CN104468151A - System and method for keeping TCP (Transmission Control Protocol) session during cluster switching - Google Patents
System and method for keeping TCP (Transmission Control Protocol) session during cluster switching Download PDFInfo
- Publication number
- CN104468151A CN104468151A CN201310418949.9A CN201310418949A CN104468151A CN 104468151 A CN104468151 A CN 104468151A CN 201310418949 A CN201310418949 A CN 201310418949A CN 104468151 A CN104468151 A CN 104468151A
- Authority
- CN
- China
- Prior art keywords
- tcp
- equipment
- load
- cluster
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention discloses a system for keeping a TCP (Transmission Control Protocol) session during cluster switching. The system is constructed by connecting a client, Internet, a router, a load balance equipment cluster and real servers in sequence, wherein the load balance equipment cluster consists of master load balance equipment and slave load balance equipment; and both the master load balance equipment and the slave load balance equipment are constructed by connecting load balance application modules, TCP session backup and recovery modules, TCP modules, IP (Internet Protocol) modules and Network cards together. According to the system, all TCP sessions on the master equipment are backed up in advance from the slave equipment, and previous TCP sessions can be recovered according to session metadata backed up on the slave equipment after switching to the slave equipment, so that a current TCP connection session is prevented from being influenced.
Description
Technical field
The present invention relates to network application and pay control field, particularly a kind of load-balancing device keeps the system and method for TCP session when cluster switches.
Background technology
In a network environment, the effect of TCP transmission agreement and characteristic are responsible for finding the problem in transmission, once there being problem to send signal, requires again to transmit, until all data securities are correctly transferred to destination; The effect of load balancing and characteristic are for client provides Virtual Service, and client is asked the real service be given to thereafter, load-balancing device plays the effect of forming a connecting link between network and real server.
In prior art, in order to ensure the reliability of transport services, cluster generally can be adopted to carry out redundancy backup to load-balancing device, when a device fails, alternate device can correspondingly be enabled automatically, improves reliability of service and sustainability, under normal circumstances with this, the TCP session request received after switching for cluster, can respond normally.But for processing the TCP session of request before switching, mostly can select to abandon as solution.The TCP conversation failure of a part of user can be caused like this.
For the load balancing of the TCP service that load-balancing device provides, in client and Virtual Service and two TCP sessions between load-balancing device and backstage real service, can be set up.Be limited to the characteristic of TCP, when there is cluster because of fault etc. and switching, these two TCP sessions can not use, because there is no this two sessions and state recording thereof in the new equipment be switched to, the TCP message being subordinate to this session follow-up can be caused like this to be dropped, and in other words the way of prior art only ensures that the TCP session request arrived after cluster switches can correctly process.The shortcoming of prior art is apparent, such as when client accesses the TCP server on backstage by load balancing main equipment, in mutual process, main equipment breaks down, be switched to stand-by equipment, due to the particularity of Transmission Control Protocol, only between client and main equipment, and between main equipment and server, preserve TCP session, after being switched to stand-by equipment, due to client and stand-by equipment, and connect session without any TCP between stand-by equipment and server, result in follow-up TCP message cannot pass on, can only discard processing, network communication quality is declined.Therefore, when load-balancing device generation cluster switches, how to keep the continuity of TCP session to become and ensure network communication quality problem demanding prompt solution.
Chinese patent 200810241694.2 disclose a kind of support Transmission Control Protocol to connect backup method and equipment, the method realizes in the reversed process of active and standby plate, keep Transmission Control Protocol to connect not disconnection by the Hot Spare that the active and standby plate Transmission Control Protocol of support equipment connects at IP layer.The problem of this invention solve only the not disconnection that the Routing Protocol based on TCP transmits, and all data flow not disconnections based on the application protocol on Transmission Control Protocol during unresolved load-balancing device cluster switching, still cannot overcome the communication quality decline problem caused because cluster switches.
Summary of the invention
For overcoming Problems existing in prior art, the object of this invention is to provide a kind of load-balancing device in cluster handoff procedure, ensure that all data flow based on Transmission Control Protocol are unaffected, handoff procedure is transparent generation for client, makes the generation that the imperceptible cluster of client switches.
A kind of cluster of the present invention keeps the system of TCP session when switching, be linked in sequence by client, the Internet, router, load-balancing device cluster and real server to form, described load-balancing device cluster is by load balancing main equipment and form from equipment, wherein main equipment and from equipment by load balancing application module, TCP session backup and recover module, tcp module, IP module and network interface card be interconnected to constitute.
Keep the method for TCP session when a kind of cluster of the present invention switches, to comprise the following steps and step by step:
Step one, to the Virtual Service of intrasystem each load-balancing device configuration TCP, the Virtual Service of described configuration TCP comprises step by step following:
Step by step one, client accesses real server thereafter indirectly by accessing described Virtual Service, and the Virtual Service type described in configuration is TCP type;
Step by step two, the real service type described in configuration is TCP, and client first accesses the load-balancing device providing Virtual Service, and then load-balancing device is balancedly assigned to different real server client-requested and gets on;
Step by step three, configure a real service group, group is the set of described real service;
Step by step four, described real service is joined in the real service group of above-mentioned foundation;
Step by step five, working load balance policy associates above-mentioned Virtual Service and Virtual Service group, and Virtual Service distributes to different real service groups according to different strategies client-requested.
Step 2, load-balancing device cluster configuration, comprises step by step following:
Step by step one, each interface at allocation cluster place and ID, the IP of the above-mentioned Virtual Service of cluster backup and Virtual Service group thereof;
Step by step two, configure preempt-mode and the priority of this cluster, the load-balancing device that priority is high is main equipment, and other is from equipment;
Step by step three, for increasing the configuration same with above-mentioned main equipment from equipment;
Step by step four, in main equipment tcp module, increase TCP session backup and recovery configuring;
Step by step five, from equipment tcp module, increasing TCP session backup and recovery configuring accordingly.
For Transmission Control Protocol itself, it is an agreement having state, and when cluster is switched to an other equipment, its original TCP session status will be lost.The present invention is just to provide a kind of scheme, and when in cluster, equipment switches, TCP session originally still can continue use what be newly switched to from equipment.Because in the technical scheme that the present invention mentions, back up TCP sessions all on main equipment in a slave device in advance, when being switched to from equipment, can according to the conversation metadata backed up from equipment, recover the TCP session once had, thus it is unaffected to ensure that existing TCP connects session.
Accompanying drawing explanation
Fig. 1 is present system structural representation;
Fig. 2 is a kind of embodiment schematic diagram of the inventive method.
Embodiment
In the following description, many ins and outs are proposed in order to make reader understand the application better.But persons of ordinary skill in the art may appreciate that even without these ins and outs with based on the many variations of following execution mode and amendment, is also each claim of the application technical scheme required for protection.
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, embodiments of the present invention are described in further detail.
As Fig. 1, in the load-balancing environment of cluster, normally two load-balancing devices are as a cluster.The network system that the load-balancing device of cluster is built can be linked in sequence by client 10, the Internet 20, router three 0, load-balancing device cluster 40 and real server 50 and form.Wherein load-balancing device cluster 40 can form a cluster by load equalizer 41 and load equalizer 42, is system providing virtual service.Operationally, one is main equipment to system, such as load balancing 41, and one is from equipment, such as, and load balancing 42.
As shown in Figure 2, described master-slave equipment can be backed up by load balancing application module 411, TCP session and be recovered module 412, tcp module 413, IP module 414 and network interface card 415 and be interconnected to constitute; Wherein main equipment and from the increase TCP session backup corresponding tcp module of equipment and recovery configuring.Main equipment is often set up a TCP session, all synchronously can set up a TCP session backup from equipment.Like this, work as master-failure, switch to main equipment from equipment, and take over all IP addresses.After switching, when above-mentioned TCP session message is sent, can issue from equipment, from equipment according to the agreement TCP message, IP address and port numbers go TCP conversation module to look for session object, now, just switch from equipment and main equipment, TCP session information originally only retains on the master, session object when can not find switching from equipment, when looking for session object connection to have no resolution from equipment, a session will be recovered from TCP session backup module, this conversation metadata newly recovered is the same with session object state on the master, so just can continue to provide to have served.Generally, in a cluster environment, we are doing a backup to all TCP sessions of main equipment from equipment, when main equipment is unavailable be switched to from equipment time, can rely on and recover complete TCP session from the TCP conversation metadata equipment, thus continue as client service is provided.
Now lift an example, in certain large-scale group load-balancing device cluster procurement item, propose network environment configuration requirement and have three servers providing TCP to serve, IP is 10.3.0.20 respectively, 10.3.0.21 and 10.3.0.22, two Array APV8600 load-balancing devices are used to realize two demands:
Demand one, is implemented to the request load balancing of these three TCP server;
Demand two, when cluster switches, client's side link mortality is zero..
The system configuration of certain large-scale group load-balancing device cluster above-mentioned can be built according to the structure shown in Fig. 1, wherein provide the equipment of Virtual Service can form a cluster by two Array APV8600 load-balancing devices, the IP address of this cluster can be 220.57.54.88, the IP of two load-balancing device interfaces is respectively 10.3.0.250,10.3.0.251; Real server can be made up of the real server of three thereafter 51,52,53, real server corresponding IP address be 10.3.0.20,10.3.0.21 and 10.3.0.22 respectively.For client demand, be implemented to the request load balancing of these three TCP server and keep when cluster switches the concrete grammar step of TCP session as follows:
Step one, to the Virtual Service of above-mentioned two load-balancing devices configuration TCP, because rely on cluster environment, for Array operating system command, on two ArrayAV8600 load-balancing devices, do following configuration respectively:
Step by step one, client serves the real service of indirectly accessing thereafter by accesses virtual, configuring this Virtual Service type is TCP type.Namely define a Virtual Service, client serves the real service of indirectly accessing thereafter by accesses virtual; Defining this Virtual Service type is TCP type, and IP address is 220.57.54.88, and port is 5180.Following Array1 represents that load-balancing device 41, Array2 represents load-balancing device 42, and the program of a correspondence is expressed as step by step::
Array1(config)slb virtual tcp tcpvs220.57.54.885180
Array2(config)slb virtual tcp tcpvs220.57.54.885180
Step by step two, the real service type described in configuration is TCP, and client first accesses the load-balancing device providing Virtual Service, and then load-balancing device is balancedly assigned to different real server client-requested and gets on.Namely define three real service, type is all that TCP, IP are respectively 10.3.0.20,10.3.0.21 and 10.3.0.22, and port is 5180.The first accesses virtual service equipment of client, then load-balancing device is balancedly assigned to different real server client-requested and gets on, and the program of two correspondences is expressed as step by step:
Array1(config)slb real tcp tcpr110.3.0.205180
Array1(config)slb real tcp tcpr210.3.0.215180
Array1(config)slb real tcp tcpr310.3.0.225180
Array2(config)slb real tcp tcpr110.3.0.205180
Array2(config)slb real tcp tcpr210.3.0.215180
Array2(config)slb real tcp tcpr310.3.0.225180
Step by step three, configure a real service group, group is the set of real service.The service request organized to one in general can be assigned to uniformly in all real service in this group and go.Method is that rr(round robin wheel is named scheduling), new TCP connection can hit tcpr1, tcpr2 and tcpr3 in turn.Configure an IP pond simultaneously, go with the IP in IP pond the real service connecting backstage, in order to avoid there is the situation that port is not enough, be also the necessary condition that TCP session keeps, the program of three correspondences is expressed as step by step simultaneously:
Array1(config)slb group method tcpg1rr
Array1(config)ip pool pool110.3.0.10010.3.0.102
Array1(config)slb proxyip tcpg1pool1
Array2(config)slb group method tcpg1rr
Array2(config)ip pool pool110.3.0.10010.3.0.102
Array2(config)slb proxyip tcpg1pool1
Step by step four, real service is joined in the real service group of above-mentioned foundation, because load-balancing algorithm is all real service request be distributed in a group is balancedly assigned in this group, at this moment have three real service in this group, the program of four correspondences is expressed as step by step:
Array1(config)slb group member tcpg1tcpr1
Array1(config)slb group member tcpg1tcpr2
Array1(config)slb group member tcpg1tcpr3
Array2(config)slb group member tcpg1tcpr1
Array2(config)slb group member tcpg1tcpr2
Array2(config)slb group member tcpg1tcpr3
Step by step five, working load balance policy associates above-mentioned Virtual Service and Virtual Service group, the present embodiment Array AV8600 load-balancing device provides the strategy of a lot of load balancing, Virtual Service distributes to different service groups according to different strategies client-requested, here in order to simply can only use default strategy, requests all so all can hit tcpg1 group, and the program of five correspondences is expressed as follows step by step:
Array1(config)slb policy default tcpvs tcpg1
Array2(config)slb policy default tcpvs tcpg1
After the part of the above-mentioned load balancing Virtual Service to intrasystem each load-balancing device configuration TCP has configured, following steps two are by allocation cluster part.
Step 2, load-balancing device cluster configuration, comprises step by step following:
Step by step one, each interface at allocation cluster place and ID, the IP of the above-mentioned Virtual Service of cluster backup and Virtual Service group thereof.Namely be defined as which virtual IP address and do cluster backup.We need the IP of Virtual Service, and the IP for connecting backstage real service does cluster backup.The program mode of one is expressed as follows step by step:
Array1(config)cluster virtual ifname"port1"100
Array1(config)cluster virtual vip“port1”100220.57.54.88
Array1(config)cluster virtual vip“port1”10010.3.0.100
Array1(config)cluster virtual vip“port1”10010.3.0.101
Array1(config)cluster virtual vip“port1”10010.3.0.102
Step by step two, configure preempt-mode and the priority of this cluster, the load-balancing device that priority is high is main equipment, and other is from equipment.Namely preempt-mode and the priority of this cluster is defined.Whose priority is high, and who is exactly main equipment, and other is from equipment.The program expression of two is as follows step by step:
Array1(config)cluster virtual preempt"port1"1001
Array1(config)cluster virtual priority"port1"100200Primary
Step by step three, for increasing the configuration same with above-mentioned main equipment from equipment.The program expression of three is as follows step by step:
Array2(config)cluster virtual ifname"port1"100
Array2(config)cluster virtual vip“port1”100220.57.54.88
Array2(config)cluster virtual vip“port1”10010.3.0.100
Array2(config)cluster virtual vip“port1”10010.3.0.101
Array2(config)cluster virtual vip“port1”10010.3.0.102
Array2(config)cluster virtual preempt"port1"1001
Array2(config)cluster virtual priority"port1"100100Primary
Step by step four, in main equipment TCP conversation module, increase the backup of TCP conversation metadata and recovery configuring accordingly.Ha ssf(high available high availability) be TCP session command prefix, on represents that opening TCP session backs up and recovery, the opposite end of peer(backup) refer to from which platform device backup connection.The program expression of four is as follows step by step:
Array1(config)ha ssf on
Array1(config)ha ssf on tcpvs
Array1(config)ha ssf peer10.3.0.251
Step by step five, accordingly, from equipment TCP conversation module, increasing the backup of TCP conversation metadata and recovery configuring.The program expression of five is as follows step by step:
Array2(config)ha ssf on
Array2(config)ha ssf on tcpvs
Array2(config)ha ssf peer10.3.0.250
So far, above-mentioned two demands of client are just completed.
It should be noted that, the each unit mentioned in the present invention's each equipment execution mode is all logical block, physically, a logical block can be a physical location, also can be a part for a physical location, can also realize with the combination of multiple physical location, the Physical realization of these logical blocks itself is not most important, and the combination of the function that these logical blocks realize is only the key solving technical problem proposed by the invention.In addition, in order to outstanding innovative part of the present invention, the present invention does not introduce above-mentioned each equipment execution mode and the unit not too close with solving technical problem relation proposed by the invention, but this does not show to there is not the said equipment execution mode and other is about implementation unit.
Although by referring to some of the preferred embodiment of the invention, to invention has been diagram and describing, but those of ordinary skill in the art should be understood that and can do various change to it in the form and details, and without departing from the spirit and scope of the present invention.
Claims (2)
1. when a cluster switches, keep the system of TCP session, be linked in sequence by client, the Internet, router, load-balancing device cluster and real server to form, described load-balancing device cluster is by load balancing main equipment and form from equipment, it is characterized in that main equipment and is interconnected to constitute by load balancing application module, TCP session backup and recovery module, tcp module, IP module and network interface card from equipment.
2. keep a method for TCP session when cluster switches, it is characterized in that comprising the following steps:
Step one, to the Virtual Service of intrasystem each load-balancing device configuration TCP, the Virtual Service of described configuration TCP comprises step by step following:
Step by step one, client accesses real server thereafter indirectly by accessing described Virtual Service, and the Virtual Service type described in configuration is TCP type;
Step by step two, the real service type described in configuration is TCP, and client first accesses the load-balancing device providing Virtual Service, and then load-balancing device is balancedly assigned to different real server client-requested and gets on;
Step by step three, configure a real service group, group is the set of described real service;
Step by step four, described real service is joined in the real service group of above-mentioned foundation;
Step by step five, working load balance policy associates above-mentioned Virtual Service and Virtual Service group, and Virtual Service distributes to different real service groups according to different strategies client-requested.
Step 2, load-balancing device cluster configuration, comprises step by step following:
Step by step one, each interface at allocation cluster place and ID, the IP of the above-mentioned Virtual Service of cluster backup and Virtual Service group thereof;
Step by step two, configure preempt-mode and the priority of this cluster, the load-balancing device that priority is high is main equipment, and other is from equipment;
Step by step three, for increasing the configuration same with above-mentioned main equipment from equipment;
Step by step four, in main equipment tcp module, increase TCP session backup and recovery configuring;
Step by step five, from equipment tcp module, increasing TCP session backup and recovery configuring accordingly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310418949.9A CN104468151B (en) | 2013-09-13 | 2013-09-13 | A kind of system and method for keeping TCP sessions during cluster switching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310418949.9A CN104468151B (en) | 2013-09-13 | 2013-09-13 | A kind of system and method for keeping TCP sessions during cluster switching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104468151A true CN104468151A (en) | 2015-03-25 |
| CN104468151B CN104468151B (en) | 2017-09-29 |
Family
ID=52913579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310418949.9A Active CN104468151B (en) | 2013-09-13 | 2013-09-13 | A kind of system and method for keeping TCP sessions during cluster switching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104468151B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104901881A (en) * | 2015-04-30 | 2015-09-09 | 华为技术有限公司 | Route device, load balancing device, and message distribution method and system |
| CN105553701A (en) * | 2015-12-11 | 2016-05-04 | 国网青海省电力公司 | Distribution network adjustment and control system and control method thereof |
| WO2017215408A1 (en) * | 2016-06-14 | 2017-12-21 | 中兴通讯股份有限公司 | Session switching control method and apparatus and access point device |
| CN107547394A (en) * | 2017-08-14 | 2018-01-05 | 新华三信息安全技术有限公司 | A kind of load-balancing device dispositions method more living and device |
| CN108063783A (en) * | 2016-11-08 | 2018-05-22 | 上海有云信息技术有限公司 | The dispositions method and device of a kind of load equalizer |
| CN110011767A (en) * | 2019-04-17 | 2019-07-12 | 北京百度网讯科技有限公司 | Method and apparatus for TCP connection backup |
| CN110971698A (en) * | 2019-12-09 | 2020-04-07 | 北京奇艺世纪科技有限公司 | Data forwarding system, method and device |
| CN111030999A (en) * | 2019-11-15 | 2020-04-17 | 广州辰河质检技术有限公司 | Method for extracting files based on network data packet |
| CN113573344A (en) * | 2021-06-21 | 2021-10-29 | 深圳震有科技股份有限公司 | SMF session detection method based on 5G and terminal |
| CN114301763A (en) * | 2021-12-15 | 2022-04-08 | 山石网科通信技术股份有限公司 | Distributed cluster fault processing method and system, electronic device and storage medium |
| CN114598704A (en) * | 2022-03-16 | 2022-06-07 | 浪潮云信息技术股份公司 | TCP connection fault-tolerant method based on four-layer load balancing cluster |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1725702A (en) * | 2004-07-20 | 2006-01-25 | 联想网御科技(北京)有限公司 | Network safety equipment and assemblied system and method for implementing high availability |
| CN101605092A (en) * | 2009-07-10 | 2009-12-16 | 浪潮电子信息产业股份有限公司 | A kind of content-based SiteServer LBS |
| CN102255633A (en) * | 2010-05-20 | 2011-11-23 | 中兴通讯股份有限公司 | Method and system for multi-stand user backup |
| CN102685237A (en) * | 2012-05-16 | 2012-09-19 | 东南大学 | Method for requesting session maintaining and dispatching in cluster environment |
| CN102968310A (en) * | 2012-12-05 | 2013-03-13 | 武汉烽火普天信息技术有限公司 | Integrated high-performance application software architecture and construction method thereof |
-
2013
- 2013-09-13 CN CN201310418949.9A patent/CN104468151B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1725702A (en) * | 2004-07-20 | 2006-01-25 | 联想网御科技(北京)有限公司 | Network safety equipment and assemblied system and method for implementing high availability |
| CN101605092A (en) * | 2009-07-10 | 2009-12-16 | 浪潮电子信息产业股份有限公司 | A kind of content-based SiteServer LBS |
| CN102255633A (en) * | 2010-05-20 | 2011-11-23 | 中兴通讯股份有限公司 | Method and system for multi-stand user backup |
| CN102685237A (en) * | 2012-05-16 | 2012-09-19 | 东南大学 | Method for requesting session maintaining and dispatching in cluster environment |
| CN102968310A (en) * | 2012-12-05 | 2013-03-13 | 武汉烽火普天信息技术有限公司 | Integrated high-performance application software architecture and construction method thereof |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016173403A1 (en) * | 2015-04-30 | 2016-11-03 | 华为技术有限公司 | Routing device, load balancing device, and message distribution method and system |
| CN104901881A (en) * | 2015-04-30 | 2015-09-09 | 华为技术有限公司 | Route device, load balancing device, and message distribution method and system |
| CN105553701A (en) * | 2015-12-11 | 2016-05-04 | 国网青海省电力公司 | Distribution network adjustment and control system and control method thereof |
| WO2017215408A1 (en) * | 2016-06-14 | 2017-12-21 | 中兴通讯股份有限公司 | Session switching control method and apparatus and access point device |
| CN107508848A (en) * | 2016-06-14 | 2017-12-22 | 中兴通讯股份有限公司 | Session method for handover control, device and access point apparatus |
| CN108063783A (en) * | 2016-11-08 | 2018-05-22 | 上海有云信息技术有限公司 | The dispositions method and device of a kind of load equalizer |
| CN107547394A (en) * | 2017-08-14 | 2018-01-05 | 新华三信息安全技术有限公司 | A kind of load-balancing device dispositions method more living and device |
| CN110011767B (en) * | 2019-04-17 | 2022-09-27 | 北京百度网讯科技有限公司 | Method and apparatus for TCP connection backup |
| CN110011767A (en) * | 2019-04-17 | 2019-07-12 | 北京百度网讯科技有限公司 | Method and apparatus for TCP connection backup |
| CN111030999A (en) * | 2019-11-15 | 2020-04-17 | 广州辰河质检技术有限公司 | Method for extracting files based on network data packet |
| CN111030999B (en) * | 2019-11-15 | 2021-09-24 | 广州辰河质检技术有限公司 | Method for extracting files based on network data packet |
| CN110971698A (en) * | 2019-12-09 | 2020-04-07 | 北京奇艺世纪科技有限公司 | Data forwarding system, method and device |
| CN110971698B (en) * | 2019-12-09 | 2022-04-22 | 北京奇艺世纪科技有限公司 | Data forwarding system, method and device |
| CN113573344A (en) * | 2021-06-21 | 2021-10-29 | 深圳震有科技股份有限公司 | SMF session detection method based on 5G and terminal |
| CN114301763A (en) * | 2021-12-15 | 2022-04-08 | 山石网科通信技术股份有限公司 | Distributed cluster fault processing method and system, electronic device and storage medium |
| CN114598704A (en) * | 2022-03-16 | 2022-06-07 | 浪潮云信息技术股份公司 | TCP connection fault-tolerant method based on four-layer load balancing cluster |
| CN114598704B (en) * | 2022-03-16 | 2024-05-17 | 浪潮云信息技术股份公司 | TCP connection fault tolerance method based on four-layer load balancing cluster |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104468151B (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104468151A (en) | System and method for keeping TCP (Transmission Control Protocol) session during cluster switching | |
| CN110912780B (en) | High-availability cluster detection method, system and controlled terminal | |
| US11734138B2 (en) | Hot standby method, apparatus, and system | |
| TWI724106B (en) | Business flow control method, device and system between data centers | |
| US8842518B2 (en) | System and method for supporting management network interface card port failover in a middleware machine environment | |
| CN112003716A (en) | Data center dual-activity implementation method | |
| CN103019889A (en) | Distributed file system and failure processing method thereof | |
| CN101488918A (en) | Multi-network card server access method and system | |
| EP2888865B1 (en) | System and method for supporting high available (ha) network communication in a middleware machine environment | |
| US20140177431A1 (en) | Graceful failover of a principal link in a fiber-channel fabric | |
| JP2009003923A (en) | Slot interface access device, method thereof, program thereof, main device redundancy configuration, and main device replacing method | |
| JP2013030190A (en) | Slot interface access device, method and program thereof, and redundancy configuration and alternative method of main device | |
| JPH1185644A (en) | System switching control method for redundancy system | |
| WO2011110134A2 (en) | Method, device and broadband access server system for load share | |
| CN116192863B (en) | Micro-service flow processing method, DPU service grid deployment method and system | |
| JP5767309B2 (en) | Emergency switching method and system | |
| US7830880B2 (en) | Selective build fabric (BF) and reconfigure fabric (RCF) flooding | |
| CN114116216A (en) | Method and device for realizing high availability of distributed block storage based on vip | |
| CN104780097A (en) | Method for hot standby under non-fully-connected network topology condition and first router equipment | |
| EP3627766B1 (en) | Method and system for switching between active bng and standby bng | |
| US20160381132A1 (en) | Sysplexport allocation across a z/os sysplex | |
| US9083618B2 (en) | Centralized backup system and backup method for an homogeneous real-time system at different locations | |
| CN101170544A (en) | A communication method in high-availability cluster system based on single practical IP address | |
| CN114785762B (en) | Implementation method and device of cloud computing system, terminal equipment and storage medium | |
| KR101190475B1 (en) | A Triple DHCP System and DHCP Message Processing Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100125 Beijing city Chaoyang District Liangmaqiao Road No. 40 building 10 room 1001, twenty-first Century Patentee after: Beijing Huayao Technology Co., Ltd Address before: 100125 Beijing city Chaoyang District Liangmaqiao Road No. 40 building 10 room 1001, twenty-first Century Patentee before: Huayao (China) Technology Co., Ltd. |