WO2016058169A1 - 数据流分发方法和设备 - Google Patents

数据流分发方法和设备 Download PDF

Info

Publication number
WO2016058169A1
WO2016058169A1 PCT/CN2014/088785 CN2014088785W WO2016058169A1 WO 2016058169 A1 WO2016058169 A1 WO 2016058169A1 CN 2014088785 W CN2014088785 W CN 2014088785W WO 2016058169 A1 WO2016058169 A1 WO 2016058169A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
data stream
distribution
keyword
information
Prior art date
Application number
PCT/CN2014/088785
Other languages
English (en)
French (fr)
Inventor
沈颖燕
张继东
徐江平
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN201480076763.2A priority Critical patent/CN106165359B/zh
Priority to PCT/CN2014/088785 priority patent/WO2016058169A1/zh
Priority to EP14903910.9A priority patent/EP3200407B1/en
Priority to JP2017520921A priority patent/JP6456495B2/ja
Publication of WO2016058169A1 publication Critical patent/WO2016058169A1/zh
Priority to US15/489,456 priority patent/US10715589B2/en

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
    • H04L67/1023—Server selection for load balancing based on a hash applied to IP addresses or costs

Definitions

  • Embodiments of the present invention relate to the field of communications, and more particularly, to a data stream distribution method and apparatus.
  • the data stream is composed of a multi-layer protocol.
  • the current data stream distribution method generally includes: the load balancer receives the data stream, and parses and obtains the protocol data in the received data stream, which is generally the destination IP address of the data stream, the triplet or the fifth.
  • the information such as the tuple is distributed according to the protocol data in the acquired data stream, and the data stream of the same protocol data is sent to the application server for processing by hashing or polling.
  • the load balancer needs to parse a specific protocol in the data stream to distribute the data stream.
  • the load balancer itself needs various interfaces. The data flow of the protocol is parsed, which makes the load balancer itself more complicated to distribute the data stream.
  • Embodiments of the present invention provide a data stream distribution method and apparatus, which reduce the complexity of a data stream distribution processing performed by a load balancer.
  • a method for data stream distribution comprising: a load balancer receiving a data stream; the load balancer reading the first data in the data stream according to a first distribution rule, according to the read
  • the first data in the data stream generates a keyword, queries the first distribution information according to the keyword, and determines to process the number according to the first distribution information.
  • the first distribution rule and the first distribution information are generated by the application server according to an interface protocol and sent to the load balancer, or the first distribution rule and the first distribution information are according to an interface protocol.
  • the load balancer sends the data flow to the determined application server.
  • the first data is the first distribution rule indicating the determined data read by the load balancer; or the first data is the first a distribution rule indicating start location data, offset data, and length data in the data stream read by the load balancer; or the first data indicating the load balancer read for the first distribution rule
  • the starting position data, the offset data, the length data, and the mask data in the data stream are taken.
  • the first distribution rule is configured to be used to indicate that the load balancer reads the data stream
  • the first data generates a keyword according to the first data in the read data stream, and queries the indication information of the first distribution information according to the keyword.
  • the first distribution information includes the first data generated according to the interface protocol.
  • the load balancer queries the first distribution information according to the keyword, and determines an application server that processes the data stream according to the first distribution information And the load balancer acquires and processes the data flow according to the keyword, the correspondence between the keyword generated according to the first data in the interface protocol and the application server information that processes the data flow.
  • Application server information determining an application service that processes the data stream Server.
  • the first distribution information includes the first data according to the interface protocol.
  • the load balancer queries the first distribution information according to the keyword, and determines, according to the first distribution information, an application server that processes the data stream, including: The load balancer determines the second distribution rule according to the keyword, the correspondence between the keyword generated according to the first data of the interface protocol and the second distribution rule, and determines the processing according to the second distribution rule.
  • the application server of the data stream includes:
  • the second distribution rule includes: instructing the load balancer to read the second data in the data stream Generating a keyword according to the second data in the read data stream, and querying the indication information of the second distribution information according to the keyword.
  • the second distribution information includes a keyword generated according to the second data of the interface protocol and an application server information that processes the data stream
  • the load balancer queries the second distribution information according to the keyword, and determines, according to the second distribution information, an application server that processes the data stream, including: the load balancer according to the key And obtaining, according to a correspondence between a keyword generated by the second data of the interface protocol and application server information of the processed data stream, information of the application server that processes the data stream, and determining an application server that processes the data stream.
  • the first data and the second data are data in different levels of protocols in the data stream, and the level of the second data is higher than a protocol of the first data. a hierarchy; or the first data and the second data are different data in the same chromatography protocol in the data stream.
  • the load balancer acquires flow feature information of the data flow;
  • the equalizer determines a first distribution rule of the data flow according to a correspondence between the flow feature information of the data flow and the first distribution rule.
  • the second aspect provides a data stream distribution method, including: a receiving unit, configured to receive a data stream; and a processing unit, configured to read the first data in the data stream according to the first distribution rule, according to the reading And taking the first data in the data stream to generate a keyword, querying the first distribution information according to the keyword, determining, according to the first distribution information, an application server that processes the data stream, the first distribution rule and The first distribution information is generated by the application server according to the interface protocol and sent to the load balancer, or the first distribution rule and the first distribution information are configured on the load balancer according to an interface protocol; The data stream is sent to the determined application server.
  • the first data is the first distribution rule indicating the determined data read by the load balancer; or the first data is the first a distribution rule indicating start location data, offset data, and length data in the data stream read by the load balancer; or the first data indicating the load balancer read for the first distribution rule
  • the starting position data, the offset data, the length data, and the mask data in the data stream are taken.
  • the first distribution rule is configured to be used to indicate that the load balancer reads the data stream
  • the first data generates a keyword according to the first data in the read data stream, and queries the indication information of the first distribution information according to the keyword.
  • the first distribution information includes generating according to the first data in the interface protocol.
  • the processing unit is configured to query the first distribution information according to the keyword, and determine, according to the first distribution information, that the data stream is processed according to the correspondence between the keyword and the application server information that processes the data stream.
  • the application server includes: the processing unit, configured to acquire, according to the keyword, the correspondence between the keyword generated according to the first data in the interface protocol and the application server information that processes the data stream.
  • the application server information of the data stream determines an application server that processes the data stream.
  • the first distribution information includes the first data according to the interface protocol.
  • the processing unit is configured to query the first distribution information according to the keyword, and determine, according to the first distribution information, an application server that processes the data stream, including:
  • the processing unit is configured to determine, according to the keyword, the second distribution rule according to the correspondence between the keyword generated by the first data of the interface protocol and the second distribution rule, according to the second distribution rule An application server that processes the data stream is determined.
  • the second distribution rule includes: instructing the load balancer to read the second data in the data stream, and generating a keyword according to the second data in the read data stream, according to the The keyword queries the indication information of the second distribution information.
  • the second distribution information includes a keyword generated according to the second data of the interface protocol and an application server information that processes the data stream Correspondence between
  • the processing unit is configured to query the second distribution information according to the keyword, and determine, according to the second distribution information, an application server that processes the data stream, including:
  • the processing unit acquires information of the application server that processes the data stream according to the correspondence between the keyword, the keyword generated according to the second data of the interface protocol, and the application server information of the processed data stream, and determines An application server that processes the data stream.
  • the first data and the second data are data in different hierarchical protocols in the data stream And the level of the protocol in which the second data is located is higher than the level of the protocol in which the first data is located; or the first data and the second data are different data in the same chromatography protocol in the data stream .
  • the processing unit is further configured to acquire flow feature information of the data stream; The correspondence between the flow feature information of the data flow and the first distribution rule determines a first distribution rule of the data flow.
  • a method for data stream distribution comprising: a receiver, configured to: Receiving a data stream; the processor, configured to read the first data in the data stream according to the first distribution rule, generate a keyword according to the first data in the read data stream, and query according to the keyword a first distribution information, where the application server that processes the data stream is determined according to the first distribution information, where the first distribution rule and the first distribution information are generated by an application server according to an interface protocol and sent to the device, or The first distribution rule and the first distribution information are configured on the device according to an interface protocol, and the transmitter is configured to send the data stream to the determined application server.
  • the first data is the first distribution rule indicating the determined data read by the device; or the first data is the first distribution a rule indicating start location data, offset data, and length data in the data stream read by the device; or the first data is the first distribution rule indicating the data stream read by the device Medium start position data, offset data, length data, and mask data.
  • the first distribution rule includes, in the first distribution rule, a a data, generating a keyword according to the first data in the read data stream, and querying the indication information of the first distribution information according to the keyword.
  • the first distribution information includes generating according to the first data in the interface protocol.
  • the processor is configured to query the first distribution information according to the keyword, and determine, according to the first distribution information, an application that processes the data stream Server, package
  • the processor is configured to acquire, according to the keyword, a correspondence between a keyword generated according to the first data in the interface protocol and application server information that processes the data stream, and process the data stream.
  • the application server information determines an application server that processes the data stream.
  • the first distribution information includes the first data according to the interface protocol.
  • the processor is configured to query the first distribution information according to the keyword, and determine, according to the first distribution information, an application server that processes the data stream, including:
  • the processing unit is configured to determine, according to the keyword, the second distribution rule according to the correspondence between the keyword generated by the first data of the interface protocol and the second distribution rule, and determine according to the second distribution rule An application server that processes the data stream.
  • the second distribution rule includes, in the second distribution rule, indicating that the device reads the second data in the data stream, according to The second data in the read data stream generates a keyword, and the indication information of the second distribution information is queried according to the keyword.
  • the second distribution information includes a keyword generated according to the second data of the interface protocol and an application server information that processes the data stream Corresponding relationship between the processor, the second distribution information is queried according to the keyword, and the application server that processes the data stream is determined according to the second distribution information, including: the processor according to the keyword, Keyword generated according to the second data of the interface protocol and application server information of the processed data stream Corresponding relationships are obtained, the information of the application server that processes the data stream is obtained, and an application server that processes the data stream is determined.
  • the first data and the second data are data in different hierarchical protocols in the data stream And the level of the protocol in which the second data is located is higher than the level of the protocol in which the first data is located; or the first data and the second data are different data in the same chromatography protocol in the data stream .
  • the processor is further configured to acquire flow feature information of the data stream; The correspondence between the flow feature information of the data flow and the first distribution rule determines a first distribution rule of the data flow.
  • the load balancer may read data in the data stream according to an indication sent by the application server according to the interface protocol or according to a distribution rule configured on the load balancer by the interface protocol. Based on the keywords generated by the read data, an application server that processes the data stream is determined, and the data stream is sent to the determined application server.
  • the load balancer can read the data stream according to the indication of the general distribution rule, and then distribute the data stream, thereby reducing the complexity of the data stream distribution processing by the load balancer.
  • FIG. 1 is a diagram showing a network architecture provided by an embodiment of the present invention.
  • FIG. 2 is a schematic flowchart of a data stream distribution method according to an embodiment of the present invention.
  • FIG. 3 is a schematic block diagram of a data stream distribution apparatus according to an embodiment of the present invention.
  • FIG. 4 is a schematic block diagram of a data stream distribution apparatus according to an embodiment of the present invention.
  • GSM Global System of Mobile communication
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • FDD Frequency Division Duplex
  • TDD Time Division Duplex
  • UMTS Universal Mobile Telecommunication System
  • WiMAX Worldwide Interoperability for Microwave Access
  • FIG. 1 is a network architecture diagram of an application scenario of an embodiment of the present invention.
  • the load balancer 101 is a device that uses various allocation algorithms to distribute network requests to various available application servers, thereby enabling network visitors to obtain the best possible network experience; generally, the load The equalizer has different forms. In addition to being a load balancer in an independent sense, it can also be integrated on other communication devices to achieve the effect of distributing network requests to various application servers.
  • the load balancer can generally be used with multiple applications. Server connection.
  • the application server 102 is generally a server for processing a plurality of different network requests.
  • the application server may exist separately, or may handle different requests for communication devices (for example, Gateway GPRS Support Node or Serving GPRS SUPPORT NODE, etc.) for internal load balancing. Node.
  • FIG. 2 is a schematic flowchart of a method for data stream distribution according to an embodiment of the present invention.
  • the method can be performed by a load balancer, but the invention is not limited thereto.
  • the method includes:
  • the load balancer receives the data stream.
  • the load balancer reads the first data in the data stream according to the first distribution rule, generates a keyword according to the first data in the read data stream, and searches for the first keyword according to the keyword.
  • Distributing information determining, according to the first distribution information, an application server that processes the data stream, where the first distribution rule and the first distribution information are generated by an application server according to an interface protocol and sent to the load balancer, or The first distribution rule and the first distribution information are configured on the load balancer according to an interface protocol;
