CN102055737B - Method, device and system for remote logining multinuclear system hardware thread - Google Patents
Method, device and system for remote logining multinuclear system hardware thread Download PDFInfo
- Publication number
- CN102055737B CN102055737B CN 200910210619 CN200910210619A CN102055737B CN 102055737 B CN102055737 B CN 102055737B CN 200910210619 CN200910210619 CN 200910210619 CN 200910210619 A CN200910210619 A CN 200910210619A CN 102055737 B CN102055737 B CN 102055737B
- Authority
- CN
- China
- Prior art keywords
- vcpu
- message
- terminal
- multiple nucleus
- nucleus system
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/12—Protocol engines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
- H04L69/161—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
Abstract
The invention discloses a method, device and system for remote logining a multinuclear system hardware thread. The method comprises the steps that a network acceleration engine of a multinuclear system sends TCP (Transmission Control Protocol) demand messages received from a terminal to a main v CPU (virtual Central Processing Unit), the main v CPU sends the TCP demand messages to a correspondingtarget v CPU for processing, and the target v CPU sends TCP response messages to the terminal through the network acceleration engine. In the invention, under the condition that the multinuclear system is provided with only one external Ethernet port, remote logining of all the v CPUs of the multinuclear system can be realized to facilitate respective maintenance and fault location of all the v CPUs of the multinuclear system. Compared with a multi-IP (Internet Protocol) address multinuclear system still in the trial run stage, which can also achieve remote logining to a specific v CPU in a telnet or FTP (File Transfer Protocol) or other manners, however, the method provided by the invention doesn't occupy a large quantity of the limited IP resources.
Description
Technical field
The present invention relates to the network processing unit technical field, relate in particular to a kind of method, Apparatus and system of telnet multiple nucleus system hardware thread.
Background technology
In the development of electronic technology process, because the demand that reduces cost, wireless base system uses polycaryon processor as network processing unit increasingly extensively.There are a plurality of nuclears polycaryon processor inside, each nuclear inside has a plurality of hardware threads again, hardware thread can move different and software version independently separately, so on the angle of software, each hardware thread can be regarded a vCPU (virtual Central ProcessingUnit, virtual CPU) as.
Generally, polycaryon processor system in wireless base station also claims multiple nucleus system, and the as a whole service that externally provides is provided, and a multiple nucleus system only uses an external Ethernet interface, has only an IP (Internet Protocol, Internet protocol) address.But for the ease of the hardware thread in the multiple nucleus system is safeguarded and fault location, need be remotely logged into by telnet agreement: telnet or FTP modes such as (File TransferProtocol, file transfer protocol (FTP)) and carry out some operation on the specific vCPU.And existing technology can not be remotely logged into the line operate of going forward side by side on the specific vCPU all at the single core processor system.Even be in the multiple nucleus system of many IP address in trial run stage at present, though can be remotely logged into specific vCPU by modes such as telnet or FTP, in this implementation with a large amount of limited IP resources that takies.
Summary of the invention
The technical problem to be solved in the present invention is, a kind of method, Apparatus and system of telnet multiple nucleus system hardware thread is provided, and externally only provides under the situation of an Ethernet interface at multiple nucleus system, is remotely logged into each vCPU of multiple nucleus system.
The technical solution used in the present invention is that the method for described telnet multiple nucleus system hardware thread comprises:
Terminal and multiple nucleus system obtain destination address mutually;
Terminal sends the TCP request message according to destination address to multiple nucleus system;
The TCP request message that comes self terminal that the network acceleration engine of multiple nucleus system will receive sends to main vCPU;
Main vCPU sends to corresponding purpose vCPU with the TCP request message and handles;
Purpose vCPU sends to terminal with the TCP response message according to destination address by the network acceleration engine.
Described terminal and multiple nucleus system obtain destination address mutually and comprise that terminal obtains MAC Address and multiple nucleus system obtains MAC Address to terminal to multiple nucleus system.
