CN102035865B - Data storing and addressing methods, systems and equipment - Google Patents
Data storing and addressing methods, systems and equipment Download PDFInfo
- Publication number
- CN102035865B CN102035865B CN 200910179926 CN200910179926A CN102035865B CN 102035865 B CN102035865 B CN 102035865B CN 200910179926 CN200910179926 CN 200910179926 CN 200910179926 A CN200910179926 A CN 200910179926A CN 102035865 B CN102035865 B CN 102035865B
- Authority
- CN
- China
- Prior art keywords
- data
- group
- stored
- write request
- token
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003860 storage Methods 0.000 claims abstract description 46
- 238000013500 data storage Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000012856 packing Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000010076 replication Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 241000931705 Cicada Species 0.000 description 1
- 206010033799 Paralysis Diseases 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses data storing and addressing methods, data storing and addressing systems and data storing and addressing equipment, which are used for solving the problems of low safety, low reliability and low data reading efficiency of the conventional system. A storage cluster consisting of a plurality of store proxies (SP) is partitioned into at least two SP groups, wherein each SP group comprises at least two SPs; and each SP in each SP group is provided with a group identifier and an intra-group identifier of the SP group to which the SP belongs. The data storing method comprises the following steps that: a write proxy (WP) receives a data write request sent by a client, wherein the data write request carries data to be stored; the WP selects an SP serving as a target SP from the storage cluster according to the received data write request and forwards the data write request to the target SP; and the target SP generates a unique data identifier for the data to be stored carried in the received data write request, stores the generated data identifier and corresponding data to the stored and returning the generated data identifier to the client, wherein the data identifier comprises the group identifier and the intra-group identifier of the target SP.
Description
Technical field
The application relates to database technical field, relates in particular to a kind of data storage and addressing data method, system and equipment.
Background technology
When realizing the memory function that Web uses, usually adopt the mode of database.Database is the set with the structural data of certain organizational form storage, and to inserting new data in the database, inquiry, modification legacy data all can carry out according to public and controlled mode.In the less situation of the data volume of in and database less to the visit capacity of database, storing, use a storage server (SP, Store proxy) to satisfy the demands; Along with the demand that the visit capacity to database increases and stores mass data, the general memory cluster that is formed by many SP that adopts.In data storage procedure, be the unique Data Identification of data allocations to be stored by management server, and from the memory cluster, select purpose SP that purpose SP is responsible for writing this Data Identification and corresponding data to be stored.In order to guarantee the safe and reliable of data storage, need to adopt the mode of back-up storage, the data that are same Data Identification are stored in respectively on many SP, and are responsible for safeguarding a central allocation table by management server, the Data Identification of each data of record and corresponding many SP that write in the central allocation table.Based on above-mentioned data storage method, in the addressing data process, at first by management server according to central allocation table, determine to store many SP of data to be read, from many SP that determine, choose again a SP executing data read operation.
In the prior art, data storage and addressing data need management server to carry out unified scheduling of resource and distribution, and be very high to the software and hardware requirement of management server, in case management server breaks down, will be so that the whole system paralysis causes the security of system reliability lower; And twice addressing of addressing data process need is so that the reading efficiency of data is lower.
Summary of the invention
The application provides a kind of data storage and addressing data method, system and equipment, and is lower in order to the security reliability that solves existing system, and the lower problem of the reading efficiency of data.
The application provides a kind of date storage method, the memory cluster that is comprised of many storage server SP is divided at least two SP groups, each SP organizes and comprises at least two SP, and every SP in each SP group disposes group sign and the interior sign of group of place SP group, and described method comprises:
Write acting server WP and receive the data write request that client sends, wherein carry data to be stored;
Described WP selects a SP as purpose SP from the memory cluster according to the data write request that receives, and described data write request is forwarded on the described purpose SP;
Described purpose SP is that the data to be stored of carrying in the data write request that receives generate unique Data Identification, preserve the Data Identification and the corresponding data to be stored that generate, and the Data Identification that generates returned to client by described WP, wherein, described purpose SP employing table is stored data to be stored, and described Data Identification comprises that the group that purpose SP place SP organizes identifies in identifying, organizing, the table of the table at data to be stored place identifies and show interior numbering.
The application provides a kind of data-storage system, comprise the memory cluster that is formed by many storage server SP and write acting server WP, described memory cluster is divided at least two SP groups, each SP group comprises at least two SP, every SP in each SP group disposes group sign and the interior sign of group of place SP group, wherein:
The described acting server WP that writes, be used for receiving the data write request that client sends, wherein carry data to be stored, according to the data write request that receives, from the memory cluster, select a SP as purpose, and described data write request is forwarded on the described purpose SP;
Described purpose SP, be used to the data to be stored of carrying in the data write request that receives to generate unique Data Identification, preserve the Data Identification and the corresponding data to be stored that generate, and the Data Identification that generates returned to client by described WP, wherein, described purpose SP employing table is stored data to be stored, and described Data Identification comprises that the group that purpose SP place SP organizes identifies in identifying, organizing, the table of the table at data to be stored place identifies and show interior numbering.
The application provides a kind of storage server, comprising:
The first memory cell is used for storing the group sign of pre-configured place storage server SP group and organizes interior sign;
Receiving element is used for the receive data write request, wherein carries data to be stored;
Generation unit, be used to the data to be stored of carrying in the data write request that receives to generate unique Data Identification, wherein, the employing table is stored data to be stored, and described Data Identification comprises that the group that this SP place SP organizes identifies in identifying, organizing, the table of the table at data to be stored place identifies and show interior numbering;
Processing unit is used for preserving the Data Identification and the corresponding data to be stored that generate, and returns the Data Identification of generation.
The application provides a kind of addressing data method based on above-mentioned date storage method, comprising:
Read acting server RP and receive the data read request that client sends, wherein carry the Data Identification of data to be read;
Described RP determines the target SP of the described data to be read of storage according to sign in the group sign that comprises in the described Data Identification and the group, and described data read request is forwarded on the described target SP;
Numbering reads corresponding data in the table sign that described target SP comprises according to the Data Identification that carries in the data read request and the table, and the data communication device that reads out is crossed described RP returns to client.
The application provides a kind of addressing data system based on above-mentioned data-storage system, and comprise described memory cluster and read acting server RP, wherein:
The described acting server RP that reads is used for receiving the data read request that client sends, and wherein carries the Data Identification of data to be read; According to sign in the group sign that comprises in the described Data Identification and the group, determine the target storage server SP of the described data to be read of storage, and described data read request is forwarded on the described target SP;
Described target SP is used for that numbering reads corresponding data in the table sign that comprises according to the Data Identification that the data read request that receives is carried and the table, and the data communication device that reads out is crossed described RP returns to client.
The application provides a kind of acting server, comprising:
Receiving element is used for receiving the data read request that client sends, and wherein carries the Data Identification of data to be read;
Determining unit is used for the group sign that comprises according to described Data Identification and organizes interior sign, determines the target storage server SP of the described data to be read of storage;
Retransmission unit is used for described data read request is forwarded to described target SP.
The date storage method that the application provides and addressing data method are applied in the memory cluster, and the memory cluster consists of the distributed storage system take the SP group as unit, and each SP group comprises at least two SP, disposes sign in group sign and the group on the SP.In data storage procedure, by WP the data write request that client sends is forwarded on the purpose SP, identify the generated data sign and carry out the data storage according to the group sign of configuration and in organizing by purpose SP, need not to rely on special management server distribute data to identify and safeguard central allocation table; In the addressing data process, directly orient target SP by the Data Identification that carries in the data read request of RP according to the client transmission, need not to rely on special management server to carry out twice addressing according to central allocation table.The application need not to rely on special management server to carry out unified scheduling of resource and distribution, has promoted the security of system reliability; The addressing data process need not the secondary addressing, has promoted the reading efficiency of data.
Description of drawings
Fig. 1 is data-storage system configuration diagram in the embodiment of the present application;
Fig. 2 is date storage method flow chart in the embodiment of the present application;
Fig. 3 is the structural representation of SP in the embodiment of the present application;
Fig. 4 is addressing data system architecture schematic diagram in the embodiment of the present application;
Fig. 5 is addressing data method flow diagram in the embodiment of the present application;
Fig. 6 is the structural representation of RP in the embodiment of the present application.
