CN104994186A - Query method, processor and device of media access control address - Google Patents
Query method, processor and device of media access control address Download PDFInfo
- Publication number
- CN104994186A CN104994186A CN201510397380.1A CN201510397380A CN104994186A CN 104994186 A CN104994186 A CN 104994186A CN 201510397380 A CN201510397380 A CN 201510397380A CN 104994186 A CN104994186 A CN 104994186A
- Authority
- CN
- China
- Prior art keywords
- processor
- address
- keyword
- information
- hash table
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/09—Mapping addresses
- H04L61/10—Mapping addresses of different types
- H04L61/103—Mapping addresses of different types across network layers, e.g. resolution of network layer into physical layer addresses or address resolution protocol [ARP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/09—Mapping addresses
- H04L61/25—Mapping addresses of the same type
- H04L61/2503—Translation of Internet protocol [IP] addresses
- H04L61/256—NAT traversal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2101/00—Indexing scheme associated with group H04L61/00
- H04L2101/60—Types of network addresses
- H04L2101/618—Details of network addresses
- H04L2101/622—Layer-2 addresses, e.g. medium access control [MAC] addresses
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Embodiments of the invention provide a query method, a processor and a device of a media access control address, wherein the method comprises: a first processor receives a data packet sent by a second processor, wherein the data packet comprises interconnection protocol IP information of at least one network, and the IP information comprises an IP address and a prefix parameter corresponding to the IP address; the first processor determines a keyword corresponding to each IP address, wherein the keyword corresponds to the IP address in a one-to-one correspondent manner; and finally, the first processor quires the keyword in a corresponding hash table according to the prefix parameter corresponding to each IP address, and sends a media access control MAC address stored in a hash address corresponding to the keyword to the second processor in the case of query success. Therefore, the query efficiency of the MAC address is improved, and thus the data transmission time delay between mainframes is reduced.
Description
Technical field
The embodiment of the present invention relates to computer networking technology, particularly relates to a kind of querying method of media access control address, processor and device.
Background technology
Along with the fast development of Internet Transmission, the transfer of data between main frame is increasing with other speed of millions.And address resolution protocol (Address Resolution Protocol is called for short ARP) table inquiry is the most crucial link of transfer of data between main frame.
In ethernet networks, a main frame will carry out direct communication with another main frame, must know that the media interviews of destination host control (Media Access Control, be called for short MAC) address, i.e. destination-mac address, this destination-mac address is obtained by inquire address analysis protocol ARP table, and wherein each list item of ARP table comprises agreement (Internet Protocol the is called for short IP) address and the MAC Address corresponding with this IP address that interconnect between a network.So-called " address resolution " is exactly the main frame destination-mac address process that the IP address of query aim main frame is corresponding before transmission frame.The basic function of ARP agreement is exactly by target ip address, query aim MAC Address, to ensure carrying out smoothly of communication.In prior art, mainly by central processing unit (the Central Processing Unit of main frame, be called for short CPU) list item of ARP table is inquired about one by one according to target ip address, until inquire above-mentioned target ip address, wherein include other data table items of millions in this ARP table.
But because the data of ARP table are huge, therefore, the method efficiency comparison of the inquiry MAC Address that prior art provides is low, and then causes data between hosts propagation delay time larger.
Summary of the invention
The embodiment of the present invention provides a kind of querying method of media access control address, processor and device, thus improves search efficiency, and then reduces the data transmission delay between main frame.
First aspect, the embodiment of the present invention provides a kind of querying method of media access control address, comprising:
First processor receives the packet that the second processor sends, and described packet comprises the protocol IP information interconnected between at least one network, and described IP information comprises: an IP address and the prefix parameter corresponding with described IP address;
Described first processor determines the keyword that each described IP address is corresponding, described keyword and described IP address one_to_one corresponding;
The prefix parameter that described first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding;
If successful inquiring, then the MAC address stored in the Hash Round Robin data partition that described keyword is corresponding is sent to described second processor.
In conjunction with first aspect, in the first possibility execution mode of first aspect, the prefix parameter that described first processor is corresponding according to each described IP address also comprised inquire about described keyword in the Hash table of correspondence before:
Described first processor sets up m Hash table, and wherein, it is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding that a described m Hash table is respectively used to store prefix parameter, and wherein, m is the length of described IP address.
May execution mode in conjunction with the first of first aspect or first aspect, in the second possibility execution mode of first aspect, if described first processor comprises at least one core, any one core comprises multiple thread, and described packet comprises at least two IP information;
The prefix parameter that then described first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, specifically comprises:
The prefix parameter of described first processor included by described at least two IP information is by the keyword corresponding to the different IP addresses of the multiple threads on any one core described in the Hash table of correspondence at least two IP information described in parallel query.
May execution mode in conjunction with the first of first aspect or first aspect, in the third possibility execution mode of first aspect, if described first processor comprises at least two cores, and described packet comprises at least two IP information, the prefix parameter that then described first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, specifically comprises;
The prefix parameter of described first processor included by described at least two IP information is by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
May any one of execution mode in conjunction with first aspect to the third of first aspect, may in execution mode at the 4th kind of first aspect, described first processor is determined specifically to comprise the keyword that each described IP address is corresponding:
Described IP address transition is ten's digit by described first processor, and wherein said ten's digit is keyword corresponding to described IP address.
May any one of execution mode to the 4th kind of first aspect in conjunction with first aspect, may in execution mode at the 5th kind of first aspect, described first processor is graphic process unit, and described second processor is central processing unit.
Second aspect, the embodiment of the present invention provides a kind of querying method of media access control address, comprising:
Second processor sends packet to first processor, described packet comprises the protocol IP information interconnected between at least one network, described IP information comprises: an IP address and the prefix parameter corresponding with described IP address, the keyword that each described IP address is corresponding is determined to make described first processor, and the prefix parameter corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding, described keyword and described IP address one_to_one corresponding;
Described second processor receives the MAC address stored in the Hash Round Robin data partition corresponding at described keyword of described first processor transmission.