Described terminal to the detailed process that multiple nucleus system obtains MAC Address is:
Terminal sends the ARP request message to multiple nucleus system;
The network acceleration engine of multiple nucleus system receives the ARP request message of self terminal, and sends to main vCPU processing;
Main vCPU sends the arp reply message that has the multiple nucleus system MAC Address by the network acceleration engine to terminal.
The detailed process that described multiple nucleus system obtains MAC Address to terminal is:
VCPU in the multiple nucleus system sends the ARP request message by the network acceleration engine to terminal;
Terminal sends the arp reply message that has the terminal MAC Address to multiple nucleus system;
The network acceleration engine of multiple nucleus system receives the arp reply message of self terminal, and sends to main vCPU processing;
Main vCPU is distributed to all handling from vCPU with the arp reply message.
Described main vCPU and handle the arp reply message have the terminal MAC Address from vCPU and comprise: the MAC Address of terminal is recorded to described main vCPU and from the ARP table of vCPU.
After the TCP request message that comes self terminal that the network acceleration engine of described multiple nucleus system will receive sent to main vCPU, main vCPU sent to the TCP request message before corresponding purpose vCPU handles, and main vCPU also will carry out following processing:
The length of IP stem is increased in the length of the IP message that carries the TCP request message;
Recomputate the IP stem verification and;
The TCP request message is added that receiving the laggard row of net slogan encapsulates.
Bind respectively under the situation of service port number separately at each vCPU of described multiple nucleus system, described main vCPU sends to corresponding purpose vCPU according to the service port number of carrying in the TCP request message with the TCP request message and handles;
Described service port number is to determine according to the processor numbering of each vCPU in the multiple nucleus system self and the telnet protocol service port numbers of standard.
The present invention also provides a kind of device of telnet multiple nucleus system hardware thread, comprising:
The network acceleration engine is used for receiving the message of self terminal and sending to main vCPU, and the message that receives from all vCPU in the multiple nucleus system sends to terminal;
First message processing module (MPM) is arranged in main vCPU, the ARP request message in the message of receiving for the treatment of main vCPU, and the arp reply message that will carry the multiple nucleus system MAC Address by the network acceleration engine sends to terminal;
The message distribution module is arranged in main vCPU, and the arp reply message that is used for message that main vCPU is received is distributed to all message processing module (MPM)s from vCPU; The TCP request message is sent to message processing module (MPM) among the corresponding purpose vCPU;
Second message processing module (MPM) is arranged in all vCPU, after being used for receiving the arp reply message, the MAC Address of the terminal of wherein carrying is recorded in the local ARP table; Carry out telnet order or FTP order in the TCP request message, by the network acceleration engine TCP response message is sent to terminal.
Bind respectively under the situation of service port number separately at each vCPU of multiple nucleus system, described message distribution module further sends to second message processing module (MPM) among the corresponding purpose vCPU according to the service port number of carrying in the TCP request message with the TCP request message;
Described service port number is to determine according to the processor numbering of each vCPU in the multiple nucleus system self and the telnet protocol service port numbers of standard.
The present invention also provides a kind of system of telnet multiple nucleus system hardware thread, and terminal links to each other with multiple nucleus system by the Internet, and this system also comprises:
The network acceleration engine is used for receiving the message of self terminal and sending to main vCPU, and the message that receives from all vCPU in the multiple nucleus system sends to terminal;
First message processing module (MPM) is arranged in main vCPU, the ARP request message in the message of receiving for the treatment of main vCPU, and the arp reply message that will carry the multiple nucleus system MAC Address by the network acceleration engine sends to terminal;
The message distribution module is arranged in main vCPU, and the arp reply message that is used for message that main vCPU is received is distributed to all message processing module (MPM)s from vCPU; The TCP request message is sent to message processing module (MPM) among the corresponding purpose vCPU;
Second message processing module (MPM) is arranged in all vCPU, after being used for receiving the arp reply message, the MAC Address of the terminal of wherein carrying is recorded in the local ARP table; Carry out telnet order or FTP order in the TCP request message, by the network acceleration engine TCP response message is sent to terminal.
