traffic transferred to another service cluster in the newly added traffic may be calculated according to the above manner, and then, a ratio of the migration traffic to the newly added traffic may be used as a traffic migration parameter of the service cluster at the current time. And the corresponding flow bearing parameters can be calculated in a (1-dp) mode.
In practical applications, the feedback control loop of fig. 3 may be modified to form a feedback control loop for determining the migration flow parameter. Referring to fig. 4, the current load (L) of the service cluster may be determined by the STF module according to the newly added assumed traffic (nL) in the service cluster at the current time, and then the error load (e) may be generated according to the current load (L) and the load threshold (th), and the error load (e) may generate the migration traffic (d) diverted from the service cluster through the controller. And calculating a flow migration parameter (dp) according to the migration flow (d) and the assumed flow (nL). Specifically, the sum of the migration flow and the assumed flow may be used as a new flow, and the ratio of the migration flow to the new flow may be used as a flow migration parameter through the calculation module. The flow bearing parameters can be obtained by calculation through a calculation module according to a (1-dp) mode. The calculated flow bearing parameter and the newly added flow at the next moment can be synthesized to generate the bearing flow at the next moment, and the bearing flow at the next moment can be used for regulating the migration flow transferred from the service cluster in the next feedback regulation. Thus, according to the feedback control loop shown in fig. 4, the traffic migration parameter and the traffic assumed parameter of the service cluster may be generated.
In one embodiment, traffic migration parameters of a service cluster may be referenced when screening candidate clusters from the service cluster. Specifically, when the traffic migration parameter (dp) of a service cluster is 100%, it indicates that the load of the service cluster is quite high, and any newly added traffic cannot be received, and the service cluster should not be considered as a candidate cluster. In view of this, when a cluster that cannot provide a service for a domain name resolution request is removed from a service cluster, a cluster that is marked as being inoperable may be removed from the service cluster, and a cluster whose traffic migration parameter reaches a specified parameter threshold may be removed from the service cluster. The specified parameter threshold value can be flexibly adjusted according to actual conditions, for example, the specified parameter threshold value can be 100%.
In an embodiment, after the remaining service clusters are ranked according to the service quality parameters, candidate clusters may be sequentially searched from the remaining service clusters according to the ranking results and the traffic migration parameters of the service clusters. When searching for a candidate cluster, the traffic migration parameters of each service cluster may be detected in sequence according to the sorting result. If the assignment of the traffic migration parameter of the current service cluster is not the designated parameter value, the current service cluster can be used as a candidate cluster, and the traffic migration parameter of the next service cluster is continuously detected. And if the assignment of the traffic migration parameter of the current service cluster is the designated parameter value, the search process of the candidate cluster can be ended after the current service cluster is used as a candidate cluster. The above-mentioned designated parameter value may be a lower value, because the traffic migration parameter represents the probability of transferring new traffic from the service cluster, and if the traffic migration parameter is lower, it indicates that the probability of admitting the new traffic is high, and at this time, the probability that the traffic needs to be allocated in other service clusters is lower, so that it may not be necessary to search for too many candidate clusters. In practical applications, the specified parameter value may be 0, which means that if a candidate cluster with a traffic migration parameter assigned to 0 is searched, the search process may be stopped, because the current candidate cluster may necessarily receive the newly added traffic. In the manner described above, one or more candidate clusters may be searched. The traffic assuming parameter and the traffic migrating parameter of each candidate cluster may be generated in the manner shown in fig. 4.
S5: and determining a target cluster in each candidate cluster according to the traffic assuming parameters, and using the target cluster as a response of the domain name resolution request.
In this embodiment, the load balancing server may select a target cluster from the candidate clusters, and use the target cluster as a response to the domain name resolution request. In practical applications, one target cluster may be randomly selected, and the randomly selected target cluster may be responded. In addition, the target cluster to respond to can also be selected according to the traffic burden parameter of the candidate cluster.