  • the load balancer sends the data stream to the determined application server.
  • an application server has one or more service interfaces, and a protocol corresponding to an interface generally has multiple layers.
  • the corresponding protocol includes an Internet Protocol (IP) protocol, and may also include a transport layer control.
  • IP Internet Protocol
  • TCP Transmission Control Protocol
  • UDP User Datagram Protocol
  • SCTP Stream Control Transmission Protocol
  • the protocol corresponding to the interface (referred to as the interface protocol) is related to the specific interface.
  • the application server can generate distribution rules and distribution information according to the data of the interface protocol.
  • the application server may generate a distribution rule and distribution information according to data of an interface protocol, and send the information to the load balancer to instruct the load balancer to distribute the data stream according to specific protocol data in the data flow, so that the data flow is distributed.
  • the load balancer can analyze the current increasingly diverse and complicated protocol types according to the instructions, and accurately distribute the corresponding data flows, so that the load balancer load balancing capability is improved, and the load balancer itself needs to be reduced to various interfaces. The complexity of parsing the data stream of the protocol.
  • distribution rules and distribution information can be configured on the load balancer based on the data of the interface protocol.
  • the load balancer may read the data in the data flow according to the indication sent by the application server according to the interface protocol or according to the distribution rule configured on the load balancer by the interface protocol, according to The generated data generates keywords, determines the application server that processes the data stream, and sends the data stream to the determined application server.
  • the load balancer can read the data of the data stream according to the indication of the general distribution rule, thereby distributing the data stream, and reducing the data of the load balancer.
  • the complexity of stream distribution processing is a stream distribution rule configured on the load balancer by the interface protocol, according to The generated data generates keywords, determines the application server that processes the data stream, and sends the data stream to the determined application server.
  • the load balancer After receiving the data flow, the load balancer obtains flow feature information of the data flow, where the flow feature information is information that can be used to identify the data flow.
  • the flow characteristic information of the data stream may be a source IP address, a destination IP address, a triplet information, or a quintuple information of the data stream, and the like, which is not limited by the present invention.
  • the load balancer obtains flow characteristic information of the data flow, and determines a first distribution rule of the data flow according to the flow characteristic information of the data flow. There is a correspondence between the distribution rule and the flow feature information of the data flow, and the load balancer can determine the first distribution rule of the data flow according to the flow feature information of the data flow.
  • the distribution rule includes indication information for instructing the load balancer to read data in the data stream, generating a keyword according to the data in the data stream, and querying the first distribution information according to the keyword. That is, the first distribution rule includes: instructing the load balancer to read the first data in the data stream, generating a keyword according to the first data in the read data stream, and querying according to the keyword The indication information of the first distribution information.
  • the manner in which the load balancer reads the data in the data stream according to the indication of the distribution rule mainly includes the following manners: First, the load balancer reads the data determined in the data flow according to the indication of the distribution rule, for example, the load balancer according to the distribution rule. Instructing to read data such as the IP address or port number of the data stream, and second, the load balancer reads the start data (Offset) data, the offset (Offset) data, and the length in the data stream according to the indication of the distribution rule (Length Data, or read start data (Offset) data, offset (Length) data, and mask (Mask) data in the data stream.
  • the load balancer reads the data determined in the data flow according to the indication of the distribution rule, for example, the load balancer according to the distribution rule. Instructing to read data such as the IP address or port number of the data stream, and second, the load balancer reads the start data (Offset) data, the offset (Offset) data, and the length in the
  • the load balancer reads the first data in the data stream according to the first distribution rule, where the first data is the first distribution rule indicating the determined data read by the load balancer, or the first One data Instructing, by the first distribution rule, start location data, offset data, and length data in the data stream read by the load balancer, or instructing the load balancer to read for the first distribution rule The starting position data, the offset data, the length data, and the mask data in the data stream.
  • the load balancer reads the data in the data stream according to the indication of the distribution rule, generates a keyword according to the read data, and queries the first distribution information according to the generated keyword, thereby determining an application server that processes the data stream.
  • the load balancer generates a keyword according to the data in the read data stream.
  • the load balancer may perform one or more data in the read data stream to generate a keyword according to a defined algorithm.
  • the algorithm for generating a keyword may include various types of conventional algorithms, such as performing OR, AND, plus, and subtraction operations.
  • the load balancer reads data in the data stream according to the indication information in the forwarding rule, for example, reading field 1 and field 2 in the data stream, and the algorithm for generating the keyword may be a plus (+) operation, that is, the keyword is Field 1 + Field 2.
  • the load balancer can flexibly read data in the data stream according to the indication of the distribution rule sent by the application server or configured on the load balancer, and generate the data according to the read data.
  • the load balancer reads the data in the data stream according to the distribution rule, generates a keyword according to the data of the read data stream, queries the distribution information according to the generated keyword, and determines an application server that processes the data stream according to the first distribution information.
  • the distribution information may be configured in the load balancer according to the interface protocol, or the application server generates and sends the information to the load balancer according to the interface protocol, which is not limited by the present invention.
  • the distribution information includes a correspondence between keywords generated according to data in the interface protocol and application server information processing the data stream.
  • the application server that processes the data stream may be determined according to the correspondence between the keyword generated by the data in the interface protocol and the application server information of the processed data stream.
  • the distribution information is a correspondence relationship between a keyword generated according to data in the interface protocol and application server information processing the data stream, and the load balancer may generate a keyword according to the data generated by the read data stream.
  • the first distribution information may include a correspondence between a keyword generated according to the first data in the interface protocol and application server information that processes the data flow, where the load balancer queries according to the keyword Determining an application server that processes the data stream according to the first distribution information, including: the load balancer generates, according to the keyword, the keyword generated according to the first data in the data stream Corresponding to the processing server information processing the data stream, acquiring application server information for processing the data stream, and determining an application server that processes the data stream. Therefore, based on the technical solution provided by the embodiment of the present invention, the load balancer can read the data in the data flow according to the indication in the general distribution rule, and determine the application server that processes the data flow according to the keyword generated by the read data. , the data stream is sent to the determined application server. The load balancer can distribute the data stream according to the general distribution rule, and reduces the complexity of the data stream distribution processing by the load balancer.
  • the load balancer reads the first data in the data stream according to the indication of the first distribution rule, generates a keyword according to the read first data, and queries the first distribution information according to the keyword.
  • the first distribution information includes a correspondence between a keyword generated according to the first data of the interface protocol and a second distribution rule.
  • the second distribution rule includes means for instructing the load balancer to read the second data in the data stream, according to The second data in the read data stream generates a keyword, and the indication information of the second distribution information is queried according to the keyword.
  • the second distribution information includes a correspondence between a keyword generated according to the second data of the interface protocol and application server information of the processed data flow, and the load balancer queries the second distribution information according to the keyword, according to the Determining, by the second distribution information, an application server that processes the data stream, including: between the keyword generated by the load balancer according to the keyword, the second protocol data, and application server information of a processed data stream Corresponding relationship, obtaining information of the application server that processes the data stream, and determining an application server that processes the data stream.
  • the application server of the stream enables the load balancer to read more specific data in the data stream according to the specific conditions of the interface protocol, distribute the data stream to the corresponding application server, and enhance the load balancing capability of the load balancer.
  • the first data and the second data are data in different levels of protocols in the data stream, and the chromatogram of the protocol in which the second data is located is higher than a level of the protocol in which the first data is located.
  • the first data is data of a transport layer control protocol in the data stream
  • the second data is data of an application layer protocol
  • the first data and the second data are in the same chromatographic protocol in the data stream
  • Different data for example, the first data is triplet information of the data stream, and the second data is quintuple information of the data stream. That is, the application server generates specific distribution rules and distribution information according to the interface protocol.
  • the load balancer determines a first distribution rule of the data flow according to the flow characteristic information of the data flow, and reads the data flow according to the indication of the first distribution rule.
  • the quintuple information is obtained by querying the first distribution information according to the keyword generated by the quintuple information, and acquiring the second distribution rule according to the correspondence between the keyword included in the first distribution information and the second distribution rule, according to the And the instruction of the distribution rule reads the seven-tuple information in the data stream, generates a keyword according to the seven-tuple information, queries the second distribution information, and further generates the key according to the seven-tuple included in the second distribution information.
  • the correspondence between the word and the specific application server information determines the application server that processes the data stream.
  • the load balancer can read data in the data stream according to the indication in the general distribution rule, and generate the data according to the read data.
  • the keyword determines the application server that processes the data stream and sends the data stream to the determined application server.
  • the load balancer can distribute the data stream according to the general distribution rule, and reduces the complexity of the data stream distribution processing by the load balancer. And by nesting another distribution rule in the distribution information, and then determining the application server that processes the data flow according to the indication of another distribution rule, so that the load balancer can read the data flow more specifically according to the specific conditions of the interface protocol. Data, distribute the data stream to the corresponding application server, and enhance the load balancing capability of the load balancer.
  • the following is a specific embodiment of the embodiment of the invention shown in FIG.
  • the method can be performed by a load balancer, but the invention is not limited thereto.
  • the load balancer receives the data stream and determines the distribution rules of the data stream.
  • the distribution rules can be sent by the application server to the load balancer or distributed on the load balancer.
  • the distribution rule may be generated by the application server according to the interface protocol data and sent to the load balancer or configured to distribute the rules in the load balancer according to the interface protocol data.
  • the distribution rule (distribution rule 1) has a correspondence with the stream feature information of the data stream.
  • the flow feature information is information that can identify the data flow, and may be an IP address, a triplet, or a quintuple information.
  • the present invention is not limited thereto; the distribution rule includes indication information, and the indication information is used for
  • the load balancer is instructed to read the data in the data stream, generate a keyword according to the read data, and determine an application server that processes the data stream according to the generated keyword. Specifically, the distribution information may be queried according to the generated keyword.
  • the distribution information includes a correspondence between a keyword generated based on the interface protocol data and application server information processing the data stream.
  • the load balancer can thereby determine the distribution information of the data stream.
  • the distribution information includes a correspondence between the keyword generated according to the data of the interface protocol and the information of the application server that processes the data stream, and the load balancer may, according to the indication information, generate the keyword, the keyword, and the keyword.
  • the distribution rule includes a correspondence between the keyword and another distribution rule (distribution rule 2), that is, the load balancer may indicate the indication information according to the generated keyword, the keyword, and another distribution rule. Corresponding relationship, the other distribution rule is determined, and then the application server that processes the data stream is determined according to the another distribution rule (step may refer to the relevant step of determining the application server that processes the data stream according to the distribution rule 1).
  • the load balancer determines an application server that processes the data stream according to the distribution rule.
  • the load balancer reads the data in the data stream according to the indication information in the distribution rule 1.
  • the main way to read the data in the data stream is as follows.
  • the indication information in the distribution rule instructs the load balancer to read the finger in the data stream.
  • Set the data For example, the source IP address, the destination IP address, the triplet information, the quintuple information, or the quintuple information in the data stream are read.
  • the indication information in the distribution rule instructs the load balancer to read the start data (Offset) data, the offset (Offset) data, and the length (Length) data in the data stream; or read the start position in the data stream ( Begin) Data, Offset data, Length data, and Mask data.
  • the indication information in the distribution rule may instruct the load balancer to read one or more data in the data stream. Further, the indication information in the distribution rule instructs the load balancer to generate a keyword according to the read data.
  • the algorithm for generating a keyword may include various types of conventional algorithms, such as performing OR, AND, ADD, DEC, VALUE, VALUE, NUMBER, AND NON.
  • the load balancer reads the field 1 and the field 2 in the protocol data in the data flow according to the indication information in the forwarding rule, and the algorithm for generating the keyword may be a plus (+) operation, that is, the keyword is the field 1+ field 2.
  • the load balancer determines the distribution information according to the keyword according to the indication information in the distribution rule. There are two ways to determine the distribution of information based on keywords:
  • the distribution information includes a correspondence between keywords generated by the interface protocol data and information of the application server or a keyword generated by the interface protocol data and another score. Correspondence between rules. Then, the load balancer can determine the distribution information according to the keyword and the corresponding relationship described above.
  • the load balancer compares the keyword with the preset value according to the indication information in the distribution rule. If the keyword is the same as the preset value, the distribution information is determined to be the distribution information A. If the keyword is different from the preset value, the determination is determined. The distribution information is distribution information B.
  • the load balancer determines the distribution information according to the indication information in the distribution rule. If the determined distribution information includes information of the application server that processes the data stream, the load balancer may determine the application server that processes the data stream according to the acquired information of the application server that processes the data stream.
