CN103731460A - Pooling device for establishing network server pool - Google Patents
Pooling device for establishing network server pool Download PDFInfo
- Publication number
- CN103731460A CN103731460A CN201210392450.0A CN201210392450A CN103731460A CN 103731460 A CN103731460 A CN 103731460A CN 201210392450 A CN201210392450 A CN 201210392450A CN 103731460 A CN103731460 A CN 103731460A
- Authority
- CN
- China
- Prior art keywords
- server
- pond
- pools
- information
- function module
- 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
Abstract
The invention provides a pooling device for enabling computer network servers to form a server pool. The pooling device comprises a pooling device registration/logout function module, a pooling device failure detection and management function module, a pooling device information collecting function module, a pooling device server selection function module, a pooling device pool name analysis function module, and a pooling device information synchronous function module. The pooling device can be used for establishing a logic server pool of any scale quickly and effectively, and ensures the normal operation of the server pool through a series of mechanisms, ensures that the resource of the server pool reaches a best utilization state, improves the utilization rate of the server resource to maximum extent, and eliminates unfavorable influence brought by server failures.
Description
[technical field]
The invention relates to web server computer field, particularly about a kind of Chi Huaqi that builds webserver pond.
[background technology]
In having the application system of a large amount of Concurrency Access, the disposal ability of separate unit server cannot be born, in order to improve the treating capacity of server, conventionally adopt one group to provide a server cluster of server formation of same services jointly to share whole user's visit capacity, and need to dispose an equipment that is referred to as load equalizer at the front end of this group server, load equalizer equipment is accepted whole users' access request, then according to corresponding balance policy, the request of different user is distributed to respectively to different servers, after server process, result will return to load equalizer, then load equalizer returns to user by result again, user's visit capacity is just distributed to multiple servers by load equalizer and has been processed simultaneously like this, thereby significantly improve the disposal ability of system.
As shown in Figure 1, in this SiteServer LBS, customer flow all penetrates load equalizer equipment, and due to load equalizer employing specialized hardware realization conventionally, its disposal ability is stronger.But along with user's visit capacity is increased sharply, performance stronger single equipment will face the problem that self performance bottleneck brings equally.
There is flow bottleneck in conventional load equalizing system, its reason is whole data traffics, all by separate unit load equalizer equipment, born, and the handling property bottleneck of hardware device is intrinsic, is also impossible change.
[summary of the invention]
The object of the invention is to the defect for prior art, propose the Chi Huaqi of server pools system that a kind of structure can be eliminated the flow bottleneck problem of SiteServer LBS.
For reaching aforementioned object, a kind of pond of the present invention device, it is responsible for multiple servers to form a virtual server pools, and the running status of each station server is monitored in real time and gathered; Provide pond name analysis function, to can allow user facilitate accessing server simultaneously;
Wherein said pond device comprises:
The check in/check out functionality module of pond device: server needs initiatively to register at device place, pond before adding server pools, during registration, need provide the pertinent system information of server, comprise: server ip address, service port number, service agreement, pond name information; Pond device receives after the registration request of server, to verify this server info, if the verification passes, by this server registers a server list, and induction-arrangement, server, before exiting server pools, need to be handled logout procedure at device place, pond, and pond device is deleted from server list with being about to this server info;
The fault detect of pond device and management function module: in server pools system, pond device is responsible for server to carry out periodic health-and-status check according to the register information of server, once discovery server fault, pond device is deleted this server at once from server pools, to guarantee that in server pools, Servers-all is all effective, available;
The information collection function module of pond device: pond device periodically carries out system information acquisition to Servers-all in pond, comprise: the collection of the system related information of CPU, internal memory, Internet Use and so on, and this system information is arranged, for server selection strategy provides foundation;
The server selection function module of pond device: according to pond device to relevant informations such as the monitoring of server in each server pools, information gatherings, according to the selection strategy of server, all the time preferentially select the server of resource situation optimum, for pond name analysis provides foundation, to guarantee at any time can acquire for any user the server resource of real-time optimum;
Hua Qi pond, pond name analysis functional module: client-access server pools, first at device place, pond, do pond name analysis, the analysis request that pond device is submitted to according to client, in the server list of oneself, inquire about, conventionally each pond name corresponding a plurality of servers, pond device is installed and is realized the selection strategy determining, and for this user selects a best server ip, and this result is fed back to client to resolve the form of receiveing the response;
Pond device information synchronizing function module: server is registered or nullified at certain pond device, this pond device all can be notified lastest imformation other all Chi Huaqi in real time; If certain pond device discovery server fault, can in own server list of preserving, this server be deleted at once, by other all ponds these servers of device of server update message informing, break down simultaneously, after other pond devices are notified, also at once this server is deleted from the server list of its preservation; Pond device collects new server system information, as long as system information changes, all by other pond devices of real-time informing to guarantee the consistency of all ponds device information.
According to one embodiment of present invention, described pond device its for building server pools system, the server pools system of its structure comprises: server pools, pond device and client, wherein server pools has identical function by one group, and being unified the server composition that management is got up, each server pools is all used unique pond name as sign; Client comprises the client computer in access services device pond.
The server pools system building by pond of the present invention device, when server need to add server pools, can initiatively at device place, pond, register, the relevant information (comprising: server ip, Service-Port, service agreement, pond name etc.) of self is provided to pond device, pond device is being safeguarded a server list, according to the register information of server, real-time update this part of server list; Before server closing, need nullify at device place, pond, pond device is deleted this server according to log-off message from this server list; Pond device also periodically carries out real-time system information acquisition (comprising: CPU, internal memory, Internet Use etc.) to server simultaneously, the fault detection mechanism of server pools system, to the real-time health examination of the server in server list, once discovery server fault, also can initiatively this server be deleted from server list, thereby guarantee that in server pools, server is all normal.
Pond device can carry out arbitrary extension, the information synchronization mechanism of pond device has guaranteed that the information between the device of Duo Tai pond is synchronous, like this when any pond device breaks down, can not cause information dropout, can not affect the normal operation of server pools system yet, Duo Tai pond device is worked simultaneously, has eliminated the possibility of the Single Point of Faliure of Chi Huaqi.
User is by name access services device pond, pond, need first at device place, pond, to do pond name analysis, pond device uses server selector to be made as the server that variant user selects to have best resource situation, and feed back to user as analysis result, user connects with regard to direct and this server like this, and carries out information interaction.
Pond device has played very crucial effect in server pools system, pond device can fast and effeciently be set up the server pools in logic of random scale, and by a series of mechanism of above introduction, ensured the normal operation of server pools: server health status detects, server failure is processed, server system Real-time Collection, according to server real-time system information and server health, be user's Dynamic Selection and distribute the server of best resource situation, the resource that ensures server pools reaches best behaviour in service, improve to greatest extent the utilization rate of server resource, and eliminate the adverse effect bring because of server failure.
[accompanying drawing explanation]
Fig. 1 is the structural representation of the server network system of existing employing load equalizer.
Fig. 2 is the structural representation of server network system of the present invention.
Fig. 3 is the structural representation of pond of the present invention device.
Fig. 4 is the construction method flow chart of server network system of the present invention.
Fig. 5 is registration message form schematic diagram of the present invention.
Fig. 6 is name parameter format schematic diagram in pond in registration message form of the present invention.
Fig. 7 is server parameter form schematic diagram in registration message form of the present invention.
Fig. 8 is the registration of the present invention form schematic diagram of receiveing the response.
Fig. 9 is continuously active message format schematic diagram of the present invention.
Figure 10 is the form schematic diagram of system parameters in continuously active message format of the present invention.
Figure 11 is continuously active acknowledge message form schematic diagram of the present invention.
Figure 12 is server update message format schematic diagram of the present invention.
[embodiment]
Alleged " embodiment " or " embodiment " refers to special characteristic, structure or the characteristic that can be contained at least one implementation of the present invention herein.Different local in this manual " in one embodiment " that occur not all refer to same embodiment, neither be independent or the embodiment mutually exclusive with other embodiment optionally.
Refer to shown in Fig. 2, webserver cluster of the present invention is a kind of server pools system.As shown in Figure 2, server pools system of the present invention comprises:
Server pools: server pools has identical function by one group, and be unified the server composition that management is got up, each server pools is all used unique pond name as sign;
Pond device: be the management equipment of server pools, be responsible for multiple servers to form a virtual server pools, and the running status of each station server is monitored in real time and gathered; Provide pond name analysis function, to can allow user facilitate accessing server simultaneously;
Client: the client computer in access services device pond.
The server that many of the present invention have same services function forms a server pools in logic according to pond name, server pools is managed and is monitored by Chi Huaqi, user is by name access services device pond, pond, first at device place, pond, carry out pond name analysis, then according to analysis result, the direct concrete server of access, without by any transferring equipment, thereby has eliminated the flow bottleneck that transferring equipment may cause.
Pond device serves as the role of Resource Manager in server pools system, and the efficiency of management of Chi Huaqi directly has influence on the overall operation efficiency of server pools.
Refer to shown in Fig. 3, it shows the functional module structure schematic diagram of pond of the present invention device.As shown in Figure 3, pond of the present invention device comprises:
The check in/check out functionality module of pond device: server needs initiatively to register (registration) at device place, pond before adding server pools, during registration, need provide the pertinent system information of server, comprise: the information such as server ip address, service port number, service agreement, pond name; Pond device receives after the registration request of server, verify this server info, if the verification passes, by this server registers a server list, and induction-arrangement.Server, before exiting server pools, need to be handled at device place, pond logout procedure (deregistration).Pond device is deleted from server list with being about to this server info.
The fault detect of pond device and management function module: in server pools system, pond device is responsible for server to carry out periodic health-and-status check according to the register information of server, once discovery server fault, pond device is deleted this server at once from server pools, and this mechanism of Chi Huaqi can guarantee that in server pools, Servers-all is all effective, available.
The information collection function module of pond device: pond device periodically carries out system information acquisition to Servers-all in pond, comprise: the collection of the system related informations such as CPU, internal memory, Internet Use, and this system information is arranged, for server selection strategy provides foundation.
The server selection function module of pond device: according to pond device to relevant informations such as the monitoring of server in each server pools, information gatherings, according to the selection strategy of server, all the time preferentially select the server of resource situation optimum, for pond name analysis provides foundation, this function, has guaranteed at any time for any user, can acquire the server resource of real-time optimum.
Hua Qi pond, pond name analysis functional module: client-access server pools, first at device place, pond, do pond name analysis, the analysis request that pond device is submitted to according to client, in the server list of oneself, inquire about, conventionally each pond name corresponding a plurality of servers, pond device is installed and is realized the selection strategy determining, and for this user selects a best server ip, and this result is fed back to client to resolve the form of receiveing the response.
Pond device information synchronizing function module: server is registered or nullified at certain pond device, this pond device all can be notified lastest imformation other all Chi Huaqi in real time; If certain pond device discovery server fault, can in own server list of preserving, this server be deleted at once, by server update message (Server_Update), notify other all ponds these servers of device to break down simultaneously, after other pond devices are notified, also at once this server is deleted from the server list of its preservation; Pond device collects new server system information, as long as system information changes, all by other pond devices of real-time informing.Guaranteed like this consistency of all ponds device information.
Refer to shown in Fig. 4, it shows that passing through pond of the present invention device builds a flow chart without the SiteServer LBS of bottleneck, as shown in Figure 4, the structure without bottleneck load-balanced server system of the present invention, implementation step is as follows:
Step S1: set up server pools, and the server pools name for providing the server of same services to form, it is pond name, pond name is the unique identification name of server pools, that be that 26 Latin alphabets from a to z and 10 Arabic numerals of 0 to 9 and "-" and ". " symbol form by several and by certain level and logic arrangement, naming method is consistent with domain name (Domain Name).Pond name can not repeat, and the multiple servers with same services has same pond name.
Step S2: service registration (registration): when service starts, server need be registered at device place, pond, during registration, to provide relevant system information, comprise: pond name, unique service identifier, server ip address, serve port, service agreement, service detection, balance policy etc.The process of service registration is by send registration (registration) message to pond device, to server, receive that Chi Huaqi beams back the registration_response message of coming and completes, and has comprised in registration message and has served relevant pond name information and information on services.Refer to shown in Fig. 5 to Fig. 7, it has shown respectively in registration message form schematic diagram of the present invention, registration message form of the present invention server parameter form schematic diagram in pond name parameter format schematic diagram, registration message form of the present invention.And refer to shown in Fig. 8, it has shown the registration of the present invention form schematic diagram of receiveing the response.
Step S3: server info is synchronous: pond device is received after registration message, to according to pond name, sort out it, be kept among its inner server list (Server List), publisher server updating message (Server_Update) is given other pond devices simultaneously, this service registration information is synchronized in other servers, thereby guarantees that the server List in the device of all ponds is consistent.
Step S4: server state monitoring: pond device can carry out monitor check to its host servers every a time period, once finding that there is server breaks down, from the server list (Server List) of its maintenance, delete at once this server, send server update message to other pond devices simultaneously, other pond devices are received after this message, also from the server list of oneself, delete this server simultaneously.
Step S5: pond name analysis: before user access server pond, must send pond name analysis request to pond device, the server list that pond device keeps according to self, and according to the balance policy of server pools for user selects one to be considered to best server ip, result is returned to user;
Step S6: user access server: according to the result of pond name analysis, user directly connects with server, and according to balance policy, different users passes through pond name analysis, can obtain different server ips, user's visit capacity is just assigned on different servers like this.
Wherein in the step of aforementioned server state monitoring, server health examination is carried out in the following ways:
Method one: send continuously active message (Keep_Alive) to server, if receive continuously active acknowledge message (Keep_Alive_Ack), show that server is normal;
Method two: pond device active probe server ip and port, initiatively create server TCP and connect, successful connection shows that server is normal;
Method three: active probe service agreement, the service agreement that pond device uses according to user to server sends specific agreement, then judges the situation of server according to the answer of server.
Wherein the concrete process of method one is: pond device every one regular time interval to this server, send continuously active message Keep_Alive.Refer to shown in Fig. 9 and Figure 10, it shows respectively and in one embodiment of the present of invention, keeps the form of alive messages and keep the form that in alive messages, system parameters is described.
Server is received after continuously active message Keep_Alive, replies to Chi Huaqi at once with continuously active acknowledge message Keep_Alive_Ack.Refer to shown in Figure 11, it shows the form of continuously active acknowledge message of the present invention.In continuously active acknowledge message Keep_Alive_Ack, server has attached the correlation behavior information (such as CPU usage, network usage, memory usage, hard disk utilization rate etc.) of self.Pond device can be known the real-time system situation of server like this, and can be with reference to the situation as according to judgement server.In some cases, although server operation is all normal, but because resource is close to approach exhaustion, such as CPU usage, network usage, memory usage, hard disk utilization rate etc., surpass predetermined value, continue operation and may cause larger problem, this situation, pond device can be predicted in advance, can be failed server by this Servers installed.
If the continuously active message Keep_Alive that pond device sends, in setting-up time (timeout), do not receive continuously active acknowledge message Keep_Alive_Ack, send continuously rapidly several continuously active message Keep_Alive, if still do not receive continuously active acknowledge message Keep_Alive_Ack, can determining server break down, this fault may have multiple may: server delay machine, software fault, network failure etc., in a word in this case, user is the service that cannot use this server certainly.
Wherein the detailed process of method three is: because server is when registering, himself relevant information of service is provided, such as: service agreement, IP address, port numbers, and whether carry out the information such as service detection, if need to carrying out service detection, server (sees server parameter Server Parameter in Fig. 7, service detection 0x1 is for opening, 0x0 is for closing), pond device is according to these information, this server is carried out to periodic service availability detection, method is according to its service agreement, to send probe message to the IP of appointment and port, then the response by server judges that normally whether its service.
Here by an example explanation Chi Huaqi, how by server parameter, to carry out service availability detection: suppose that the information that server A provides when registration is:
| Service agreement | http |
| IP address | 192．168．100．9 |
| Serve port | 8080 |
| Pond name | WWW．test．com |
| Service detection | 0xl |
Pond device, according to these information, can be simulated once the accessing operation that common user uses browser, then according to it, responds, and whether normally surveys its service.Pond device is initiatively initiated to set up a tcp to 192.168.100.9:8080 and is connected, and sends a HTTP message, thes contents are as follows:
GET/HTTP/1.1
Host：WWW．test．com
User-Agent：Mozilla/5．0
Accept：*/*
If the service of server A is normal, pond device obtains following HTTP and replys message.
HTTP/1．1?200?OK
Dare：Thu，27?Sep?2012?16：06：28?GMT
Server：BWS/1．0
Content-Length：9783
Content-Type：text/html：charset=gbk
Cache-Control：private
Wherein 200 in the first row " HTTP/1.1 200 OK " is exactly HTTP conditional code, according to this HTTP conditional code, just can judge its server health.
HTTP conditional code is described as follows (only enumerating part):
| HTTP conditional code | Explanation |
| 200 | Normally |
| 403 | Resource is unavailable |
| 404 | Cannot find the resource of assigned address |
| 503 | Serve unavailable |
| ... | ... |
According to above example, if the HTTP conditional code that pond device is received is 200, the service that shows server A is normal, otherwise it is abnormal to judge the service of server A, and server A breaks down, and can do further troubleshooting subsequently.
No matter in which detection (Keep_Alive and service detection), pond device is judged certain server and is broken down, all will to other pond devices, send server update message at once and require pond device that this server is deleted from server list, be also aforesaid server info synchronizing step.Refer to shown in Figure 12, it shows the form of server update message in one embodiment of the present of invention, wherein in this server update message wherein more new element (Update Action) be defined as follows:
Update Action=0x1 increases service;
Update Action=0x2 deletes service.
The server pools system building by pond of the present invention device, when server need to add server pools, can initiatively at device place, pond, register, the relevant information (comprising: server ip, Service-Port, service agreement, pond name etc.) of self is provided to pond device, pond device is being safeguarded a server list, according to the register information of server, real-time update this part of server list; Before server closing, need nullify at device place, pond, pond device is deleted this server according to log-off message from this server list; Pond device also periodically carries out real-time system information acquisition (comprising: CPU, internal memory, Internet Use etc.) to server simultaneously, the fault detection mechanism of server pools system, to the real-time health examination of the server in server list, once discovery server fault, also can initiatively this server be deleted from server list, thereby guarantee that in server pools, server is all normal.
Pond device can carry out arbitrary extension, the information synchronization mechanism of pond device has guaranteed that the information between the device of Duo Tai pond is synchronous, like this when any pond device breaks down, can not cause information dropout, can not affect the normal operation of server pools system yet, Duo Tai pond device is worked simultaneously, has eliminated the possibility of the Single Point of Faliure of Chi Huaqi.
User is by name access services device pond, pond, need first at device place, pond, to do pond name analysis, pond device uses server selector to be made as the server that variant user selects to have best resource situation, and feed back to user as analysis result, user connects with regard to direct and this server like this, and carries out information interaction.
Pond device has played very crucial effect in server pools system, pond device can fast and effeciently be set up the server pools in logic of random scale, and by a series of mechanism of above introduction, ensured the normal operation of server pools: server health status detects, server failure is processed, server system Real-time Collection, according to server real-time system information and server health, be user's Dynamic Selection and distribute the server of best resource situation, the resource that ensures server pools reaches best behaviour in service, improve to greatest extent the utilization rate of server resource, and eliminate the adverse effect bring because of server failure.
Above-mentioned explanation has fully disclosed the specific embodiment of the present invention.It is pointed out that being familiar with any change that person skilled in art does the specific embodiment of the present invention does not all depart from the scope of claims of the present invention.Correspondingly, the scope of claim of the present invention is also not limited only to previous embodiment.
Claims (2)
1. build the Chi Huaqi in webserver pond, it is responsible for multiple servers to form a virtual server pools, and the running status of each station server is monitored in real time and gathered; Provide pond name analysis function, to can allow user facilitate accessing server simultaneously;
Wherein said pond device comprises:
The check in/check out functionality module of pond device: server needs initiatively to register at device place, pond before adding server pools, during registration, need provide the pertinent system information of server, comprise: server ip address, service port number, service agreement, pond name information; Pond device receives after the registration request of server, to verify this server info, if the verification passes, by this server registers a server list, and induction-arrangement, server, before exiting server pools, need to be handled logout procedure at device place, pond, and pond device is deleted from server list with being about to this server info;
The fault detect of pond device and management function module: in server pools system, pond device is responsible for server to carry out periodic health-and-status check according to the register information of server, once discovery server fault, pond device is deleted this server at once from server pools, to guarantee that in server pools, Servers-all is all effective, available;
The information collection function module of pond device: pond device periodically carries out system information acquisition to Servers-all in pond, comprise: the collection of the system related information of CPU, internal memory, Internet Use and so on, and this system information is arranged, for server selection strategy provides foundation;
The server selection function module of pond device: according to pond device to relevant informations such as the monitoring of server in each server pools, information gatherings, according to the selection strategy of server, all the time preferentially select the server of resource situation optimum, for pond name analysis provides foundation, to guarantee at any time can acquire for any user the server resource of real-time optimum;
Hua Qi pond, pond name analysis functional module: client-access server pools, first at device place, pond, do pond name analysis, the analysis request that pond device is submitted to according to client, in the server list of oneself, inquire about, conventionally each pond name corresponding a plurality of servers, pond device is installed and is realized the selection strategy determining, and for this user selects a best server ip, and this result is fed back to client to resolve the form of receiveing the response;
Pond device information synchronizing function module: server is registered or nullified at certain pond device, this pond device all can be notified lastest imformation other all Chi Huaqi in real time; If certain pond device discovery server fault, can in own server list of preserving, this server be deleted at once, by other all ponds these servers of device of server update message informing, break down simultaneously, after other pond devices are notified, also at once this server is deleted from the server list of its preservation; Pond device collects new server system information, as long as system information changes, all by other pond devices of real-time informing to guarantee the consistency of all ponds device information.
2. pond as claimed in claim 1 device, it is characterized in that: it is for building server pools system, the server pools system of its structure comprises: server pools, pond device and client, wherein server pools has identical function by one group, and being unified the server composition that management is got up, each server pools is all used unique pond name as sign; Client comprises the client computer in access services device pond.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210392450.0A CN103731460A (en) | 2012-10-16 | 2012-10-16 | Pooling device for establishing network server pool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210392450.0A CN103731460A (en) | 2012-10-16 | 2012-10-16 | Pooling device for establishing network server pool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103731460A true CN103731460A (en) | 2014-04-16 |
Family
ID=50455386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210392450.0A Pending CN103731460A (en) | 2012-10-16 | 2012-10-16 | Pooling device for establishing network server pool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103731460A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105262839A (en) * | 2015-11-03 | 2016-01-20 | 国云科技股份有限公司 | Remote logging method for specified terminal in mode of load balancing |
| CN107852604A (en) * | 2015-04-07 | 2018-03-27 | 安博科技有限公司 | System and method for providing global virtual network (GVN) |
| CN109788012A (en) * | 2017-11-14 | 2019-05-21 | 阿里巴巴集团控股有限公司 | A kind of health examination method and device, health examination control method and controller |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102075384A (en) * | 2010-12-20 | 2011-05-25 | 创新科存储技术有限公司 | Performance test system and method |
| CN102437933A (en) * | 2012-01-04 | 2012-05-02 | 无锡云捷科技有限公司 | Fault tolerance system and method of server |
| CN102571699A (en) * | 2010-12-20 | 2012-07-11 | 中兴通讯股份有限公司 | Method for selecting application server in application server pool and device adopting same |
-
2012
- 2012-10-16 CN CN201210392450.0A patent/CN103731460A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102075384A (en) * | 2010-12-20 | 2011-05-25 | 创新科存储技术有限公司 | Performance test system and method |
| CN102571699A (en) * | 2010-12-20 | 2012-07-11 | 中兴通讯股份有限公司 | Method for selecting application server in application server pool and device adopting same |
| CN102437933A (en) * | 2012-01-04 | 2012-05-02 | 无锡云捷科技有限公司 | Fault tolerance system and method of server |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107852604A (en) * | 2015-04-07 | 2018-03-27 | 安博科技有限公司 | System and method for providing global virtual network (GVN) |
| CN105262839A (en) * | 2015-11-03 | 2016-01-20 | 国云科技股份有限公司 | Remote logging method for specified terminal in mode of load balancing |
| CN105262839B (en) * | 2015-11-03 | 2019-03-05 | 国云科技股份有限公司 | The remote entry method of designated terminal under a kind of load-sharing mode |
| CN109788012A (en) * | 2017-11-14 | 2019-05-21 | 阿里巴巴集团控股有限公司 | A kind of health examination method and device, health examination control method and controller |
| CN109788012B (en) * | 2017-11-14 | 2022-04-01 | 阿里巴巴集团控股有限公司 | Health examination method and device, health examination control method and controller |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103853627B (en) | By the method and system relatively analyzing virtual machine performance issue reason with physical machine | |
| US11838247B2 (en) | Method and system for interaction servicing | |
| CN102891868B (en) | The load-balancing method of a kind of distributed system and device | |
| CN101605092A (en) | A kind of content-based SiteServer LBS | |
| US20130007253A1 (en) | Method, system and corresponding device for load balancing | |
| KR101408037B1 (en) | Virtual Machine Integration Monitoring Apparatus and method for Cloud system | |
| CN111083181B (en) | Equipment scheduling method, gateway and system for large-scale access to Internet of things | |
| US20150319233A1 (en) | Load balancing among servers in a multi-data center environment | |
| CN103581276A (en) | Cluster management device and system, service client side and corresponding method | |
| CN106034137A (en) | Intelligent scheduling method for distributed system, and distributed service system | |
| CN109787827B (en) | CDN network monitoring method and device | |
| CN106993037A (en) | A kind of method that load-balanced server based on distributed system realizes high availability | |
| CN103731289A (en) | Method for automatic expansion of network server | |
| CN112015544A (en) | Load balancing method, device and equipment of k8s cluster and storage medium | |
| JP2014515851A5 (en) | ||
| CN102437935B (en) | WEB application monitoring method and equipment | |
| CN103259684A (en) | Internet service monitoring method and system | |
| CN100461719C (en) | System and method for detecting service healthiness | |
| CN103731287A (en) | Method for selecting server to take over fault server | |
| CN111221700B (en) | Cluster node state monitoring method, device, equipment and readable storage medium | |
| CN103731290A (en) | Server failure switching method | |
| CN103731365A (en) | Bottleneck-free load balancing network server system and establishment method thereof | |
| CN112256498A (en) | Fault processing method and device | |
| CN105100185B (en) | System and method for processing database state notifications in a transactional middleware machine environment | |
| CN103731460A (en) | Pooling device for establishing network server pool |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140416 |