Embodiment
The embodiment of the present application is for the problem that exists in available data storage and the addressing data scheme, a kind of institutional framework of improved memory cluster has at first been proposed, the memory cluster that is comprised of many SP is divided at least two SP groups, each SP group comprises at least two SP, every SP in each SP group disposes group sign and the interior sign of group of place SP group, the group sign of distributing to each SP group needs to guarantee its uniqueness, and need to guarantee to distribute to sign in the group of every SP can with the group of other SP in this SP group in identify and distinguish.
Comprise even number platform SP in the memory cluster in order to realize simply, can to set, and per two SP are divided into a SP group.Illustrate:
Suppose to comprise in the memory cluster 40 SP, the memory cluster is divided into 20 SP groups, each SP group comprises two SP.For each the SP group in the memory cluster, the group sign can be assigned as 01,02,03 successively ... 20.For two SP in SP group, can be for wherein being designated odd number in a SP assign group, for example 1,3,5, can be called the odd numbers machine in the embodiment of the present application; Be designated even number in another SP assign group, for example 2,4,8, can be called the even numbers machine in the embodiment of the present application.On this basis, for group sign and the interior sign of group of every SP configuration place SP group in the memory cluster, for example be the odd numbers machine configuration 011 in the SP group 01, be SP organizes the even numbers machine configuration 122 in 12.
For the situation that comprises odd number platform SP in the memory cluster, three SP wherein can be divided into a SP group, per two SP among all the other SP are divided into a SP group.Illustrate:
Suppose to comprise in the memory cluster 25 SP, the memory cluster can be divided into 12 SP groups, one of them SP group comprises three SP, and all the other each SP groups comprise two SP.For each the SP group in the memory cluster, the group sign can be assigned as 01,02,03 successively ... 12.For the SP group that comprises three SP, can be designated 3,6,9 for being designated to be designated in 1,4,7, the second SP assign group in 2,5,8, the three SP assign group in SP assign group wherein.
Need to prove, can divide into groups flexibly according to the scale of memory cluster in the implementation that the SP quantity that each SP group comprises can be different, be no less than two as long as guarantee to be no less than the SP that two SP organize and each SP group comprises.Can as long as guarantee to distinguish, for example comprise the situation of many SP for a SP group according to sign in grouping situation flexible allocation group sign and the group in the implementation, can be for being designated 1,2,3,4 in each SP successively assign group ...
On the basis of above-mentioned memory cluster, the embodiment of the present application provides a kind of data-storage system, as shown in Figure 1, comprise the memory cluster and the WP(Write Proxy that are formed by many SP101, write acting server) 102, in the actual system architecture, WP can comprise many equally, forms the WP cluster.Wherein:
WP102 is used for receiving the data write request that client sends, and wherein carries data to be stored, according to the data write request that receives, selects a SP as purpose SP from the memory cluster, and this data write request is forwarded on the purpose SP;
In the implementation, be used for the jar bag that links to each other with the WP cluster based on the Java technology in client exploitation, when the user need to store data, wrap by client call jar, the data write request is sent on the WP in the WP cluster.WP can select a SP who has stored the data volume minimum as purpose SP from the memory cluster based on load-balancing algorithm, and the data write request is transmitted to this purpose SP.
Purpose SP101, be used to the data to be stored of carrying in the data write request that receives to generate unique Data Identification, preserve the Data Identification and the corresponding data to be stored that generate, and the Data Identification that generates returned to client by WP102, wherein this Data Identification comprises sign in the group sign of purpose SP place SP group and the group;
In the implementation, also comprise numbering in table sign and the table in the Data Identification that generates, for the ease of addressing, the memory space of SP generally is separated into a plurality of tables according to setting rule, many data of storage in each table, the Data Identification that each bar data is corresponding unique, for example 1009030000000011, wherein front 2 " 10 " represent that the group of the SP group at this data place is designated 10, the 3rd to the 6th " 0903 " the table sign that represents the table at this data place, last 1 " 1 " represents the interior sign of group of the SP at this data place, remaining " 000000001 " represents to number in the table of these data in table, which bar data during indication is specifically shown, thus accurately locate data.The structure of Data Identification can be set flexibly, follows unified structure in the system and gets final product.Better, for the ease of management, the table that is used for the storage data among the purpose SP can be separated by the time, for example data weekly are stored on the table, table is designated the data in 09 year the 3rd week of storage in the table of " 0903 ", table is designated the data in 09 year the 4th week of storage in the table of " 0904 ", etc.Can limit the time cycle of separating according to the business demand of system's needs carrying in the implementation, the figure place that takies by change table sign satisfies the miscellaneous service demand.Table among the purpose SP also can monthly be cut apart, cuts apart quarterly even cut apart per year.
In order to guarantee the safe and reliable of data storage, adopt the mode of active and standby storage, after purpose SP successfully preserves the data to be stored of the Data Identification of generation and correspondence, can generate replication log or generate replication log by purpose SP generation replication log or by special log server by WP, be responsible for this data Replica to the backup SP of purpose SP corresponding at least one the backup SP of SP.In the embodiment of the present application, can adopt mutually redundant mode between each SP in the same SP group.Concrete, organize the situation that comprises two SP for a SP, the odd numbers machine is the backup of even numbers machine, the even numbers machine is the backup of odd numbers machine; Organize the situation that comprises many SP for a SP, backup mode can be more flexible, the below's minute situation explanation.If a SP group comprises even number platform SP, to comprise that four SP as example, can backup each other in twos, for example a machine is No. two machine backups, and No. two machines are a machine backup, and No. three machines are No. four machine backups, and No. four machines are No. three machine backups; Also can back up by winding, for example a machine is No. two machines backups, and No. two machines are No. three machines backups, and No. three machines are No. four machines backups, and No. four machines are a machine backup; Can also be other each SP backup in the group by each interior SP of SP group.If a SP group comprises odd number platform SP, can back up by winding, also can be interior other each SP backup of group by each interior SP of SP group.But in the addressing data process, general direct reading out data from the main frame and reading out data from the backup machine not.
Because data write operation is the consumption data base resource relatively, in order to limit the data write operation concurrency of separate unit SP, guarantee that separate unit SP can not receive excessive data write request within certain time period, be each the SP configuration token bucket in the memory cluster, dispose simultaneously the token update cycle, in the zero hour of each token update cycle, pack in the token bucket of self token of fixed qty of each SP.For each SP, if it receives the data write request namely as purpose SP, before generating unique Data Identification for the data to be stored of carrying in the data write request that receives, need to carry out following operation: when the data write request arrives, judge whether operable token is arranged in the token bucket, if, then from token bucket, delete a token, if not, then before the zero hour of next token update cycle, reject new data write request.
Wherein, a kind of possibility structure of SP as shown in Figure 2, comprising:
The first memory cell 201 is used for storing the group sign of pre-configured place storage server SP group and organizes interior sign;
Receiving element 202 is used for the receive data write request, wherein carries data to be stored;
Better, this SP also comprises:
The second memory cell 205 is used for storing pre-configured token bucket;
Updating block 206 was used in the zero hour of each token update cycle, the token of the fixed qty of packing in the token bucket;
The framework of based on data storage system, the embodiment of the present application provide a kind of date storage method, as shown in Figure 3, comprising:
S301, WP receive the data write request that client sends, and wherein carry data to be stored;
S302, WP select a SP as purpose SP from the memory cluster according to the data write request that receives, and this data write request is forwarded on the purpose SP;
Better, WP selects a SP who has stored the data volume minimum as purpose SP from the memory cluster;
When S303, purpose SP arrive at the data write request, judge whether operable token is arranged in the token bucket, if so, then carry out S304, if not, then carry out S305;
S304, purpose SP delete a token from token bucket, and turn to execution S306;
S305, purpose SP rejected new data write request before the zero hour of next token update cycle;
S306, purpose SP are that the data to be stored of carrying in the data write request that receives generate unique Data Identification, comprise group sign and the interior sign of group of purpose SP place SP group in this Data Identification;
S307, purpose SP preserve Data Identification and the corresponding data to be stored that generate, and the Data Identification that generates is returned to client by WP.
Need to prove that if each SP in the memory cluster does not dispose token bucket, then step S303 ~ S305 need not to carry out, after S302 is complete, directly turns to and carry out S306.
Based on above-mentioned data-storage system, the embodiment of the present application correspondence provides a kind of addressing data system, as shown in Figure 4, comprise the memory cluster and the RP(Read Proxy that are formed by many SP101, read acting server) 103, in the actual system architecture, RP can comprise many equally, form the RP cluster, and RP and WP can merge setting, that is to say that the acting server of a physics can possess the function of RP and WP simultaneously.Wherein:
RP103 is used for receiving the data read request that client sends, and wherein carries the Data Identification of data to be read; According to sign in the group sign that comprises in this Data Identification and the group, determine the target SP of storage data to be read, and data read request is forwarded on the target SP;
In the implementation, be used for the jar bag that links to each other with the RP cluster based on the Java technology in client exploitation, when the user needs reading out data, wrap by client call jar, data read request is sent on the RP in the RP cluster.
Target SP101 is used for reading corresponding data according to the Data Identification that the data read request that receives is carried, and the data communication device that reads out is crossed RP103 returns to client;
Owing to also comprise numbering in table sign and the table in the Data Identification, so target SP101 directly orients these data according to this Data Identification.
Wherein, a kind of possibility structure of RP as shown in Figure 5, comprising:
Receiving element 501 is used for receiving the data read request that client sends, and wherein carries the Data Identification of data to be read;
Determining unit 502 is used for the group sign that comprises according to this Data Identification and organizes interior sign, determines the target SP of these data to be read of storage;
Based on above-mentioned date storage method, the embodiment of the present application correspondence provides a kind of addressing data method, as shown in Figure 6, comprising:
S601, RP receive the data read request that client sends, and wherein carry the Data Identification of data to be read;
S602, RP determine the target SP of these data to be read of storage according to sign in the group sign that comprises in the described Data Identification and the group, and this data read request is forwarded on the target SP;
S603, target SP read corresponding data according to the Data Identification that carries in the data read request, and the data communication device that reads out is crossed this RP return to client.
The date storage method that the application provides and addressing data method are applied in the memory cluster, and the memory cluster consists of the distributed storage system take the SP group as unit, and each SP group comprises at least two SP, disposes sign in group sign and the group on the SP.In data storage procedure, by WP the data write request that client sends is forwarded on the purpose SP, identify the generated data sign and carry out the data storage according to the group sign of configuration and in organizing by purpose SP, need not to rely on special management server distribute data to identify and safeguard central allocation table; In the addressing data process, directly orient target SP by the Data Identification that carries in the data read request of RP according to the client transmission, need not to rely on special management server to carry out twice addressing according to central allocation table.The application need not to rely on special management server to carry out unified scheduling of resource and distribution, has promoted the security of system reliability; The addressing data process need not the secondary addressing, has promoted the reading efficiency of data.
The embodiment that it will be understood by those skilled in the art that the application can be provided as method, system, equipment or computer program.Therefore, the application can adopt complete hardware implementation example, complete implement software example or in conjunction with the form of the embodiment of software and hardware aspect.And the application can adopt the form of the computer program of implementing in one or more computer-usable storage medium (including but not limited to magnetic disc store, CD-ROM, optical memory etc.) that wherein include computer usable program code.
The application is that reference is described according to flow chart and/or the block diagram of method, equipment (system) and the computer program of the embodiment of the present application.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or the block diagram and/or square frame and flow chart and/or the block diagram and/or the combination of square frame.Can provide these computer program instructions to the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device producing a machine, so that the instruction of carrying out by the processor of computer or other programmable data processing device produces the device of the function that is used for being implemented in flow process of flow chart or a plurality of flow process and/or square frame of block diagram or a plurality of square frame appointments.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, so that the instruction that is stored in this computer-readable memory produces the manufacture that comprises command device, this command device is implemented in the function of appointment in flow process of flow chart or a plurality of flow process and/or square frame of block diagram or a plurality of square frame.
These computer program instructions also can be loaded on computer or other programmable data processing device, so that carry out the sequence of operations step producing computer implemented processing at computer or other programmable devices, thereby be provided for being implemented in the step of the function of appointment in flow process of flow chart or a plurality of flow process and/or square frame of block diagram or a plurality of square frame in the instruction that computer or other programmable devices are carried out.
Although described the application's preferred embodiment, in a single day those skilled in the art get the basic creative concept of cicada, then can make other change and modification to these embodiment.So claims are intended to all changes and the modification that are interpreted as comprising preferred embodiment and fall into the application's scope.
Obviously, those skilled in the art can carry out various changes and modification and the spirit and scope that do not break away from the application to the application.Like this, if these of the application are revised and modification belongs within the scope of the application's claim and equivalent technologies thereof, then the application also is intended to comprise these changes and modification interior.
Claims (13)
1. date storage method, it is characterized in that the memory cluster that is comprised of many storage server SP is divided at least two SP groups, each SP group comprises at least two SP, every SP in each SP group disposes group sign and the interior sign of group of place SP group, and described method comprises:
Write acting server WP and receive the data write request that client sends, wherein carry data to be stored;
Described WP selects a SP as purpose SP from the memory cluster according to the data write request that receives, and described data write request is forwarded on the described purpose SP;
Described purpose SP is that the data to be stored of carrying in the data write request that receives generate unique Data Identification, preserve the Data Identification and the corresponding data to be stored that generate, and the Data Identification that generates returned to client by described WP, wherein, described purpose SP employing table is stored data to be stored, and described Data Identification comprises that the group that purpose SP place SP organizes identifies in identifying, organizing, the table of the table at data to be stored place identifies and show interior numbering.
2. the method for claim 1 is characterized in that, each SP in the described memory cluster disposes token bucket, in the zero hour of each token update cycle, and pack in the token bucket of self token of fixed qty of each SP; And
Be before the data to be stored of carrying in the data write request generate unique Data Identification, also to comprise at described purpose SP:
When described purpose SP arrives at described data write request, judge whether operable token is arranged in the token bucket, if, then from token bucket, delete a token, if not, then before the zero hour of next token update cycle, reject new data write request.
3. method as claimed in claim 1 or 2 is characterized in that, described WP selects a SP who has stored the data volume minimum as purpose SP from the memory cluster.
4. the method for claim 1 is characterized in that, the table that is used for the storage data among the described purpose SP was separated by the time.
5. such as claim 1,2 or 4 arbitrary described methods, it is characterized in that, backup each other between each SP in the same SP group.
6. data-storage system, it is characterized in that, comprise the memory cluster that is formed by many storage server SP and write acting server WP, described memory cluster is divided at least two SP groups, each SP group comprises at least two SP, every SP in each SP group disposes group sign and the interior sign of group of place SP group, wherein:
The described acting server WP that writes, be used for receiving the data write request that client sends, wherein carry data to be stored, according to the data write request that receives, from the memory cluster, select a SP as purpose, and described data write request is forwarded on the described purpose SP;
Described purpose SP, be used to the data to be stored of carrying in the data write request that receives to generate unique Data Identification, preserve the Data Identification and the corresponding data to be stored that generate, and the Data Identification that generates returned to client by described WP, wherein, described purpose SP employing table is stored data to be stored, and described Data Identification comprises that the group that purpose SP place SP organizes identifies in identifying, organizing, the table of the table at data to be stored place identifies and show interior numbering.
7. system as claimed in claim 6 is characterized in that, each SP in the described memory cluster disposes token bucket, in the zero hour of each token update cycle, and pack in the token bucket of self token of fixed qty of each SP; And
Described purpose SP also is used for judging whether operable token is arranged in the token bucket when described data write request arrives, if so, then from token bucket, delete a token, if not, then before the zero hour of next token update cycle, reject new data write request.
8. a storage server is characterized in that, comprising:
The first memory cell is used for storing the group sign of pre-configured place storage server SP group and organizes interior sign;
Receiving element is used for the receive data write request, wherein carries data to be stored;
Generation unit, be used to the data to be stored of carrying in the data write request that receives to generate unique Data Identification, wherein, the employing table is stored data to be stored, and described Data Identification comprises that the group that this SP place SP organizes identifies in identifying, organizing, the table of the table at data to be stored place identifies and show interior numbering;
Processing unit is used for preserving the Data Identification and the corresponding data to be stored that generate, and returns the Data Identification of generation.
9. storage server as claimed in claim 8 is characterized in that,
The second memory cell is used for storing pre-configured token bucket;
Updating block was used in the zero hour of each token update cycle, the token of the fixed qty of packing in the described token bucket;
Judging unit is used for judging whether operable token is arranged in the token bucket when described data write request arrives, and if so, then deletes a token from token bucket, and triggers described generation unit; If not, then control described receiving element before the zero hour of next token update cycle, reject new data write request, and trigger described generation unit.
10. the addressing data method based on the described date storage method of claim 1 is characterized in that, comprising:
Read acting server RP and receive the data read request that client sends, wherein carry the Data Identification of data to be read;
Described RP determines the target SP of the described data to be read of storage according to sign in the group sign that comprises in the described Data Identification and the group, and described data read request is forwarded on the described target SP;
Numbering reads corresponding data in the table sign that described target SP comprises according to the Data Identification that carries in the data read request and the table, and the data communication device that reads out is crossed described RP returns to client.
11. the addressing data system based on the described data-storage system of claim 6 is characterized in that, comprises described memory cluster and reads acting server RP, wherein:
The described acting server RP that reads is used for receiving the data read request that client sends, and wherein carries the Data Identification of data to be read; According to sign in the group sign that comprises in the described Data Identification and the group, determine the target storage server SP of the described data to be read of storage, and described data read request is forwarded on the described target SP;
Described target SP is used for that numbering reads corresponding data in the table sign that comprises according to the Data Identification that the data read request that receives is carried and the table, and the data communication device that reads out is crossed described RP returns to client.
12. system as claimed in claim 11 is characterized in that, described write acting server WP and read acting server RP merge to arrange.
13. an acting server is characterized in that, comprising:
Receiving element is used for receiving the data read request that client sends, and wherein carries the Data Identification of data to be read;
Determining unit is used for the group sign that comprises according to described Data Identification and organizes interior sign, determines the target storage server SP of the described data to be read of storage;
Retransmission unit is used for described data read request is forwarded to described target SP.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910179926 CN102035865B (en) | 2009-09-30 | 2009-09-30 | Data storing and addressing methods, systems and equipment |
| HK11108667.2A HK1154718B (en) | 2011-08-16 | Data storage and data addressing method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910179926 CN102035865B (en) | 2009-09-30 | 2009-09-30 | Data storing and addressing methods, systems and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102035865A CN102035865A (en) | 2011-04-27 |
| CN102035865B true CN102035865B (en) | 2013-04-17 |
Family
ID=43888186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910179926 Active CN102035865B (en) | 2009-09-30 | 2009-09-30 | Data storing and addressing methods, systems and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102035865B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102724301B (en) * | 2012-05-29 | 2015-02-04 | 中国联合网络通信集团有限公司 | Cloud database system and method and equipment for reading and writing cloud data |
| US11086898B2 (en) * | 2013-03-13 | 2021-08-10 | Amazon Technologies, Inc. | Token-based admission control for replicated writes |
| CN104202375B (en) * | 2014-08-22 | 2017-10-24 | 广州华多网络科技有限公司 | The method and system of synchrodata |
| CN105610971B (en) * | 2016-01-29 | 2019-07-02 | 北京京东尚科信息技术有限公司 | A kind of load-balancing method and device |
| CN107092437B (en) * | 2016-02-17 | 2019-11-22 | 杭州海康威视数字技术股份有限公司 | Data write-in, read method and device, cloud storage system |
| CN107229455B (en) | 2016-03-24 | 2019-09-17 | 阿里巴巴集团控股有限公司 | A kind of method for processing business, apparatus and system |
| CN106897335B (en) * | 2016-06-28 | 2020-11-27 | 创新先进技术有限公司 | Service data storage method, record identifier generation method and device |
| CN106993022B (en) * | 2016-12-30 | 2020-03-31 | 中国银联股份有限公司 | Identification management method for cluster, identification server and corresponding system |
| CN109597567B (en) * | 2017-09-30 | 2022-03-08 | 网宿科技股份有限公司 | Data processing method and device |
| CN109726212A (en) * | 2018-12-29 | 2019-05-07 | 杭州宏杉科技股份有限公司 | Data-storage system and method |
| CN112099728B (en) * | 2019-06-18 | 2022-09-16 | 华为技术有限公司 | A method and device for performing write and read operations |
| CN112732169A (en) * | 2019-10-28 | 2021-04-30 | 中兴通讯股份有限公司 | Data writing or reading method, device, storage medium and electronic device |
| CN112000641B (en) * | 2020-07-31 | 2022-08-30 | 新华三大数据技术有限公司 | Data storage method, device and system |
| CN113783916B (en) * | 2020-10-16 | 2022-12-27 | 北京沃东天骏信息技术有限公司 | Information synchronization method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE515344C2 (en) * | 1994-02-08 | 2001-07-16 | Ericsson Telefon Ab L M | Distributed database system |
| US6381669B1 (en) * | 1999-12-27 | 2002-04-30 | Gregory V. Chudnovsky | Multi-bank, fault-tolerant, high-performance memory addressing system and method |
| CN101299211A (en) * | 2007-04-30 | 2008-11-05 | 王霞 | Distributed enquiring method of wireless radio frequency recognition data |
| CN100530125C (en) * | 2007-08-24 | 2009-08-19 | 成都索贝数码科技股份有限公司 | Safe data storage method |
-
2009
- 2009-09-30 CN CN 200910179926 patent/CN102035865B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| HK1154718A1 (en) | 2012-04-27 |
| CN102035865A (en) | 2011-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102035865B (en) | Data storing and addressing methods, systems and equipment | |
| JP7090744B2 (en) | Distributed database cluster system and data synchronization method | |
| CN105447075B (en) | The computer implemented method divided for dynamic | |
| CN108170768B (en) | Database synchronization method, device and readable medium | |
| CN112559637B (en) | Data processing method, device, equipment and medium based on distributed storage | |
| CN102411637B (en) | Metadata management method of distributed file system | |
| CN103186554A (en) | Distributed data mirroring method and data storage node | |
| CN105930498A (en) | Distributed database management method and system | |
| WO2021145915A1 (en) | Memory health tracking for differentiated data recovery configurations | |
| CN105989123A (en) | Data synchronization method, apparatus and system | |
| CN105630418A (en) | Data storage method and device | |
| CN104035836A (en) | Automatic disaster tolerance recovery method and system in cluster retrieval platform | |
| WO2021057482A1 (en) | Method and device for generating bloom filter in blockchain | |
| CN110134338A (en) | A kind of distributed memory system and its data redundancy protection method and relevant device | |
| CN113760513A (en) | Distributed task scheduling method, device, equipment and medium | |
| CN102779138A (en) | Hard disk access method of real time data | |
| CN110427364A (en) | A kind of data processing method, device, electronic equipment and storage medium | |
| CN111638995A (en) | Metadata backup method, device and equipment and storage medium | |
| KR20190108020A (en) | Method for processing transactions using blockchain, and transaction management server using the same | |
| CN109144783A (en) | A kind of distribution magnanimity unstructured data backup method and system | |
| CN108021562A (en) | Deposit method, apparatus and distributed file system applied to distributed file system | |
| CN104679883A (en) | Method for rapidly archiving data and reducing storage space by utilizing partition replacement | |
| CN103365740A (en) | Data cold standby method and device | |
| CN110221778A (en) | Processing method, system, storage medium and the electronic equipment of hotel's data | |
| CN110427390B (en) | Data query method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1154718 Country of ref document: HK |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: GR Ref document number: 1154718 Country of ref document: HK |