  • the load balancer receives the data flow, and obtains the flow feature information of the data flow, and the flow feature information may be the source IP address of the data flow; the load balancer determines the distribution rule of the data flow according to the flow characteristic information of the data flow, and the distribution rule includes Instructing the load balancer to read the triplet information in the data stream, generating a keyword according to the triplet information, and determining the distribution information according to the keyword, and the load balancer reads the ternary of the data flow according to the indication information in the distribution rule.
  • the load balancer can read the data in the data stream according to the indication information in the distribution rule sent or configured by the application server, and determine the application server that processes the data stream. The complexity of the load balancer to distribute the data stream is reduced, and the effect of load balancing is achieved.
  • the load balancer determines the distribution rule according to the flow feature information of the data flow, and determines the distribution information according to the distribution rule, where the determined distribution information further includes another distribution rule, and the load balancer according to the another distribution rule Identify another distribution, and further Identify the application server that processes the data stream.
  • the load balancer receives the data stream, obtains the stream feature information in the data stream, and may be the triplet information of the data stream, and determines the distribution rule 1 of the data stream according to the triplet information of the data stream; the load balancer According to the indication information in the distribution rule 1, reading the data in the data stream may be reading the quintuple information in the data stream, generating a keyword according to the quintuple information of the read data stream, and determining the distribution according to the keyword.
  • Information 1 includes a keyword generated according to the quintuple information in the interface protocol data and a distribution rule 2, and the load balancer generates a keyword and a distribution rule according to the quintuple information in the interface protocol data.
  • the distribution rule 2 includes a seven-tuple indicating that the load balancer reads the data stream (or may be TCP protocol data indicating the read data stream, GDP protocol data, etc.) Determining, according to the read seven-tuple data, a distribution information 2 including a keyword generated according to the seven-tuple information of the interface protocol data and processing the data stream Based on the correspondence between the application servers, the load balancer may determine an application server that processes the data stream according to the distribution information 2, and distribute the data stream to the application server for processing.
  • FIG. 3 is a schematic block diagram of a data stream distribution apparatus according to an embodiment of the present invention.
  • the apparatus may be a load balancer in the foregoing embodiment, which is not limited by the present invention.
  • the apparatus can be used to perform the data stream distribution method provided by the above embodiments. This embodiment and the above embodiments can be referred to each other.
  • the receiving unit 301 is configured to receive a data stream.
  • the processing unit 302 is configured to read the first part of the data stream according to the first distribution rule. a data, generating a keyword according to the first data in the read data stream, querying the first distribution information according to the keyword, and determining, according to the first distribution information, an application server that processes the data stream,
  • the first distribution rule and the first distribution information are generated by the application server according to the interface protocol and sent to the device, or the first distribution rule and the first distribution information are configured on the device according to an interface protocol;
  • the sending unit 303 is configured to send the data stream to the determined application server.
  • the load balancer may read the data in the data flow according to the indication sent by the application server according to the interface protocol or according to the distribution rule configured on the load balancer by the interface protocol, according to The generated data generates keywords, determines the application server that processes the data stream, and sends the data stream to the determined application server.
  • the load balancer can read the data stream according to the indication of the general distribution rule, and then distribute the data stream, thereby reducing the complexity of the data stream distribution processing by the load balancer.
  • the first data of the first data is the first distribution rule indicating the determined data read by the load balancer; or the first data is the first distribution rule indicating the load Starting bit data, offset data, and length data in the data stream read by the equalizer; or the first data is in the data stream read by the load balancer by the first distribution rule Start position data, offset data, length data, and mask data.
  • the processing unit 302 reads the data in the data stream, can read the data determined in the data stream according to the indication in the distribution rule, or read the starting position data, the offset data, and the length data in the data stream, or Read start position data, offset data, length data, and mask data in the data stream.
  • the load balancer reads the data stream according to the indication information in the application server or the distribution rule configured on the load balancer.
  • the related data enables the load balancer to analyze the increasingly complex and diverse interface protocols, and reduces the complexity of the data distribution and distribution of the load balancer itself.
  • the first distribution rule includes: instructing the load balancer to read the first data in the data stream, and generating a keyword according to the first data in the read data stream, according to the The keyword queries the indication information of the first distribution information.
  • the first distribution information includes a correspondence between a keyword generated according to the first data in the interface protocol and application server information that processes the data stream.
  • the processing unit 302 is configured to query the first distribution information according to the keyword, and determine, according to the first distribution information, an application server that processes the data stream, where the processing unit 302 is configured to use the keyword according to the keyword Obtaining, according to the correspondence between the keyword generated by the first data in the interface protocol and the application server information processing the data flow, acquiring application server information for processing the data flow, and determining an application for processing the data flow server.
  • the apparatus can flexibly read data in the data stream according to the indication of the distribution rule sent by the application server or configured on the load balancer, and generate the data according to the read data.
  • the keyword determines the distribution information to determine the application server that processes the data stream.
  • the first distribution information includes a correspondence between a keyword generated according to the first data of the interface protocol and a second distribution rule; the processing unit 302 is configured to: Determining the first distribution information according to the keyword, and determining, by the first distribution information, the application server that processes the data stream, where the processing unit 302 is configured to use the interface protocol according to the keyword Corresponding relationship between the first data generated keyword and the second distribution rule, determining the second distribution rule Then, an application server that processes the data stream is determined according to the second distribution rule.
  • the second distribution rule includes: instructing the device to read second data in the data stream, and generating a keyword according to the second data in the read data stream, according to the key
  • the word queries the indication information of the second distribution information.
  • the second distribution information includes a correspondence between the keyword generated according to the second data of the interface protocol and the application server information of the processed data stream, and the processing unit 302 queries the second distribution information according to the keyword, Determining, according to the second distribution information, an application server that processes the data stream, including: the processing unit 302, according to the keyword, a keyword generated according to the second data of the interface protocol, and an application server that processes the data stream Corresponding relationship between the information, acquiring information of the application server that processes the data stream, and determining an application server that processes the data stream.
  • the data stream distribution apparatus nests other distribution rules in the distribution rule to instruct the apparatus to read data in the data stream, so that the apparatus can read more detailed data in the data stream.
  • the specific conditions of the interface protocol more specific data in the data stream can be read, and the data stream is accurately distributed to the corresponding application server for processing according to the read data, thereby enhancing the load balancing capability of the data stream distribution device.
  • the first data and the second data are data in different levels of protocols in the data stream, and the level of the protocol in which the second data is located is higher than a level of the protocol in which the first data is located; Or the first data and the second data are different data in the same chromatography protocol in the data stream.
  • the processing unit 302 is further configured to acquire flow feature information of the data flow, and determine a first distribution of the data flow according to a correspondence between the flow feature information of the data flow and the first distribution rule. rule.
  • FIG. 4 is a schematic diagram of an apparatus for distributing data streams according to an embodiment of the present invention.
  • the device may be the load balancer in the above embodiment, which is not limited in the present invention.
  • the apparatus can perform the method of the above embodiments.
  • the embodiments of the present invention and the above embodiments can be referred to each other.
  • a receiver 401 configured to receive a data stream
  • the processor 402 is configured to: read, according to the first distribution rule, the first data in the data stream, generate a keyword according to the first data in the read data stream, and query the first distribution according to the keyword And determining, according to the first distribution information, an application server that processes the data stream, where the first distribution rule and the first distribution information are generated by an application server according to an interface protocol and sent to the device, or the first The distribution rule and the first distribution information are configured on the device according to an interface protocol;
  • the sender 403 is configured to send the data stream to the determined application server.
  • the device may be a load balancer, and the load balancer may be configured according to an indication that the application server sends according to an interface protocol or configured according to an interface protocol on a load balancer.
  • the data in the data stream is read, and the application server that processes the data stream is determined according to the keyword generated by the read data, and the data stream is sent to the determined application server.
  • the load balancer can read the data stream according to the indication of the general distribution rule, and then distribute the data stream, thereby reducing the complexity of the data stream distribution processing by the load balancer.
  • the first data of the first data is the first distribution rule indicating the determined data read by the load balancer; or the first data is the first distribution rule indicating the device Reading the start position data, the offset data, and the length data in the data stream; or the first data is the first distribution rule indicating the start position data in the data stream read by the device , offset data, length data, and mask data.
  • the processor 402 reads the data in the data stream to read the data determined in the data stream according to the indication in the distribution rule, or read the start position data, the offset data, and the length data in the data stream, or Read start position data, offset data, length data, and mask data in the data stream.
  • the load balancer reads related data in the data flow according to the indication information in the application server or the distribution rule configured on the load balancer, so that the load balancer can analyze the increasingly complex and diverse interface protocols and reduce the load.
  • the equalizer itself performs the complexity of data stream parsing and distribution.
  • the first distribution rule includes: instructing the load balancer to read the first data in the data stream, and generating a keyword according to the first data in the read data stream, according to the The keyword queries the indication information of the first distribution information.
  • the first distribution information includes a correspondence between a keyword generated according to the first data in the interface protocol and application server information that processes the data stream.
  • the processor 402 is configured to query the first distribution information according to the keyword, and determine, according to the first distribution information, an application server that processes the data stream, where the processor 402 is configured to use the keyword according to the keyword Obtaining, according to the correspondence between the keyword generated by the first data in the interface protocol and the application server information processing the data flow, acquiring application server information for processing the data flow, and determining an application for processing the data flow server.
  • the apparatus can flexibly read data in the data stream according to the indication of the distribution rule sent by the application server or configured on the load balancer, and generate the data according to the read data.
  • the keyword determines the distribution information to determine the application server that processes the data stream.
  • the first distribution information includes a correspondence between a keyword generated according to the first data of the interface protocol and a second distribution rule; the processor 402 is configured to: Determining, according to the keyword, the first distribution information, determining, according to the first distribution information, an application server that processes the data stream, where the processor 402 is configured to use, according to the keyword, the interface protocol Corresponding relationship between the first data generated keyword and the second distribution rule determines the second distribution rule, and determines an application server that processes the data stream according to the second distribution rule.
  • the second distribution rule includes: instructing the load balancer to read the second data in the data stream, and generating a keyword according to the second data in the read data stream, according to the The keyword queries the indication information of the second distribution information.
  • the second distribution information includes a correspondence between a keyword generated according to the second data of the interface protocol and application server information of the processed data stream, and the processor 402 queries the second distribution information according to the keyword, Determining, according to the second distribution information, an application server that processes the data stream, comprising: the processor 402, according to the keyword, a keyword generated according to the second data of the interface protocol, and an application server that processes the data stream Corresponding relationship between the information, acquiring information of the application server that processes the data stream, and determining an application server that processes the data stream.
  • the data stream distribution apparatus nests other distribution rules in the distribution rule to instruct the apparatus to read data in the data stream, so that the apparatus can read more detailed data in the data stream.
  • the specific conditions of the interface protocol more specific data in the data stream can be read, and the data stream is accurately distributed to the corresponding application server for processing according to the read data, thereby enhancing the load balancing capability of the data stream distribution device.
  • the first data and the second data are data in different levels of protocols in the data stream, and the level of the protocol in which the second data is located is higher than a level of the protocol in which the first data is located; Or the first data and the second data are the same in the data stream Different data in the chromatography protocol.
  • the processor 402 is further configured to acquire flow feature information of the data stream, and determine a first distribution of the data flow according to a correspondence between the flow feature information of the data flow and the first distribution rule. rule.
  • the processor may be a central processing unit (“CPU"), and the processor may also be other general-purpose processors, digital signal processors (DSPs), and dedicated processors. Integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the above steps may be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software.
  • the steps of the method disclosed in the embodiments of the present invention may be directly implemented as a hardware processor, or may be performed by a combination of hardware and software modules in the processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, or an electrical, mechanical or other form of connection.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention contributes in essence or to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • Including a number of instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to execute All or part of the steps of the method described in various embodiments of the invention.
  • the foregoing storage medium includes: a USB flash drive, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a disk or a CD.
  • ROM Read-Only Memory
  • RAM Random Access Memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer And Data Communications (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Communication Control (AREA)

