CN103618778A - System and method for achieving data high concurrency through Linux virtual host - Google Patents
System and method for achieving data high concurrency through Linux virtual host Download PDFInfo
- Publication number
- CN103618778A CN103618778A CN201310594261.6A CN201310594261A CN103618778A CN 103618778 A CN103618778 A CN 103618778A CN 201310594261 A CN201310594261 A CN 201310594261A CN 103618778 A CN103618778 A CN 103618778A
- Authority
- CN
- China
- Prior art keywords
- real server
- address
- subscriber
- load equalizer
- main station
- 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
Images
Landscapes
- Computer And Data Communications (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a system and method for achieving the data high concurrency through a Linux virtual host. The system comprises a load balancer and at least one real server. The load balancer is respectively connected with the real servers through a router. The load balancer and the real servers are connected with a user host computer through the Internet with the firewall. The method comprises the steps that the user host computer starts a linkage, an access request is forwarded to the real servers through the load balancer, the real servers directly return a result to the user host computer, and data are read and written. Compared with the prior art, the system and method have the advantages that cost is saved, expansion is easy, deploying, upgrading and maintaining are convenient, and the requirement for the high concurrency of the data size can be met.
Description
Technical field
The present invention relates to a kind ofly for the high concurrent treatment technology of data, especially relate to a kind of Linux of utilization fictitious host computer and realize the high concurrent system and method for data.
Background technology
Computer cluster is a kind of computer system, it by one group of loose integrated computer software and (or) hardware couples together the evaluation work that highly closely cooperated.In some sense, they can be counted as a computer.Single computer in group system is commonly referred to node, conventionally by local area network (LAN), connects.Cluster computer be commonly used to improve single computer computational speed and (or) reliability, because it possesses stronger retractility, group system is widely used in a plurality of fields of the Internet.
The fast development of the Internet, is changing our Working and life styles.Along with people are strong all the more to the dependence of network, different industries, different classes of software systems are also competitively reached the standard grade.For passing through the organization of the Internet issuing service, user's experience property will determine its existence matter of fundamental importance to a great extent.Simultaneously, development along with business on line, it is of common occurrence that software systems face the situation of high Concurrency Access and mass data flow, disposal ability and calculating strength that each nucleus equipment in system is born also can correspondingly increase, system bottleneck problem will be come out very soon, finally will certainly have influence on user's experience property.If eliminate existing equipment, do HardwareUpgring, will cause the waste of resource, and if face the surge of traffic carrying capacity later, the HardwareUpgring cost of the great number of having to again again drop into, even performance more remarkable equipment can not meet the demand of traffic carrying capacity in the future.
One of current scheme addressing these problems is to use high performance server.As described above, high-performance server means high hardware cost, and when Data Concurrent is to a certain extent time, this station server is by the whole bottleneck that is system.And aspect software, adopt high performance database and high efficiency programming language, although can bring larger improvement, when on market, most products adopt this software approach, its advantage will not exist yet.In some nonessential business, this scheme can solve concurrent problem, but does not possess versatility, does not also meet most real world applications scenes.
Second solution is to adopt proxy server, the Concurrency Access of data is distributed to other nodes of cluster inside, then inter-process result is finally returned to user by proxy server.This kind of scheme is by being distributed to request of data other nodes, must alleviate the operating pressure to proxy server, yet proxy server is as unique entrance and exit of data, will inevitably become a bottleneck, it requires proxy server to have higher hardware configuration, can improve to greatest extent the concurrency of system.
Summary of the invention
Object of the present invention is exactly to provide a kind of Linux of utilization fictitious host computer to realize the high concurrent system and method for data in order to overcome the defect of above-mentioned prior art existence.
Object of the present invention can be achieved through the following technical solutions:
A kind of Linux of utilization fictitious host computer is realized the high concurrent system of data, comprise a load equalizer and at least one real server, described load equalizer is connected with every real server respectively by router, described load equalizer is connected subscriber's main station with real server by being provided with the Internet of fire compartment wall, described load equalizer disposes one for the external service IP of subscriber's main station access, described real server disposes an inside IP identical with external service IP, and its ARP responds in closed condition.
Described load equalizer and real server are Linux fictitious host computer, and both can be the Same Physical main frame of identity coincidence.
Described load equalizer and real server are connected on the Same Physical network segment by same network interface card.