In conjunction with second aspect, in the first possibility execution mode of second aspect, described second processor also comprises: described second processor obtains at least one packet to be sent before sending packet to first processor; Described second processor extracts the described IP information in each described packet to be sent.
May execution mode in conjunction with the first of second aspect or second aspect, may in execution mode at the second of second aspect, described first processor is graphic process unit, and described second processor is central processing unit.
The third aspect, the embodiment of the present invention provides a kind of processor, comprising:
Receiver module, for receiving the packet that another processor sends, described packet comprises the protocol IP information interconnected between at least one network, and described IP information comprises: an IP address and the prefix parameter corresponding with described IP address;
Determination module, for determining the keyword that each described IP address is corresponding, described keyword and described IP address one_to_one corresponding;
Enquiry module, inquires about described keyword for the prefix parameter corresponding according to each described IP address, wherein said prefix parameter and described Hash table one_to_one corresponding in the Hash table of correspondence;
Sending module, for when described enquiry module successful inquiring, sends to another processor described by the MAC address stored in the Hash Round Robin data partition that described keyword is corresponding.
In conjunction with the third aspect, in the first possibility execution mode of the third aspect, also comprise: set up module;
Described module of setting up is for setting up m Hash table, and wherein, it is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding that a described m Hash table is respectively used to store prefix parameter, and wherein, m is the length of described IP address.
May execution mode in conjunction with the first of the third aspect or the third aspect, in the second possibility execution mode of the third aspect, if described first processor comprises at least one core, any one core comprises multiple thread, and described packet comprises at least two IP information;
Then described enquiry module specifically for:
Prefix parameter included by described at least two IP information is by the keyword corresponding to the different IP addresses of the multiple threads on any one core described in the Hash table of correspondence at least two IP information described in parallel query.
May execution mode in conjunction with the first of the third aspect or the third aspect, may in execution mode at the third of the third aspect, if described first processor comprises at least two cores, and described packet comprises at least two IP information;
Then described enquiry module specifically for:
Prefix parameter included by described at least two IP information is by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
May any one of execution mode in conjunction with the third aspect to the third of the third aspect, may in execution mode at the 4th kind of the third aspect, described determination module specifically for:
Be ten's digit by described IP address transition, wherein said ten's digit is keyword corresponding to described IP address.
May any one of execution mode to the 4th kind of the third aspect in conjunction with the third aspect, may in execution mode at the 5th kind of the third aspect, described processor is graphic process unit, and another processor described is central processing unit.
Fourth aspect, the embodiment of the present invention provides a kind of processor, comprising:
Sending module, for sending packet to another processor, described packet comprises the protocol IP information interconnected between at least one network, described IP information comprises: an IP address and the prefix parameter corresponding with described IP address, the keyword that each described IP address is corresponding is determined to make another processor described, and the prefix parameter corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding, described keyword and described IP address one_to_one corresponding;
Receiver module, for receiving the MAC address stored in the Hash Round Robin data partition corresponding at described keyword of described another processor transmission.
In conjunction with fourth aspect, in the first possibility execution mode of fourth aspect, also comprise: acquisition module and extraction module;
Described acquisition module, for obtaining at least one packet to be sent;
Described extraction module, for extracting the described IP information in each described packet to be sent.
May execution mode in conjunction with the first of fourth aspect or fourth aspect, may in execution mode at the second of fourth aspect, described processor is central processing unit, and another processor described is graphic process unit.
5th aspect, the embodiment of the present invention provides a kind of inquiry unit of media access control address, comprising: the processor as described in the third aspect to any one in the 5th kind of possibility execution mode of the third aspect and the processor as described in fourth aspect to any one in the second possibility execution mode of fourth aspect.
The embodiment of the present invention provides a kind of querying method of media access control address, processor and device, wherein the method comprises: first, first processor receives the packet that the second processor sends, packet comprises the protocol IP information interconnected between at least one network, and IP information comprises: an IP address and the prefix parameter corresponding with IP address; Secondly, first processor determines the keyword that each IP address is corresponding, keyword and IP address one_to_one corresponding; Finally, prefix parameter key word of the inquiry in the Hash table of correspondence that first processor is corresponding according to each IP address, if successful inquiring, then sends to the second processor by the MAC address stored in the Hash Round Robin data partition that keyword is corresponding.Thus improve the search efficiency of MAC Address, and then reduce the data transmission delay between main frame.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, introduce doing one to the accompanying drawing used required in embodiment or description of the prior art simply below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The querying method flow chart of a kind of media access control address that Fig. 1 provides for one embodiment of the invention;
The relation schematic diagram of at least one IP information that Fig. 2 provides for one embodiment of the invention and Hash table;
The relation schematic diagram of at least one IP information that Fig. 3 provides for one embodiment of the invention and core;
The relation schematic diagram of at least one IP information that Fig. 4 provides for one embodiment of the invention and thread;
The flow chart of the querying method of a kind of media access control address that Fig. 5 provides for another embodiment of the present invention;
The structural representation of a kind of processor that Fig. 6 provides for one embodiment of the invention;
The structural representation of a kind of processor that Fig. 7 provides for another embodiment of the present invention;
The structural representation of a kind of processor that Fig. 8 provides for yet another embodiment of the invention;
The structural representation of a kind of processor that Fig. 9 provides for further embodiment of this invention;
The structural representation of the inquiry unit of a kind of media access control address that Figure 10 provides for one embodiment of the invention.
Embodiment
For making the object of the embodiment of the present invention, technical scheme and advantage clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The embodiment of the present invention is based on any one network topology structure in computer network, such as: tree, hub-and-spoke configuration, loop configuration etc., and any two main frames in network topology structure will carry out transfer of data, first need at the target MAC (Media Access Control) address corresponding according to object IP address lookup.Introduce a kind of querying method of MAC address below:
The querying method flow chart of a kind of media access control address that Fig. 1 provides for one embodiment of the invention, the executive agent of the method is first processor, first processor can be graphic process unit (GraphicProcessing Unit, be called for short GPU), the second mentioned below processor can be CPU, and certainly, the present invention is not limited thereto, as long as first processor performance is higher than the second processor, usual first processor and the second processor are positioned on same main frame.The querying method of this media access control address specifically comprises the steps:
S101: first processor receives the packet that the second processor sends, and described packet comprises the protocol IP information interconnected between at least one network, and described IP information comprises: an IP address and the prefix parameter corresponding with described IP address;
Particularly, first processor receives the packet that the second processor sends, and among the video memory this packet being stored to first processor, packet comprises at least one IP information, wherein these IP information are the IP information that the second processor extracts from packet to be sent, such as: the main frame at first processor and the second processor place needs to send packet to destination host, so include object IP address in this packet to be sent, and the prefix parameter that object IP address is corresponding, when internet protocol version is internet protocol version 4 (Internet Protocol version 4, be called for short IPv4) time, so the prefix parameter of IP address can be 1 to 32, when version is IPv6, so the prefix parameter of IP address can be 1 to 48, no matter be IPv4 or IPv6, prefix parameter corresponding to each IP address is unique.In order to improve data transmission efficiency, usual second processor is once transferred to first processor to multiple IP information package.
S102: first processor determines the keyword that each IP address is corresponding, keyword and IP address one_to_one corresponding;
Particularly, first processor is determined specifically to comprise the keyword that each IP address is corresponding: IP address transition is ten's digit by first processor, and wherein ten's digit is keyword corresponding to IP address.
S103: prefix parameter key word of the inquiry in the Hash table of correspondence that first processor is corresponding according to each IP address, wherein prefix parameter and Hash table one_to_one corresponding;
Particularly, in the embodiment of the present invention first processor and the second processor place main frame on store multiple Hash table, such as: when IP version is IPv4, on this main frame store 32 Hash tables, when IP version is IPv6, on this main frame store 48 Hash tables.For IPv4 version, 32 Hash tables store keyword corresponding to IP address that prefix parameter is 1 to 32 respectively, and each Hash table stores at least one keyword, such as: what certain Hash table stored is all prefix parameter be 8 keyword corresponding to IP address.So when first processor need to inquire about prefix parameter be the MAC Address corresponding to IP address of 8 time, then first store to be all prefix parameter be 8 keyword corresponding to IP address Hash table in inquire about keyword corresponding to IP address.
Usually, first processor comprises at least one core, and these Hash tables can be positioned on different core, therefore when carrying out Hash table inquiry, can realize parallel processing.
S104: if successful inquiring, then send to the second processor by the MAC address stored in the Hash Round Robin data partition that keyword is corresponding.
Particularly, first processor is just responsible for inquiry MAC Address, when after successful inquiring, this MAC Address can be sent to the second processor, to make the second processor can by Packet Generation to be sent to main frame corresponding to this MAC Address, such as: after GPU inquires MAC Address, this MAC Address is sent to CPU, the main frame that Packet Generation to be sent finally gives this MAC Address corresponding by CPU.
The embodiment of the present invention provides a kind of querying method of media access control address, comprise: first, first processor receives the packet that the second processor sends, packet comprises the protocol IP information interconnected between at least one network, and IP information comprises: an IP address and the prefix parameter corresponding with IP address; Secondly, first processor determines the keyword that each IP address is corresponding, keyword and IP address one_to_one corresponding; Finally, prefix parameter key word of the inquiry in the Hash table of correspondence that first processor is corresponding according to each IP address, if successful inquiring, then sends to the second processor by the MAC address stored in the Hash Round Robin data partition that keyword is corresponding.Only MAC Address need be inquired about in the Hash table of correspondence by the method first processor, and first processor only just need can inquire MAC Address according to keyword, in addition, second processor performance of first processor is higher than first processor, thus improve the search efficiency of MAC Address, and then reduce the data transmission delay between main frame.
Alternatively, before the S103 step of above-described embodiment, also comprise: first processor sets up m Hash table, wherein, it is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding that m Hash table is respectively used to store prefix parameter, and wherein, m is the length of IP address.
Particularly, the process setting up Hash table is: first, determines the keyword in Hash table to be deposited, then calculates Hash Round Robin data partition according to this keyword, secondly, and the MAC Address that storage key is corresponding in the memory space that this Hash Round Robin data partition is corresponding.Wherein, the method calculating Hash Round Robin data partition can adopt any one method of the prior art, such as: direct addressing, digital analysis method, middle square method, jackknife method, random number method or leaving remainder method.
Below for leaving remainder method, get keyword by several 4194301 except the remainder of rear gained is Hash Round Robin data partition.I.e. H (key)=key MOD p.H is hash function, and key represents keyword, and wherein keyword is here the ten's digit that IP address transition becomes.
But, when setting up Hash table, the problem of conflict may be there is, namely same Hash Round Robin data partition may be obtained to different keywords, i.e. key1 ≠ key2, and H (key1)=H (key2), such as: keyword key1 and key2 remainder are all 4, in order to the problem of managing conflict, open addressing, again hashing of the prior art etc. can be adopted to process this conflict, finally reach keyword and Hash Round Robin data partition result one to one.Be equivalent to from setting up Hash table on the basis of original Hash table set up to the method managed conflict, establish an offset table again, list item in offset table comprises: keyword and address offset amount corresponding to keyword, finally, comprehensive Hash table and offset table determine the Hash Round Robin data partition that each keyword is corresponding.Be equivalent to, on the basis of original Hash table set up, also can be understood as: first determine the hash function h that Hash table is corresponding from setting up Hash table to the method managed conflict
0, a side-play amount function h is then determined in order to manage conflict
1, when IP address is p, then the Hash Round Robin data partition that the keyword of this IP address is corresponding is h
0(p) and h
1(p) sum.
For IPv4, in this case, the length of IP address is 32, so first processor can set up 32 Hash tables, the relation schematic diagram of at least one IP information that Fig. 2 provides for one embodiment of the invention and Hash table, as shown in Figure 2, packet comprises at least one IP information, and wherein Hash table 1 to Hash table 32 is respectively used to inquire about keyword corresponding to IP address that prefix parameter is 1 to 32.Such as: Hash table 1 is for inquiring about keyword corresponding to IP address that all prefix parameter are 1.And these Hash tables may be stored in the core of first processor, the corresponding relation of Hash table and core can be: one to one or many-to-one relation.
If first processor comprises at least two cores, and packet comprises at least two IP information, then the prefix parameter that first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, specifically comprises; The prefix parameter of first processor included by least two IP information is by keyword different IP addresses corresponding to of at least two cores in the Hash table of correspondence in parallel query at least two IP information.The relation schematic diagram of at least one IP information that Fig. 3 provides for one embodiment of the invention and core, as shown in Figure 3, this first processor comprises N number of core, the keyword that each core parallel query different IP addresses is corresponding, so-called parallel query is: such as: two cores in first processor are respectively the first core and the second core, two IP information are included in packet, each IP information comprises: an IP address and the prefix parameter corresponding with IP address, two IP information can be called: an IP information and the 2nd IP information, one IP information comprises: an IP address and first prefix parameter corresponding with an IP address, 2nd IP information comprises: the 2nd IP address and second prefix parameter corresponding with the 2nd IP address, wherein, first processor searches keyword corresponding to an IP address by the first core according to the first prefix parameter of an IP address in the Hash table of correspondence, in the Hash table of correspondence, keyword corresponding to the 2nd IP address is searched according to the second prefix parameter of the 2nd IP address by the second core, because the first core and the second core are two independently cores, therefore can by keyword corresponding to the different IP address of their parallel queries and the 2nd IP address.
Further, a usual core can set up multiple thread, particularly, if first processor comprises at least one core, any one core comprises multiple thread, and packet comprise at least two IP information; The prefix parameter that then first processor is corresponding according to each IP address inquires about described keyword in the Hash table of correspondence, specifically comprises: the prefix parameter of first processor included by least two IP information is by keyword different IP addresses corresponding to of multiple threads in the Hash table of correspondence in parallel query at least two IP information on any one core.The relation schematic diagram of at least one IP information that Fig. 4 provides for one embodiment of the invention and thread, as shown in Figure 4, each core of first processor opens multiple thread, each thread can be inquired about keyword corresponding to an IP address, such as: in any one core in first processor, establish two threads, they can be called the first thread and the second thread, and include two IP information in packet, each IP information comprises: an IP address and the prefix parameter corresponding with IP address, two IP information can be called: an IP information and the 2nd IP information, one IP information comprises: an IP address and first prefix parameter corresponding with an IP address, 2nd IP information comprises: the 2nd IP address and second prefix parameter corresponding with the 2nd IP address, wherein first processor inquires about keyword corresponding to an IP address by the first thread, keyword corresponding to the 2nd IP address is inquired about by the second thread, because the first thread and the second thread are two separate threads, therefore can by keyword corresponding to the different IP address of their parallel queries and the 2nd IP address, the Query Result of last each thread sends to the second processor.
Further, first processor is determined specifically to comprise the keyword that each IP address is corresponding:
Described IP address transition is ten's digit by described first processor, and wherein said ten's digit is keyword corresponding to described IP address.
The embodiment of the present invention provides a kind of querying method of media access control address, if wherein first processor comprises at least two cores, then endorse with keyword corresponding to parallel query different IP addresses at least two, further, if any one core comprises multiple thread, then multiple thread also can keyword corresponding to parallel query different IP addresses, then, in the Hash table of correspondence, directly MAC Address can be inquired about according to keyword, above-mentioned parallel query method significantly improves the search efficiency of first processor, and then reduces the data transmission delay between main frame.
Lower mask body introduces a kind of application scenarios of querying method of media access control address: open system interconnection (Open System Interconnection, being called for short OSI) model has 7 Rotating fields, wherein, 7 layers of OSI from top to bottom respectively: application layer, presentation layer, session layer, transport layer, network layer, data link layer and physical layer, it is on the middle and senior level, namely the 4th layer defines the function of application program to layer 7, ground floor to third layer mainly towards by the data flow end to end of network.To test the 4th layer of function to layer 7 application program, such as: test the 4th layer to the fire-proof function in layer 7, secure socket layer protocol (Security Socket Layer, be called for short SSL) equipment, load equalizer etc., important step is the exchanges data realizing between test lead by router, due to usual test data substantial amounts, therefore, the present invention realizes the exchanges data between test lead by a supercomputer, here supercomputer has the query function of the media access control address made referrals in the embodiment of the present invention, supercomputer is between two the 4th layer to layer 7 application testing end, and supercomputer comprises first processor and the second processor, first processor receives the packet that the second processor sends, packet comprises the protocol IP information interconnected between at least one network, IP information comprises: an IP address and the prefix parameter corresponding with IP address, first processor determines the keyword that each IP address is corresponding, keyword and IP address one_to_one corresponding, prefix parameter key word of the inquiry in the Hash table of correspondence that first processor is corresponding according to each IP address, wherein prefix parameter and Hash table one_to_one corresponding, if successful inquiring, then the MAC address stored in the Hash Round Robin data partition that keyword is corresponding is sent to the second processor.With the test lead making the second processor send to MAC Address corresponding data to be sent.
Further, if the first processor of this supercomputer comprises at least one core, any one core comprises multiple thread, and packet comprises at least two IP information; The prefix parameter that then first processor is corresponding according to each IP address inquires about described keyword in the Hash table of correspondence, specifically comprises: the prefix parameter of first processor included by least two IP information is by keyword different IP addresses corresponding to of multiple threads in the Hash table of correspondence in parallel query at least two IP information on any one core.
Further, if the first processor of this supercomputer comprises at least two cores, and packet comprises at least two IP information, then the prefix parameter that described first processor is corresponding according to each IP address inquires about described keyword in the Hash table of correspondence, specifically comprises; The prefix parameter of described first processor included by described at least two IP information is by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
This supercomputer only need inquire about MAC Address for each IP address in the Hash table of correspondence, and first processor only just need can inquire MAC Address according to keyword, in addition, the function of parallel query can be realized between each core in this supercomputer, and between each thread, also can realize the function of parallel query, thus improve the search efficiency of MAC Address, and then improve the testing efficiency of test lead.
The flow chart of the querying method of a kind of media access control address that Fig. 5 provides for another embodiment of the present invention, as shown in Figure 5, the executive agent of the method is the second processor, second processor can be CPU, first processor mentioned below can be GPU, and certainly, the present invention is not limited thereto, as long as first processor performance is higher than the second processor, usual first processor and the second processor are positioned on same main frame.The querying method of this media access control address specifically comprises the steps:
S501: the second processor sends packet to first processor, packet comprises the protocol IP information interconnected between at least one network, IP information comprises: an IP address and the prefix parameter corresponding with IP address, the keyword that each IP address is corresponding is determined to make first processor, and prefix parameter in the Hash table of correspondence the key word of the inquiry corresponding according to each IP address, wherein prefix parameter and Hash table one_to_one corresponding, keyword and IP address one_to_one corresponding;
Particularly, usual second processor comprises multiple as far as possible IP information to the packet that first processor sends, thus avoid frequently sending IP information to first processor, data transmission efficiency can be improved like this, in the embodiment of the present invention first processor and the second processor place main frame on store multiple Hash table, such as: when IP version is IPv4, on this main frame store 32 Hash tables, when IP version is IPv6, this main frame stores 48 Hash tables.For IPv4 version, 32 Hash tables store keyword corresponding to IP address that prefix parameter is 1 to 32 respectively, and each Hash table stores at least one keyword, such as: what certain Hash table stored is all prefix parameter be 8 keyword corresponding to IP address.
S502: the second processor receives the MAC address stored in the Hash Round Robin data partition corresponding at keyword of first processor transmission.
After finding the keyword of certain IP address in the Hash table of first processor in correspondence, then can determine the Hash Round Robin data partition that keyword is corresponding, MAC Address corresponding to IP address is then stored in memory space corresponding to this Hash Round Robin data partition, after second processor receives MAC Address, then can send data to the main frame belonging to this MAC Address.
The embodiment of the present invention provides a kind of querying method of media access control address, comprise: the second processor sends packet to first processor, packet comprises the protocol IP information interconnected between at least one network, IP information comprises: an IP address and the prefix parameter corresponding with IP address, the keyword that each IP address is corresponding is determined to make first processor, and prefix parameter in the Hash table of correspondence the key word of the inquiry corresponding according to each IP address, second processor receives the MAC address stored in the Hash Round Robin data partition corresponding at keyword of first processor transmission, because the second processor is once transferred to first processor to multiple IP information package, thus improve data transmission efficiency.
Alternatively, the second processor also comprises: the second processor obtains at least one packet to be sent before sending packet to first processor; Second processor extracts the IP information in each packet to be sent.The IP information wherein extracted is specially: IP address and the prefix parameter corresponding with IP address.
The structural representation of a kind of processor that Fig. 6 provides for one embodiment of the invention, wherein this processor can be graphic process unit GPU, and as shown in Figure 6, this processor specifically comprises:
Receiver module 601, for receiving the packet that another processor sends, packet comprises the protocol IP information interconnected between at least one network, and IP information comprises: an IP address and the prefix parameter corresponding with IP address;
Determination module 602, for determining the keyword that each IP address is corresponding, keyword and IP address one_to_one corresponding;
Enquiry module 603, for prefix parameter in the Hash table of correspondence the key word of the inquiry corresponding according to each IP address, wherein prefix parameter and Hash table one_to_one corresponding;
Sending module 604, for when enquiry module 603 successful inquiring, sends to another processor by the MAC address stored in the Hash Round Robin data partition that keyword is corresponding.
Wherein, here another processor can be central processor CPU, particularly, receiver module 601 receives the packet that CPU sends, and among the video memory this packet being stored to GPU, packet comprises at least one IP information, wherein these IP information are the IP information that CPU extracts from packet to be sent, such as: the main frame at GPU and CPU place needs to send packet to destination host, so include object IP address in this packet to be sent, and the prefix parameter that object IP address is corresponding, when internet protocol version is internet protocol version 4 (Internet Protocol version 4, be called for short IPv4) time, so the prefix parameter of IP address can be 1 to 32, when version is IPv6, so the prefix parameter of IP address can be 1 to 48, no matter be IPv4 or IPv6, prefix parameter corresponding to each IP address is unique.In order to improve data transmission efficiency, usual CPU is once transferred to first processor to multiple IP information package.
Further, in the embodiment of the present invention GPU and CPU place main frame on store multiple Hash table, such as: when IP version is IPv4, on this main frame store 32 Hash tables, when IP version is IPv6, on this main frame store 48 Hash tables.For IPv4 version, 32 Hash tables store keyword corresponding to IP address that prefix parameter is 1 to 32 respectively, and each Hash table stores at least one keyword, such as: what certain Hash table stored is all prefix parameter be 8 keyword corresponding to IP address.So when GPU need to inquire about prefix parameter be the MAC Address corresponding to IP address of 8 time, then first store to be all prefix parameter be 8 keyword corresponding to IP address Hash table in inquire about keyword corresponding to IP address.
Usually, GPU comprises at least one core, and these Hash tables can be positioned on different core, therefore when carrying out Hash table inquiry, can realize parallel processing.
Further, GPU is just responsible for inquiry MAC Address, when after successful inquiring, this MAC Address can be sent to CPU, to make CPU can by Packet Generation to be sent to main frame corresponding to this MAC Address.
The processor that the present embodiment provides, may be used for perform embodiment illustrated in fig. 1 in method step, it realizes principle and technique effect is similar, repeats no more herein.