Abstract

本发明公开了一种数据流分发的方法和装置，该方法中：负载均衡器可以根据应用服务器根据接口协议发送的或者根据接口协议配置于负载均衡器上的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则的指示，读取数据流的数据，进而进行数据流的分发，降低了负载均衡器进行数据流分发处理的复杂程度。

Description

数据流分发方法和设备 技术领域
本发明实施例涉及通信领域，并且更具体地，涉及数据流分发方法和装置。
背景技术
数据流由多层协议组成，当前数据流分发的方法一般为：负载均衡器接收数据流，解析获取接收到的数据流中的协议数据，一般为数据流的目的IP地址、三元组或者五元组等信息，根据获取到的数据流中的协议数据对数据流进行分发，将相同协议数据的数据流以哈希或者轮询的方法发送到应用服务器进行处理。
根据现有技术中提供的数据流分发方法，负载均衡器需解析数据流中的具体协议进行数据流的分发，然而随着接口协议的多样化和复杂化，负载均衡器本身需要对各类接口协议的数据流进行解析，导致负载均衡器本身对于数据流的分发处理愈发复杂。
发明内容
本发明实施例提供一种数据流分发的方法和装置，降低负载均衡器进行数据流分发处理的复杂度。
第一方面，提供了一种数据流分发的方法，包括：负载均衡器接收数据流；所述负载均衡器根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数 据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述负载均衡器的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述负载均衡器上；所述负载均衡器将所述数据流发送至所述确定的应用服务器。
结合第一方面，在第一种可能的实现方式中，所述第一数据为所述第一分发规则指示所述负载均衡器读取的确定的数据；或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据和长度数据；或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。
结合第一方面和第一方面的第一种可能的实现方式，在第二种可能的实现方式中，所述第一分发规则中包括用于指示所述负载均衡器读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
结合第一方面或结合第一方面的第一种或第二种可能的实现方式，在第三种可能的实现方式中，所述第一分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，所述负载均衡器根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述负载均衡器根据所述关键字，所述根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服 务器。
结合第一方面或结合第一方面的第一种至第三种中任一可能的实现方式，在第四种可能的实现方式中，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；所述负载均衡器根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述负载均衡器根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规则，根据所述第二分发规则确定处理所述数据流的应用服务器。
结合第一方面的第四种可能的实现方式，在第五种可能的实现方式中，所述第二分发规则中包括用于指示所述负载均衡器读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。
结合第一方面的第五种可能的实现方式，在第六种可能的实现方式中，所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，所述负载均衡器根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：所述负载均衡器根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。
结合第一方面的第五种或第六种可能的实现方式，在第七种可能 的实现方式中，所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据。
结合第一方面或者第一方面的第一种至第七种中任一可能的实现方式，在第八种实现方式中，所述负载均衡器获取所述数据流的流特征信息；所述负载均衡器根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
第二方面，提供了一种数据流分发的方法，包括：接收单元，用于接收数据流；处理单元，用于根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述负载均衡器的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述负载均衡器上；发送单元，用于将所述数据流发送至所述确定的应用服务器。
结合第二方面，在第一种可能的实现方式中，所述第一数据为所述第一分发规则指示所述负载均衡器读取的确定的数据；或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据和长度数据；或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。
结合第二方面和第二方面的第一种可能的实现方式，在第二种可能的实现方式中，所述第一分发规则中包括用于指示所述负载均衡器读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
结合第二方面或结合第二方面的第一中或第二种任一可能的实现方式，在三种可能的实现方式中，所述第一分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，所述处理单元用于根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理单元用于根据所述关键字，所述根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。
结合第二方面或结合第二方面的第一种至第三种中任一可能的实现方式，在第四种可能的实现方式中，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；所述处理单元用于根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理单元用于根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规则，根据所述第二分发规则确定处理所述数据流的应用服务器。
结合第二方面的第四种可能的实现方式，在第五种可能的实现方 式中，所述第二分发规则中包括用于指示所述负载均衡器读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。
结合第二方面的第五种可能的实现方式，在第六种可能的实现方式中，所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，
所述处理单元根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：
所述处理单元根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。
结合第二方面的第五种或第六种可能的实现方式，在第七种可能的实现方式中，所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据。
结合第二方面或者第二方面的第一种至第七种中任一可能的实现方式，在第八种实现方式中，所述处理单元还用于获取所述数据流的流特征信息；根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
第三方面，提供了一种数据流分发的方法，包括：接收器，用于 接收数据流；处理器，用于根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述装置的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述装置上；发送器，用于将所述数据流发送至所述确定的应用服务器。
结合第三方面，在第一种可能的实现方式中，所述第一数据为所述第一分发规则指示所述装置读取的确定的数据；或者所述第一数据为所述第一分发规则指示所述装置读取的所述数据流中起始位置数据、偏移量数据和长度数据；或者所述第一数据为所述第一分发规则指示所述装置读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。
结合第三方面和第三方面的第一种可能的实现方式，在第二种可能的实现方式中，所述第一分发规则中包括用于指示所述装置读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
结合第三方面或结合第三方面的第一中或第二种任一可能的实现方式，在三种可能的实现方式中，所述第一分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，所述处理器用于根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包 括：所述处理器用于根据所述关键字，所述根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。
结合第三方面或结合第三方面的第一种至第三种中任一可能的实现方式，在第四种可能的实现方式中，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；所述处理器用于根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理单元用于根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规则，根据所述第二分发规则确定处理所述数据流的应用服务器。
结合第三方面的第四种可能的实现方式，在第五种可能的实现方式中，所述第二分发规则中包括用于指示所述装置读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。
结合第三方面的第五种可能的实现方式，在第六种可能的实现方式中，所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，所述处理器根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：所述处理器根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息 之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。
结合第三方面的第五种或第六种可能的实现方式，在第七种可能的实现方式中，所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据。
结合第三方面或者第三方面的第一种至第七种中任一可能的实现方式，在第八种实现方式中，所述处理器还用于获取所述数据流的流特征信息；根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
因此，结合本发明实施例提供的上述技术方案，负载均衡器可以根据应用服务器根据接口协议发送的或者根据接口协议配置于负载均衡器上的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则的指示，读取数据流的数据，进而进行数据流的分发，降低了负载均衡器进行数据流分发处理的复杂程度。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对本发明实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面所描述的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得 其他的附图。
图1示出了本发明实施例提供的网络架构图。
图2示出了本发明实施例提供的一种数据流分发方法的示意性流程图。
图3示出了本发明实施例提供的一种数据流分发装置的示意性框图。
图4示出了本发明实施例提供的一种数据流分发装置的示意性框图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明的一部分实施例，而不是全部实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都应属于本发明保护的范围。
应理解，本发明实施例的技术方案可以应用于各种通信系统，例如：全球移动通讯(Global System of Mobile communication，简称为“GSM”)系统、码分多址(Code Division Multiple Access，简称为“CDMA”)系统、宽带码分多址(Wideband Code Division Multiple Access，简称为“WCDMA”)系统、通用分组无线业务(General Packet Radio Service，简称为“GPRS”)、长期演进(Long Term Evolution，简称为“LTE”)系统、LTE频分双工(Frequency Division Duplex，简称为“FDD”)系统、LTE时分双工(Time Division Duplex， 简称为“TDD”)、通用移动通信系统(Universal Mobile Telecommunication System，简称为“UMTS”)、全球互联微波接入(Worldwide Interoperability for Microwave Access，简称为“WiMAX”)通信系统等。