The high concurrent method of data that realizes that adopts said system, comprises the following steps:
1) subscriber's main station is initiated link, the access request that comprises Mac address and IP address is sent to load equalizer by Internet, wherein the source address of Mac address is subscriber's main station Mac address usermac, destination address is load equalizer Mac address Vmac, the source address of IP address is subscriber's main station IP address userIP, the external service IP address VIP that destination address is load equalizer;
2) load equalizer receives the access request by firewall filtering, select a real server, upgrade behind the Mac address in access request, by router, access request is sent to selected real server, after wherein upgrading, the source address of Mac address is load equalizer Mac address Vmac, and destination address is described real server Mac address macl;
3) real server receives the access request of forwarding, the inner IP of destination address in IP address and its is mated, if the match is successful, extract and encapsulate the message in access request, upgrade behind Mac address and IP address, directly return to subscriber's main station, wherein the source address of Mac address is real server Mac address macl, destination address is subscriber's main station Mac address usermac, and the source address of IP address is external service IP address VIP, and destination address is subscriber's main station IP address userIP;
4) subscriber's main station receives after message, according to the Mac address in message and IP address, by local agent service module, is extracted the information in message and is processed this result.
Step 2) in, the selection of real server adopts the minimum link algorithm of weighting, be specially load equalizer, according to the performance of each real server, it set to weight, then the load in conjunction with each real server links number and its load weights of Weight Acquisition, by load weights, select dynamically real server, the load weights of each real server are reached unanimity.
Step 2) if in load equalizer cannot correctly forward access request to real server, to directly sending error reporting to subscriber's main station.
Step 4) in, by proxy service module, carry out data and read while processing, if current real server exists target data, the proxy service module of real server will directly be returned to target data to subscriber's main station; If there is not target data in current real server, communicate with there is the proxy service module of the real server of this target data, and obtain described target data, then return to subscriber's main station.
Step 4) in, by proxy service module, carry out data and write while processing, if when proxy service module can be to self real server data writing, write direct; If in the time of cannot be to self real server data writing, communicate with the proxy service module that can write the real server of these data, by its data writing.
Compared with prior art, the present invention has the following advantages:
1, can linearly increase real server, along with the increase of its number, concurrency will be realized linear growth.Such mode can fast, simply improve the concurrency of group system.
2. the hardware performance of load equalizer and the configuration of real server can be identical, also can be more excellent.Cluster needn't need high performance hardware device, just can reach higher concurrency, to a great extent, has reduced user's hardware cost.Meanwhile, when load equalizer hardware performance promotes, because of Response step, no longer pass through load equalizer, it all can bring higher concurrency, and it promotes effect by the several times that are common cluster.
The increase of real server with remove very simply, can greatly utilize its retractility, meet polytype user, so practical application scene is very extensive.
4. the transparency.Make the group system of the Song Ouhe that formed by a plurality of independently real server form a virtual server; When user side application program and group system are mutual, just as the same with a high-performance, high available server interaction, user side need not change, and adding and shifting out not of part server can break in service, and these are transparent to user.
Accompanying drawing explanation
Fig. 1 is the structural representation of system of the present invention;
Fig. 2 is the concrete configuration schematic diagram in the embodiment of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
Embodiment
As shown in Figure 1, the invention provides a kind of Linux of utilization fictitious host computer and realize the high concurrent system of data, this system comprises a load equalizer VS and at least one real server RS, described load equalizer VS is connected with every real server RS respectively by router one, and described load equalizer VS is connected subscriber's main station 4 with real server RS by being provided with the Internet3 of fire compartment wall 2.
The concrete configuration process of said system is as follows:
1, the configuration of load equalizer
First, use configuration tool to carry out the configuration of load equalizer, load equalizer has been realized transport layer load balancing at linux kernel, it is the core component of whole system, because it is to be operated in being only used as on network layer to distribute, there is no the generation of flow, therefore have stronger anti-load capacity.This layoutprocedure generally adopts special-purpose configuration tool ipvsadm.
Successfully disposing after load equalizer, need to simply configure it.Generally be divided into two steps, the firstth, configuration load equalizer itself, the secondth, the correlation of configuration real server and load equalizer, this operation simultaneously also need to correspondence complete on real server.
Then be add and remove real server.When having a new real server to add to come in, the layoutprocedure that only need to repeat previous step is just passable, same, when having a real server to exit from system, only needs independent configuration load equalizer just passable.When the real server after removing is added to system again, need first the server being added to be done to cleaning operation, then just can add and with the role of a new server.
2, the configuration of real server
First, guarantee that real server need to be consistent with the system version of load equalizer.
Then, the route of configuration real server.
Finally, the agency service of configuration real server.Dispatching technique based on load equalizer, when the initial SYN message of a TCP connection arrives, load equalizer is just dispatched to a real server, forwards the packet to it.After this by looking into transmit messages civilian IP and TCP heading address, guarantee that the follow-up message of this connection is forwarded to this real server.Owing to being sent to which platform real server regardless of request, different subscriber's main stations is accessed identical data, and returning results of requirement must be all the same, will ask like this real server that identical service is provided.The effect of proxy service module has: being used for the scheduling of responsive load equalizer, for the internal data access between real server, is the network configuration of full symmetric between them.
3, intrasystem network configuration
The effect of router is to make load equalizer and real server all by a network interface card, to be connected on the Same Physical network segment.An external service IP of load equalizer configuration, name is called VIP, this IP address can directly be accessed by subscriber's main station, real server disposes an inside IP identical with external service IP, and for real server adds a routing rule that can arrive internal gateway, the arp that simultaneously closes real server responds.
In addition, the present invention opens and discloses a kind of high concurrent method of data that realizes that adopts said system, and the detailed process of the method is as follows:
1) subscriber's main station is initiated link, the access request that comprises Mac address and IP address is sent to load equalizer by Internet, wherein the source address src mac of Mac address is subscriber's main station Mac address usermac, destination address dst mac is load equalizer Mac address Vmac, the source address source ip of IP address is subscriber's main station IP address userIP, destination address dst ip is the external service IP address VIP of load equalizer, specific as follows:
2) load equalizer receives the access request by firewall filtering, select a real server, upgrade behind the Mac address in access request, by router, access request is sent to selected real server, if load equalizer cannot correctly forward access request to real server, to directly sending error reporting to subscriber's main station.After wherein upgrading, the source address of Mac address is load equalizer Mac address Vmac, and destination address is described real server Mac address macl, specific as follows:
3) real server receives the access request of forwarding, the inner IP of destination address in IP address and its is mated, if the match is successful, extract and encapsulate the message in access request, upgrade behind Mac address and IP address, directly return to subscriber's main station, wherein the source address of Mac address is real server Mac address macl, destination address is subscriber's main station Mac address usermac, the source address of IP address is external service IP address VIP, destination address is subscriber's main station IP address userIP, specific as follows:
4) subscriber's main station receives after message, according to the Mac address in message and IP address, by local agent service module, is extracted the information in message and is processed this result.
Wherein, step 2) in, the selection of real server adopts the minimum link algorithm of weighting, be specially load equalizer, according to the performance of each real server, it set to weight, then the load in conjunction with each real server links number and its load weights of Weight Acquisition, by load weights, select dynamically real server, the load weights of each real server are reached unanimity.
Step 4) in, by proxy service module, carry out data and read while processing, if current real server exists target data, the proxy service module of real server will directly be returned to target data to subscriber's main station; If there is not target data in current real server, communicate with there is the proxy service module of the real server of this target data, and obtain described target data, then return to subscriber's main station.And carry out data by proxy service module, write while processing, if when proxy service module can be to self real server data writing, write direct; If in the time of cannot be to self real server data writing, communicate with the proxy service module that can write the real server of these data, by its data writing.
The system with a load equalizer and two real server of take is example, and its layoutprocedure is specially:
1. load equalizer VS.
1.1 install
First select distribution version Red Hat Enterprise Linux Server release 6.2 (Santiago) of linux system, and by the old process of selected distribution edition system, linux system is installed.After installation, then software module that service software system requires to be necessary is installed, user's configuration tool (ipvsadm) is installed, after successful installation, SiteServer LBS successful installation.
1.2 configuration
1.2.1 configuration is redirected
#echo″1″>/proc/sys/net/ipv4/ip_forward
#echo″0″>/proc/sys/net/ipv4/conf/all/send_redirects
#echo″0″>/proc/sys/net/ipv4/conf/default/send_redirects
#echo″0″>/proc/sys/net/ipv4/conf/eth0/send_redirects
#echo″0″>/proc/sys/net/ipv4/conf/eth1/send_redirects
1.2.2 remove ipvsadm table
#ipvsadm-C
1.2.3 increase VS
#ipvsadm-A-t192.168.92.100：9000
1.2.4 increase by two real server
#ipvsadm-a-t192.168.92.100：9000-r10.0.0.8-g
#ipvsadm-a-t192.168.92.100：9000-r10.0.0.9-g
2. install, configure two identical real server systems, title is respectively RS1, RS2.
Select Red Hat Enterprise Linux Server release6.2 (Santiago) distribution version, this linux system is installed, and the software module of all dependences is installed, business software is installed.
3. complete after above-mentioned two steps, this step need to be VS, RS1, RS2 network and connect.During configuration network environment, require load equalizer and real server all by a network interface card, to be connected on the Same Physical network segment, and configure corresponding IP address.
3.1 inner private ip configurations:
On VS, be configuration #ifconfig eth010.0.0.10
On RS1, be configuration #ifconfig eth010.0.0.8
On RS2, be configuration #ifconfig eth010.0.0.9
3.2 one of configuration are service VIP externally:
On VS, be configuration #ifconfig eth0:0192.168.92.100.
3.3 configure RS1, RS2 simultaneously;
#ifconfig lo：0192.168.92.100
4., after having configured, test.Subscriber's main station in a large number, repeatedly to VIP, initiate request, with monitoring software, can observe:
IP Virtual Server version1.2.1(size＝4096)
Prot LocalAddress：Port Scheduler Flags
->RemoteAddress：Port Forward Weight ActiveConn InActConn
TCP192.168.92.100：9000sh
->10.0.0.8：9000 Route 1 0 33
->10.0.0.9：9000 Route 1 0 33
The request that can see client from is above forwarded to RS1, two real server of RS2 are processed.
When business demand is increased sharply, can the linear number that increases real server, meet consumers' demand fast, and keep user transparent.Otherwise, support real server to remove from system, to reduce cluster scale, better control cost, adaptation business changes.
Claims (8)
1. one kind is utilized Linux fictitious host computer to realize the high concurrent system of data, it is characterized in that, comprise a load equalizer and at least one real server, described load equalizer is connected with every real server respectively by router, described load equalizer is connected subscriber's main station with real server by being provided with the Internet of fire compartment wall, described load equalizer disposes one for the external service IP of subscriber's main station access, described real server disposes an inside IP identical with external service IP, and its ARP responds in closed condition.
2. a kind of Linux of utilization fictitious host computer is realized the high concurrent system of data according to claim 1, it is characterized in that, described load equalizer and real server are Linux fictitious host computer, and both can be the Same Physical main frame of identity coincidence.
3. a kind of Linux of utilization fictitious host computer is realized the high concurrent system of data according to claim 1, it is characterized in that, described load equalizer and real server are connected on the Same Physical network segment by same network interface card.
4. the high concurrent method of data that realizes that adopts system described in claim 1, is characterized in that, comprises the following steps:
1) subscriber's main station is initiated link, the access request that comprises Mac address and IP address is sent to load equalizer by Internet, wherein the source address of Mac address is subscriber's main station Mac address usermac, destination address is load equalizer Mac address Vmac, the source address of IP address is subscriber's main station IP address userIP, the external service IP address VIP that destination address is load equalizer;
2) load equalizer receives the access request by firewall filtering, select a real server, upgrade behind the Mac address in access request, by router, access request is sent to selected real server, after wherein upgrading, the source address of Mac address is load equalizer Mac address Vmac, and destination address is described real server Mac address macl;
3) real server receives the access request of forwarding, the inner IP of destination address in IP address and its is mated, if the match is successful, extract and encapsulate the message in access request, upgrade behind Mac address and IP address, directly return to subscriber's main station, wherein the source address of Mac address is real server Mac address macl, destination address is subscriber's main station Mac address usermac, and the source address of IP address is external service IP address VIP, and destination address is subscriber's main station IP address userIP;
4) subscriber's main station receives after message, according to the Mac address in message and IP address, by local agent service module, is extracted the information in message and is processed this result.
5. method according to claim 4, it is characterized in that, step 2) in, the selection of real server adopts the minimum link algorithm of weighting, be specially load equalizer, according to the performance of each real server, it set to weight, then the load in conjunction with each real server links number and its load weights of Weight Acquisition, by load weights, select dynamically real server, the load weights of each real server are reached unanimity.
6. method according to claim 4, is characterized in that step 2) if in load equalizer cannot correctly forward access request to real server, directly to subscriber's main station, send error reporting.
7. method according to claim 4, it is characterized in that, step 4) in, by proxy service module, carry out data and read while processing, if current real server exists target data, the proxy service module of real server will directly be returned to target data to subscriber's main station; If there is not target data in current real server, communicate with there is the proxy service module of the real server of this target data, and obtain described target data, then return to subscriber's main station.
8. method according to claim 4, is characterized in that step 4) in by proxy service module, carry out data and write while processing, if when proxy service module can be to self real server data writing, write direct; If in the time of cannot be to self real server data writing, communicate with the proxy service module that can write the real server of these data, by its data writing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310594261.6A CN103618778A (en) | 2013-11-21 | 2013-11-21 | System and method for achieving data high concurrency through Linux virtual host |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310594261.6A CN103618778A (en) | 2013-11-21 | 2013-11-21 | System and method for achieving data high concurrency through Linux virtual host |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103618778A true CN103618778A (en) | 2014-03-05 |
Family
ID=50169482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310594261.6A Pending CN103618778A (en) | 2013-11-21 | 2013-11-21 | System and method for achieving data high concurrency through Linux virtual host |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103618778A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104049690A (en) * | 2014-06-10 | 2014-09-17 | 浪潮电子信息产业股份有限公司 | Model design method by using critical application host to cope with high concurrent business |
| CN105812320A (en) * | 2014-12-30 | 2016-07-27 | 北京神州泰岳软件股份有限公司 | Method, server and system for realizing communication between user host and first host, |
| CN106790675A (en) * | 2017-01-23 | 2017-05-31 | 天地融科技股份有限公司 | Load-balancing method, equipment and system in a kind of cluster |
| CN110417921A (en) * | 2019-09-06 | 2019-11-05 | 广州华多网络科技有限公司 | A kind of method and load balancing service device of load balancing |
| CN110620802A (en) * | 2018-06-20 | 2019-12-27 | 华为技术有限公司 | Load balancing method and device |
| CN113709054A (en) * | 2021-07-16 | 2021-11-26 | 济南浪潮数据技术有限公司 | Keepallved-based LVS (Low Voltage differential Signaling) system deployment adjusting method, device and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020032798A1 (en) * | 2000-09-08 | 2002-03-14 | Wei Xu | Systems and methods for packet sequencing |
| WO2002021804A1 (en) * | 2000-09-08 | 2002-03-14 | Spontaneous Networks, Inc. | Systems and methods for packet distribution |
| CN101296238A (en) * | 2008-06-17 | 2008-10-29 | 杭州华三通信技术有限公司 | Method and equipment for remaining persistency of security socket layer conversation |
| CN101815033A (en) * | 2010-03-12 | 2010-08-25 | 成都市华为赛门铁克科技有限公司 | Method, device and system for load balancing |
| CN103023942A (en) * | 2011-09-27 | 2013-04-03 | 奇智软件（北京）有限公司 | Load balancing method, device and system of server |
| CN103036967A (en) * | 2012-12-10 | 2013-04-10 | 北京奇虎科技有限公司 | Data download system and device and method for download management |
| CN103384255A (en) * | 2011-12-31 | 2013-11-06 | 华为数字技术（成都）有限公司 | Load balancing method, server and system for virtual machine cluster |
-
2013
- 2013-11-21 CN CN201310594261.6A patent/CN103618778A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020032798A1 (en) * | 2000-09-08 | 2002-03-14 | Wei Xu | Systems and methods for packet sequencing |
| WO2002021804A1 (en) * | 2000-09-08 | 2002-03-14 | Spontaneous Networks, Inc. | Systems and methods for packet distribution |
| CN101296238A (en) * | 2008-06-17 | 2008-10-29 | 杭州华三通信技术有限公司 | Method and equipment for remaining persistency of security socket layer conversation |
| CN101815033A (en) * | 2010-03-12 | 2010-08-25 | 成都市华为赛门铁克科技有限公司 | Method, device and system for load balancing |
| CN103023942A (en) * | 2011-09-27 | 2013-04-03 | 奇智软件（北京）有限公司 | Load balancing method, device and system of server |
| CN103384255A (en) * | 2011-12-31 | 2013-11-06 | 华为数字技术（成都）有限公司 | Load balancing method, server and system for virtual machine cluster |
| CN103036967A (en) * | 2012-12-10 | 2013-04-10 | 北京奇虎科技有限公司 | Data download system and device and method for download management |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104049690A (en) * | 2014-06-10 | 2014-09-17 | 浪潮电子信息产业股份有限公司 | Model design method by using critical application host to cope with high concurrent business |
| CN105812320A (en) * | 2014-12-30 | 2016-07-27 | 北京神州泰岳软件股份有限公司 | Method, server and system for realizing communication between user host and first host, |
| CN105812320B (en) * | 2014-12-30 | 2019-09-27 | 北京神州泰岳软件股份有限公司 | Realize method, server and the system of subscriber's main station and the first main-machine communication |
| CN106790675A (en) * | 2017-01-23 | 2017-05-31 | 天地融科技股份有限公司 | Load-balancing method, equipment and system in a kind of cluster |
| CN110620802A (en) * | 2018-06-20 | 2019-12-27 | 华为技术有限公司 | Load balancing method and device |
| CN110417921A (en) * | 2019-09-06 | 2019-11-05 | 广州华多网络科技有限公司 | A kind of method and load balancing service device of load balancing |
| CN110417921B (en) * | 2019-09-06 | 2020-11-06 | 广州华多网络科技有限公司 | Load balancing method and load balancing service device |
| CN113709054A (en) * | 2021-07-16 | 2021-11-26 | 济南浪潮数据技术有限公司 | Keepallved-based LVS (Low Voltage differential Signaling) system deployment adjusting method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102648455B (en) | Server and stream control routine | |
| CN103618778A (en) | System and method for achieving data high concurrency through Linux virtual host | |
| CN101442493B (en) | Method for distributing IP message, cluster system and load equalizer | |
| CN103201989B (en) | The methods, devices and systems of control data transmission | |
| CN102932472B (en) | Data processing method and communication system | |
| US11095716B2 (en) | Data replication for a virtual networking system | |
| CN102377640B (en) | Message processing apparatus, message processing method and preprocessor | |
| JP5594171B2 (en) | Communication processing apparatus, address learning program, and address learning method | |
| US9910687B2 (en) | Data flow affinity for heterogenous virtual machines | |
| CN102457439A (en) | Virtual switching system and method of cloud computing system | |
| CN105933248B (en) | Service insertion within a basic virtual network environment | |
| CN103930882A (en) | Architecture of networks with middleboxes | |
| CN110633175B (en) | Multi-computer-room data processing method based on micro-service, electronic equipment and storage medium | |
| CN106341338B (en) | A kind of retransmission method and device of message | |
| CN103281257B (en) | A kind of protocol message processing method and equipment | |
| CN102752219B (en) | Method for implementing virtual device (VD) interconnection and switching equipment | |
| US9973574B2 (en) | Packet forwarding optimization without an intervening load balancing node | |
| CN110011941B (en) | Message forwarding method and device | |
| CN105939267B (en) | Outband management method and device | |
| CN105357114A (en) | Distributed network equipment | |
| EP3588856A1 (en) | Technologies for hot-swapping a legacy appliance with a network functions virtualization appliance | |
| CN111405590B (en) | Method, device and storage medium for exporting data traffic of virtualized network element | |
| CN103368872A (en) | Data packet forwarding system and method | |
| CN112583655B (en) | Data transmission method and device, electronic equipment and readable storage medium | |
| US20050188070A1 (en) | Vertical perimeter framework for providing application services |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 201112 Shanghai, Minhang District, United Airlines route 1188, building second layer A-1 unit 8 Applicant after: SHANGHAI EISOO INFORMATION TECHNOLOGY CO., LTD. Address before: 200072 room 3, building 840, No. 101 Middle Luochuan Road, Shanghai, Zhabei District Applicant before: Shanghai Eisoo Software Co.,Ltd. |
|
| COR | Change of bibliographic data | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140305 |
|
| RJ01 | Rejection of invention patent application after publication |