Specifically, the traffic burden parameter and the total burden parameter of each candidate cluster may be as shown in table 1:
TABLE 1 traffic and Total bearing parameters for candidate clusters
Where dp may represent a traffic migration parameter of the candidate cluster, and the traffic migration parameter of the candidate cluster cN is the above specified parameter value (which may be 0, for example). The total load bearing parameter in table 1 is the sum of traffic bearing parameters of candidate clusters (including the current candidate cluster) located before the current candidate cluster.
When determining the target cluster from the candidate clusters, the total load bearing parameters in table 1 may be referred to, and the total load bearing parameters in table 1 may serve as the accumulated probability values of the current candidate cluster, which are distributed between 0 and 1. These accumulated probability values may divide the total probability interval of [0,1] into a plurality of small probability intervals, such that each candidate cluster may correspond to one of the probability intervals. Therefore, the probability interval corresponding to each candidate cluster can be calculated according to the traffic sharing parameters of each candidate cluster. In determining the target cluster, a random probability value between 0 and 1 may be generated and the target probability interval in which the random probability value is located is identified. In this way, the candidate cluster corresponding to the target probability interval may be used as the determined target cluster, and the virtual IP address of the target cluster is fed back to the initiator of the domain name resolution request. Specifically, the load balancing server may feed back the virtual IP address of the target cluster to the domain name resolution server, and the domain name resolution server may feed back the virtual IP address to the user client.
In another embodiment, the target cluster may be further determined according to the traffic burden parameter of the candidate cluster and a preset adjustment coefficient. The preset adjusting coefficient can be a value between 0 and 1, and can be flexibly selected according to actual conditions. Specifically, for the current candidate cluster, the decision threshold of the current candidate cluster may be generated according to the following formula:
J＝[1-dp(c)]K
where J denotes a determination threshold of the current candidate cluster c, and K denotes the preset adjustment coefficient.
After the decision threshold of the candidate cluster is generated, a random probability value between 0 and 1 may be generated, and if the random probability value is smaller than the decision threshold of the candidate cluster, the candidate cluster is used as a determined target cluster, and the virtual IP address of the target cluster is fed back to the initiator of the domain name resolution request. And if the random probability value is greater than or equal to the judgment threshold of the candidate cluster, continuing to judge the next candidate cluster in the same way until a target cluster meeting the judgment condition is found. In practical applications, if all candidate clusters are traversed and still a suitable target cluster cannot be searched, the target cluster may be searched again from the first candidate cluster, and the value of K may be appropriately changed. If the number of times of traversing each candidate cluster reaches a specified number of times (for example, 3 times of traversing) and the target cluster still cannot be determined, it indicates that the load of the current candidate cluster is relatively high, at this time, alarm information may be generated, a target cluster is randomly determined in each candidate cluster, and the virtual IP address of the target cluster is fed back to the initiator of the domain name resolution request.
In one embodiment, the number of the target clusters screened from the candidate clusters may also be multiple, and the virtual IP addresses of the multiple target clusters may be fed back to the initiator of the domain name resolution request. The number of times that each target cluster appears in the feedback result may be proportional to the traffic assumed parameter. Therefore, the cluster with better flow receiving capacity can appear in the feedback result for many times, thereby achieving the effect of load balancing.
Therefore, according to the mode, the appropriate target cluster can be screened out to provide service for the user client by combining the actual load condition of each candidate cluster.
Referring to fig. 5, the present application further provides a traffic scheduling system, which includes:
the service cluster identification unit is used for receiving a domain name resolution request pointing to a target domain name and identifying a service cluster of the target domain name;
a parameter determining unit, configured to screen candidate clusters from the service clusters, and determine a traffic undertaking parameter corresponding to each candidate cluster, where the traffic undertaking parameter is used to characterize a probability that the candidate cluster accepts traffic of the target domain name;
and the cluster determining unit is used for determining a target cluster in each candidate cluster according to the traffic assuming parameters and using the target cluster as a response of the domain name resolution request.
In one embodiment, the parameter determination unit comprises:
the cluster removing module is used for removing clusters which cannot provide service for the domain name resolution request from the service clusters;
the sequencing module is used for acquiring the service quality parameters of the rest service clusters and sequencing the rest service clusters according to the service quality parameters;
the candidate cluster searching module is used for sequentially searching candidate clusters from the remaining service clusters according to the sorting result according to the flow migration parameters of the remaining service clusters; the traffic migration parameter is used for representing the probability of transferring the traffic of the new domain name resolution request from the service cluster.
In one embodiment, the cluster determining unit includes:
the probability interval calculation module is used for calculating the probability interval corresponding to each candidate cluster according to the flow bearing parameters of each candidate cluster;
the interval identification module is used for generating a random probability value and identifying a target probability interval where the random probability value is located;
and the target cluster determining module is used for taking the candidate cluster corresponding to the target probability interval as the determined target cluster and feeding back the virtual IP address of the target cluster to the initiator of the domain name resolution request.
In one embodiment, the cluster determining unit includes:
a decision threshold generation module, configured to generate a decision threshold of the candidate cluster according to the traffic assumed parameter of the candidate cluster and a preset adjustment coefficient;
and the threshold comparison module is used for generating a random probability value, taking the candidate cluster as a determined target cluster if the random probability value is smaller than the judgment threshold of the candidate cluster, and feeding back the virtual IP address of the target cluster to the initiator of the domain name resolution request.
Referring to fig. 6, the present application further provides a traffic scheduling apparatus, where the traffic scheduling apparatus includes a memory and a processor, where the memory is used to store a computer program, and when the computer program is executed by the processor, the traffic scheduling method is implemented.
As can be seen from the above, according to the technical solutions provided by one or more embodiments of the present application, when a domain name resolution request of a target domain name is received, a service cluster of the target domain name can be identified from a plurality of service clusters. Subsequently, the identified service clusters may be screened, thereby determining candidate clusters that can provide domain name resolution services. To determine a responsive target cluster from the candidate clusters, a traffic share parameter for each candidate cluster may be calculated that characterizes a probability that the candidate cluster accepts traffic of which the target is famous. Finally, according to the calculated flow bearing parameters, a target cluster can be determined and used as a response of the domain name resolution request. Therefore, the method and the device for providing the domain name resolution service do not configure a fixed resource server for the target domain name, but dynamically determine the target cluster capable of providing the service from a plurality of service clusters, so that the stability of the domain name resolution service can be ensured, and the efficient domain name resolution service can be provided.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for embodiments of the system and of the device, reference may be made to the introduction of embodiments of the method described above in contrast to the explanation.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an embodiment of the present application, and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (18)
1. A traffic scheduling method, characterized in that the method comprises:
receiving a domain name resolution request pointing to a target domain name, and identifying a service cluster of the target domain name;
screening candidate clusters from the service clusters, and determining a traffic undertaking parameter corresponding to each candidate cluster, wherein the traffic undertaking parameter is used for representing the probability of the candidate clusters for accepting the traffic of the target domain name;
and determining a target cluster in each candidate cluster according to the traffic assuming parameters, and using the target cluster as a response of the domain name resolution request.
2. The method of claim 1, wherein screening the service clusters for candidate clusters comprises:
removing clusters which can not provide service for the domain name resolution request from the service clusters;
obtaining the service quality parameters of the rest service clusters, and sequencing the rest service clusters according to the service quality parameters;
searching candidate clusters from the remaining service clusters in sequence according to the sorting result according to the flow migration parameters of the remaining service clusters; the traffic migration parameter is used to characterize the probability of transferring new traffic out of the service cluster.
3. The method of claim 2, wherein eliminating clusters from the service clusters that cannot serve the domain name resolution request comprises:
removing clusters marked as inoperable from the service clusters; and
and removing the clusters with the flow migration parameters reaching the specified parameter threshold from the service clusters.
4. The method of claim 2, wherein searching for the candidate cluster from the remaining service clusters comprises:
detecting the flow migration parameters of each service cluster in sequence according to the sequencing result;
if the assignment of the flow migration parameter of the current service cluster is not the designated parameter value, taking the current service cluster as a candidate cluster, and continuously detecting the flow migration parameter of the next service cluster;
and if the assignment of the flow migration parameter of the current service cluster is the designated parameter value, taking the current service cluster as a candidate cluster, and ending the search process of the candidate cluster.
5. The method of claim 2, wherein the traffic migration parameter of the service cluster at the current time is determined as follows:
determining newly added traffic at the current moment, and determining migration traffic transferred to other service clusters in the newly added traffic;
and taking the ratio of the migration flow to the newly added flow as a flow migration parameter of the service cluster at the current moment.
6. The method of claim 5, wherein determining migration traffic of the newly added traffic that is transferred to other service clusters comprises:
calculating the current load of the service cluster at the current moment and the historical load of the service cluster at the previous moment;
calculating a first difference between the current load and a load threshold, and calculating a second difference between the current load and the historical load;
calculating a first product of the first difference and a proportional gain, and calculating a second product of the second difference and a differential gain;
and taking the sum of the first product, the second product and the migration traffic at the previous moment as the migration traffic at the current moment.
7. The method of claim 6, wherein calculating the current load of the service cluster at the current time comprises:
acquiring a current working state parameter of the service cluster, and calculating the current load of the service cluster at the current moment according to the acquired working state parameter; wherein the working state parameter comprises at least one of:
the bandwidth occupied by the target domain name in the service cluster at the current moment; total bandwidth of the service cluster at the current time; the CPU utilization rate of the service cluster at the current moment; the CPU utilization rate of the target domain name generated in the service cluster at the current moment; the number of HTTP requests newly generated by the target domain name in the service cluster at the current moment; the number of TCP connections generated by the target domain name in the service cluster at the current moment; the total number of TCP connections in the service cluster at the current time; the bandwidth occupied by newly increased flow in the service cluster at the current moment; maximum bandwidth supported by the service cluster.
8. The method of claim 6 or 7, wherein calculating the current load of the service cluster at the current time comprises:
calculating a first ratio between the bandwidth occupied by the target domain name in the service cluster at the current moment and the total bandwidth of the service cluster;
calculating a second ratio between the connection number of the target domain name in the service cluster at the current moment and the total connection number of the service cluster;
and acquiring the CPU utilization rate of the service cluster at the current moment, and taking the maximum value among the first ratio, the second ratio and the CPU utilization rate as the current load of the service cluster.
9. The method of claim 1, wherein determining a traffic exposure parameter corresponding to each of the candidate clusters comprises:
determining the current load of the candidate cluster according to the newly increased assumed flow in the candidate cluster at the current moment, and generating an error load according to the current load and a load threshold;
generating migration traffic transferred from the candidate cluster based on the error load, and calculating to obtain a traffic migration parameter according to the migration traffic and the assumed traffic;
and generating a traffic assuming parameter of the candidate cluster according to the traffic migration parameter, and generating an assuming traffic of the next moment according to the traffic assuming parameter and a newly added traffic of the next moment, wherein the assuming traffic of the next moment is used for adjusting the migration traffic transferred from the candidate cluster.
10. The method of claim 9, wherein determining the current load of the candidate cluster comprises:
and calculating a product between the adjusting coefficient and the historical load at the last moment, and taking the sum of the product and the assumed flow as the current load of the candidate cluster.
11. The method of claim 1, wherein determining a target cluster among the candidate clusters comprises:
calculating a probability interval corresponding to each candidate cluster according to the flow bearing parameters of each candidate cluster;
generating a random probability value, and identifying a target probability interval where the random probability value is located;
and taking the candidate cluster corresponding to the target probability interval as a determined target cluster, and feeding back the virtual IP address of the target cluster to the initiator of the domain name resolution request.
12. The method of claim 11, wherein calculating the probability interval corresponding to each candidate cluster comprises:
for a current candidate cluster, adding traffic undertaking parameters of each candidate cluster before the current candidate cluster, and taking the added result as an accumulated probability value of the current candidate cluster;
and dividing probability intervals by using the accumulated probability values of the candidate clusters to generate the probability intervals corresponding to the candidate clusters.
13. The method of claim 11, wherein the number of the target clusters is plural, and the number of occurrences of each target cluster is proportional to a traffic load parameter of the target cluster.
14. The method of claim 1, wherein determining a target cluster among the candidate clusters comprises:
generating a judgment threshold value of the candidate cluster according to the traffic bearing parameter and a preset regulation coefficient of the candidate cluster;
and generating a random probability value, if the random probability value is smaller than the judgment threshold of the candidate cluster, taking the candidate cluster as a determined target cluster, and feeding back the virtual IP address of the target cluster to the initiator of the domain name resolution request.
15. The method according to claim 14, wherein the product of the traffic burden parameter and the preset adjustment coefficient is used as the decision threshold of the candidate cluster.
16. The method of claim 14, further comprising:
and if the number of times of traversing each candidate cluster reaches the specified number of times and a target cluster cannot be determined, generating alarm information, randomly determining a target cluster in each candidate cluster, and feeding back the virtual IP address of the target cluster to the initiator of the domain name resolution request.
17. A traffic scheduling system, the system comprising:
the service cluster identification unit is used for receiving a domain name resolution request pointing to a target domain name and identifying a service cluster of the target domain name;
a parameter determining unit, configured to screen candidate clusters from the service clusters, and determine a traffic undertaking parameter corresponding to each candidate cluster, where the traffic undertaking parameter is used to characterize a probability that the candidate cluster accepts traffic of the target domain name;
and the cluster determining unit is used for determining a target cluster in each candidate cluster according to the traffic assuming parameters and using the target cluster as a response of the domain name resolution request.
18. A traffic scheduling device, characterized in that the traffic scheduling device comprises a memory for storing a computer program which, when executed by the processor, implements the method according to any of claims 1 to 16.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010467398.5A CN111787060B (en) | 2020-05-28 | 2020-05-28 | Traffic scheduling method, system and device |
| PCT/CN2020/096602 WO2021237826A1 (en) | 2020-05-28 | 2020-06-17 | Traffic scheduling method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010467398.5A CN111787060B (en) | 2020-05-28 | 2020-05-28 | Traffic scheduling method, system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111787060A true CN111787060A (en) | 2020-10-16 |
| CN111787060B CN111787060B (en) | 2022-01-07 |
Family
ID=72754158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010467398.5A Active CN111787060B (en) | 2020-05-28 | 2020-05-28 | Traffic scheduling method, system and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111787060B (en) |
| WO (1) | WO2021237826A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113504976A (en) * | 2021-06-10 | 2021-10-15 | 中国联合网络通信集团有限公司 | Software defined network architecture scheduling method, system, terminal device and storage medium |
| CN114466020A (en) * | 2022-01-04 | 2022-05-10 | 百果园技术(新加坡)有限公司 | Service request processing method, device, equipment, storage medium and program product |
| CN114584565A (en) * | 2020-12-01 | 2022-06-03 | 中移(苏州)软件技术有限公司 | Application protection method and system, electronic equipment and storage medium |
| CN114884944A (en) * | 2022-04-28 | 2022-08-09 | 广东电网有限责任公司 | Data processing method, device, equipment and storage medium |
| CN115225507A (en) * | 2022-07-21 | 2022-10-21 | 天翼云科技有限公司 | Server group resource allocation method, device, equipment and medium |
| CN115665263A (en) * | 2022-10-19 | 2023-01-31 | 上海浦东发展银行股份有限公司 | Flow allocation method, device, server and storage medium |
| CN114884944B (en) * | 2022-04-28 | 2024-04-30 | 广东电网有限责任公司 | Data processing method, device, equipment and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114448897B (en) * | 2021-12-29 | 2024-01-02 | 天翼云科技有限公司 | Target migration method and device |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101114927A (en) * | 2006-07-24 | 2008-01-30 | 华为技术有限公司 | System and method for implementing load balancing |
| CN101442435A (en) * | 2008-12-25 | 2009-05-27 | 华为技术有限公司 | Method and apparatus for managing business data of distributed system and distributed system |
| CN101754280A (en) * | 2009-12-28 | 2010-06-23 | 华为技术有限公司 | Multi-carrier load balancing method and device |
| CN102118433A (en) * | 2010-12-27 | 2011-07-06 | 网宿科技股份有限公司 | Multiple-tier distributed cluster system |
| CN102149138A (en) * | 2011-05-26 | 2011-08-10 | 东南大学 | Method for balancing gateway load of wireless Mesh network |
| CN102523231A (en) * | 2011-12-27 | 2012-06-27 | 北京蓝汛通信技术有限责任公司 | Flow scheduling method based on DNS analysis, apparatus and server thereof |
| CN102739414A (en) * | 2012-07-12 | 2012-10-17 | 苏州阔地网络科技有限公司 | Netmeeting drifting method and system |
| EP2688354A1 (en) * | 2012-07-20 | 2014-01-22 | Alcatel Lucent | Radio access point for managing user-plane of a plurality of bearers |
| CN103595649A (en) * | 2013-11-21 | 2014-02-19 | 迈普通信技术股份有限公司 | Method and system for achieving load balance |
| CN103746929A (en) * | 2014-01-13 | 2014-04-23 | 刘保太 | Optimal access flow scheduling method based on DNS (Domain Name System) and optimal access flow scheduling equipment based on DNS |
| CN104301243A (en) * | 2014-09-22 | 2015-01-21 | 华为技术有限公司 | Load control method and device |
| CN104615498A (en) * | 2015-01-22 | 2015-05-13 | 北京仿真中心 | Dynamic load balancing method of trunking system based on task immigration |
| US9253144B2 (en) * | 2011-12-22 | 2016-02-02 | International Business Machines Corporation | Client-driven load balancing of dynamic IP address allocation |
| US9473415B2 (en) * | 2014-02-20 | 2016-10-18 | Netspeed Systems | QoS in a system with end-to-end flow control and QoS aware buffer allocation |
| CN106059945A (en) * | 2016-05-13 | 2016-10-26 | 浙江宇视科技有限公司 | Flow control method and video monitoring system |
| CN108769271A (en) * | 2018-08-20 | 2018-11-06 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of load balancing |
| CN108984307A (en) * | 2018-07-19 | 2018-12-11 | 中国联合网络通信集团有限公司 | Calculating task moving method and calculating task transference apparatus |
| CN109347947A (en) * | 2018-10-15 | 2019-02-15 | 郑州云海信息技术有限公司 | A kind of method of load balancing, name server and cluster nas server |
| CN109976917A (en) * | 2019-04-08 | 2019-07-05 | 科大讯飞股份有限公司 | A kind of load dispatching method, device, load dispatcher, storage medium and system |
| CN110830604A (en) * | 2019-10-28 | 2020-02-21 | 腾讯科技（深圳）有限公司 | DNS scheduling method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040249939A1 (en) * | 2003-05-23 | 2004-12-09 | International Business Machines Corporation | Methods and apparatus for dynamic and optimal server set selection |
| CN101593133B (en) * | 2009-06-29 | 2012-07-04 | 北京航空航天大学 | Method and device for load balancing of resources of virtual machine |
| CN104750541B (en) * | 2015-04-22 | 2018-01-16 | 成都睿峰科技有限公司 | A kind of virtual machine migration method |
| CN109981805B (en) * | 2017-12-28 | 2022-04-15 | 中国移动通信集团山东有限公司 | Domain name resolution method and device |
| US10972387B2 (en) * | 2018-06-16 | 2021-04-06 | Versa Networks, Inc. | Application performance based path-selection using dynamic metrics |
-
2020
- 2020-05-28 CN CN202010467398.5A patent/CN111787060B/en active Active
- 2020-06-17 WO PCT/CN2020/096602 patent/WO2021237826A1/en active Application Filing
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101114927A (en) * | 2006-07-24 | 2008-01-30 | 华为技术有限公司 | System and method for implementing load balancing |
| CN101442435A (en) * | 2008-12-25 | 2009-05-27 | 华为技术有限公司 | Method and apparatus for managing business data of distributed system and distributed system |
| CN101754280A (en) * | 2009-12-28 | 2010-06-23 | 华为技术有限公司 | Multi-carrier load balancing method and device |
| CN102118433A (en) * | 2010-12-27 | 2011-07-06 | 网宿科技股份有限公司 | Multiple-tier distributed cluster system |
| CN102149138A (en) * | 2011-05-26 | 2011-08-10 | 东南大学 | Method for balancing gateway load of wireless Mesh network |
| US9253144B2 (en) * | 2011-12-22 | 2016-02-02 | International Business Machines Corporation | Client-driven load balancing of dynamic IP address allocation |
| CN102523231A (en) * | 2011-12-27 | 2012-06-27 | 北京蓝汛通信技术有限责任公司 | Flow scheduling method based on DNS analysis, apparatus and server thereof |
| CN102739414A (en) * | 2012-07-12 | 2012-10-17 | 苏州阔地网络科技有限公司 | Netmeeting drifting method and system |
| EP2688354A1 (en) * | 2012-07-20 | 2014-01-22 | Alcatel Lucent | Radio access point for managing user-plane of a plurality of bearers |
| CN103595649A (en) * | 2013-11-21 | 2014-02-19 | 迈普通信技术股份有限公司 | Method and system for achieving load balance |
| CN103746929A (en) * | 2014-01-13 | 2014-04-23 | 刘保太 | Optimal access flow scheduling method based on DNS (Domain Name System) and optimal access flow scheduling equipment based on DNS |
| US9473415B2 (en) * | 2014-02-20 | 2016-10-18 | Netspeed Systems | QoS in a system with end-to-end flow control and QoS aware buffer allocation |
| CN104301243A (en) * | 2014-09-22 | 2015-01-21 | 华为技术有限公司 | Load control method and device |
| CN104615498A (en) * | 2015-01-22 | 2015-05-13 | 北京仿真中心 | Dynamic load balancing method of trunking system based on task immigration |
| CN106059945A (en) * | 2016-05-13 | 2016-10-26 | 浙江宇视科技有限公司 | Flow control method and video monitoring system |
| CN108984307A (en) * | 2018-07-19 | 2018-12-11 | 中国联合网络通信集团有限公司 | Calculating task moving method and calculating task transference apparatus |
| CN108769271A (en) * | 2018-08-20 | 2018-11-06 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of load balancing |
| CN109347947A (en) * | 2018-10-15 | 2019-02-15 | 郑州云海信息技术有限公司 | A kind of method of load balancing, name server and cluster nas server |
| CN109976917A (en) * | 2019-04-08 | 2019-07-05 | 科大讯飞股份有限公司 | A kind of load dispatching method, device, load dispatcher, storage medium and system |
| CN110830604A (en) * | 2019-10-28 | 2020-02-21 | 腾讯科技（深圳）有限公司 | DNS scheduling method and device |
Non-Patent Citations (2)
| Title |
|---|
| C. JAYASHRI: "Big data transfers through dynamic and load balanced flow on cloud networks", 《IEEE》 * |
| 赵季红: "软件定义承载网中基于负载均衡的虚拟网络重配置方法", 《计算机应用研究》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114584565A (en) * | 2020-12-01 | 2022-06-03 | 中移(苏州)软件技术有限公司 | Application protection method and system, electronic equipment and storage medium |
| CN114584565B (en) * | 2020-12-01 | 2024-01-30 | 中移(苏州)软件技术有限公司 | Application protection method and system, electronic equipment and storage medium |
| CN113504976A (en) * | 2021-06-10 | 2021-10-15 | 中国联合网络通信集团有限公司 | Software defined network architecture scheduling method, system, terminal device and storage medium |
| CN113504976B (en) * | 2021-06-10 | 2023-05-23 | 中国联合网络通信集团有限公司 | Scheduling method, system, terminal equipment and storage medium for software-defined network architecture |
| CN114466020A (en) * | 2022-01-04 | 2022-05-10 | 百果园技术(新加坡)有限公司 | Service request processing method, device, equipment, storage medium and program product |
| CN114884944A (en) * | 2022-04-28 | 2022-08-09 | 广东电网有限责任公司 | Data processing method, device, equipment and storage medium |
| CN114884944B (en) * | 2022-04-28 | 2024-04-30 | 广东电网有限责任公司 | Data processing method, device, equipment and storage medium |
| CN115225507A (en) * | 2022-07-21 | 2022-10-21 | 天翼云科技有限公司 | Server group resource allocation method, device, equipment and medium |
| CN115225507B (en) * | 2022-07-21 | 2024-03-08 | 天翼云科技有限公司 | Server group resource allocation method, device, equipment and medium |
| CN115665263A (en) * | 2022-10-19 | 2023-01-31 | 上海浦东发展银行股份有限公司 | Flow allocation method, device, server and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021237826A1 (en) | 2021-12-02 |
| CN111787060B (en) | 2022-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111787060B (en) | Traffic scheduling method, system and device | |
| CN107026907B (en) | Load balancing method, load balancer and load balancing system | |
| US7373644B2 (en) | Automated server replication | |
| CN109547517B (en) | Method and device for scheduling bandwidth resources | |
| CN112073542B (en) | Fog node scheduling method and device, computer equipment and storage medium | |
| US20180288141A1 (en) | Http scheduling system and method of content delivery network | |
| CN110401657B (en) | Processing method and device for access log | |
| CN107105013B (en) | File processing method, server, terminal and system | |
| CN112445774A (en) | Distributed shared file system and data processing method thereof | |
| CN108322495B (en) | Method, device and system for processing resource access request | |
| CN113794690B (en) | Data processing method, device, nonvolatile storage medium and processor | |
| CN111614484A (en) | Node flow calling and recovering method, system and central server | |
| CN109189578B (en) | Storage server allocation method, device, management server and storage system | |
| CN107835262A (en) | A kind of streaming media server dynamical load distribution method | |
| CN111078391A (en) | Service request processing method, device and equipment | |
| CN113676514A (en) | File source returning method and device | |
| CN108124021B (en) | Method, device and system for obtaining Internet Protocol (IP) address and accessing website | |
| CN115168017B (en) | Task scheduling cloud platform and task scheduling method thereof | |
| CN114244805B (en) | Domain name configuration method and device | |
| CN116016584A (en) | Equipment data transfer method, equipment and medium based on Internet of things platform | |
| CN113238836A (en) | Distributed content scheduling method, scheduling system and central server | |
| CN112948104B (en) | Load balancing data acquisition method and device | |
| CN113760549A (en) | Pod deployment method and device | |
| CN114124797A (en) | Server routing method and device, electronic equipment and storage medium | |
| CN105763508B (en) | Data access method and application 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 |