图1示出了本发明实施例的一种应用场景的网络架构图。如图1所示，负载均衡器101为一种采用各种分配算法将网络请求分散到各个可用的应用服务器上，从而使得网络访问者获得尽可能最佳的网络体验的设备；一般地，负载均衡器有不同的形式，除了可以作为独立意义上的负载均衡器外，也可能集成在其他通信设备上，以达到将网络请求分散到各个应用服务器的效果，负载均衡器一般可以与多个应用服务器连接。应用服务器102一般为用于处理多种不同的网络请求的服务器，应用服务器可以单独存在，也可以为通信设备(例如Gateway GPRS Support Node或Serving GPRS SUPPORT NODE等)中处理不同请求，进行内部负载均衡的节点。
图2示出了本发明实施例提供的一种数据流分发的方法的示意性流程图。该方法可以由负载均衡器执行，但是本发明对此并不限制。如图2所示，该方法包括：
S201、负载均衡器接收数据流；
S202、所述负载均衡器根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述负载均衡器的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述负载均衡器上；
S203、所述负载均衡器将所述数据流发送至所述确定的应用服务器。
一般地，应用服务器有一个或多个业务接口，一个接口对应的协议的层次一般有多层，例如对应的协议包括因特网互联(Internet Protocol，简称为“IP”)协议，还可以包括传输层控制(Transmission Control Protocol，简称为“TCP”)协议、或用户数据报(User Datagram Protocol，简称为“UDP”)协议、或流传输控制(Stream Control Transmission Protocol，简称为“SCTP”)协议，还可以包括应用层协议。接口对应的协议(简称接口协议)的情况与具体的接口相关。应用服务器可以根据接口协议的数据生成分发规则和分发信息。具体地，应用服务器可以根据一种接口协议的数据生成一种分发规则和分发信息，并发送至负载均衡器，以指示负载均衡器根据数据流中具体的协议数据，对数据流进行分发，使得负载均衡器可以根据指示解析当前日益多样化且繁杂的协议类型，并对相应数据流进行准确的分发处理，使得负载均衡器的负载均衡能力得到提高，且降低负载均衡器本身需要对各类接口协议的数据流进行解析的复杂程度。类似的，也可以根据接口协议的数据在负载均衡器上配置分发规则和分发信息。
因此，基于本发明实施例提供的技术方案，负载均衡器可以根据应用服务器根据接口协议发送的或者根据接口协议配置于负载均衡器上的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则的指示，读取数据流的数据，进而进行数据流的分发，降低了负载均衡器进行数据 流分发处理的复杂程度。
负载均衡器接收数据流后，获取数据流的流特征信息，所述流特征信息为可以用于标识数据流的信息。例如，数据流的流特征信息可以为数据流的源IP地址、目的IP地址、三元组信息或者五元组信息等，本发明对此并不限制。
负载均衡器获取数据流的流特征信息，根据数据流的流特征信息，确定数据流的第一分发规则。分发规则和数据流的流特征信息之间存在对应关系，负载均衡器可以根据数据流的流特征信息，确定数据流的第一分发规则。
分发规则中包括用于指示所述负载均衡器读取数据流中的数据，根据数据流中的数据生成关键字，根据关键字查询第一分发信息的指示信息。即第一分发规则中包括用于指示所述负载均衡器读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
负载均衡器根据分发规则的指示读取数据流中的数据的方式主要有以下方式：一是负载均衡器根据分发规则的指示，读取数据流中确定的数据，例如负载均衡器根据分发规则的指示，读取数据流的IP地址或者端口号等数据，二是负载均衡器根据分发规则的指示，读取数据流中起始位置(Begin)数据、偏移量(Offset)数据和长度(Length)数据，或者读取数据流中起始位置(Begin)数据、偏移量(Offset)数据、长度(Length)数据和掩码(Mask)数据。因此，负载均衡器根据第一分发规则，读取数据流中的第一数据，所述第一数据为所述第一分发规则指示所述负载均衡器读取的确定的数据，或者所述第一数据 为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据和长度数据，或者为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。负载均衡器根据分发规则的指示，读取数据流中的数据，根据读取的数据生成关键字，根据生成的关键字查询第一分发信息，从而确定处理数据流的应用服务器。所述负载均衡器根据读取的所述数据流中的数据生成关键字，具体可以是负载均衡器将读取的数据流中的一个或多个数据，按照定义的算法进行运算生成关键字。生成关键字的算法可以包括多种类型的常规算法，例如进行或、与、加、减等运算。例如：负载均衡器根据转发规则中的指示信息读取数据流中的数据，例如读取数据流中的字段1和字段2，生成关键字的算法可以是加(+)运算，即关键字为字段1+字段2。
因此，基于本发明实施例提供的技术方案，负载均衡器可以根据应用服务器发送的或者配置于负载均衡器上的分发规则的指示，灵活读取数据流中的数据，根据读取的数据生成的关键字，确定分发信息，从而确定处理数据流的应用服务器。
负载均衡器根据分发规则，读取数据流中的数据，根据读取的数据流的数据生成关键字，根据生成的关键字查询分发信息，根据第一分发信息确定处理数据流的应用服务器。其中，分发信息可以是根据接口协议配置于负载均衡器中，或者应用服务器根据接口协议生成并发送至负载均衡器的，本发明对此并不限制。分发信息中包括根据接口协议中的数据生成的关键字和处理数据流的应用服务器信息之间的对应关系。
负载均衡器根据读取的数据流的数据生成关键字后，可以根据接口协议中数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，确定处理数据流的应用服务器。此处，分发信息为根据接口协议中数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，负载均衡器可以根据读取的数据流的数据生成的关键字，在上述分发信息(多个根据接口协议中数据生成的关键字和处理数据流的应用服务器信息之间的对应关系)中，查询与根据读取的数据流的数据生成的关键字对应的对应关系。即第一分发信息中可以包括根据所述接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，所述负载均衡器根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述负载均衡器根据所述关键字，所述根据所述数据流中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。因此，基于本发明实施例提供的技术方案，载均衡器可以根据通用的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则，进行数据流的分发，降低了负载均衡器进行数据流分发处理的复杂程度。
在本发明的另一实施例中，负载均衡器根据第一分发规则的指示，读取数据流中的第一数据，根据读取的第一数据生成关键字，根据关键字查询第一分发信息，该第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系。所述第二分发规则中包括用于指示所述负载均衡器读取所述数据流中的第二数据，根据 读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，所述负载均衡器根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：所述负载均衡器根据所述关键字、所述第二协议数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。由此，通过在分发信息中嵌套另一分发规则，根据另一分发规则的指示，读取数据流中的其他数据，进而根据其他数据生成的关键字，查询其他分发信息，进而确定处理数据流的应用服务器，使得负载均衡器可以根据接口协议的具体情况，读取数据流中更加具体的数据，将数据流分发至相应的应用服务器上，增强负载均衡器的负载均衡能力。
具体地，所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层析高于所述第一数据所处协议的层次(例如第一数据为数据流中传输层控制协议的数据，第二数据为应用层协议的数据)；或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据(例如第一数据为数据流的三元组信息、第二数据为数据流的五元组信息)。即应用服务器根据接口协议的情况，生成具体的分发规则和分发信息。
例如，负载均衡器在接收数据流后，根据数据流的流特征信息确定数据流的第一分发规则，根据第一分发规则的指示，读取数据流中 的五元组信息，根据五元组信息生成的关键字，查询获取第一分发信息，根据第一分发信息中包括的关键字与第二分发规则的对应关系，获取第二分发规则，根据第二分发规则的的指示，读取数据流中的七元组信息，根据七元组信息生成关键字，查询获取第二分发信息，进而根据第二分发信息中包括的根据七元组生成的关键字和具体应用服务器信息之间的对应关系，确定处理数据流的应用服务器。
因此，基于本发明实施例提供的技术方案，基于本发明实施例提供的技术方案，负载均衡器可以根据通用的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则，进行数据流的分发，降低了负载均衡器进行数据流分发处理的复杂程度。且通过在分发信息中嵌套另一分发规则，进而根据另一分发规则的指示，确定处理数据流的应用服务器，使得负载均衡器可以根据接口协议的具体情况，读取数据流中更加具体的数据，将数据流分发至相应的应用服务器上，增强负载均衡器的负载均衡能力。
下述为图2示出的本发明实施例的一个具体实施例。该方法可以由负载均衡器执行，但是本发明对此并不限制。
首先、负载均衡器接收数据流，确定数据流的分发规则。
一般地，可以由应用服务器发送分发规则至负载均衡器，或者在负载均衡器上配置分发规则。该分发规则可以由应用服务器根据接口协议数据生成并发送分发规则至负载均衡器或者根据接口协议数据在负载均衡器配置分发规则。
该分发规则(分发规则1)与数据流的流特征信息存在对应关系。 该流特征信息为可以标识数据流的信息，一般可以为IP地址、三元组或者五元组信息等，本发明对此并不限制；该分发规则中包括指示信息，该指示信息为用于指示负载均衡器，读取数据流中的数据，根据读取的数据生成关键字，根据生成的关键字确定处理数据流的应用服务器，具体地，可以根据生成的关键字查询分发信息。分发信息包括根据接口协议数据生成的关键字和处理数据流的应用服务器信息之间的对应关系。若分发信息中包括的根据接口协议数据生成的关键字与负载均衡器根据读取的数据生成的关键字之间存在对应关系，则负载均衡器可由此确定该数据流的分发信息。该分发信息中包括根据接口协议的数据生成的关键字和处理数据流的应用服务器的信息的对应关系，则负载均衡器可在该指示信息的指示下，根据生成的关键字、该关键字和处理数据流的应用服务器的信息的对应关系，获取处理数据流的应用服务器信息，确定处理数据流的应用服务器。若该分发规则包括该关键字和另一分发规则(分发规则2)的对应关系，即负载均衡器可在该指示信息的指示信，根据生成的关键字、该关键字和另一分发规则的对应关系，确定该另一分发规则，进而根据该另一分发规则，确定处理数据流的应用服务器(步骤可参考根据分发规则1确定处理数据流的应用服务器的相关步骤)。
其次、负载均衡器根据分发规则，确定处理数据流的应用服务器。
具体地，负载均衡器根据分发规则1中的指示信息，读取数据流中的数据。读取数据流中的数据主要有以下方式。
1、该分发规则中的指示信息指示负载均衡器读取数据流中的指 定数据。例如读取数据流中的源IP地址、目的IP地址、三元组信息、五元组信息或者七元组信息等。
2、该分发规则中的指示信息指示负载均衡器读取数据流中起始位置(Begin)数据、偏移量(Offset)数据和长度(Length)数据；或者读取数据流中起始位置(Begin)数据、偏移量(Offset)数据、长度(Length)数据和掩码(Mask)数据。
例如读取：Begin：IP payload Begin
OffSet:AA
Length:BB
Mask:XXXXXXXX
可选地，该分发规则中的指示信息可以指示负载均衡器读取数据流中的一个或多个数据。进一步地，该分发规则中的指示信息指示负载均衡器根据读取的数据，生成关键字。生成关键字的算法可以包括多种类型的常规算法，例如进行或、与、加、减、大于，小于，等于，不等于等运算。例如：负载均衡器根据转发规则中的指示信息读取数据流中协议数据中的字段1和字段2，生成关键字的算法可以是加(+)运算，即关键字为字段1+字段2。
进一步地，负载均衡器根据分发规则中的指示信息，根据关键字确定分发信息。根据关键字确定分发信息有两种方式：