Adopt technique scheme, the present invention has following advantage at least:
Method, the Apparatus and system of telnet multiple nucleus system hardware thread of the present invention, the TCP request message that comes self terminal that the network acceleration engine of multiple nucleus system will receive sends to main vCPU, main vCPU sends to corresponding purpose vCPU with the TCP request message and handles, and purpose vCPU sends to terminal by the network acceleration engine with the TCP response message.The present invention can externally only provide under the situation of an Ethernet interface at multiple nucleus system, is remotely logged into each vCPU of multiple nucleus system, so that respectively each vCPU of multiple nucleus system is safeguarded and fault location.Compare with the multiple nucleus system of the many IP address that still is in the trial run stage in the prior art, though can be remotely logged into specific vCPU by modes such as telnet or FTP, the present invention is need not mode a large amount of takies limited IP resource.
Description of drawings
Fig. 1 is the composition schematic diagram of multiple nucleus system among first and second embodiment of the present invention;
Fig. 2 is the method flow diagram of the described telnet multiple nucleus system of first embodiment of the invention hardware thread;
Fig. 3 obtains the MAC Address flow chart for terminal to multiple nucleus system;
Fig. 4 obtains the MAC Address flow chart for multiple nucleus system to terminal;
Fig. 5 is the method flow diagram of the described telnet multiple nucleus system of second embodiment of the invention hardware thread;
Fig. 6 is the described telnet multiple nucleus system of third embodiment of the invention hardware thread device schematic diagram;
Fig. 7 is the described telnet multiple nucleus system of fourth embodiment of the invention hardware thread system schematic.
Embodiment
Reach technological means and the effect that predetermined purpose is taked for further setting forth the present invention, below in conjunction with accompanying drawing and preferred embodiment, method, the Apparatus and system of the described telnet multiple nucleus system hardware thread that the present invention is proposed, describe in detail as after.
Aspect embedded real-time operating system, in the high field of high-quality precision and sophisticated technology such as VxWorks is widely used in its good reliability and remarkable real-time and communicate by letter, military affairs, Aeronautics and Astronautics and real-time requirement.VxWorks is supported the Internet agreement of standard, and the ICP/IP protocol stack is arranged, and provides functions such as telnet, ftp, so the embodiment of the invention is that operating system is described based on VxWorks.
First embodiment of the invention, to comprise a main vCPU and three multiple nucleus systems from vCPU are example, the composition of this multiple nucleus system as shown in Figure 1.The user lands multiple nucleus system by the mode of telnet agreement, and a kind of method of telnet multiple nucleus system hardware thread as shown in Figure 2, comprises the steps:
Step s101, all vCPU of startup multiple nucleus system, the initialization network interface is tied to network interface with IP stack, and network interface IP is set.Because multiple nucleus system only externally provides a unified IP, so the IP that each nuclear arranges is identical.Each vCPU of multiple nucleus system binds service port number separately respectively, and described service port number is to determine according to the processor numbering of each vCPU in the multiple nucleus system self and the telnet protocol service port numbers of standard.In same multiple nucleus system, because the processor of each vCPU self numbering is unique, the telnet service port number on each vCPU is also inequality.Because the user also knows definite mode of the service port number of all vCPU in advance, therefore the user carries service port number by terminal in the telnet request message of multiple nucleus system transmission, and this service port number will be used for distinguishing the purpose vCPU that will login when main vCPU handles the telnet request message.
Step s102 because telnet is based on ICP/IP protocol, need know destination address during LA Management Room communication, such as the MAC Address of the network equipment, so terminal and multiple nucleus system need obtain destination address mutually, specifically comprises following process:
1) terminal is obtained MAC Address to multiple nucleus system, as shown in Figure 3, comprising:
Step s1, terminal sends the ARP request message to multiple nucleus system;
Step s2, the network acceleration engine of multiple nucleus system receives the ARP request message of self terminal, and sends to main vCPU processing;
Step s3, main vCPU sends the arp reply message that has the multiple nucleus system MAC Address by the network acceleration engine to terminal.