The structural representation of a kind of processor that Fig. 7 provides for another embodiment of the present invention, wherein this processor can be graphic process unit GPU, and wherein this processor is except comprising receiver module 601, determination module 602, outside enquiry module 603 and sending module 604, also comprise: set up module 605; Described module 605 of setting up is for setting up m Hash table, and wherein, it is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding that a described m Hash table is respectively used to store prefix parameter, and wherein, m is the length of described IP address.It should be noted that, the receiver module 601 in Fig. 7, determination module 602, enquiry module 603 and sending module 604 and the receiver module 601 in Fig. 6, determination module 602, enquiry module 603 is identical with sending module 604 function, again repeats no more.
Further, if this processor comprises at least one core, any one core comprises multiple thread, and described packet comprises at least two IP information; Then described enquiry module 603 specifically for: the prefix parameter included by described at least two IP information by the keyword corresponding to the different IP addresses of the multiple threads on any one core described in the Hash table of correspondence at least two IP information described in parallel query.
Further, if this processor comprises at least two cores, and described packet comprises at least two IP information; Then described enquiry module 603 specifically for: the prefix parameter included by described at least two IP information by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
Described determination module 602 specifically for: be ten's digit by described IP address transition, wherein said ten's digit is keyword corresponding to described IP address.
The processor that the embodiment of the present invention provides can realize parallel query between multinuclear, and can also realize the parallel query of multithreading on any one core, thus significantly improves search efficiency, and then reduces the data transmission delay between main frame.
The structural representation of a kind of processor that Fig. 8 provides for yet another embodiment of the invention, wherein this processor can be central processor CPU, and as shown in Figure 8, this processor comprises:
Sending module 801, for sending packet to another processor, described packet comprises the protocol IP information interconnected between at least one network, described IP information comprises: an IP address and the prefix parameter corresponding with described IP address, the keyword that each described IP address is corresponding is determined to make another processor described, and the prefix parameter corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding, described keyword and described IP address one_to_one corresponding;
Receiver module 802, for receiving the MAC address stored in the Hash Round Robin data partition corresponding at described keyword of described another processor transmission.
It should be noted that, another processor here can be graphic process unit GPU.Particularly, usual CPU comprises multiple as far as possible IP information to the packet that GPU sends, thus avoid frequently sending IP information to GPU, data transmission efficiency can be improved like this, in the embodiment of the present invention GPU and CPU place main frame on store multiple Hash table, such as: when IP version is IPv4, on this main frame store 32 Hash tables, when IP version is IPv6, this main frame stores 48 Hash tables.For IPv4 version, 32 Hash tables store keyword corresponding to IP address that prefix parameter is 1 to 32 respectively, and each Hash table stores at least one keyword, such as: what certain Hash table stored is all prefix parameter be 8 keyword corresponding to IP address.After finding the keyword of certain IP address in the Hash table of GPU in correspondence, then can determine the Hash Round Robin data partition that keyword is corresponding, MAC Address corresponding to IP address is then stored in memory space corresponding to this Hash Round Robin data partition, after CPU receives MAC Address, then can send data to the main frame belonging to this MAC Address.
The processor that the present embodiment provides, may be used for perform embodiment illustrated in fig. 5 in method step, it realizes principle and technique effect is similar, repeats no more herein.
The structural representation of a kind of processor that Fig. 9 provides for further embodiment of this invention, wherein this processor can be central processor CPU, as shown in Figure 9, wherein this processor is except comprising sending module 801 and receiver module 802, also comprises acquisition module 901 and extraction module 902; Described acquisition module 901, for obtaining at least one packet to be sent; Described extraction module 902, for extracting the described IP information in each described packet to be sent.
The structural representation of the inquiry unit of a kind of media access control address that Figure 10 provides for one embodiment of the invention, the inquiry unit of this media access control address can be the smart machines such as computer, notebook computer or panel computer, it comprises first processor 1001 and the second processor 1002, wherein first processor 1001 comprises receiver module, for receiving the packet that another processor sends, packet comprises the protocol IP information interconnected between at least one network, and IP information comprises: an IP address and the prefix parameter corresponding with IP address; Determination module, for determining the keyword that each IP address is corresponding, keyword and IP address one_to_one corresponding; Enquiry module, for prefix parameter in the Hash table of correspondence the key word of the inquiry corresponding according to each IP address, wherein prefix parameter and Hash table one_to_one corresponding; Sending module, for when enquiry module successful inquiring, sends to another processor by the MAC address stored in the Hash Round Robin data partition that keyword is corresponding.
Usually, first processor 1001 comprises at least one core, and these Hash tables can be positioned on different core, therefore when carrying out Hash table inquiry, can realize parallel processing.
This first processor 1001 also comprises: set up module, for setting up m Hash table, wherein, a described m Hash table is respectively used to store prefix parameter is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding, wherein, m is the length of described IP address.Further, if this first processor 1001 comprises at least one core, any one core comprises multiple thread, and described packet comprises at least two IP information; Then described enquiry module specifically for: the prefix parameter included by described at least two IP information by the keyword corresponding to the different IP addresses of the multiple threads on any one core described in the Hash table of correspondence at least two IP information described in parallel query.
Further, if this first processor 1001 comprises at least two cores, and described packet comprises at least two IP information; Then described enquiry module specifically for: the prefix parameter included by described at least two IP information by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
Described determination module specifically for: be ten's digit by described IP address transition, wherein said ten's digit is keyword corresponding to described IP address.
Second processor 1002 comprises: sending module, for sending packet to another processor, described packet comprises the protocol IP information interconnected between at least one network, described IP information comprises: an IP address and the prefix parameter corresponding with described IP address, the keyword that each described IP address is corresponding is determined to make another processor described, and the prefix parameter corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding, described keyword and described IP address one_to_one corresponding,
Receiver module, for receiving the MAC address stored in the Hash Round Robin data partition corresponding at described keyword of described another processor transmission.Second processor 1002 also comprises acquisition module and extraction module; Described acquisition module, for obtaining at least one packet to be sent; Described extraction module, for extracting the described IP information in each described packet to be sent.
The inquiry unit of the media access control address that the present embodiment provides, comprise first processor and the second processor, wherein processor described in first processor and Fig. 6 and Fig. 7 realize principle and technique effect is similar, repeat no more herein, processor described in second processor and Fig. 8 and Fig. 9 realize principle and technique effect is similar, repeat no more herein.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each embodiment of the method can have been come by the hardware that program command is relevant.Aforesaid program can be stored in a computer read/write memory medium.This program, when performing, performs the step comprising above-mentioned each embodiment of the method; And aforesaid storage medium comprises: ROM, RAM, magnetic disc or CD etc. various can be program code stored medium.
Last it is noted that above each embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme.
Claims (19)
1. a querying method for media access control address, is characterized in that, comprising:
First processor receives the packet that the second processor sends, and described packet comprises the protocol IP information interconnected between at least one network, and described IP information comprises: an IP address and the prefix parameter corresponding with described IP address;
Described first processor determines the keyword that each described IP address is corresponding, described keyword and described IP address one_to_one corresponding;
The prefix parameter that described first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding;
If successful inquiring, then the MAC address stored in the Hash Round Robin data partition that described keyword is corresponding is sent to described second processor.
2. method according to claim 1, is characterized in that, the prefix parameter that described first processor is corresponding according to each described IP address also comprised inquire about described keyword in the Hash table of correspondence before:
Described first processor sets up m Hash table, and wherein, it is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding that a described m Hash table is respectively used to store prefix parameter, and wherein, m is the length of described IP address.
3. method according to claim 1 and 2, is characterized in that, if described first processor comprises at least one core, any one core comprises multiple thread, and described packet comprises at least two IP information;
The prefix parameter that then described first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, specifically comprises:
The prefix parameter of described first processor included by described at least two IP information is by the keyword corresponding to the different IP addresses of the multiple threads on any one core described in the Hash table of correspondence at least two IP information described in parallel query.
4. method according to claim 1 and 2, it is characterized in that, if described first processor comprises at least two cores, and described packet comprises at least two IP information, the prefix parameter that then described first processor is corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, specifically comprises;
The prefix parameter of described first processor included by described at least two IP information is by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
5. the method according to any one of claim 1-4, is characterized in that, described first processor is determined specifically to comprise the keyword that each described IP address is corresponding:
Described IP address transition is ten's digit by described first processor, and wherein said ten's digit is keyword corresponding to described IP address.
6. the method according to any one of claim 1-5, is characterized in that, described first processor is graphic process unit, and described second processor is central processing unit.
7. a querying method for media access control address, is characterized in that, comprising:
Second processor sends packet to first processor, described packet comprises the protocol IP information interconnected between at least one network, described IP information comprises: an IP address and the prefix parameter corresponding with described IP address, the keyword that each described IP address is corresponding is determined to make described first processor, and the prefix parameter corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding, described keyword and described IP address one_to_one corresponding;
Described second processor receives the MAC address stored in the Hash Round Robin data partition corresponding at described keyword of described first processor transmission.
8. method according to claim 7, is characterized in that, described second processor also comprises before sending packet to first processor:
Described second processor obtains at least one packet to be sent;
Described second processor extracts the described IP information in each described packet to be sent.
9. the method according to claim 7 or 8, is characterized in that, described first processor is graphic process unit, and described second processor is central processing unit.
10. a processor, is characterized in that, comprising:
Receiver module, for receiving the packet that another processor sends, described packet comprises the protocol IP information interconnected between at least one network, and described IP information comprises: an IP address and the prefix parameter corresponding with described IP address;
Determination module, for determining the keyword that each described IP address is corresponding, described keyword and described IP address one_to_one corresponding;
Enquiry module, inquires about described keyword for the prefix parameter corresponding according to each described IP address, wherein said prefix parameter and described Hash table one_to_one corresponding in the Hash table of correspondence;
Sending module, for when described enquiry module successful inquiring, sends to another processor described by the MAC address stored in the Hash Round Robin data partition that described keyword is corresponding.
11. processors according to claim 10, is characterized in that, also comprise: set up module;
Described module of setting up is for setting up m Hash table, and wherein, it is the MAC Address that keyword corresponding to the IP address of 1 to m and each keyword are corresponding that a described m Hash table is respectively used to store prefix parameter, and wherein, m is the length of described IP address.
12. processors according to claim 10 or 11, it is characterized in that, if described first processor comprises at least one core, any one core comprises multiple thread, and described packet comprise at least two IP information;
Then described enquiry module specifically for:
Prefix parameter included by described at least two IP information is by the keyword corresponding to the different IP addresses of the multiple threads on any one core described in the Hash table of correspondence at least two IP information described in parallel query.
13. processors according to claim 10 or 11, it is characterized in that, if described first processor comprises at least two cores, and described packet comprises at least two IP information;
Then described enquiry module specifically for:
Prefix parameter included by described at least two IP information is by the keyword corresponding to the different IP addresses of described at least two cores in the Hash table of correspondence at least two IP information described in parallel query.
14. processors according to any one of claim 10-13, is characterized in that, described determination module specifically for:
Be ten's digit by described IP address transition, wherein said ten's digit is keyword corresponding to described IP address.
15. processors according to any one of claim 10-14, it is characterized in that, described processor is graphic process unit, and another processor described is central processing unit.
16. 1 kinds of processors, is characterized in that, comprising:
Sending module, for sending packet to another processor, described packet comprises the protocol IP information interconnected between at least one network, described IP information comprises: an IP address and the prefix parameter corresponding with described IP address, the keyword that each described IP address is corresponding is determined to make another processor described, and the prefix parameter corresponding according to each described IP address inquires about described keyword in the Hash table of correspondence, wherein said prefix parameter and described Hash table one_to_one corresponding, described keyword and described IP address one_to_one corresponding;
Receiver module, for receiving the MAC address stored in the Hash Round Robin data partition corresponding at described keyword of described another processor transmission.