1、分发信息中包括根据接口协议数据生成的关键字和应用服务器的信息的对应关系或者包括接口协议数据生成的关键字和另一分 发规则之间的对应关系。则负载均衡器可以根据关键字和上述的对应关系，确定分发信息。
2、负载均衡器根据分发规则中的指示信息，将关键字与预设值进行比较，若关键字与预设值相同，确定分发信息为分发信息A，若关键字与预设值不同，确定分发信息为分发信息B。
进一步地，负载均衡器根据分发规则中的指示信息，确定分发信息。若确定的分发信息中包括处理数据流的应用服务器的信息，则负载均衡器可以根据获取的处理数据流的应用服务器的信息，确定处理数据流的应用服务器。例如：负载均衡器接收数据流，获取数据流的流特征信息，流特征信息可以为数据流的源IP地址；负载均衡器根据数据流的流特征信息确定数据流的分发规则，分发规则中包括指示负载均衡器读取数据流中的三元组信息，根据三元组信息生成关键字，根据关键字确定分发信息，则负载均衡器根据分发规则中的指示信息，读取数据流的三元组信息，根据三元组信息生成关键字，根据关键字确定分发信息；分发信息中包括根据三元组生成的关键字和处理数据流的应用服务器的信息，则负载均衡器可以根据分发信息确定处理数据流的应用服务器。因此，基于本发明的实施例，负载均衡器可以根据应用服务器发送的或者配置的分发规则中的指示信息，读取数据流中的数据，确定处理数据流的应用服务器。降低了负载均衡器对数据流进行分发处理的复杂程度，达到了负载均衡的效果。
可选地，负载均衡器根据数据流的流特征信息，确定分发规则，进行根据分发规则确定分发信息，该确定的分发信息中还包括有另一分发规则，负载均衡器根据该另一分发规则确定另一分发信息，进而 确定处理数据流的应用服务器。例如：负载均衡器接收数据流，获取数据流中的流特征信息，可以是数据流的三元组信息，根据该数据流的三元组信息，确定该数据流的分发规则1；负载均衡器根据分发规则1中的指示信息，读取数据流中的数据，可以是读取数据流中的五元组信息，根据读取的数据流的五元组信息生成关键字，根据关键字确定分发信息1；该分发信息1中包括根据接口协议数据中的五元组信息生成的关键字和分发规则2，则负载均衡器根据接口协议数据中的的五元组信息生成的关键字和分发规则2的对应关系，确定数据流的分发规则2,该分发规则2中包括指示负载均衡器读取数据流的七元组(或者可以是指示读取数据流的TCP协议数据、GDP协议数据等)，根据该读取的七元组数据确定分发信息2，该分发信息2中包括根据接口协议数据的七元组信息生成的关键字和处理该数据流的应用服务器的对应关系，负载均衡器可以根据该分发信息2确定处理数据流的应用服务器，将数据流分发至该应用服务器进行处理。因此，基于本发明实施例提供的方法，在分发规则中嵌套其他分发规则，以指示负载均衡器读取数据流中的数据，使得负载均衡器可以读取数据流中的更详细数据，可以根据接口协议的具体情况，读取数据流中更加具体的数据，根据读取的数据将数据流准确分发至相应的应用服务器进行处理，增强负载均衡器的负载均衡能力。
图3示出了本发明实施例提供的一种数据流分发装置的示意性框图，该装置可以是上述实施例中的负载均衡器，本发明对此并不限制。该装置可用于执行上述实施例提供的数据流分发方法。本实施例与上述实施例可以相互参考。
接收单元301、用于接收数据流；
处理单元302、用于根据第一分发规则，读取所述数据流中的第 一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述装置的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述装置上；
发送单元303、用于将所述数据流发送至所述确定的应用服务器。
因此，基于本发明实施例提供的技术方案，负载均衡器可以根据应用服务器根据接口协议发送的或者根据接口协议配置于负载均衡器上的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则的指示，读取数据流的数据，进而进行数据流的分发，降低了负载均衡器进行数据流分发处理的复杂程度。
具体地，所述第一数据所述第一数据为所述第一分发规则指示所述负载均衡器读取的确定的数据；或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据和长度数据；或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。所述处理单元302读取数据流中的数据即可按照分发规则中的指示，读取数据流中确定的数据，或者读取数据流中起始位置数据、偏移量数据和长度数据，或者读取数据流中起始位置数据、偏移量数据、长度数据和掩码数据。因此，负载均衡器根据应用服务器或者配置于负载均衡器上的分发规则中的指示信息，读取数据流中的 相关数据，使得负载均衡器可以解析当前日益复杂多样化的接口协议，降低了负载均衡器本身进行数据流解析分发的复杂度。
进一步地，所述第一分发规则中包括用于指示所述负载均衡器读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
在本发明实施例提供的一种数据分发的装置中，所述第一分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，所述处理单元302用于根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理单元302用于根据所述关键字，所述根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。
因此，基于本发明实施例提供的数据流分发装置，该装置可以根据应用服务器发送的或者配置于负载均衡器上的分发规则的指示，灵活读取数据流中的数据，根据读取的数据生成的关键字，确定分发信息，从而确定处理数据流的应用服务器。
在本发明实施例提供的另一数据流分发装置中，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；所述处理单元302用于根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理单元302用于根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规 则，根据所述第二分发规则确定处理所述数据流的应用服务器。具体地，所述第二分发规则中包括用于指示所述装置读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，则所述处理单元302根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：所述处理单元302根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。因此，基于本发明实施例提供的数据流分发装置，在分发规则中嵌套其他分发规则，以指示该装置读取数据流中的数据，使得该装置可以读取数据流中的更详细数据，可以根据接口协议的具体情况，读取数据流中更加具体的数据，根据读取的数据将数据流准确分发至相应的应用服务器进行处理，增强该数据流分发装置的负载均衡能力。
具体地，所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据。
可选地，所述处理单元302还用于获取所述数据流的流特征信息；根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
图4示出了本发明实施例提供的一种数据流分发的装置的示意性 框图。该装置可以是上述实施例中的负载均衡器，本发明对此并不限制。该装置可以执行上述实施例中的方法。本发明实施例与上述实施例可相互参考。
接收器401、用于接收数据流；
处理器402、用于根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述装置的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述装置上；
发送器403、用于将所述数据流发送至所述确定的应用服务器。
因此，基于本发明实施例提供的技术方案，该装置，可以是负载均衡器，负载均衡器可以根据应用服务器根据接口协议发送的或者根据接口协议配置于负载均衡器上的分发规则中的指示，读取数据流中的数据，根据读取的数据生成的关键字，确定处理数据流的应用服务器，将数据流发送确定的应用服务器上。使得负载均衡器可以根据通用的分发规则的指示，读取数据流的数据，进而进行数据流的分发，降低了负载均衡器进行数据流分发处理的复杂程度。
具体地，所述第一数据所述第一数据为所述第一分发规则指示所述负载均衡器读取的确定的数据；或者所述第一数据为所述第一分发规则指示所述装置读取的所述数据流中起始位置数据、偏移量数据和长度数据；或者所述第一数据为所述第一分发规则指示所述装置读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。 所述处理器402读取数据流中的数据即可按照分发规则中的指示，读取数据流中确定的数据，或者读取数据流中起始位置数据、偏移量数据和长度数据，或者读取数据流中起始位置数据、偏移量数据、长度数据和掩码数据。因此，负载均衡器根据应用服务器或者配置于负载均衡器上的分发规则中的指示信息，读取数据流中的相关数据，使得负载均衡器可以解析当前日益复杂多样化的接口协议，降低了负载均衡器本身进行数据流解析分发的复杂度。
进一步地，所述第一分发规则中包括用于指示所述负载均衡器读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
在本发明实施例提供的一种数据分发的装置中，所述第一分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，所述处理器402用于根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理器402用于根据所述关键字，所述根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。
因此，基于本发明实施例提供的数据流分发装置，该装置可以根据应用服务器发送的或者配置于负载均衡器上的分发规则的指示，灵活读取数据流中的数据，根据读取的数据生成的关键字，确定分发信息，从而确定处理数据流的应用服务器。
在本发明实施例提供的另一数据流分发装置中，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；所述处理器402用于根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：所述处理器402用于根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规则，根据所述第二分发规则确定处理所述数据流的应用服务器。具体地，所述第二分发规则中包括用于指示所述负载均衡器读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，则所述处理器402根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：所述处理器402根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。因此，基于本发明实施例提供的数据流分发装置，在分发规则中嵌套其他分发规则，以指示该装置读取数据流中的数据，使得该装置可以读取数据流中的更详细数据，可以根据接口协议的具体情况，读取数据流中更加具体的数据，根据读取的数据将数据流准确分发至相应的应用服务器进行处理，增强该数据流分发装置的负载均衡能力。
具体地，所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；或者所述第一数据与所述第二数据为所述数据流中相同 层析协议中的不同数据。
可选地，所述处理器402还用于获取所述数据流的流特征信息；根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
应理解，在本发明实施例中，该处理器可以是中央处理单元(Central Processing Unit，简称为“CPU”)，该处理器还可以是其他通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在实现过程中，上述各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本发明实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例中描述的各方法步骤和单元，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各实施例的步骤及组成。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。本领域普通技术人员可以对每个特定的应用来使用不同方法来 实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接，也可以是电的，机械的或其它的形式连接。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本发明实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行 本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，简称为“ROM”)、随机存取存储器(Random Access Memory，简称为“RAM”)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (18)

  1. 一种数据流分发方法，其特征在于，包括：
    负载均衡器接收数据流；
    所述负载均衡器根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述负载均衡器的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述负载均衡器上；
    所述负载均衡器将所述数据流发送至所述确定的应用服务器。
  2. 根据权利要求1中所述的方法，其特征在于：
    所述第一数据为所述第一分发规则指示所述负载均衡器读取的确定的数据；
    或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据和长度数据；
    或者所述第一数据为所述第一分发规则指示所述负载均衡器读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。
  3. 根据权利1或2中任一所述的方法，其特征在于，所述第一分发规则中包括用于指示所述负载均衡器读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
  4. 根据权利要求1-3中任一所述的方法，其特征在于，所述第一 分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，
    所述负载均衡器根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：
    所述负载均衡器根据所述关键字，所述根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。
  5. 根据权利要求1-3中任一所述的方法，其特征在于，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；
    所述负载均衡器根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：
    所述负载均衡器根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规则，根据所述第二分发规则确定处理所述数据流的应用服务器。
  6. 根据权利要求5所述的方法，其特征在于，所述第二分发规则中包括用于指示所述负载均衡器读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。
  7. 根据权利要求6所述的方法，其特征在于，所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用 服务器信息之间的对应关系，
    所述负载均衡器根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：
    所述负载均衡器根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。
  8. 根据权利要求6或7中所述的方法，其特征在于，
    所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；
    或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据。
  9. 根据权利要求1-8中任一所述的方法，其特征在于，所述方法还包括：
    所述负载均衡器获取所述数据流的流特征信息；
    所述负载均衡器根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
  10. 一种数据流分发装置，其特征在于，包括：
    接收单元，用于接收数据流；
    处理单元，用于根据第一分发规则，读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键 字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，所述第一分发规则和第一分发信息为应用服务器根据接口协议生成并发送至所述装置的,或者所述第一分发规则和第一分发信息为根据接口协议配置于所述装置上；
    发送单元，用于将所述数据流发送至所述确定的应用服务器。
  11. 根据权利要求10所述的装置，其特征在于
    所述第一数据为所述第一分发规则指示所述装置读取的确定的数据；
    或者所述第一数据为所述第一分发规则指示所述装置读取的所述数据流中起始位置数据、偏移量数据和长度数据；
    或者所述第一数据为所述第一分发规则指示所述装置读取的所述数据流中起始位置数据、偏移量数据、长度数据和掩码数据。
  12. 根据权利要求10或11中任一所述的装置，其特征在于，所述第一分发规则中包括用于指示所述装置读取所述数据流中的第一数据，根据读取的所述数据流中的第一数据生成关键字，根据所述关键字查询第一分发信息的指示信息。
  13. 根据权利要求9-12中任一所述的装置，其特征在于，所述第一分发信息中包括根据接口协议中的第一数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，
    所述处理单元用于根据所述关键字查询第一分发信息，根据所述第一分发信息确定处理所述数据流的应用服务器，包括：
    所述处理单元用于根据所述关键字，所述根据接口协议中的第一 数据生成的关键字和处理所述数据流的应用服务器信息之间的对应关系，获取处理所述数据流的应用服务器信息，确定处理所述数据流的应用服务器。
  14. 根据权利10-12中任一所述的装置，其特征在于，所述第一分发信息中包括根据接口协议的第一数据生成的关键字和第二分发规则的对应关系；
    所述处理单元用于根据所述关键字查询第一分发信息,根据所述第一分发信息确定处理所述数据流的应用服务器，包括：
    所述处理单元用于根据所述关键字，所述根据所述接口协议的第一数据生成的关键字和第二分发规则的对应关系，确定所述第二分发规则，根据所述第二分发规则确定处理所述数据流的应用服务器。
  15. 根据权利要求14所述的装置，其特征在于，所述第二分发规则中包括用于指示所述装置读取所述数据流中的第二数据，根据读取的所述数据流中的第二数据生成关键字，根据所述关键字查询第二分发信息的指示信息。
  16. 根据权利要求15所述的装置，其特征在于，所述第二分发信息中包括根据接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，
    所述处理单元根据所述关键字查询第二分发信息，根据所述第二分发信息确定处理所述数据流的应用服务器，包括：
    所述处理单元根据所述关键字、根据所述接口协议的第二数据生成的关键字和处理数据流的应用服务器信息之间的对应关系，获取所 述处理数据流的应用服务器的信息，确定处理所述数据流的应用服务器。
  17. 根据权利要求15或16中任一所述的装置，其特征在于，
    所述第一数据与所述第二数据为所述数据流中不同层次协议中的数据，所述第二数据所处协议的层次高于所述第一数据所处协议的层次；
    或者所述第一数据与所述第二数据为所述数据流中相同层析协议中的不同数据。
  18. 根据权利要求10-17中任一所述的装置，其特征在于，
    所述处理单元还用于获取所述数据流的流特征信息；根据所述数据流的流特征信息与第一分发规则之间的对应关系确定所述数据流的第一分发规则。
PCT/CN2014/088785 2014-10-17 2014-10-17 数据流分发方法和设备 WO2016058169A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
CN201480076763.2A CN106165359B (zh) 2014-10-17 2014-10-17 数据流分发方法和设备
PCT/CN2014/088785 WO2016058169A1 (zh) 2014-10-17 2014-10-17 数据流分发方法和设备
EP14903910.9A EP3200407B1 (en) 2014-10-17 2014-10-17 Data flow distribution method and device
JP2017520921A JP6456495B2 (ja) 2014-10-17 2014-10-17 データストリーム分配方法及び装置
US15/489,456 US10715589B2 (en) 2014-10-17 2017-04-17 Data stream distribution method and apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/088785 WO2016058169A1 (zh) 2014-10-17 2014-10-17 数据流分发方法和设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US15/489,456 Continuation US10715589B2 (en) 2014-10-17 2017-04-17 Data stream distribution method and apparatus

Publications (1)

Publication Number Publication Date
WO2016058169A1 true WO2016058169A1 (zh) 2016-04-21

Family

ID=55745981

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/088785 WO2016058169A1 (zh) 2014-10-17 2014-10-17 数据流分发方法和设备

Country Status (5)

Country Link
US (1) US10715589B2 (zh)
EP (1) EP3200407B1 (zh)
JP (1) JP6456495B2 (zh)
CN (1) CN106165359B (zh)
WO (1) WO2016058169A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112380257A (zh) * 2020-11-26 2021-02-19 厦门市美亚柏科信息股份有限公司 一种网络数据流锁定方法、终端设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7443796B1 (en) * 2000-08-30 2008-10-28 Cisco Technology, Inc. Distributed, rule based packet redirection
US20080275943A1 (en) * 2007-05-04 2008-11-06 Cisco Technology, Inc. Application load balancing for different domains
CN102882939A (zh) * 2012-09-10 2013-01-16 北京蓝汛通信技术有限责任公司 负载均衡方法、设备及泛域名加速访问系统

Family Cites Families (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6944162B1 (en) 2000-10-03 2005-09-13 Alcatel Tuple-based lookup scheme for packet switching node
US7774484B1 (en) * 2002-12-19 2010-08-10 F5 Networks, Inc. Method and system for managing network traffic
JP2006259812A (ja) * 2005-03-15 2006-09-28 Hitachi Ltd 動的キュー負荷分散方法、システム及びプログラム
US8370649B2 (en) * 2006-03-31 2013-02-05 Cisco Technology, Inc. Stream control failover utilizing an attribute-dependent protection mechanism
US20080112326A1 (en) * 2006-11-09 2008-05-15 Avaya Technology Llc Load-Balancing Routes In Multi-Hop Ad-Hoc Wireless Networks
US20080170575A1 (en) * 2007-01-12 2008-07-17 Czuchry Andrew J System and method for distributed intelligent-assistant control of predictive digital information distribution
JP5493479B2 (ja) * 2008-10-03 2014-05-14 富士通株式会社 サービス提供システム、方法、一意性保証情報設定管理プログラム、負荷分散プログラム、及び管理装置
US8321873B2 (en) * 2009-06-09 2012-11-27 Yahoo! Inc. System and method for offline data generation for online system analysis
US10621518B2 (en) * 2009-07-10 2020-04-14 Disney Enterprises, Inc. Interoperable keychest
US20110161657A1 (en) * 2009-12-31 2011-06-30 Verizon Patent And Licensing Inc. Method and system for providing traffic hashing and network level security
US20120230194A1 (en) * 2011-03-11 2012-09-13 Broadcom Corporation Hash-Based Load Balancing in Large Multi-Hop Networks with Randomized Seed Selection
US20120287946A1 (en) * 2011-05-13 2012-11-15 Broadcom Corporation Hash-Based Load Balancing with Flow Identifier Remapping
CN102255816B (zh) * 2011-08-18 2015-03-25 北京华为数字技术有限公司 负载分担方法及装置
US8804736B1 (en) * 2011-09-23 2014-08-12 Juniper Networks, Inc. Network tunneling using a label stack delimiter
CN104205752A (zh) * 2012-03-30 2014-12-10 日本电气株式会社 分布式存储系统、控制装置、客户终端、负载平衡方法以及程序
US9032488B2 (en) * 2012-04-17 2015-05-12 Salesforce.Com, Inc. Cross instance user authentication architecture
US9325785B2 (en) * 2012-06-29 2016-04-26 Rodolfo Kohn Device, system, and method for client-governed session persistency between one or more clients and servers of a data center
CN102769575A (zh) * 2012-08-08 2012-11-07 南京中兴特种软件有限责任公司 一种用于智能网卡的流量负载均衡方法
US9374276B2 (en) * 2012-11-01 2016-06-21 Microsoft Technology Licensing, Llc CDN traffic management in the cloud
CN102970242B (zh) * 2012-11-09 2015-06-17 深圳市共进电子股份有限公司 一种实现负载均衡的方法
JP5758934B2 (ja) * 2013-02-26 2015-08-05 日本電信電話株式会社 振分けサーバおよびそのプログラム
US9124564B2 (en) * 2013-08-22 2015-09-01 Cisco Technology, Inc. Context awareness during first negotiation of secure key exchange
IN2013MU03081A (zh) * 2013-09-27 2015-08-07 Sudarshan Deshmukh
US9502111B2 (en) * 2013-11-05 2016-11-22 Cisco Technology, Inc. Weighted equal cost multipath routing
US9967183B2 (en) * 2013-12-20 2018-05-08 Huawei Technologies Co., Ltd. Source routing with entropy-header
US9503374B2 (en) * 2014-01-22 2016-11-22 Futurewei Technologies, Inc. Apparatus for hybrid routing in SDN networks to avoid congestion and achieve good load balancing under fluctuating traffic load
US9501325B2 (en) * 2014-04-11 2016-11-22 Maxeler Technologies Ltd. System and method for shared utilization of virtualized computing resources
US10715587B2 (en) * 2014-04-11 2020-07-14 Maxeler Technologies Ltd. System and method for load balancing computer resources
US9584594B2 (en) * 2014-04-11 2017-02-28 Maxeler Technologies Ltd. Dynamic provisioning of processing resources in a virtualized computational architecture
US10275258B2 (en) * 2014-06-30 2019-04-30 Vmware, Inc. Systems and methods for enhancing the availability of multi-tier applications on cloud computing platforms
US9709964B2 (en) * 2014-07-11 2017-07-18 Cummins Power Generation Ip, Inc. Genset power control in power systems

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7443796B1 (en) * 2000-08-30 2008-10-28 Cisco Technology, Inc. Distributed, rule based packet redirection
US20080275943A1 (en) * 2007-05-04 2008-11-06 Cisco Technology, Inc. Application load balancing for different domains
CN102882939A (zh) * 2012-09-10 2013-01-16 北京蓝汛通信技术有限责任公司 负载均衡方法、设备及泛域名加速访问系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3200407A4 *

Also Published As

Publication number Publication date
US20170223098A1 (en) 2017-08-03
EP3200407A4 (en) 2017-11-08
US10715589B2 (en) 2020-07-14
EP3200407B1 (en) 2019-08-28
CN106165359A (zh) 2016-11-23
CN106165359B (zh) 2020-05-08
JP6456495B2 (ja) 2019-01-23
EP3200407A1 (en) 2017-08-02
JP2018501681A (ja) 2018-01-18

Similar Documents

Publication Publication Date Title
US10897431B2 (en) Cloud resource processing method and physical node
US10623339B2 (en) Reduced orthogonal network policy set selection
US20170048148A1 (en) Method, apparatus, and system for load balancing of service chain
WO2017114206A1 (zh) 短链接处理方法、装置及短链接服务器
CN104137491A (zh) 通过服务网关管理服务的方法
WO2014139481A1 (zh) 报文处理方法及设备
EP3437259A1 (en) Interworking between physical network and virtual network
WO2015101113A1 (zh) 处理报文的方法与设备
US11431765B2 (en) Session migration—based scheduling method and server
US8953600B2 (en) Telemetry data routing
WO2016070822A1 (zh) 媒体资源反馈方法及装置
EP3068081B1 (en) Method and apparatus for generating flow table
WO2016197689A1 (zh) 处理报文的方法、装置和系统
EP3384642B1 (en) Forwarding table compression
US9749262B2 (en) Packet processing method and forwarding element
WO2015149367A1 (zh) 报文处理的方法与设备
US20130243001A1 (en) Node and method for transmitting and receiving content-centric network (ccn) packet in ccn
WO2016058169A1 (zh) 数据流分发方法和设备
US9838259B1 (en) Methods for managing client defined response requirements in DNS query and devices thereof
CN106790441B (zh) 创建策略模板表的方法及装置、会话处理的方法及装置
CN106453144B (zh) 软件定义网络中的报文处理方法和设备
EP3884621A1 (en) Systems and methods to filter out noisy application signatures to improve precision of first packet application classification
EP2654269B1 (en) Node and method for generating shortened name robust against change in hierarchical name in content-centric network (CCN)

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14903910

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017520921

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2014903910

Country of ref document: EP