2) multiple nucleus system obtains MAC Address to terminal, as shown in Figure 4, comprising:
Step s4, all vCPU in the multiple nucleus system send the ARP request message by the network acceleration engine to terminal;
Step s5, terminal sends the arp reply message that has the terminal MAC Address to multiple nucleus system;
Step s6, the network acceleration engine of multiple nucleus system receives the arp reply message of self terminal, and sends to main vCPU, and main vCPU is recorded to the MAC Address of terminal in the local ARP table;
Step s7, main vCPU learns according to the contextual information of arp reply message and receives the net slogan, the arp reply message is added that receiving the laggard row of net slogan encapsulates, arp reply message after will encapsulating then is distributed to all from vCPU, and all is recorded to the MAC Address of terminal the local ARP table from vCPU.
Need to prove above-mentioned 1) terminal obtains MAC Address and 2 to multiple nucleus system) multiple nucleus system obtains these two processes of MAC Address to terminal does not have sequencing, can take place simultaneously.
Step s103, terminal sends the telnet request message according to destination address to multiple nucleus system.
Step s104, the network acceleration engine NAE of multiple nucleus system receives the telnet request message that terminal is sent, and by internuclear communication the telnet request message is sent to main vCPU.Internuclear communication generally all is the high-speed traffic mode that par-ticular processor inside provides, for example the FMN of the polycaryon processor of RMI Corp. (Fast MessagingNetwork, fast message network).
Step s105, main vCPU is, and the telnet request message is analyzed, judge whether its service port number of carrying is the service port number of self, if the service port number of self, jump procedure s106 then, otherwise illustrate that this service port number is certain service port number from vCPU, jump procedure s107.
Step s106 directly handles the telnet request message, carries out the telnet order in the telnet request message, and the telnet response message is sent to the network acceleration engine by internuclear communication, sends to terminal by the network acceleration engine, and flow process finishes.
Step s107, main vCPU be for the IP message of carrying telnet request message, and the length of IP stem is increased in the length of IP message, recomputate then verification and.The reason of carrying out this step is, during the IP layer of prior art after vCPU receives message handled to the verification of the IP stem of IP message and and the length of IP message change to some extent, the verification of IP stem and be assigned 0, and the length of IP message has been deducted the length of IP stem, and among the present invention when if the message received of main vCPU need be distributed to from vCPU, from vCPU receive the verification of having changed the IP stem and and the message of the length of IP message after can think error message and abandon, so here will be with the IP message reinstatement of the carrying telnet request message changed, could normal process after receiving from vCPU.
Telnet request message after step s108, main vCPU will encapsulate by internuclear communication sends to corresponding to its service port number of carrying vCPU, and the telnet request message is discharged.
Step s109 receives from vCPU therefrom to parse telnet request message after the encapsulation and to receive net slogan, former telnet request message, and carries out validity checking to receiving network interface number, message length etc., receives the network interface from message and applies for resource.
Step s110, the telnet that carries out the telnet request message from vCPU orders, and the telnet response message is directly sent to the network acceleration engine by internuclear communication, sends to terminal by the network acceleration engine.
Second embodiment of the invention, to comprise a main vCPU and three multiple nucleus systems from vCPU are example, the composition of this multiple nucleus system as shown in Figure 1.The user lands multiple nucleus system by the mode of File Transfer Protocol, and a kind of method of telnet multiple nucleus system hardware thread as shown in Figure 5, comprises the steps:
Step s201, all vCPU of startup multiple nucleus system, the initialization network interface is tied to network interface with IP stack, and network interface IP is set.Because multiple nucleus system only externally provides a unified IP, so the IP that each nuclear arranges is identical.Each vCPU of multiple nucleus system binds service port number separately respectively, and described service port number is to determine according to the processor numbering of each vCPU in the multiple nucleus system self and the File Transfer Protocol service port number of standard.In same multiple nucleus system, because the processor of each vCPU self numbering is unique, the FTP service port number on each vCPU is also inequality.Because the user also knows definite mode of the service port number of all vCPU in advance, therefore the user carries service port number by terminal in the FTP request message of multiple nucleus system transmission, and this service port number will be used for distinguishing the purpose vCPU that will login when main vCPU handles the FTP request message.
Step s202 because FTP is based on ICP/IP protocol, need know destination address during LA Management Room communication, such as the MAC Address of the network equipment, so at first terminal and multiple nucleus system need obtain destination address mutually, concrete comprises following process:
1) terminal is obtained MAC Address to multiple nucleus system, as shown in Figure 3, comprising:
Step s1, terminal sends the ARP request message to multiple nucleus system;
Step s2, the network acceleration engine of multiple nucleus system receives the ARP request message of self terminal, and sends to main vCPU processing;
Step s3, main vCPU sends the arp reply message that has the multiple nucleus system MAC Address by the network acceleration engine to terminal.
2) multiple nucleus system obtains MAC Address to terminal, as shown in Figure 4, comprising:
Step s4, all vCPU in the multiple nucleus system send the ARP request message by the network acceleration engine to terminal;
Step s5, terminal sends the arp reply message that has the terminal MAC Address to multiple nucleus system;
Step s6, the network acceleration engine of multiple nucleus system receives the arp reply message of self terminal, and sends to main vCPU, and main vCPU is recorded to the MAC Address of terminal in the local ARP table;
Step s7, main vCPU learns according to the contextual information of arp reply message and receives the net slogan, the arp reply message is added that receiving the laggard row of net slogan encapsulates, arp reply message after will encapsulating then is distributed to all from vCPU, and all is recorded to the MAC Address of terminal the local ARP table from vCPU.
Need to prove above-mentioned 1) terminal obtains MAC Address and 2 to multiple nucleus system) multiple nucleus system obtains the sequencing that do not have of these two processes of MAC Address to terminal, can take place simultaneously.
Step s203, terminal sends the FTP request message according to destination address to multiple nucleus system.
Step s204, the network acceleration engine of multiple nucleus system is received the FTP request message that terminal is sent, and by internuclear communication the FTP request message is sent to main vCPU.Internuclear communication generally all is the high-speed traffic mode that par-ticular processor inside provides, for example the fast message network FMN of the polycaryon processor of RMI Corp..
Step s205, main vCPU is, and the FTP request message is analyzed, and judges that its service port number of carrying still is certain service port number from vCPU for self service port number, if the service port number of self, jump procedure s206 then, otherwise jump procedure s207.
Step s206 directly handles the FTP request message, carries out the FTP order in the FTP request message, and the FTP response message is sent to the network acceleration engine by internuclear communication, sends to terminal by the network acceleration engine, and flow process finishes.
Step s207, main vCPU be for the IP message of carrying FTP request message, and the length of IP stem is increased in the length of IP message, recomputate then verification and.The reason of carrying out this step is, during the IP layer of prior art after vCPU receives message handled to the verification of the IP stem of IP message and and the length of IP message change to some extent, the verification of IP stem and be assigned 0, and the length of IP message has been deducted the length of IP stem, and among the present invention when if the message received of main vCPU need be distributed to from vCPU, from vCPU receive the verification of having changed the IP stem and and the message of the length of IP message after can think error message and abandon, so here the IP message of the carrying FTP request message changed will be restored to the original state, could normal process after receiving from vCPU.
FTP request message after step s208, main vCPU will encapsulate by internuclear communication sends to corresponding to its service port number of carrying vCPU, and the FTP request message is discharged.
Step s209 receives from vCPU therefrom to parse FTP request message after the encapsulation and to receive net slogan, former FTP request message, and carries out validity checking to receiving network interface number, message length etc., receives the network interface from message and applies for resource.
Step s210, the FTP that carries out the FTP request message from vCPU orders, and the FTP response message is directly sent to the network acceleration engine by internuclear communication, sends to terminal by the network acceleration engine.
Third embodiment of the invention, a kind of device of telnet multiple nucleus system hardware thread as shown in Figure 6, comprising:
The network acceleration engine is used for receiving the message of self terminal and sending to main vCPU, and the message that receives from all vCPU in the multiple nucleus system sends to terminal.
First message processing module (MPM) is arranged in main vCPU, the ARP request message in the message of receiving for the treatment of main vCPU, and the arp reply message that will carry the multiple nucleus system MAC Address by the network acceleration engine sends to terminal.
The message distribution module is arranged in main vCPU, and the arp reply message that is used for message that main vCPU is received is distributed to all message processing module (MPM)s from vCPU.Bind respectively under the situation of service port number separately at each vCPU of multiple nucleus system, this module can send to message processing module (MPM) among the corresponding purpose vCPU with the TCP request message according to the service port number of carrying in the TCP request message, and service port number is definite according to the Telnet service port number of the processor numbering of each vCPU in the multiple nucleus system self and standard.
Second message processing module (MPM), be arranged in all vCPU, after being used for receiving the arp reply message, the MAC Address of the terminal of wherein carrying is recorded in the local ARP table, carry out telnet order or FTP order in the TCP request message, by the network acceleration engine TCP response message is sent to terminal.
Because telnet agreement and File Transfer Protocol all are the agreements on Transmission Control Protocol upper strata, telnet message and FTP message all belong to the TCP message.
Fourth embodiment of the invention, as shown in Figure 7, a kind of system of telnet multiple nucleus system hardware thread, terminal links to each other with multiple nucleus system by IP network, and this system also comprises:
The network acceleration engine is used for receiving the message of self terminal and sending to main vCPU, and the message that receives from all vCPU in the multiple nucleus system sends to terminal.
First message processing module (MPM) is arranged in main vCPU, the ARP request message in the message of receiving for the treatment of main vCPU, and the arp reply message that will carry the multiple nucleus system MAC Address by the network acceleration engine sends to terminal.
The message distribution module is arranged in main vCPU, and the arp reply message that is used for message that main vCPU is received is distributed to all message processing module (MPM)s from vCPU.Bind respectively under the situation of service port number separately at each vCPU of multiple nucleus system, this module can send to message processing module (MPM) among the corresponding purpose vCPU with the TCP request message according to the service port number of carrying in the TCP request message, and service port number is definite according to the Telnet service port number of the processor numbering of each vCPU in the multiple nucleus system self and standard.
Second message processing module (MPM), be arranged in all vCPU, after being used for receiving the arp reply message, the MAC Address of the terminal of wherein carrying is recorded in the local ARP table, carry out telnet order or FTP order in the TCP request message, by the network acceleration engine TCP response message is sent to terminal.
By the explanation of embodiment, should be to reach technological means and the effect that predetermined purpose takes to be able to more deeply and concrete understanding to the present invention, yet appended diagram only provide with reference to the usefulness of explanation, the present invention is limited.
Claims (10)
1. the method for a telnet multiple nucleus system hardware thread is characterized in that, comprising:
Terminal and multiple nucleus system obtain destination address mutually;
Terminal sends the TCP request message according to destination address to multiple nucleus system;
The TCP request message that comes self terminal that the network acceleration engine of multiple nucleus system will receive sends to main vCPU;
Main vCPU sends to corresponding purpose vCPU with the TCP request message and handles; Concrete, binding respectively under the situation of service port number separately at each vCPU of described multiple nucleus system, described main vCPU sends to corresponding purpose vCPU according to the service port number of carrying in the TCP request message with the TCP request message and handles;
Purpose vCPU sends to terminal with the TCP response message according to destination address by the network acceleration engine.
2. according to the method for the described telnet multiple nucleus system of claim 1 hardware thread, it is characterized in that described terminal and multiple nucleus system obtain destination address mutually and comprise that terminal obtains MAC Address and multiple nucleus system obtains MAC Address to terminal to multiple nucleus system.
3. according to the method for the described telnet multiple nucleus system of claim 2 hardware thread, it is characterized in that described terminal to the detailed process that multiple nucleus system obtains MAC Address is:
Terminal sends the ARP request message to multiple nucleus system;
The network acceleration engine of multiple nucleus system receives the ARP request message of self terminal, and sends to main vCPU processing;
Main vCPU sends the arp reply message that has the multiple nucleus system MAC Address by the network acceleration engine to terminal.
4. according to the method for claim 2 or 3 described telnet multiple nucleus system hardware threads, it is characterized in that the detailed process that described multiple nucleus system obtains MAC Address to terminal is:
All vCPU in the multiple nucleus system send the ARP request message by the network acceleration engine to terminal;
Terminal sends the arp reply message that has the terminal MAC Address to multiple nucleus system;
The network acceleration engine of multiple nucleus system receives the arp reply message of self terminal, and sends to main vCPU processing;
Main vCPU is distributed to all handling from vCPU with the arp reply message.
5. according to the method for the described telnet multiple nucleus system of claim 4 hardware thread, it is characterized in that described main vCPU and handle the arp reply message have the terminal MAC Address from vCPU and comprise: the MAC Address of terminal is recorded to described main vCPU and from the ARP table of vCPU.
6. according to the method for claim 1 or 2 or 3 or 5 described telnet multiple nucleus system hardware threads, it is characterized in that, after the TCP request message that comes self terminal that the network acceleration engine of described multiple nucleus system will receive sends to main vCPU, main vCPU sends to the TCP request message before the corresponding purpose vCPU processing, and main vCPU also will carry out following processing:
The length of IP stem is increased in the length of the IP message that carries the TCP request message;
Recomputate the IP stem verification and;
The TCP request message is added that receiving the laggard row of net slogan encapsulates.
7. according to the method for the described telnet multiple nucleus system of claim 1 hardware thread, it is characterized in that,
Described service port number is to determine according to the processor numbering of each vCPU in the multiple nucleus system self and the telnet protocol service port numbers of standard.
8. the device of a telnet multiple nucleus system hardware thread is characterized in that, comprising:
The network acceleration engine is used for receiving the message of self terminal and sending to main vCPU, and the message that receives from all vCPU in the multiple nucleus system sends to terminal;
First message processing module (MPM) is arranged in main vCPU, the ARP request message in the message of receiving for the treatment of main vCPU, and the arp reply message that will carry the multiple nucleus system MAC Address by the network acceleration engine sends to terminal;
The message distribution module is arranged in main vCPU, and the arp reply message that is used for message that main vCPU is received is distributed to all second message processing module (MPM)s from vCPU; TCP request message in the message that main vCPU is received sends to second message processing module (MPM) among the corresponding purpose vCPU;
Second message processing module (MPM) is arranged in all vCPU, after being used for receiving the arp reply message, the MAC Address of the terminal of wherein carrying is recorded in the local ARP table; Carry out telnet order or FTP order in the TCP request message, by the network acceleration engine TCP response message is sent to terminal.
9. the device of described telnet multiple nucleus system hardware thread according to Claim 8, it is characterized in that, bind respectively under the situation of service port number separately at each vCPU of multiple nucleus system, described message distribution module further sends to second message processing module (MPM) among the corresponding purpose vCPU according to the service port number of carrying in the TCP request message with the TCP request message;
Described service port number is to determine according to the processor numbering of each vCPU in the multiple nucleus system self and the telnet protocol service port numbers of standard.
10. the system of a telnet multiple nucleus system hardware thread is characterized in that, terminal links to each other with multiple nucleus system by the Internet, and this system also comprises:
The network acceleration engine is used for receiving the message of self terminal and sending to main vCPU, and the message that receives from all vCPU in the multiple nucleus system sends to terminal;
First message processing module (MPM) is arranged in main vCPU, the ARP request message in the message of receiving for the treatment of main vCPU, and the arp reply message that will carry the multiple nucleus system MAC Address by the network acceleration engine sends to terminal;
The message distribution module is arranged in main vCPU, and the arp reply message that is used for message that main vCPU is received is distributed to all second message processing module (MPM)s from vCPU; TCP request message in the message that main vCPU is received sends to second message processing module (MPM) among the corresponding purpose vCPU;
Second message processing module (MPM) is arranged in all vCPU, after being used for receiving the arp reply message, the MAC Address of the terminal of wherein carrying is recorded in the local ARP table; Carry out telnet order or FTP order in the TCP request message, by the network acceleration engine TCP response message is sent to terminal.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910210619 CN102055737B (en) | 2009-11-04 | 2009-11-04 | Method, device and system for remote logining multinuclear system hardware thread |
| PCT/CN2010/074498 WO2010145582A1 (en) | 2009-11-04 | 2010-06-25 | Method, device and system for remote accessing to hardware thread in multi-core system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910210619 CN102055737B (en) | 2009-11-04 | 2009-11-04 | Method, device and system for remote logining multinuclear system hardware thread |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102055737A CN102055737A (en) | 2011-05-11 |
| CN102055737B true CN102055737B (en) | 2013-09-11 |
Family
ID=43355879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910210619 Expired - Fee Related CN102055737B (en) | 2009-11-04 | 2009-11-04 | Method, device and system for remote logining multinuclear system hardware thread |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102055737B (en) |
| WO (1) | WO2010145582A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106357554A (en) * | 2015-07-13 | 2017-01-25 | 中兴通讯股份有限公司 | Packet receiving method and device of network port of equipment internal processor |
| WO2022225541A1 (en) * | 2021-04-20 | 2022-10-27 | Arris Enterprises Llc | Secure access for vcores |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101159765A (en) * | 2006-10-06 | 2008-04-09 | 英特尔公司 | Network interface techniques |
| CN101178666A (en) * | 2007-12-13 | 2008-05-14 | 中兴通讯股份有限公司 | Coordinating and scheduling method between heterogeneous multi-core |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7895431B2 (en) * | 2004-09-10 | 2011-02-22 | Cavium Networks, Inc. | Packet queuing, scheduling and ordering |
| CN101262501B (en) * | 2008-04-23 | 2011-04-20 | 杭州华三通信技术有限公司 | An inter-core communication method in multi-core system and one multi-core system |
-
2009
- 2009-11-04 CN CN 200910210619 patent/CN102055737B/en not_active Expired - Fee Related
-
2010
- 2010-06-25 WO PCT/CN2010/074498 patent/WO2010145582A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101159765A (en) * | 2006-10-06 | 2008-04-09 | 英特尔公司 | Network interface techniques |
| CN101178666A (en) * | 2007-12-13 | 2008-05-14 | 中兴通讯股份有限公司 | Coordinating and scheduling method between heterogeneous multi-core |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102055737A (en) | 2011-05-11 |
| WO2010145582A1 (en) | 2010-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102075358B (en) | System and method for distributing and deploying content of large-scale server cluster | |
| CN100492302C (en) | Method for realizing interprocess asynchronous communication based on Java | |
| CN1700674B (en) | Packet generation method, communication method, packet processing method | |
| US9569289B2 (en) | Generic distributed processing for multi-agent systems | |
| CN102148768B (en) | Message forwarding method and device | |
| US8369244B2 (en) | Method for operating an ethernet-capable field-bus device | |
| US7949754B2 (en) | Method and apparatus for prescribing station identifiers in a profit IO network | |
| CN108848025B (en) | Data processing method, intelligent gateway and Internet of things system | |
| CN106100955B (en) | Industrial internet field layer broadband bus data depth detection implementation method | |
| US7269661B2 (en) | Method using receive and transmit protocol aware logic modules for confirming checksum values stored in network packet | |
| CN110417687B (en) | Message sending and receiving method and device | |
| CN102055737B (en) | Method, device and system for remote logining multinuclear system hardware thread | |
| CN108093041A (en) | Single channel VDI proxy servers and implementation method | |
| CN109005150B (en) | Non-link communication method and system based on Ethernet MAC address | |
| CN106059964A (en) | Message forwarding method and apparatus | |
| CN113364660A (en) | Data packet processing method and device in LVS load balancing | |
| CN111092952B (en) | Data interaction method and related product | |
| CN106302432B (en) | A kind of communication device and control method based on car networking | |
| CN102246494A (en) | Systems and methods for allocating network resources from one address realm to clients in a different address realm | |
| CN103905392A (en) | Dynamic Host Configuration Protocol (DHCP) server selection method, device and system | |
| CN112333293A (en) | Network component and addressing of network components of a charging park | |
| CN116567094A (en) | Service information processing method based on micro service system | |
| CN101087232A (en) | An access method, system and device based on Ethernet point-to-point protocol | |
| CN109981813A (en) | Message processing method and device | |
| CN111240867B (en) | Information communication system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130911 Termination date: 20171104 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |