CN106790563A - Distributed memory system and method - Google Patents
Distributed memory system and method Download PDFInfo
- Publication number
- CN106790563A CN106790563A CN201611221617.1A CN201611221617A CN106790563A CN 106790563 A CN106790563 A CN 106790563A CN 201611221617 A CN201611221617 A CN 201611221617A CN 106790563 A CN106790563 A CN 106790563A
- Authority
- CN
- China
- Prior art keywords
- server
- master server
- data
- master
- secondary master
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0668—Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/30—Decision processes by autonomous network management units using voting and bidding
Abstract
The present invention proposes a kind of distributed memory system and method, is related to big data field of storage.Wherein, a kind of distributed memory system of the invention, including：Master server, for processing data and data storage, and sends the data to secondary master server and from server；Secondary master server, the data of primary server is carried out for storing, and switch to master server according to from the election results of server when master server delays machine；With, from server, the data of primary server are carried out for storing, corrupt data is provided the user, and elect new master server from secondary master server when master server delays machine.Data, services are provided the user by various servers in such system, access efficiency is improve；When master server failure, can there is secondary master server and switch to master server in time, improve failure and solve efficiency, improve the stability and reliability of system.
Description
Technical field
The present invention relates to big data field of storage, particularly a kind of distributed memory system and method.
Background technology
With social networks, mobile Internet, and e-commerce technology are continued to develop, and that is managed based on network is mutual
Networking enterprise is increasingly liked by people.People also create substantial amounts of content while frequently using internet.This
A little contents are exactly data, and each Internet firm is substantially all in rear end and has a set of mature and stable distributed system and be used for
Storage, calculating and the analysis of data, extract data value.Being also required to a set of efficient, reliable data buffering system simultaneously is used for
The fast reaction of the Internet, applications, a sluggish application cannot get user's favor certainly.
It is many using the method for designing based on Multi-Paxos algorithms in the prior art, but because such algorithm is more difficult
To understand, engineer easily malfunctions in programming, causes the unstable of system；And another is based on Raft algorithms
Method for designing is barely satisfactory in reading speed and troubleshooting speed.
The content of the invention
A kind of Distributed Storage scheme it is an object of the present invention to propose stability and high efficiency.
According to an aspect of the present invention, a kind of distributed memory system is proposed, including：Master server Main-Leader,
For processing data and data storage, and send the data to secondary master server and from server；Secondary master server Deputy-
Leader, the data of primary server is carried out for storing, and cut according to from the election results of server when master server delays machine
It is changed to master server；With, from server Follower, the data of primary server are carried out for storing, it is unreliable to provide the user
Data, and new master server is elected from secondary master server when master server delays machine.
Alternatively, distributed memory system includes a master server, at least one secondary master server and at least two
From server.
Alternatively, master server is connected with from server by heartbeat message holding；Master server is additionally operable to when machine is delayed
Restart and switch to from server；From server specifically for：When the heartbeat message for carrying out primary server cannot be received, really
Determine master server to delay machine；By from the interaction between server, being elected from secondary master server based on the first predetermined policy new
Master server；Secondary master server is additionally operable to, when being new master server from Server election, switch to master server.
Alternatively, it is additionally operable to from server：After new master server is elected from secondary master server, by from service
Interaction between device, new secondary master server is elected based on the second predetermined policy from from server；When being elected as new pair
Secondary master server is switched to during master server.
Alternatively, master server specifically for：The write-in data from user are received, storage write-in data simultaneously generate daily record
Information；Write-in data are sent to secondary master server based on reliable data transmission mode；Write-in data are passed through into corrupt data
Transmission means is sent to from server；Secondary master server is additionally operable to generate log information when the data is written.
Alternatively, secondary master server is additionally operable to, when master server is switched to, data storage be updated based on log information.
Master server, secondary master server are used in such system, distributed storage is carried out from server architecture, by various
Server provides the user data, services, improves access efficiency；When master server failure, can there is secondary master server timely
Master server is switched to, failure is improve and is solved efficiency, improve the stability and reliability of system.
According to another aspect of the present invention, a kind of distributed storage method is proposed, including：When master server delays machine from
Server elects new master server from secondary master server, wherein, master server processing data and data storage, and by number
According to being sent to secondary master server and from server；Secondary master server storage carrys out the data of primary server；Come from server storage
The data of primary server simultaneously provide the user corrupt data；According to the election results from server, secondary master server switching
It is master server.
Alternatively, the quantity of master server is 1, and the quantity of secondary master server is more than 1, is from the quantity of server
More than 2.
Alternatively, also include：Master server and between server by heartbeat message keep connect；When master server is delayed
During machine, master server is restarted and is switched to from server；New master server bag is elected from secondary master server from server
Include：When from server the heartbeat message for carrying out primary server cannot be received, determine that master server is delayed machine；Pass through from server
From the interaction between server, new master server is elected from secondary master server based on the first predetermined policy；According to from service
The election results of device, secondary master server switches to the master server to include：It is secondary when being new master server from Server election
Master server switches to master server.
Alternatively, also include：After new master server is elected from secondary master server from server, by from service
Interaction between device, new secondary master server is elected based on the second predetermined policy from from server；When being elected as new pair
During master server, secondary master server is switched to from server.
Alternatively, also include：Master server receives the write-in data from user, and storage write-in data simultaneously generate daily record letter
Breath；Write-in data are sent to secondary master server based on reliable data transmission mode；Write-in data are passed by corrupt data
Defeated mode is sent to from server；Secondary master server storage write-in data, and generate log information.
Alternatively, also include：When secondary master server switches to master server, data storage is updated based on log information.
By such method, can using master server, secondary master server, distribution carried out from server architecture deposit
Storage, data, services are provided the user by various servers, improve access efficiency；When master server failure, can exist secondary main
Server switches to master server in time, improves failure and solves efficiency, improves the stability and reliability of system.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is the schematic diagram of one embodiment of distributed memory system of the invention.
Fig. 2 is the schematic diagram of one embodiment of server switching in distributed memory system of the invention.
Fig. 3 is the signaling diagram of one embodiment of data write-in in distributed memory system of the invention.
Fig. 4 is the signaling diagram of one embodiment of digital independent in distributed memory system of the invention.
Fig. 5 is the flow chart of one embodiment of distributed storage method of the invention.
Fig. 6 is the flow chart of another embodiment of distributed storage method of the invention.
Fig. 7 is the flow chart of one embodiment of data write-in in distributed storage method of the invention.
Specific embodiment
Below by drawings and Examples, technical scheme is described in further detail.
The schematic diagram of one embodiment of distributed memory system of the invention is as shown in Figure 1.Wherein, master server 101
Can processing data and data storage, and send the data to secondary master server and from server；Secondary master server 111, secondary master
Server 112 can respectively store the data for carrying out primary server, and when master server delays machine according to the election from server
Result switches to master server, and multiple pair master servers can be included in system；Can be stored from server 121,122 and come autonomous
The data of server, provide the user corrupt data, and are elected from secondary master server when master server delays machine new
Master server, can include multiple from server in system.
Master server, secondary master server are used in such system, distributed storage is carried out from server architecture, by various
Server provides the user data, services, improves access efficiency；Secondary master server and carry out primary server from server storage
Data, so as to ensure that the data consistency of multiple servers；When master server failure, can there is secondary master server timely
Master server is switched to, failure is improve and is solved efficiency, improve the stability and reliability of system.
In one embodiment, when initial start, multiple parallel servers can be included in system, after start completion,
A master server, at least one secondary server, and multiple from server are generated in distributed memory system.Distributed storage
The structure of system can be divided into two-layer, and wherein master server and secondary master server is located at active layers, performs user data treatment, number
According to the function that backup and distributed network heartbeat are processed；Passive layer is located at from server, the operation of synchronous active layer data is performed.
In one embodiment, system maintenance personnel can as needed specify the quantity of secondary master server.In one embodiment, may be used
With the weight of each server in configuration system, master server, secondary master server are determined according to the size of weight, by system its
His server is used as from server.
Such system can be quickly generated by master server, secondary main service and from the structure of server, improve system life
Into efficiency.
In one embodiment, at least there are three servers in distributed memory system, wherein, serviced based on one
Device, one not only for secondary master server but also be that, from server, also one is from server.Such distributed memory system can
It is enough to meet using the structure of major and minor master and slave server, ensure that again from server conduct an election when being capable of compliance meaning
See, it is ensured that the normal operation of system.
In one embodiment, the determination of multiple role servers can be divided into two stages：Primary server role determines
Determine with secondary primary server role.From server by interaction election determine master server, and then by interaction election determine from
Server.If there are multiple pair master servers in system maintenance personnel depaly system, carried out successively from server repeatedly secondary main
Server election, until meeting the quantity of secondary master server.In one embodiment, can be calculated according to Raft algorithms or Paxos
Method realizes master server, the election of secondary master server.In another embodiment, can be that each server configures different power
Weight, the size based on weight realizes master server, the election of secondary master server.
Such distributed memory system compliance can anticipate rapidly when master server, secondary master server are elected
See, improve the toggle speed of system.
The schematic diagram of one embodiment of server switching is as shown in Figure 2 in distributed memory system of the invention.Main clothes
Business device is connected with from server by heartbeat message holding, therefore, when master server 201 delays machine, from server 221, from clothes
Business device 222 etc. can be discovered rapidly cannot receive the heartbeat message of master server, determine that master server 201 is delayed machine.Delay machine
Master server 201 is restarted and is switched to from server.From server by the way that from the interaction between server, first can be based on pre-
Fixed strategy elects new master server from secondary master server.In one embodiment, the first predetermined policy can be according to
The size election master server of secondary master server weights.As shown in Fig. 2 determine that secondary master server 212 turns into new master server,
Secondary master server 212 switches to master server.Can also be predetermined based on second by from the interaction between server from server
Strategy elects a secondary master server from from server.In one embodiment, the second predetermined policy can be according to from
The secondary master server of size election of server weights, it is also possible to based on Paxos algorithms, the secondary master server of Raft algorithms election.Such as
Shown in Fig. 2, it is determined that election is secondary master server from server 222, secondary master server is switched to from server 222.
In such distributed memory system, can in time discover master server from server and delay machine, and it is main from pair in time
New master server is elected in server, new secondary master server is elected from from server, so as to ensure that system
Stabilization.
In one embodiment, access speed can be improved based on server weights election master server, secondary master server,
The defect that there is livelock using Paxos algorithms is made up, stablizes the election cycle controllable, it is ensured that the seamless switching of system, improve system
System stability.
The signaling diagram of one embodiment of data write-in is as shown in Figure 3 in distributed memory system of the invention.Wherein, it is main
Server 301, secondary master server 311, secondary master server 322, the 26S Proteasome Structure and Function from server 321 and from server 322 with
It is similar in the embodiment of Fig. 1.In distributed memory system, all of write data requests are all pointed at master server 301.
In 340, master server 301 receives write-in data.In one embodiment, master server 301 can also be received
Data processing request, master server 301 carries out data processing, generation write-in data.Master server 301 writes data and generates day
Will information.
In 341, master server 301 will write data is activation to secondary master server.
In 342, after storage write-in data, transmission is successfully written and feeds back to master server 301 secondary master server.
Master server 301 is received after being successfully written feedback information, confirmation synchronously success.Secondary master server can also generate daily record letter
Breath, so that data rewind is operated.In one embodiment, if master server 301 it is interior at preset time intervals fail to receive come from
Secondary master server is successfully written feedback information, then send write-in data to secondary master server again.
In 343, master server 301 gives from server write-in data is activation.Due to without ensureing to be deposited from server
The information of storage is completely correct, comprehensive, therefore be successfully written feedback information without being sent to master server 301 from server,
Without grade, this is successfully written feedback information to master server 301.
Such system can send the data to secondary master server and from server when data write；Due to secondary main clothes
Business device needs to keep consistent with the data of master server, therefore sends the data to secondary main service using reliable data transmission mode
Device；Due to that need not be consistent with master server from the data of server, therefore without waiting for reply, improve system effectiveness.
In one embodiment, master server can also use 2PC (Two Phase Commit Protocol, two benches
Committing protocol) algorithm to secondary master server send write-in information, to ensure the uniformity of data；Master server uses multicasting technology
Data are sent, so as to improve efficiency, the resource occupation of master server is reduced.
In one embodiment, master server and secondary master server execution journal consistency operation when data are write, right
In the data of modification, log information only does to add does not make an amendment operation.When master server occurs abnormal, new master server exists
After new secondary master server is elected, it is synchronous to first have to carry out a log information between master server before, so
The responsibility of master server can be just exercised afterwards.
Such system ensure that the content in master server is newest, comprehensive, so as to avoid due to main clothes
Business device is delayed loss of data caused by machine, it is ensured that the safety of data.
The signaling diagram of one embodiment of digital independent is as shown in Figure 4 in distributed memory system of the invention.Wherein, it is main
Server 40, secondary master server 411, secondary master server 422, the 26S Proteasome Structure and Function from server 421 and from server 422 and figure
It is similar in 1 embodiment.Client-initiated read data request can be divided into two kinds of operator schemes：Correct read mode and quick reading
Pattern.
Under correct read mode, user needs to obtain reliable, accurate data, thus user read data operation
Eventually point to master server, and the data feedback that will be read by master server is to user.
For fast read mode, user can complete to read data behaviour by any server in distributed memory system
Make.In one embodiment, the data for being needed from server and in the absence of user.
In 441, quick read requests user's request is received from server 421 in distributed memory system.
In 442, the data needed in the absence of user from server 421, initiating data syn-chronization to master server 401 please
Ask.
In 443, master server 401 will be given from server 421 from the data distributing of server request.
In 444, from server 421 by data syn-chronization to the storage of itself, and user is fed back to.
Such system can provide a user with data by from server, when the number needed in the absence of user from server
According to when, can ask to master server and supplement itself and store, so as to improve data extraction efficiency, improve the fault-tolerant of system
Property, alleviate the burden of master server.
In one embodiment, based on any one distributed memory system that will can be mentioned above or unit section
Point is extended, and generates more massive distributed storage network, thus provide more stablize, efficiently and with bigger carrying energy
The storage system of power, meets the demand of network data expansion.
In one embodiment, can using distributed memory system of the invention as single-node login system for platform is provided
Proof of identification bill.
When users log on, username and password information is submitted to and applies backstage by user, after background authentication success, is accessed and is divided
Cloth storage system carries out write operation；Distributed memory system writes a billing information according to user's unique mark；Bill is believed
Breath has carried out writing data, Backup Data and data cached operation within the storage system；Distributed memory system surrender of bills information
To applying backstage；Billing information is returned into user using backstage, shows that user has logged on.
When user accesses the service in application, service routine obtains the current billing information A of user；Service routine according to
User's unique mark reads a data to distributed memory system；Distributed memory system returns to a bill to service routine
Data B；Whether service routine compares billing information A consistent with bill data B.
If billing information A and B is inconsistent, then service routine synchronously reads a number to distributed memory system again
According to distributed memory system returns to a bill data C to service routine；Service routine compares billing information A and bill data C
Whether consistent, if inconsistent show that user is not logged in, stopping provides a user with service；If it is consistent, show that user has stepped on
Record, service routine obtains new billing information (process is similar with login process), Xiang Yong to write operation of storage system application
Family provides service and new bill, and used stamp is according to failure.
If billing information A is consistent with B, then represents user and have logged on, service routine is once write to storage system application
Operation, obtains new billing information, and service routine knows that user has logged on, and provides a user with service and new bill, used stamp
According to failure.
Such distributed memory system can be as single-node login system for platform provides proof of identification bill, on the one hand
The accuracy of authentication is ensure that, the efficiency of checking is on the other hand also improved；Simultaneously as distributed memory system is seamless
The characteristics of switching, it is possible to increase the stability of the application based on distributed memory system, secure user data is improved, improve user
Experience.
The flow chart of one embodiment of distributed storage method of the invention is as shown in Figure 5.
In step 501, master server is delayed machine.In one embodiment, distributed memory system includes main clothes
Business device, secondary master server and from server；Master server processing data and data storage, and send the data to secondary main service
Device and from server；Secondary master server storage carrys out the data of primary server；Carry out the data of primary server from server storage
And provide the user corrupt data.
In step 502, new master server is elected from secondary master server from server.
In step 503, according to the election results from server, secondary master server switches to master server.
By such method, can using master server, secondary master server, distribution carried out from server architecture deposit
Storage, data, services are provided the user by various servers, improve access efficiency；When master server failure, can exist secondary main
Server switches to master server in time, improves failure and solves efficiency, improves the stability and reliability of system.
In one embodiment, when initial start, multiple parallel servers, distributed storage system can be included in system
A master server, at least one secondary server, and multiple from server are generated in system.In one embodiment, system dimension
Shield personnel can as needed formulate the quantity of secondary server.In one embodiment, can each server in configuration system
Weight, master server, secondary master server are determined according to the size of weight, using other servers in system as from service
Device.
By such method, can be quickly generated by master server, secondary main service and from the structure of server, improve system
The efficiency of system generation.
The flow chart of another embodiment of distributed storage method of the invention is as shown in Figure 6.
In step 601, master server breaks down and machine of delaying.
In step 602, master server is restarted and is switched to from server.
In step 603, judge whether to receive the heartbeat message of primary server from server.When from service
When device cannot receive the heartbeat message for carrying out primary server, determine that master server is delayed machine, perform step 604.
In step 604, from server by from the interaction between server, based on the first predetermined policy from secondary main service
New master server is elected in device.In one embodiment, the first predetermined policy can be according to secondary master server weights
Size elects master server.
In step 605, the secondary server for being elected as new master server switches to master server.
In step 606, from server by from the interaction between server, based on the second predetermined policy from from server
In elect a secondary master server.In one embodiment, the second predetermined policy can be according to from the big of server weights
The small secondary master server of election, it is also possible to based on Paxos algorithms, the secondary master server of Raft algorithms election.
In step 607, be elected as new secondary master server switches to secondary master server from server.
By such method, can in time discover master server from server and delay machine, and in time from secondary master server
New master server is elected, new secondary master server is elected from from server, it is achieved thereby that seamless between server
Switching, it is ensured that the stabilization of system.
The flow chart of one embodiment of data write-in is as shown in Figure 7 in distributed storage method of the invention.
In step 701, master server receives write-in data.In one embodiment, master server 301 can also be received
Data processing request, master server carries out data processing, generation write-in data.Master server writes data and generates daily record letter
Breath.
In a step 702, master server will write data is activation to secondary master server.Because secondary master server needs to keep
Data with master server are consistent, and secondary master server is sent the data to using reliable data transmission mode.
In step 703, after storage write-in data, transmission is successfully written and feeds back to main service secondary master server
Device, and log information is generated, so that data rewind is operated.
In step 704, master server gives from server write-in data is activation.Due to without ensureing to be deposited from server
The information of storage is completely correct, comprehensively, therefore master server is without waiting for being successfully written feedback information.
In step 705, from the write-in data that server storage is received.
By such method, secondary master server can be sent the data to when data write and from server；Due to
Secondary master server needs to keep consistent with the data of master server, therefore sends the data to pair using reliable data transmission mode
Master server；Due to that need not be consistent with master server from the data of server, therefore without waiting for reply, improve system
Efficiency.
In one embodiment, master server and secondary master server execution journal consistency operation when data are write, right
In the data of modification, log information only does to add does not make an amendment operation.When master server occurs abnormal, new master server exists
After new secondary master server is elected, it is synchronous to first have to carry out a log information between master server before, so
The responsibility of master server can be just exercised afterwards.
By such method, ensure that the content in master server be it is newest, comprehensively, so as to avoid due to
Master server is delayed loss of data caused by machine, it is ensured that the safety of data.
In one embodiment, Client-initiated read data request can be divided into two kinds of operator schemes：Correct read mode and
Fast read mode.Under correct read mode, user needs to obtain reliable, accurate data, thus user receive data
Master server is eventually pointed to according to operation, and the data feedback that will be read by master server is to user.
By such method, can ensure that user obtains accurate data, improve the data precision guarantee.
In one embodiment, for fast read mode, user is by any server in distributed memory system
Can complete to read data manipulation, so as to improve data feedback speed, and reduce the burden of master server.
In another embodiment, if being needed when user uses fast read mode from server and in the absence of user
Data, then from server to master server initiate data synchronization request.Master server is by from the data distributing of server request
To from server；From server 421 by data syn-chronization to the storage of itself, and feed back to user.
By such method, on the one hand ensure that user can obtain feedback data, on the other hand can also make from service
Device supplements itself storage, it is to avoid repeats inquiry master server, improves data extraction efficiency, alleviates the burden of master server.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention rather than its limitations；To the greatest extent
Pipe has been described in detail with reference to preferred embodiment to the present invention, and those of ordinary skill in the art should be understood：Still
Specific embodiment of the invention can be modified or equivalent is carried out to some technical characteristics；Without deviating from this hair
The spirit of bright technical scheme, it all should cover in the middle of claimed technical scheme scope of the invention.
Claims (12)
1. a kind of distributed memory system, it is characterised in that including：
Master server, for processing data and data storage, and sends the data to secondary master server and from server；
The secondary master server, for storing the data from the master server, and when the master server delays machine according to
It is described to switch to the master server from the election results of server；With,
It is described, for storing the data from the master server, to provide the user corrupt data from server, and when described
Master server delay machine when the new master server is elected from the secondary master server.
2. system according to claim 1, it is characterised in that the distributed memory system includes the main clothes
Business device, from server described in secondary master server and at least two described at least one.
3. system according to claim 1, it is characterised in that the master server is disappeared from server with described by heartbeat
Breath keeps connection；
The master server is additionally operable to restart when machine is delayed and switch to from server；
It is described from server specifically for：
When the heartbeat message from the master server cannot be received, determine that the master server is delayed machine；
By the interaction between server, new main clothes are elected from the secondary master server based on the first predetermined policy
Business device；
The secondary master server be additionally operable to by it is described from Server election be the new master server when, switch to the master
Server.
4. system according to claim 3, it is characterised in that
It is described to be additionally operable to from server：
After the new master server is elected from the secondary master server, by the interaction between server, base
New described secondary master server is elected from server from described in the second predetermined policy；
The secondary master server is switched to when the new secondary master server is elected as.
5. system according to claim 1, it is characterised in that
The master server specifically for：
The write-in data from user are received, said write data is stored and is generated log information；
Said write data are sent to the secondary master server based on reliable data transmission mode；
Said write data are sent to by corrupt data transmission means described from server；
The secondary master server is additionally operable to generate the log information when the data is written.
6. system according to claim 1, it is characterised in that
The secondary master server is additionally operable to, when the master server is switched to, data storage be updated based on the log information.
7. a kind of distributed storage method, it is characterised in that including：
The new master server is elected from secondary master server from server when master server delays machine, wherein, the master
Server process data and data storage, and send the data to secondary master server and from server；The secondary main service
Device stores the data from the master server；It is described from data of the server storage from the master server and for user carries
For corrupt data；
According to the election results from server, the secondary master server switches to the master server.
8. system according to claim 7, it is characterised in that the quantity of the master server is 1, the secondary main service
The quantity of device is more than 1, and the quantity from server is more than 2.
9. method according to claim 1, it is characterised in that
Also include：
The master server keeps being connected from server with described by heartbeat message；
When the master server delays machine, the master server is restarted and is switched to described from server；
It is described the new master server is elected from secondary master server from server to include:
During the heartbeat message that cannot be received from server from the master server when described, the master server is determined
Delay machine；
It is described to pass through described from the interaction between server from server, selected from the secondary master server based on the first predetermined policy
Enumerate new master server；
From the election results of server described in the basis, the secondary master server switches to the master server to include：Work as quilt
It is described from Server election be the new master server when, the secondary master server switches to the master server.
10. method according to claim 9, it is characterised in that
Also include：
When it is described elect the new master server from the secondary master server from server after, by described from server
Between interaction, new described secondary master server is elected from server from described based on the second predetermined policy；
It is described to switch to the secondary master server from server when the new secondary master server is elected as.
11. methods according to claim 7, it is characterised in that also include：
The master server receives the write-in data from user, stores said write data and generates log information；
Said write data are sent to the secondary master server based on reliable data transmission mode；
Said write data are sent to by corrupt data transmission means described from server；
The secondary master server storage said write data, and generate the log information.
12. methods according to claim 11, it is characterised in that also include：
When the secondary master server switches to the master server, data storage is updated based on the log information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611221617.1A CN106790563B (en) | 2016-12-27 | 2016-12-27 | Distributed memory system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611221617.1A CN106790563B (en) | 2016-12-27 | 2016-12-27 | Distributed memory system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106790563A true CN106790563A (en) | 2017-05-31 |
| CN106790563B CN106790563B (en) | 2019-11-15 |
Family
ID=58925699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611221617.1A Active CN106790563B (en) | 2016-12-27 | 2016-12-27 | Distributed memory system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106790563B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388487A (en) * | 2018-03-01 | 2018-08-10 | 上海达梦数据库有限公司 | A kind of data loading process, device, equipment and storage medium |
| CN110166542A (en) * | 2019-05-16 | 2019-08-23 | 广东电网有限责任公司信息中心 | Distributed memory system and data read-write method based on ICP/IP protocol |
| CN110557399A (en) * | 2019-09-12 | 2019-12-10 | 苏州浪潮智能科技有限公司 | Management data synchronization method and device, storage equipment and readable storage medium |
| CN111277616A (en) * | 2018-12-04 | 2020-06-12 | 中兴通讯股份有限公司 | RDMA (remote direct memory Access) -based data transmission method and distributed shared memory system |
| CN111653052A (en) * | 2020-04-26 | 2020-09-11 | 北京三快在线科技有限公司 | Cash register system and cash register switching method |
| CN113656348A (en) * | 2021-08-25 | 2021-11-16 | 北京微纳星空科技有限公司 | Distributed cluster management system and method for satellite application big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101278540A (en) * | 2005-10-03 | 2008-10-01 | 阿玛得斯两合公司 | System and method to maintain coherence of cache contents in a multi-tier software system aimed at interfacing large databases |
| CN102006330A (en) * | 2010-12-01 | 2011-04-06 | 北京瑞信在线系统技术有限公司 | Distributed cache system, data caching method and inquiring method of cache data |
| CN102629903A (en) * | 2011-12-21 | 2012-08-08 | 奇智软件（北京）有限公司 | System and method for disaster recovery in internet application |
| CN103516549A (en) * | 2013-09-27 | 2014-01-15 | 浪潮电子信息产业股份有限公司 | File system metadata log mechanism based on shared object storage |
| CN104317803A (en) * | 2014-09-23 | 2015-01-28 | 厦门美柚信息科技有限公司 | Data access structure and method of database cluster |
| CN105554143A (en) * | 2015-12-25 | 2016-05-04 | 浪潮(北京)电子信息产业有限公司 | High-availability cache server and data processing method and system thereof |
-
2016
- 2016-12-27 CN CN201611221617.1A patent/CN106790563B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101278540A (en) * | 2005-10-03 | 2008-10-01 | 阿玛得斯两合公司 | System and method to maintain coherence of cache contents in a multi-tier software system aimed at interfacing large databases |
| CN102006330A (en) * | 2010-12-01 | 2011-04-06 | 北京瑞信在线系统技术有限公司 | Distributed cache system, data caching method and inquiring method of cache data |
| CN102629903A (en) * | 2011-12-21 | 2012-08-08 | 奇智软件（北京）有限公司 | System and method for disaster recovery in internet application |
| CN103516549A (en) * | 2013-09-27 | 2014-01-15 | 浪潮电子信息产业股份有限公司 | File system metadata log mechanism based on shared object storage |
| CN104317803A (en) * | 2014-09-23 | 2015-01-28 | 厦门美柚信息科技有限公司 | Data access structure and method of database cluster |
| CN105554143A (en) * | 2015-12-25 | 2016-05-04 | 浪潮(北京)电子信息产业有限公司 | High-availability cache server and data processing method and system thereof |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388487A (en) * | 2018-03-01 | 2018-08-10 | 上海达梦数据库有限公司 | A kind of data loading process, device, equipment and storage medium |
| CN108388487B (en) * | 2018-03-01 | 2020-09-04 | 上海达梦数据库有限公司 | Data loading method, device, equipment and storage medium |
| CN111277616A (en) * | 2018-12-04 | 2020-06-12 | 中兴通讯股份有限公司 | RDMA (remote direct memory Access) -based data transmission method and distributed shared memory system |
| CN111277616B (en) * | 2018-12-04 | 2023-11-03 | 中兴通讯股份有限公司 | RDMA-based data transmission method and distributed shared memory system |
| CN110166542A (en) * | 2019-05-16 | 2019-08-23 | 广东电网有限责任公司信息中心 | Distributed memory system and data read-write method based on ICP/IP protocol |
| CN110557399A (en) * | 2019-09-12 | 2019-12-10 | 苏州浪潮智能科技有限公司 | Management data synchronization method and device, storage equipment and readable storage medium |
| WO2021046935A1 (en) * | 2019-09-12 | 2021-03-18 | 苏州浪潮智能科技有限公司 | Management data synchronization method and apparatus, storage device and readable storage medium |
| CN111653052A (en) * | 2020-04-26 | 2020-09-11 | 北京三快在线科技有限公司 | Cash register system and cash register switching method |
| CN111653052B (en) * | 2020-04-26 | 2022-06-21 | 北京三快在线科技有限公司 | Cash register system and cash register switching method |
| CN113656348A (en) * | 2021-08-25 | 2021-11-16 | 北京微纳星空科技有限公司 | Distributed cluster management system and method for satellite application big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106790563B (en) | 2019-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106790563A (en) | Distributed memory system and method | |
| US11570255B2 (en) | SMB2 scaleout | |
| US10523545B2 (en) | System and method for managing VoIP session continuity information using logical scalable units | |
| US20210406279A1 (en) | System and method for maintaining a master replica for reads and writes in a data store | |
| US10630779B2 (en) | System and method for using VoIP session continuity information using logical scalable units | |
| CN106685691B (en) | The efficient update configuration method of terminal device in Internet of things system | |
| JP6382454B2 (en) | Distributed storage and replication system and method | |
| CN105245373B (en) | A kind of container cloud platform system is built and operation method | |
| CN107040594A (en) | The method and device of license block chain node access based on PBFT | |
| US8886796B2 (en) | Load balancing when replicating account data | |
| CN105511805A (en) | Data processing method and device for cluster file system | |
| CN106713391B (en) | Session information sharing method and sharing system | |
| CN105607954A (en) | Stateful container online migration method and apparatus | |
| CN106911648B (en) | Environment isolation method and equipment | |
| EP4213038A1 (en) | Data processing method and apparatus based on distributed storage, device, and medium | |
| CN102438042B (en) | Dynamic parameter synchronizing method and system of multipoint access device | |
| CN103986789A (en) | Method for realizing dual redundant of NFS (network file system) nodes in HADOOP HA (home address) cluster based on NFS | |
| WO2020024615A1 (en) | Consensus process recovery method and related nodes | |
| CN102710763A (en) | Method and system for pooling, slicing and fault transfer of distributed cache | |
| CN104484167B (en) | Task processing method and device | |
| CN106850724A (en) | Data push method and device | |
| CN107734017A (en) | Data service method and system | |
| CN107872492B (en) | Method and device for supporting multi-user editing of data object at server | |
| US8627412B2 (en) | Transparent database connection reconnect | |
| CN105323271B (en) | Cloud computing system and processing method and device thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |