CN101877714A - Integrated server - Google Patents
Integrated server Download PDFInfo
- Publication number
- CN101877714A CN101877714A CN2009102533090A CN200910253309A CN101877714A CN 101877714 A CN101877714 A CN 101877714A CN 2009102533090 A CN2009102533090 A CN 2009102533090A CN 200910253309 A CN200910253309 A CN 200910253309A CN 101877714 A CN101877714 A CN 101877714A
- Authority
- CN
- China
- Prior art keywords
- server
- master server
- master
- integrated
- heartbeat
- 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)
Abstract
The invention discloses an integrated server which can provide a virtual machine service to remote computers. The integrated server comprises a plurality of slave servers which have heart rate monitoring program and replacement program. One of the slave servers is selected to be used as a master server. The slave servers send one signal requiring confirmation to the master server through the heart rate monitoring program so that the slave servers can confirm whether the master server is in the operation state or not. The master server has management program, and provides the virtual machine service to the remote computers. When all the slave servers do not receive the confirmation signal of the master server, the slave servers start operating the replacement program, and one of the rest slave servers is selected as the master server.
Description
Technical field
The present invention relates to a kind of server, be particularly to a kind of integrated server.
Background technology
Along with the development of world-wide web, make and utilize many computers to provide the purpose of service routine also can realize simultaneously.And also raising for it of computer processing speed, so the also related growth of the development of virtual machine.The response that can provide client various and real-time is provided, so generally can connect to form an integrated server (Pool) with many property server.
Each station server in integrated server all is identical.Think each station server that can manage in the integrated server, therefore can therefrom select the main frame of at least one station server as other servers of management.
With general known technology, the high availability (highavailability) for improving integrated server can adopt two-server as the management main frame.One station server is in order to concentrate other servers of management and control, and another station server then is the server of control management and control.Such framework makes the cost of integrated server be enhanced, and if at the two-server of management and control a damage is arranged then can cause the problem that integrated server can't normal operation.
Summary of the invention
In view of above problem, main purpose of the present invention is to provide a kind of integrated server, in order to provide virtual machine service to far-end computer.
For achieving the above object, integrated server disclosed in this invention comprises: select one of them as master server from server from server by these for many, master server provides virtual machine to serve to far-end computer by hypervisor; Have heartbeat monitor program and replacement program from server; Send the signal master server of a confirmation request by the heartbeat monitor program from server; After master server was accepted confirmation signal, master server can regularly send a heartbeat signal and give from server; Make and confirmed from server whether master server is in the running status; When server is not all received the heartbeat signal of master server, from server, select one of them as master server then from the server replacement program that brings into operation, and by remaining.
The invention provides a kind of integrated server, it is made of multiple servers, in order to virtual machine service to be provided.Integrated server is made up of from server a plurality of, and from server selects one in the mode of rotating from these by the replacement program and serve as master server.Can avoid all loads are dropped on the same station server.
Relevant characteristics and implementation of the present invention, conjunction with figs. is described in detail as follows as most preferred embodiment now.
Description of drawings
Fig. 1 is a configuration diagram of the present invention;
Fig. 2 is an operation workflow schematic diagram of the present invention;
Fig. 3 A is the operation workflow schematic diagram that carries out the heartbeat monitor program from server by interface of the present invention;
Fig. 3 B is that master server of the present invention is created the operation workflow schematic diagram that interface carries out the heartbeat monitor program.
Wherein, Reference numeral
110 from server
120 master servers
Embodiment
The present invention can be applicable to has the computer (for example: server, PC or notebook computer etc.) that the virtual machine service is provided.The present invention does not limit for the operating system of virtual machine operation and virtual hardware environment.Also please refer to shown in Figure 1ly for clearly demonstrating overall architecture of the present invention, it is a configuration diagram of the present invention.In integrated server of the present invention, constituted by multiple servers.Select one and serve as master server 120 in these servers, remaining then is from server 110.All servers all have heartbeat monitor program, heartbeat router and replacement program.For clearly demonstrating overall operation of the present invention, also please refer to shown in Figure 2ly, it is an operation workflow schematic diagram of the present invention.
Step S210: from server, select master server from these;
Step S220: send the signal of a confirmation request to master server from server;
Step S230: master server is after obtaining the signal of confirmation request, and the heartbeat signal that sends is regularly given from server;
Step S240: from server operation heartbeat monitor program, regular reception heartbeat signal;
Step S250: when Preset Time, all not obtaining heartbeat signal from server, then should be from server operation replacement program, in order to from server, to select a master server that conduct is new by these; And
Step S260: repeat abovementioned steps S220～S250, till selecting next new master server.
Operation heartbeat router then moves the heartbeat monitor program from server 110 in master server 120.Each from server 110 by the heartbeat monitor program in order to send a confirmation signal to master server 120.Master server 120 is receiving behind the affirmation signal of server 110, and master server 120 can regularly send heartbeat signal and give from server 110, confirms that from server 110 master server 120 still is in the running status so as to allowing.
For instance, can realize the monitoring of heartbeat signal by the mode of monitoring interface (socket) from server 110.Please cooperate shown in Fig. 3 A and Fig. 3 B, it is respectively the present invention carries out the heartbeat monitor program by interface operation workflow schematic diagram.
For for server 110, operation the following step:
Step S311: create the interface of getting in touch with usefulness with master server from server;
Step S312: judge whether heartbeat message from master server;
Step S313:, then after through first Preset Time, finish interface if do not receive the heartbeat message that master server sends; And
Step S314: if after receiving heartbeat message from server from master server, repeating step S312 then.
For master server 120, operation the following step:
Step S321: create with the interface of using from server contacts in order to set up the heartbeat line; And
Step S322: receive behind the affirmation signal of server, regularly send heartbeat signal.
Except the mode of utilizing interface, more can reach an agreement on and realize by different Network Transmission.In the Intranet at integrated server place, can transmit confirmation signal by TCP from server 110 and give master server 120.After master server 120 was obtained confirmation signal, master server 120 can regularly pass through the udp broadcast heartbeat signal and give respectively from server 110.Therefore, can confirm that by the transmission of heartbeat signal master server 120 is whether still in the middle of operation.
In addition, master server 120 provides virtual machine service to far-end computer by hypervisor.Compared to known technology only is to provide virtual machine service with independent one server, and the present invention is in order to reduce the load that single server is caused, so come equally loaded by multiple servers.Therefore come of the requirement of unified management far-end computer by master server 120, so as to being split in the load average of virtual machine respectively from server 110 to Virtual Service.In other words, far-end computer by the representative of master server 120 as connection, and will be forwarded to accordingly from server 110 from every requirement of server 110 when being connected to integrated server.
Be operation integrated server that can be real-time, so the existence of master server 120 is necessary.Each station server in integrated server all has the replacement program.Since master server 120 because of managerial demand unusual fluctuation or when machine can't continue again the running.At this time need from server 110, select the master server 120 that conduct is new in addition at these.
For can be fair select master server 120, so the action that can select in the following manner of replacement program.Each all has weights from server 110, respectively from passing through the independently weights of the exchange oneself of communication path periodicity (sending out once such as per 5 minutes) between the server 110.Thus, each all has all weights from server 110 from server 110.When from server 110 when whenever receiving weights, just the weights received and the weights of oneself are made comparisons.If the weights of receiving are greater than the weights of itself, then thinking oneself does not have qualification as master server 120.When master server 120 pawns, each is checked all from server 110 whether oneself is the current weight maximum, if then bootstrapping is master server 120.
And the strategy of decision weights can be according to deciding from server 110 current load capacity, runnability or working procedure quantity.With the load is example, and the first processing unit occupancy from server is 10%, and the second processing unit occupancy from server is 15%.First is light from server compared to second from the load of server so.Therefore be 90 with first the weight setting from server, and second from server compared to first heavier, so be 85 with second the weight setting from server from the load of server.So first can judge that from server the weights of oneself are big, can boot and judge that from server the weights of oneself are low into master server 120, the second, abandon becoming master server 120.So, election just can not repeat automatically.
The invention provides a kind of integrated server, it is made of multiple servers, in order to virtual machine service to be provided.Integrated server is made up of from server 110 a plurality of, and selects one from these from server 110 in the mode of rotating by the replacement program and serve as master server 120.Can avoid all loads are dropped on the same station server.
Certainly; the present invention also can have other various embodiments; under the situation that does not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection range of the appended claim of the present invention.
Claims (4)
1. an integrated server is characterized in that, it is in order to provide a virtual machine service to a far-end computer, and this integrated server comprises:
Many from server, should have a heartbeat monitoring program and a replacement program from server;
One master server, one of them is served as from server by these, and this master server is electrically connected at these from server; And
Should be from server by this heartbeat monitor program in order to the signal that sends a confirmation request to this master server, this master server moves a heartbeat router, when this master server receives from this behind the signal of this confirmation request of server, this master server can regularly send a heartbeat signal to being somebody's turn to do from server, this master server has a hypervisor, and this master server provides this virtual machine to serve to this far-end computer by this hypervisor;
Wherein, when these when server is not all received this heartbeat signal of this master server, then these move this replacement program from server, in order to select one of them as this master server from server from these.
2. integrated server according to claim 1 is characterized in that, this master server and these respectively have a privately owned address from server, and this master server provides this virtual machine service with a publicly-owned address.
3. integrated server according to claim 2 is characterized in that, after this replacement program of operation, with this publicly-owned address cancellation of this previous master server, this selected master server is set this publicly-owned address.
4. integrated server according to claim 1 is characterized in that, this replacement program determines that according to the size of a weighted value one of them moves this replacement program from server for these, takes over as this master server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102533090A CN101877714A (en) | 2009-11-30 | 2009-11-30 | Integrated server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009102533090A CN101877714A (en) | 2009-11-30 | 2009-11-30 | Integrated server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101877714A true CN101877714A (en) | 2010-11-03 |
Family
ID=43020176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009102533090A Pending CN101877714A (en) | 2009-11-30 | 2009-11-30 | Integrated server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101877714A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106656589A (en) * | 2016-12-13 | 2017-05-10 | 武汉船舶通信研究所 | Server dual hot backup system |
| CN107196814A (en) * | 2017-07-28 | 2017-09-22 | 郑州云海信息技术有限公司 | A kind of management method and system of many clusters |
| CN107819808A (en) * | 2016-09-14 | 2018-03-20 | 北京百度网讯科技有限公司 | Communicate to connect method for building up and device |
| CN108092858A (en) * | 2018-02-07 | 2018-05-29 | 北京百度网讯科技有限公司 | For switching the method and device of agent node |
-
2009
- 2009-11-30 CN CN2009102533090A patent/CN101877714A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107819808A (en) * | 2016-09-14 | 2018-03-20 | 北京百度网讯科技有限公司 | Communicate to connect method for building up and device |
| US10609133B2 (en) | 2016-09-14 | 2020-03-31 | Beijing Baidu Netcom Science and Technology Co., Ltd | Method and device for establishing communication connection |
| CN106656589A (en) * | 2016-12-13 | 2017-05-10 | 武汉船舶通信研究所 | Server dual hot backup system |
| CN106656589B (en) * | 2016-12-13 | 2019-08-23 | 武汉船舶通信研究所 | A kind of server dual-machine hot backup system |
| CN107196814A (en) * | 2017-07-28 | 2017-09-22 | 郑州云海信息技术有限公司 | A kind of management method and system of many clusters |
| CN108092858A (en) * | 2018-02-07 | 2018-05-29 | 北京百度网讯科技有限公司 | For switching the method and device of agent node |
| CN108092858B (en) * | 2018-02-07 | 2019-10-18 | 北京百度网讯科技有限公司 | For switching the method and device of agent node |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102571452B (en) | Multi-node management method and system | |
| CN103369601B (en) | For cell-phone customer terminal provides the method for large concurrent processing and flow control | |
| CN101571813B (en) | Master/slave scheduling method in multimachine assembly | |
| CN109617731A (en) | Adaptive gateway role configuration method and device under a kind of multi-gateway environment | |
| EP1820291B1 (en) | A method, system and computer program product for coordinated monitoring and failure detection | |
| EP3229420A1 (en) | Method for establishing persistent connection between multiple smart devices and server, and smart device | |
| CN107453929B (en) | Cluster system self-construction method and device and cluster system | |
| CN107733684A (en) | A kind of multi-controller computing redundancy cluster based on Loongson processor | |
| WO2006040327A1 (en) | Method, system and program product for automated topology formation in dynamic distributed environments | |
| CN103581276A (en) | Cluster management device and system, service client side and corresponding method | |
| CN110830324B (en) | Method and device for detecting network connectivity of data center and electronic equipment | |
| CN109787827B (en) | CDN network monitoring method and device | |
| CN104717077B (en) | A kind of method, apparatus and system for managing data center | |
| CN109617807A (en) | Route information update method, device, gateway and storage medium | |
| CN101877714A (en) | Integrated server | |
| CN104618466A (en) | System for balancing load and controlling overload based on message transfer and control method of system | |
| US10554497B2 (en) | Method for the exchange of data between nodes of a server cluster, and server cluster implementing said method | |
| CN103546308A (en) | Method, device and system for distributing wireless controller network | |
| CN101145972B (en) | A disaster tolerance network management system and login method of network management clients | |
| CN106230622A (en) | A kind of cluster implementation method and device | |
| JP5647561B2 (en) | Power system supervisory control system | |
| CN108234623B (en) | Automatic balance management method for data acquisition link of distribution network master station | |
| CN101599907A (en) | Flow forwarding method and system | |
| CN113326100A (en) | Cluster management method, device and equipment and computer storage medium | |
| WO2005104435A1 (en) | Methods, devices and computer program products using a node affiliation protocol for monitoring and/or controlling networkable devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20101103 |