17. processors according to claim 16, is characterized in that, also comprise: acquisition module and extraction module;
Described acquisition module, for obtaining at least one packet to be sent;
Described extraction module, for extracting the described IP information in each described packet to be sent.
18. processors according to claim 16 or 17, it is characterized in that, described processor is central processing unit, and another processor described is graphic process unit.
The inquiry unit of 19. 1 kinds of media access control address, is characterized in that, comprising: the processor as described in any one of claim 10-15 and the processor as described in any one of claim 16-18.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510397380.1A CN104994186A (en) | 2015-07-08 | 2015-07-08 | Query method, processor and device of media access control address |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510397380.1A CN104994186A (en) | 2015-07-08 | 2015-07-08 | Query method, processor and device of media access control address |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104994186A true CN104994186A (en) | 2015-10-21 |
Family
ID=54305937
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510397380.1A Pending CN104994186A (en) | 2015-07-08 | 2015-07-08 | Query method, processor and device of media access control address |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104994186A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194613A (en) * | 2017-06-20 | 2017-09-22 | 无锡井通网络科技有限公司 | Digital asset coding method |
CN108111422A (en) * | 2017-12-29 | 2018-06-01 | 北京明朝万达科技股份有限公司 | A kind of data high-speed multichannel retransmission method and device based on DPDK |
CN111061724A (en) * | 2019-11-08 | 2020-04-24 | 珠海许继芝电网自动化有限公司 | High-speed real-time database management method and device for distribution automation system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101102286A (en) * | 2006-07-05 | 2008-01-09 | 阿里巴巴公司 | A method and device for referring to user information in instant communication system |
EP2566129A1 (en) * | 2010-12-21 | 2013-03-06 | Huawei Technologies Co., Ltd. | Method, apparatus and system for acquiring media access control address |
CN103634216A (en) * | 2013-11-04 | 2014-03-12 | 汉柏科技有限公司 | Method and equipment for forwarding datagram based on NAT 64 (Network Address Translation 64) |
CN104038425A (en) * | 2013-03-06 | 2014-09-10 | 阿里巴巴集团控股有限公司 | Method and device for forwarding Ethernet packet |
CN104410725A (en) * | 2014-09-17 | 2015-03-11 | 广州杰赛科技股份有限公司 | Processing method and processing system of GPU (Graphics Processing Unit) as well as method and system for DNS (Domain Name Server) resolution based on GPU |
-
2015
- 2015-07-08 CN CN201510397380.1A patent/CN104994186A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101102286A (en) * | 2006-07-05 | 2008-01-09 | 阿里巴巴公司 | A method and device for referring to user information in instant communication system |
EP2566129A1 (en) * | 2010-12-21 | 2013-03-06 | Huawei Technologies Co., Ltd. | Method, apparatus and system for acquiring media access control address |
CN104038425A (en) * | 2013-03-06 | 2014-09-10 | 阿里巴巴集团控股有限公司 | Method and device for forwarding Ethernet packet |
CN103634216A (en) * | 2013-11-04 | 2014-03-12 | 汉柏科技有限公司 | Method and equipment for forwarding datagram based on NAT 64 (Network Address Translation 64) |
CN104410725A (en) * | 2014-09-17 | 2015-03-11 | 广州杰赛科技股份有限公司 | Processing method and processing system of GPU (Graphics Processing Unit) as well as method and system for DNS (Domain Name Server) resolution based on GPU |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194613A (en) * | 2017-06-20 | 2017-09-22 | 无锡井通网络科技有限公司 | Digital asset coding method |
CN108111422A (en) * | 2017-12-29 | 2018-06-01 | 北京明朝万达科技股份有限公司 | A kind of data high-speed multichannel retransmission method and device based on DPDK |
CN111061724A (en) * | 2019-11-08 | 2020-04-24 | 珠海许继芝电网自动化有限公司 | High-speed real-time database management method and device for distribution automation system |
CN111061724B (en) * | 2019-11-08 | 2023-11-14 | 珠海许继芝电网自动化有限公司 | High-speed real-time database management method and device for power distribution automation system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10608866B2 (en) | Forwarding Ethernet packets | |
CN101621414B (en) | Method and apparatus for discovering network resource and topology | |
US10333845B2 (en) | Forwarding data packets | |
EP3451592B1 (en) | Packet transmission between vxlan domains | |
US20160149811A1 (en) | Method to optimize flow-based network function chaining | |
US9906449B2 (en) | System and method for reduced forwarding information storage | |
CN110505621B (en) | Terminal migration processing method and device | |
CN101465889A (en) | Network address translation equipment and request method of response address analysis protocol | |
US10574570B2 (en) | Communication processing method and apparatus | |
CN104734955A (en) | Network function virtualization implementation method, wide-band network gateway and control device | |
US9183322B2 (en) | Increasing internet protocol version 6 host table scalability in top of rack switches for data center deployments | |
US11757766B2 (en) | Reflection route for link local packet processing | |
CN109743414B (en) | Method for improving address translation availability using redundant connections and computer readable storage medium | |
CN102291472A (en) | Network address lookup method and device | |
CN106331206A (en) | Domain name management method and device | |
CN107547407A (en) | Message transmitting method, device and realization device | |
CN107580079A (en) | A kind of message transmitting method and device | |
CN106982163A (en) | The method and gateway of route are obtained on demand | |
CN104994186A (en) | Query method, processor and device of media access control address | |
US20170012874A1 (en) | Software router and methods for looking up routing table and for updating routing entry of the software router | |
US20230041395A1 (en) | Method and Device for Processing Routing Table Entries | |
CN114785733B (en) | Method for realizing session tracing in cross-VPC network flow forwarding | |
US9853891B2 (en) | System and method for facilitating communication | |
CN110636005B (en) | Knowledge routing method and device of knowledge center network | |
CN103368852A (en) | Method and system for processing hash conflict |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151021 |